docs(lsp): add feature page — setup, CLI, supported languages, troubleshooting

Covers: enable flow, server installation (detect-only default vs
hermes lsp install), how diagnostics reach the model, config knobs,
all 26 supported languages, and troubleshooting common issues.

.env.example

@@ -14,14 +14,6 @@
 # LLM_MODEL is no longer read from .env — this line is kept for reference only.
 # LLM_MODEL=anthropic/claude-opus-4.6
 
-# =============================================================================
-# LLM PROVIDER (NovitaAI)
-# =============================================================================
-# NovitaAI — 90+ models, pay-per-use
-# Get your key at: https://novita.ai/settings/key-management
-# NOVITA_API_KEY=
-# NOVITA_BASE_URL=https://api.novita.ai/openai/v1  # Override default base URL
-
 # =============================================================================
 # LLM PROVIDER (Google AI Studio / Gemini)
 # =============================================================================
@@ -281,27 +273,6 @@ BROWSER_SESSION_TIMEOUT=300
 # Browser sessions are automatically closed after this period of no activity
 BROWSER_INACTIVITY_TIMEOUT=120
 
-# Extra Chromium launch flags passed to agent-browser, comma- or newline-separated.
-# Hermes auto-injects "--no-sandbox,--disable-dev-shm-usage" when it detects root
-# or AppArmor-restricted unprivileged user namespaces (Ubuntu 23.10+, DGX Spark,
-# many container images), so leave this unset unless you need extra flags.
-# Setting this disables the auto-injection.
-# AGENT_BROWSER_ARGS=--no-sandbox
-
-# Camofox local anti-detection browser (Camoufox-based Firefox).
-# Set CAMOFOX_URL to route the browser tools through a local Camofox server
-# instead of agent-browser/Browserbase. See docs/user-guide/features/browser.md.
-# CAMOFOX_URL=http://localhost:9377
-
-# Externally managed Camofox sessions — when another app owns the visible
-# Camofox browser, set these so Hermes shares the same userId/profile instead
-# of creating its own isolated session.
-# CAMOFOX_USER_ID=
-# CAMOFOX_SESSION_KEY=
-# Set to true to reuse an already-open Camofox tab for this identity before
-# creating a new one (useful for gateway restarts).
-# CAMOFOX_ADOPT_EXISTING_TAB=false
-
 # =============================================================================
 # SESSION LOGGING
 # =============================================================================
@@ -394,6 +365,24 @@ IMAGE_TOOLS_DEBUG=false
 # CONTEXT_COMPRESSION_THRESHOLD=0.85      # Compress at 85% of context limit
 # Model is set via compression.summary_model in config.yaml (default: google/gemini-3-flash-preview)
 
+# =============================================================================
+# RL TRAINING (Tinker + Atropos)
+# =============================================================================
+# Run reinforcement learning training on language models using the Tinker API.
+# Requires the rl-server to be running (from tinker-atropos package).
+
+# Tinker API Key - RL training service
+# Get at: https://tinker-console.thinkingmachines.ai/keys
+# TINKER_API_KEY=
+
+# Weights & Biases API Key - Experiment tracking and metrics
+# Get at: https://wandb.ai/authorize
+# WANDB_API_KEY=
+
+# RL API Server URL (default: http://localhost:8080)
+# Change if running the rl-server on a different host/port
+# RL_API_URL=http://localhost:8080
+
 # =============================================================================
 # SKILLS HUB (GitHub integration for skill search/install/publish)
 # =============================================================================
@@ -416,9 +405,9 @@ IMAGE_TOOLS_DEBUG=false
 # Default STT provider is "local" (faster-whisper) — runs on your machine, no API key needed.
 # Install with: pip install faster-whisper
 # Model downloads automatically on first use (~150 MB for "base").
-# To use cloud providers instead, set GROQ_API_KEY, VOICE_TOOLS_OPENAI_KEY, or ELEVENLABS_API_KEY above.
-# Provider priority: local > groq > openai > mistral > xai > elevenlabs
-# Configure in config.yaml: stt.provider: local | groq | openai | mistral | xai | elevenlabs
+# To use cloud providers instead, set GROQ_API_KEY or VOICE_TOOLS_OPENAI_KEY above.
+# Provider priority: local > groq > openai
+# Configure in config.yaml: stt.provider: local | groq | openai
 
 # =============================================================================
 # STT ADVANCED OVERRIDES (optional)
@@ -426,12 +415,10 @@ IMAGE_TOOLS_DEBUG=false
 # Override default STT models per provider (normally set via stt.model in config.yaml)
 # STT_GROQ_MODEL=whisper-large-v3-turbo
 # STT_OPENAI_MODEL=whisper-1
-# STT_ELEVENLABS_MODEL=scribe_v2
 
 # Override STT provider endpoints (for proxies or self-hosted instances)
 # GROQ_BASE_URL=https://api.groq.com/openai/v1
 # STT_OPENAI_BASE_URL=https://api.openai.com/v1
-# ELEVENLABS_STT_BASE_URL=https://api.elevenlabs.io/v1
 
 # =============================================================================
 # MICROSOFT TEAMS INTEGRATION

.github/workflows/desktop-release.yml

@@ -1,345 +0,0 @@
-name: Desktop Release
-
-on:
-  push:
-    branches: [main]
-  release:
-    types: [published]
-  workflow_dispatch:
-    inputs:
-      channel:
-        description: Release channel to build
-        required: true
-        default: nightly
-        type: choice
-        options:
-          - nightly
-          - stable
-      release_tag:
-        description: "Required when channel=stable (example: v2026.5.5)"
-        required: false
-        type: string
-
-permissions:
-  contents: write
-
-concurrency:
-  group: desktop-release-${{ github.ref }}
-  cancel-in-progress: false
-
-jobs:
-  prepare:
-    if: github.repository == 'NousResearch/hermes-agent'
-    runs-on: ubuntu-latest
-    outputs:
-      channel: ${{ steps.meta.outputs.channel }}
-      release_name: ${{ steps.meta.outputs.release_name }}
-      release_tag: ${{ steps.meta.outputs.release_tag }}
-      version: ${{ steps.meta.outputs.version }}
-      is_stable: ${{ steps.meta.outputs.is_stable }}
-    steps:
-      - id: meta
-        env:
-          EVENT_NAME: ${{ github.event_name }}
-          INPUT_CHANNEL: ${{ github.event.inputs.channel }}
-          INPUT_RELEASE_TAG: ${{ github.event.inputs.release_tag }}
-          RELEASE_TAG_FROM_EVENT: ${{ github.event.release.tag_name }}
-          GITHUB_SHA: ${{ github.sha }}
-        run: |
-          set -euo pipefail
-
-          channel="nightly"
-          release_tag="desktop-nightly"
-          is_stable="false"
-
-          if [[ "$EVENT_NAME" == "release" ]]; then
-            channel="stable"
-            release_tag="$RELEASE_TAG_FROM_EVENT"
-            is_stable="true"
-          elif [[ "$EVENT_NAME" == "workflow_dispatch" && "$INPUT_CHANNEL" == "stable" ]]; then
-            channel="stable"
-            release_tag="$INPUT_RELEASE_TAG"
-            is_stable="true"
-          fi
-
-          if [[ "$channel" == "stable" ]]; then
-            if [[ -z "$release_tag" ]]; then
-              echo "Stable desktop releases require a release tag." >&2
-              exit 1
-            fi
-
-            version="${release_tag#v}"
-            release_name="Hermes Desktop ${release_tag}"
-          else
-            stamp="$(date -u +%Y%m%d)"
-            short_sha="${GITHUB_SHA::7}"
-            version="0.0.0-nightly.${stamp}.${short_sha}"
-            release_name="Hermes Desktop Nightly ${stamp}-${short_sha}"
-          fi
-
-          {
-            echo "channel=$channel"
-            echo "release_name=$release_name"
-            echo "release_tag=$release_tag"
-            echo "version=$version"
-            echo "is_stable=$is_stable"
-          } >> "$GITHUB_OUTPUT"
-
-  build:
-    if: github.repository == 'NousResearch/hermes-agent'
-    needs: prepare
-    strategy:
-      fail-fast: false
-      matrix:
-        include:
-          - platform: mac
-            runner: macos-latest
-            build_args: --mac dmg zip
-          - platform: win
-            runner: windows-latest
-            build_args: --win nsis msi
-    runs-on: ${{ matrix.runner }}
-    env:
-      DESKTOP_CHANNEL: ${{ needs.prepare.outputs.channel }}
-      DESKTOP_VERSION: ${{ needs.prepare.outputs.version }}
-      MAC_CSC_LINK: ${{ secrets.CSC_LINK }}
-      MAC_CSC_KEY_PASSWORD: ${{ secrets.CSC_KEY_PASSWORD }}
-      APPLE_API_KEY: ${{ secrets.APPLE_API_KEY }}
-      APPLE_API_KEY_ID: ${{ secrets.APPLE_API_KEY_ID }}
-      APPLE_API_ISSUER: ${{ secrets.APPLE_API_ISSUER }}
-      WIN_CSC_LINK: ${{ secrets.WIN_CSC_LINK }}
-      WIN_CSC_KEY_PASSWORD: ${{ secrets.WIN_CSC_KEY_PASSWORD }}
-    steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
-
-      - uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020  # v4
-        with:
-          node-version: 20
-          cache: npm
-          cache-dependency-path: package-lock.json
-
-      - uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065  # v5
-        with:
-          python-version: "3.11"
-
-      - name: Enforce signing gates for stable releases
-        if: needs.prepare.outputs.is_stable == 'true'
-        shell: bash
-        run: |
-          set -euo pipefail
-          missing=()
-
-          if [[ "${{ matrix.platform }}" == "mac" ]]; then
-            [[ -z "${MAC_CSC_LINK:-}" ]] && missing+=("CSC_LINK")
-            [[ -z "${MAC_CSC_KEY_PASSWORD:-}" ]] && missing+=("CSC_KEY_PASSWORD")
-            [[ -z "${APPLE_API_KEY:-}" ]] && missing+=("APPLE_API_KEY")
-            [[ -z "${APPLE_API_KEY_ID:-}" ]] && missing+=("APPLE_API_KEY_ID")
-            [[ -z "${APPLE_API_ISSUER:-}" ]] && missing+=("APPLE_API_ISSUER")
-          else
-            [[ -z "${WIN_CSC_LINK:-}" ]] && missing+=("WIN_CSC_LINK")
-            [[ -z "${WIN_CSC_KEY_PASSWORD:-}" ]] && missing+=("WIN_CSC_KEY_PASSWORD")
-          fi
-
-          if (( ${#missing[@]} > 0 )); then
-            echo "::error::Stable desktop release missing required secrets: ${missing[*]}"
-            exit 1
-          fi
-
-      - name: Install workspace dependencies
-        run: npm ci
-
-      - name: Install TUI dependencies
-        run: npm --prefix ui-tui ci
-
-      - name: Build bundled TUI payload
-        run: npm --prefix ui-tui run build
-
-      - name: Build desktop renderer
-        run: npm --prefix apps/desktop run build
-
-      - name: Stage Hermes payload
-        run: npm --prefix apps/desktop run stage:hermes
-
-      - name: Map macOS signing credentials
-        if: matrix.platform == 'mac'
-        shell: bash
-        run: |
-          set -euo pipefail
-          has_link=0
-          has_pass=0
-          [[ -n "${MAC_CSC_LINK:-}" ]] && has_link=1
-          [[ -n "${MAC_CSC_KEY_PASSWORD:-}" ]] && has_pass=1
-
-          if [[ $has_link -eq 1 && $has_pass -eq 1 ]]; then
-            echo "CSC_LINK=${MAC_CSC_LINK}" >> "$GITHUB_ENV"
-            echo "CSC_KEY_PASSWORD=${MAC_CSC_KEY_PASSWORD}" >> "$GITHUB_ENV"
-          elif [[ $has_link -eq 1 || $has_pass -eq 1 ]]; then
-            echo "::error::macOS signing secrets are partially configured. Set both CSC_LINK and CSC_KEY_PASSWORD."
-            exit 1
-          fi
-
-      - name: Map Windows signing credentials
-        if: matrix.platform == 'win'
-        shell: bash
-        run: |
-          set -euo pipefail
-          has_link=0
-          has_pass=0
-          [[ -n "${WIN_CSC_LINK:-}" ]] && has_link=1
-          [[ -n "${WIN_CSC_KEY_PASSWORD:-}" ]] && has_pass=1
-
-          if [[ $has_link -eq 1 && $has_pass -eq 1 ]]; then
-            echo "CSC_LINK=${WIN_CSC_LINK}" >> "$GITHUB_ENV"
-            echo "CSC_KEY_PASSWORD=${WIN_CSC_KEY_PASSWORD}" >> "$GITHUB_ENV"
-            echo "CSC_FOR_PULL_REQUEST=true" >> "$GITHUB_ENV"
-          elif [[ $has_link -eq 1 || $has_pass -eq 1 ]]; then
-            echo "::error::Windows signing secrets are partially configured. Set both WIN_CSC_LINK and WIN_CSC_KEY_PASSWORD."
-            exit 1
-          fi
-
-      - name: Build desktop installers
-        shell: bash
-        env:
-          NODE_OPTIONS: --max-old-space-size=16384
-        run: |
-          set -euo pipefail
-          npm --prefix apps/desktop run builder -- \
-            ${{ matrix.build_args }} \
-            --publish never \
-            --config.extraMetadata.version="${DESKTOP_VERSION}" \
-            --config.extraMetadata.desktopChannel="${DESKTOP_CHANNEL}"
-
-      - name: Notarize and staple macOS DMG
-        if: matrix.platform == 'mac' && needs.prepare.outputs.is_stable == 'true'
-        shell: bash
-        run: |
-          set -euo pipefail
-          dmg_path="$(ls apps/desktop/release/*.dmg | head -n 1)"
-          node apps/desktop/scripts/notarize-artifact.cjs "$dmg_path"
-
-      - name: Validate macOS notarization and Gatekeeper trust
-        if: matrix.platform == 'mac' && needs.prepare.outputs.is_stable == 'true'
-        shell: bash
-        run: |
-          set -euo pipefail
-          app_path="$(ls -d apps/desktop/release/mac*/Hermes.app | head -n 1)"
-          dmg_path="$(ls apps/desktop/release/*.dmg | head -n 1)"
-          xcrun stapler validate "$app_path"
-          xcrun stapler validate "$dmg_path"
-          spctl --assess --type execute --verbose=4 "$app_path"
-
-      - name: Generate desktop checksums
-        shell: bash
-        run: |
-          set -euo pipefail
-          node <<'EOF'
-          const crypto = require('node:crypto')
-          const fs = require('node:fs')
-          const path = require('node:path')
-
-          const releaseDir = path.resolve('apps/desktop/release')
-          const platform = process.env.PLATFORM
-          const extensions = platform === 'mac' ? ['.dmg', '.zip'] : ['.exe', '.msi']
-          const files = fs
-            .readdirSync(releaseDir)
-            .filter(name => extensions.some(ext => name.endsWith(ext)))
-            .sort()
-
-          if (!files.length) {
-            throw new Error(`No release artifacts were produced for ${platform}`)
-          }
-
-          const lines = files.map(name => {
-            const full = path.join(releaseDir, name)
-            const hash = crypto.createHash('sha256').update(fs.readFileSync(full)).digest('hex')
-            return `${hash}  ${name}`
-          })
-          fs.writeFileSync(path.join(releaseDir, `SHA256SUMS-${platform}.txt`), `${lines.join('\n')}\n`)
-          EOF
-        env:
-          PLATFORM: ${{ matrix.platform }}
-
-      - name: Upload packaged desktop artifacts
-        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02  # v4
-        with:
-          name: desktop-${{ matrix.platform }}
-          path: |
-            apps/desktop/release/*.dmg
-            apps/desktop/release/*.zip
-            apps/desktop/release/*.exe
-            apps/desktop/release/*.msi
-            apps/desktop/release/SHA256SUMS-${{ matrix.platform }}.txt
-          if-no-files-found: error
-
-  publish:
-    if: github.repository == 'NousResearch/hermes-agent'
-    needs: [prepare, build]
-    runs-on: ubuntu-latest
-    env:
-      GH_TOKEN: ${{ github.token }}
-      CHANNEL: ${{ needs.prepare.outputs.channel }}
-      RELEASE_NAME: ${{ needs.prepare.outputs.release_name }}
-      RELEASE_TAG: ${{ needs.prepare.outputs.release_tag }}
-    steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
-        with:
-          fetch-depth: 0
-
-      - uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093  # v4
-        with:
-          pattern: desktop-*
-          merge-multiple: true
-          path: dist/desktop
-
-      - name: Publish desktop assets to GitHub release
-        shell: bash
-        run: |
-          set -euo pipefail
-          shopt -s globstar nullglob
-
-          files=(
-            dist/desktop/**/*.dmg
-            dist/desktop/**/*.zip
-            dist/desktop/**/*.exe
-            dist/desktop/**/*.msi
-            dist/desktop/**/SHA256SUMS-*.txt
-          )
-
-          if (( ${#files[@]} == 0 )); then
-            echo "No desktop artifacts were downloaded for publishing." >&2
-            exit 1
-          fi
-
-          if [[ "$CHANNEL" == "nightly" ]]; then
-            git tag -f "$RELEASE_TAG" "$GITHUB_SHA"
-            git push origin "refs/tags/$RELEASE_TAG" --force
-
-            notes="Automated nightly desktop build from main. This prerelease is replaced on each new run."
-
-            if gh release view "$RELEASE_TAG" >/dev/null 2>&1; then
-              while IFS= read -r asset_name; do
-                gh release delete-asset "$RELEASE_TAG" "$asset_name" --yes
-              done < <(gh release view "$RELEASE_TAG" --json assets -q '.assets[].name')
-
-              gh release edit "$RELEASE_TAG" \
-                --title "$RELEASE_NAME" \
-                --prerelease \
-                --notes "$notes"
-            else
-              gh release create "$RELEASE_TAG" \
-                --target "$GITHUB_SHA" \
-                --title "$RELEASE_NAME" \
-                --notes "$notes" \
-                --prerelease
-            fi
-          else
-            if ! gh release view "$RELEASE_TAG" >/dev/null 2>&1; then
-              notes="Automated desktop artifacts attached by desktop-release workflow."
-              gh release create "$RELEASE_TAG" \
-                --target "$GITHUB_SHA" \
-                --title "$RELEASE_NAME" \
-                --notes "$notes"
-            fi
-          fi
-
-          gh release upload "$RELEASE_TAG" "${files[@]}" --clobber

.github/workflows/docker-publish.yml

@@ -28,10 +28,9 @@ permissions:
   contents: read
 
 # Concurrency: push/release runs are NEVER cancelled so every merge gets its
-# own SHA-tagged image; :main and :latest are guarded separately by the
-# move-main and move-latest jobs.  PR runs reuse a PR-scoped group with
-# cancel-in-progress: true so rapid pushes to the same PR collapse to the
-# latest commit.
+# own SHA-tagged image; :latest is guarded separately by the move-latest job.
+# PR runs reuse a PR-scoped group with cancel-in-progress: true so rapid
+# pushes to the same PR collapse to the latest commit.
 concurrency:
   group: docker-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: ${{ github.event_name == 'pull_request' }}
@@ -92,10 +91,10 @@ jobs:
       # pattern for multi-runner multi-platform builds.
       #
       # We apply the OCI revision label here (and again on arm64) because
-      # the move-main / move-latest jobs read it off the linux/amd64
-      # sub-manifest config of the floating tag to decide whether it's safe
-      # to advance.  The label must be on each per-arch image — manifest
-      # lists themselves don't carry image config labels.
+      # the move-latest job reads it off the linux/amd64 sub-manifest config
+      # of `:latest` to decide whether it's safe to advance.  The label must
+      # be on each per-arch image — manifest lists themselves don't carry
+      # image config labels.
       - name: Push amd64 by digest
         id: push
         if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event_name == 'release'
@@ -218,8 +217,6 @@ jobs:
     timeout-minutes: 10
     outputs:
       pushed_sha_tag: ${{ steps.mark_pushed.outputs.pushed }}
-      pushed_release_tag: ${{ steps.mark_release_pushed.outputs.pushed }}
-      release_tag: ${{ steps.tag.outputs.tag }}
     steps:
       - name: Download digests
         uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093  # v4
@@ -274,43 +271,33 @@ jobs:
           IMAGE_NAME: ${{ env.IMAGE_NAME }}
           TAG: ${{ steps.tag.outputs.tag }}
 
-      # Signal to move-main that the SHA tag is live.  Only on main pushes;
-      # releases set pushed_release_tag instead.
+      # Signal to move-latest that the SHA tag is live.  Only on main pushes;
+      # releases don't trigger move-latest (they use their own release tag).
       - name: Mark SHA tag pushed
         id: mark_pushed
         if: github.event_name == 'push' && github.ref == 'refs/heads/main'
         run: echo "pushed=true" >> "$GITHUB_OUTPUT"
 
-      # Signal to move-latest that the release tag is live.
-      - name: Mark release tag pushed
-        id: mark_release_pushed
-        if: github.event_name == 'release'
-        run: echo "pushed=true" >> "$GITHUB_OUTPUT"
-
   # ---------------------------------------------------------------------------
-  # Move :main to point at the SHA tag the merge job pushed.
-  #
-  # :main is the floating tag that tracks the tip of the main branch.  Every
-  # merge to main retags :main forward.  Users who want "latest dev build"
-  # pull :main; users who want stable releases pull :latest.
+  # Move :latest to point at the SHA tag the merge job pushed.
   #
   # The real serialization guarantee comes from the top-level concurrency
   # group (`docker-${{ github.ref }}` with `cancel-in-progress: false`),
   # which ensures at most one workflow run for this ref executes at a time.
-  # That means two move-main steps for the same ref cannot overlap.
+  # That means two move-latest steps for the same ref cannot overlap.
   #
   # This job has its own concurrency group as defense-in-depth: if the
-  # top-level group is ever loosened, queued move-mains will run serially
+  # top-level group is ever loosened, queued move-latests will run serially
   # in arrival order, each one running the ancestor check below and either
-  # advancing :main or skipping.  `cancel-in-progress: false` matches the
+  # advancing :latest or skipping.  `cancel-in-progress: false` matches the
   # top-level setting — we don't want rapid pushes to cancel a queued
-  # move-main, because the ancestor check is the real safety mechanism
-  # and queueing is cheap (move-main is a ~30s registry op).
+  # move-latest, because the ancestor check is the real safety mechanism
+  # and queueing is cheap (move-latest is a ~30s registry op).
   #
-  # Combined with the ancestor check, this means :main only ever moves
+  # Combined with the ancestor check, this means :latest only ever moves
   # forward in git history.
   # ---------------------------------------------------------------------------
-  move-main:
+  move-latest:
     if: |
       github.repository == 'NousResearch/hermes-agent'
       && github.event_name == 'push'
@@ -320,7 +307,7 @@ jobs:
     runs-on: ubuntu-latest
     timeout-minutes: 10
     concurrency:
-      group: docker-move-main-${{ github.ref }}
+      group: docker-move-latest-${{ github.ref }}
       cancel-in-progress: false
     steps:
       - name: Checkout code
@@ -337,13 +324,13 @@ jobs:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
-      # Read the git revision label off the current :main manifest, then
+      # Read the git revision label off the current :latest manifest, then
       # use `git merge-base --is-ancestor` to check whether our commit is a
-      # descendant of it.  If :main doesn't exist yet, or its label is
+      # descendant of it.  If :latest doesn't exist yet, or its label is
       # missing, we treat that as "safe to publish".  If another run already
-      # advanced :main past us (or diverged), we skip and leave it alone.
-      - name: Decide whether to move :main
-        id: main_check
+      # advanced :latest past us (or diverged), we skip and leave it alone.
+      - name: Decide whether to move :latest
+        id: latest_check
         run: |
           set -euo pipefail
           image=nousresearch/hermes-agent
@@ -351,119 +338,6 @@ jobs:
           # Pull the JSON for the linux/amd64 sub-manifest's config and extract
           # the OCI revision label with jq — Go template field access can't
           # handle dots in map keys, so using json+jq is the robust route.
-          image_json=$(
-            docker buildx imagetools inspect "${image}:main" \
-              --format '{{ json (index .Image "linux/amd64") }}' \
-              2>/dev/null || true
-          )
-
-          if [ -z "${image_json}" ]; then
-            echo "No existing :main (or inspect failed) — safe to publish."
-            echo "push_main=true" >> "$GITHUB_OUTPUT"
-            exit 0
-          fi
-
-          current_sha=$(
-            printf '%s' "${image_json}" \
-              | jq -r '.config.Labels."org.opencontainers.image.revision" // ""'
-          )
-
-          if [ -z "${current_sha}" ]; then
-            echo "Registry :main has no revision label — safe to publish."
-            echo "push_main=true" >> "$GITHUB_OUTPUT"
-            exit 0
-          fi
-
-          echo "Registry :main is at ${current_sha}"
-          echo "This run is at      ${GITHUB_SHA}"
-
-          if [ "${current_sha}" = "${GITHUB_SHA}" ]; then
-            echo ":main already points at our SHA — nothing to do."
-            echo "push_main=false" >> "$GITHUB_OUTPUT"
-            exit 0
-          fi
-
-          # Make sure we have the :main commit locally for merge-base.
-          if ! git cat-file -e "${current_sha}^{commit}" 2>/dev/null; then
-            git fetch --no-tags --prune origin \
-              "+refs/heads/main:refs/remotes/origin/main" \
-              || true
-          fi
-
-          if ! git cat-file -e "${current_sha}^{commit}" 2>/dev/null; then
-            echo "Registry :main points at an unknown commit (${current_sha}); refusing to overwrite."
-            echo "push_main=false" >> "$GITHUB_OUTPUT"
-            exit 0
-          fi
-
-          # Our SHA must be a descendant of the current :main to be safe.
-          if git merge-base --is-ancestor "${current_sha}" "${GITHUB_SHA}"; then
-            echo "Our commit is a descendant of :main — safe to advance."
-            echo "push_main=true" >> "$GITHUB_OUTPUT"
-          else
-            echo "Another run advanced :main past us (or diverged) — leaving it alone."
-            echo "push_main=false" >> "$GITHUB_OUTPUT"
-          fi
-
-      # Retag the already-pushed SHA manifest as :main.  This is a registry-
-      # side operation — no rebuild, no layer re-push — so it's quick and
-      # atomic per-tag.  The ancestor check above plus the cancel-in-progress
-      # concurrency on this job together guarantee we only ever move :main
-      # forward in git history.
-      - name: Move :main to this SHA
-        if: steps.main_check.outputs.push_main == 'true'
-        run: |
-          set -euo pipefail
-          image=nousresearch/hermes-agent
-          docker buildx imagetools create \
-            --tag "${image}:main" \
-            "${image}:sha-${GITHUB_SHA}"
-
-  # ---------------------------------------------------------------------------
-  # Move :latest to point at the release tag the merge job pushed.
-  #
-  # :latest is the floating tag that tracks the most recent stable release.
-  # Only `release: published` events advance it — never main pushes.
-  #
-  # We still run an ancestor check against the existing :latest so that a
-  # backport release on an older branch (e.g. patching v1.1.5 after v1.2.3
-  # is out) doesn't drag :latest backwards.  The check is the same shape as
-  # move-main: read the OCI revision label off the current :latest, look up
-  # that commit in git, and only advance if our release commit is a strict
-  # descendant.
-  # ---------------------------------------------------------------------------
-  move-latest:
-    if: |
-      github.repository == 'NousResearch/hermes-agent'
-      && github.event_name == 'release'
-      && needs.merge.outputs.pushed_release_tag == 'true'
-    needs: merge
-    runs-on: ubuntu-latest
-    timeout-minutes: 10
-    concurrency:
-      group: docker-move-latest
-      cancel-in-progress: false
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
-        with:
-          fetch-depth: 1000
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f  # v3
-
-      - name: Log in to Docker Hub
-        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9  # v3
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-
-      - name: Decide whether to move :latest
-        id: latest_check
-        run: |
-          set -euo pipefail
-          image=nousresearch/hermes-agent
-
           image_json=$(
             docker buildx imagetools inspect "${image}:latest" \
               --format '{{ json (index .Image "linux/amd64") }}' \
@@ -488,7 +362,7 @@ jobs:
           fi
 
           echo "Registry :latest is at ${current_sha}"
-          echo "This release is at  ${GITHUB_SHA}"
+          echo "This run is at      ${GITHUB_SHA}"
 
           if [ "${current_sha}" = "${GITHUB_SHA}" ]; then
             echo ":latest already points at our SHA — nothing to do."
@@ -497,7 +371,6 @@ jobs:
           fi
 
           # Make sure we have the :latest commit locally for merge-base.
-          # Releases can be cut from any branch, so fetch broadly.
           if ! git cat-file -e "${current_sha}^{commit}" 2>/dev/null; then
             git fetch --no-tags --prune origin \
               "+refs/heads/main:refs/remotes/origin/main" \
@@ -510,25 +383,25 @@ jobs:
             exit 0
           fi
 
-          # Our release SHA must be a descendant of the current :latest.
-          # Backport releases on older branches won't satisfy this and will
-          # be left alone — :latest stays on the newer release.
+          # Our SHA must be a descendant of the current :latest to be safe.
           if git merge-base --is-ancestor "${current_sha}" "${GITHUB_SHA}"; then
-            echo "Our release commit is a descendant of :latest — safe to advance."
+            echo "Our commit is a descendant of :latest — safe to advance."
             echo "push_latest=true" >> "$GITHUB_OUTPUT"
           else
-            echo "Existing :latest is newer than this release (likely a backport) — leaving it alone."
+            echo "Another run advanced :latest past us (or diverged) — leaving it alone."
             echo "push_latest=false" >> "$GITHUB_OUTPUT"
           fi
 
-      # Retag the already-pushed release manifest as :latest.
-      - name: Move :latest to this release tag
+      # Retag the already-pushed SHA manifest as :latest.  This is a registry-
+      # side operation — no rebuild, no layer re-push — so it's quick and
+      # atomic per-tag.  The ancestor check above plus the cancel-in-progress
+      # concurrency on this job together guarantee we only ever move :latest
+      # forward in git history.
+      - name: Move :latest to this SHA
         if: steps.latest_check.outputs.push_latest == 'true'
-        env:
-          RELEASE_TAG: ${{ needs.merge.outputs.release_tag }}
         run: |
           set -euo pipefail
           image=nousresearch/hermes-agent
           docker buildx imagetools create \
             --tag "${image}:latest" \
-            "${image}:${RELEASE_TAG}"
+            "${image}:sha-${GITHUB_SHA}"

.github/workflows/history-check.yml

@@ -1,58 +0,0 @@
-name: History Check
-
-# Rejects PRs whose branch has no common ancestor with main.
-#
-# In May 2026 PR #25045 was merged from a branch that had been disconnected
-# from main's history (likely an accidental `git checkout --orphan` or
-# `.git/` re-init).  GitHub's merge UI does not refuse merges of unrelated
-# histories, so the PR landed cleanly with the intended one-file change —
-# but its parent-less root commit (413990c94) got grafted into main as a
-# second root, and ~1500 files' worth of `git blame` history collapsed
-# onto that single commit.
-#
-# This check catches the failure mode by requiring `git merge-base` between
-# the PR head and main to be non-empty.
-
-on:
-  pull_request:
-    branches: [main]
-
-permissions:
-  contents: read
-
-jobs:
-  check-common-ancestor:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
-        with:
-          fetch-depth: 0  # full history both sides for merge-base
-
-      - name: Reject PRs with no common ancestor on main
-        run: |
-          # `git merge-base` exits non-zero AND prints nothing when the two
-          # commits share no ancestor.  We check both conditions explicitly
-          # so the failure message is clear regardless of which signal fires
-          # first.
-          if ! BASE=$(git merge-base origin/main HEAD 2>/dev/null) || [ -z "$BASE" ]; then
-            echo ""
-            echo "::error::This PR has no common ancestor with main."
-            echo ""
-            echo "Your branch's history is disconnected from main.  Common causes:"
-            echo "  - the branch was created with 'git checkout --orphan'"
-            echo "  - '.git/' was re-initialized at some point during the work"
-            echo "  - the branch was force-pushed from an unrelated repository"
-            echo ""
-            echo "Merging an unrelated-history PR grafts a parent-less root commit"
-            echo "into main and collapses git blame for every file in that snapshot."
-            echo "Reference: PR #25045 caused this and re-rooted blame on ~1500"
-            echo "files to a single orphan commit."
-            echo ""
-            echo "To fix, rebase your changes onto current main:"
-            echo "  git fetch origin main"
-            echo "  git checkout -b fix-branch origin/main"
-            echo "  # re-apply your changes (cherry-pick, copy files, etc.)"
-            echo "  git push -f origin fix-branch"
-            exit 1
-          fi
-          echo "::notice::Common ancestor with main: $BASE"

.github/workflows/nix-lockfile-fix.yml

@@ -6,8 +6,8 @@ on:
     paths:
       - 'ui-tui/package-lock.json'
       - 'ui-tui/package.json'
-      - 'apps/dashboard/package-lock.json'
-      - 'apps/dashboard/package.json'
+      - 'web/package-lock.json'
+      - 'web/package.json'
   workflow_dispatch:
     inputs:
       pr_number:
@@ -28,7 +28,7 @@ concurrency:
 jobs:
   # ── Auto-fix on main ───────────────────────────────────────────────
   # Fires when a push to main touches package.json or package-lock.json
-  # in ui-tui/ or apps/dashboard/. Runs fix-lockfiles and pushes the hash
+  # in ui-tui/ or web/. Runs fix-lockfiles and pushes the hash
   # update commit directly to main so Nix builds never stay broken.
   #
   # Safety invariants:
@@ -110,7 +110,7 @@ jobs:
             # run recompute from the correct package-lock state.
             pkg_changed="$(git diff --name-only "$BASE_SHA"..origin/main -- \
               'ui-tui/package-lock.json' 'ui-tui/package.json' \
-              'apps/dashboard/package-lock.json' 'apps/dashboard/package.json' || true)"
+              'web/package-lock.json' 'web/package.json' || true)"
             if [ -n "$pkg_changed" ]; then
               echo "::warning::Package files changed since hash computation — aborting; a fresh run will recompute"
               exit 0

.github/workflows/supply-chain-audit.yml

@@ -11,7 +11,6 @@ on:
       - '**/sitecustomize.py'
       - '**/usercustomize.py'
       - '**/__init__.pth'
-      - 'pyproject.toml'
 
 permissions:
   pull-requests: write
@@ -138,68 +137,3 @@ jobs:
         run: |
           echo "::error::CRITICAL supply chain risk patterns detected in this PR. See the PR comment for details."
           exit 1
-
-  dep-bounds:
-    name: Check PyPI dependency upper bounds
-    runs-on: ubuntu-latest
-    if: contains(github.event.pull_request.changed_files_url, 'pyproject.toml') || true
-    steps:
-      - name: Checkout
-        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
-        with:
-          fetch-depth: 0
-
-      - name: Check for unbounded PyPI deps
-        id: bounds
-        run: |
-          set -euo pipefail
-
-          BASE="${{ github.event.pull_request.base.sha }}"
-          HEAD="${{ github.event.pull_request.head.sha }}"
-
-          # Only check added lines in pyproject.toml
-          ADDED=$(git diff "$BASE".."$HEAD" -- pyproject.toml | grep '^+' | grep -v '^+++' || true)
-
-          if [ -z "$ADDED" ]; then
-            echo "found=false" >> "$GITHUB_OUTPUT"
-            exit 0
-          fi
-
-          # Match PyPI dep specs that have >= but no < ceiling.
-          # Pattern: "package>=version" without a following ",<" bound.
-          # Excludes git+ URLs (which use commit SHAs) and comments.
-          UNBOUNDED=$(echo "$ADDED" | grep -oE '"[a-zA-Z0-9_-]+(\[[^\]]*\])?>=[ 0-9.]+"' | grep -v ',<' || true)
-
-          if [ -n "$UNBOUNDED" ]; then
-            echo "found=true" >> "$GITHUB_OUTPUT"
-            echo "$UNBOUNDED" > /tmp/unbounded.txt
-          else
-            echo "found=false" >> "$GITHUB_OUTPUT"
-          fi
-
-      - name: Post unbounded dep warning
-        if: steps.bounds.outputs.found == 'true'
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          BODY="## ⚠️ Unbounded PyPI Dependency Detected
-
-          This PR adds PyPI dependencies without a \`<next_major\` upper bound. Per our [supply chain policy](../blob/main/CONTRIBUTING.md#dependency-pinning-policy-supply-chain-hardening), all PyPI deps must be pinned as \`>=floor,<next_major\`.
-
-          **Unbounded specs found:**
-          \`\`\`
-          $(cat /tmp/unbounded.txt)
-          \`\`\`
-
-          **Fix:** Add an upper bound, e.g. \`\"package>=1.2.0,<2\"\`
-
-          ---
-          *See PR #2810 and CONTRIBUTING.md for the full policy rationale.*"
-
-          gh pr comment "${{ github.event.pull_request.number }}" --body "$BODY" || echo "::warning::Could not post PR comment (expected for fork PRs)"
-
-      - name: Fail on unbounded deps
-        if: steps.bounds.outputs.found == 'true'
-        run: |
-          echo "::error::PyPI dependencies without upper bounds detected. Add <next_major ceiling per CONTRIBUTING.md policy."
-          exit 1

.github/workflows/tests.yml

@@ -55,14 +55,11 @@ jobs:
 
   e2e:
     runs-on: ubuntu-latest
-    timeout-minutes: 15
+    timeout-minutes: 10
     steps:
       - name: Checkout code
         uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
 
-      - name: Install system dependencies
-        run: sudo apt-get update && sudo apt-get install -y ripgrep
-
       - name: Install uv
         uses: astral-sh/setup-uv@d4b2f3b6ecc6e67c4457f6d3e41ec42d3d0fcb86  # v5
 

.github/workflows/upload_to_pypi.yml

@@ -1,163 +0,0 @@
-name: Publish to PyPI
-
-# Triggered by CalVer tag pushes from scripts/release.py (e.g. v2026.5.15)
-# Can also be triggered manually from the Actions tab as an escape hatch.
-on:
-  push:
-    tags:
-      - 'v20*'  # CalVer tags: v2026.5.15, v2026.5.15.2, etc.
-  workflow_dispatch:
-    inputs:
-      confirm_tag:
-        description: 'Tag to publish (e.g. v2026.5.15). Must already exist.'
-        required: true
-        type: string
-
-# Restrict default token to read-only; each job escalates as needed.
-permissions:
-  contents: read
-
-# Prevent overlapping publishes (e.g. two same-day tags pushed quickly).
-concurrency:
-  group: pypi-publish
-  cancel-in-progress: false
-
-jobs:
-  build:
-    name: Build distribution 📦
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5  # v4
-        with:
-          persist-credentials: false
-          # On workflow_dispatch, check out the confirmed tag.
-          ref: ${{ inputs.confirm_tag || github.ref }}
-          fetch-tags: true
-
-      - name: Validate tag exists
-        if: github.event_name == 'workflow_dispatch'
-        run: |
-          if ! git tag -l "${{ inputs.confirm_tag }}" | grep -q .; then
-            echo "::error::Tag '${{ inputs.confirm_tag }}' does not exist in the repo"
-            exit 1
-          fi
-
-      - name: Set up Python
-        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065  # v5
-        with:
-          python-version: '3.13'
-
-      - name: Install uv
-        uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e  # v6
-
-      - name: Set up Node.js
-        uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020  # v4
-        with:
-          node-version: '22'
-
-      - name: Build web dashboard
-        run: cd web && npm ci && npm run build
-
-      - name: Build TUI bundle
-        run: cd ui-tui && npm ci && npm run build
-
-      - name: Bundle TUI into hermes_cli
-        run: |
-          mkdir -p hermes_cli/tui_dist
-          cp ui-tui/dist/entry.js hermes_cli/tui_dist/entry.js
-
-      - name: Verify frontend assets exist
-        run: |
-          test -f hermes_cli/web_dist/index.html || { echo "ERROR: web_dist not built"; exit 1; }
-          test -f hermes_cli/tui_dist/entry.js || { echo "ERROR: tui_dist not built"; exit 1; }
-
-      - name: Bundle install.sh into wheel
-        run: |
-          mkdir -p hermes_cli/scripts
-          cp scripts/install.sh hermes_cli/scripts/install.sh
-
-      - name: Build wheel and sdist
-        run: uv build --sdist --wheel
-
-      - name: Upload distribution artifacts
-        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02  # v4
-        with:
-          name: python-package-distributions
-          path: dist/
-
-  publish:
-    name: Publish to PyPI
-    needs: build
-    runs-on: ubuntu-latest
-    environment:
-      name: pypi
-      url: https://pypi.org/p/hermes-agent
-    permissions:
-      id-token: write  # OIDC trusted publishing
-
-    steps:
-      - name: Download distribution artifacts
-        uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093  # v4
-        with:
-          name: python-package-distributions
-          path: dist/
-
-      - name: Publish to PyPI
-        uses: pypa/gh-action-pypi-publish@cef221092ed1bacb1cc03d23a2d87d1d172e277b  # v1.14.0
-        with:
-          skip-existing: true
-
-  sign:
-    name: Sign and attach to GitHub Release
-    # Only runs on tag pushes — release.py creates the GitHub Release,
-    # and workflow_dispatch won't have a matching release to attach to.
-    if: startsWith(github.ref, 'refs/tags/')
-    needs: publish
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write   # attach assets to the existing release
-      id-token: write   # sigstore signing
-
-    steps:
-      - name: Download distribution artifacts
-        uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093  # v4
-        with:
-          name: python-package-distributions
-          path: dist/
-
-      - name: Wait for GitHub Release to exist
-        env:
-          GITHUB_TOKEN: ${{ github.token }}
-        # release.py creates the GitHub Release after pushing the tag,
-        # but this workflow starts from the tag push — wait for it.
-        run: |
-          for i in $(seq 1 30); do
-            if gh release view "$GITHUB_REF_NAME" --repo "$GITHUB_REPOSITORY" >/dev/null 2>&1; then
-              echo "Release $GITHUB_REF_NAME found"
-              exit 0
-            fi
-            echo "Waiting for release... ($i/30)"
-            sleep 10
-          done
-          echo "::warning::Release $GITHUB_REF_NAME not found after 5 minutes — skipping signature upload"
-          echo "skip_sign=true" >> "$GITHUB_ENV"
-
-      - name: Sign with Sigstore
-        if: env.skip_sign != 'true'
-        uses: sigstore/gh-action-sigstore-python@f514d46b907ebcd5bedc05145c03b69c1edd8b46  # v3.0.0
-        with:
-          inputs: >-
-            ./dist/*.tar.gz
-            ./dist/*.whl
-
-      - name: Attach signed artifacts to GitHub Release
-        if: env.skip_sign != 'true'
-        env:
-          GITHUB_TOKEN: ${{ github.token }}
-        # release.py already created the GitHub Release — just upload
-        # the Sigstore signatures alongside the existing assets.
-        run: >-
-          gh release upload
-          "$GITHUB_REF_NAME" dist/*.sigstore.json
-          --repo "$GITHUB_REPOSITORY"
-          --clobber

.gitignore

@@ -54,10 +54,6 @@ environments/benchmarks/evals/
 
 # Web UI build output
 hermes_cli/web_dist/
-apps/desktop/build/
-apps/desktop/dist/
-apps/desktop/release/
-apps/desktop/*.tsbuildinfo
 
 # Web UI assets — synced from @nous-research/ui at build time via
 # `npm run sync-assets` (see web/package.json).
@@ -74,16 +70,3 @@ mini-swe-agent/
 result
 website/static/api/skills-index.json
 models-dev-upstream/
-
-# Local editor / agent tooling (machine-specific; keep in global config, not the repo)
-.codex/
-.cursor/
-.gemini/
-.zed/
-.mcp.json
-opencode.json
-config/mcporter.json
-
-hermes_cli/tui_dist/*
-hermes_cli/scripts/
-docs/superpowers/*

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "tinker-atropos"]
+	path = tinker-atropos
+	url = https://github.com/nousresearch/tinker-atropos

AGENTS.md

@@ -2,8 +2,6 @@
 
 Instructions for AI coding assistants and developers working on the hermes-agent codebase.
 
-**Never give up on the right solution.**
-
 ## Development Environment
 
 ```bash
@@ -58,6 +56,7 @@ hermes-agent/
 ├── tui_gateway/          # Python JSON-RPC backend for the TUI
 ├── acp_adapter/          # ACP server (VS Code / Zed / JetBrains integration)
 ├── cron/                 # Scheduler — jobs.py, scheduler.py
+├── environments/         # RL training environments (Atropos)
 ├── scripts/              # run_tests.sh, release.py, auxiliary scripts
 ├── website/              # Docusaurus docs site
 └── tests/                # Pytest suite (~17k tests across ~900 files as of May 2026)
@@ -68,29 +67,6 @@ hermes-agent/
 `gateway.log` when running the gateway. Profile-aware via `get_hermes_home()`.
 Browse with `hermes logs [--follow] [--level ...] [--session ...]`.
 
-## TypeScript Style
-
-Applies to TypeScript across Hermes: desktop, TUI, website, and future TS packages.
-
-- Prefer small nanostores over component state when state is shared, reused, or read by distant UI.
-- Let each feature own its atoms. Chat state belongs near chat, shell state near shell, shared state in `src/store`.
-- Components that render from an atom should use `useStore`. Non-rendering actions should read with `$atom.get()`.
-- Do not pass state through three components when the leaf can subscribe to the atom.
-- Keep persistence beside the atom that owns it.
-- Keep route roots thin. They compose routes and shell; they should not become controllers.
-- No monolithic hooks. A hook should own one narrow job.
-- Prefer colocated action modules over hidden god hooks.
-- If a callback is pure side effect, use the terse void form:
-  `onState={st => void setGatewayState(st)}`.
-- Async UI handlers should make intent explicit:
-  `onClick={() => void save()}`.
-- Prefer interfaces for public props and shared object shapes. Avoid `type X = { ... }` for object props.
-- Extend React primitives for props: `React.ComponentProps<'button'>`, `React.ComponentProps<typeof Dialog>`, `Omit<...>`, `Pick<...>`.
-- Table-driven beats condition ladders when mapping ids, routes, or views.
-- `src/app` owns routes, pages, and page-specific components.
-- `src/store` owns shared atoms.
-- `src/lib` owns shared pure helpers.
-
 ## File Dependency Chain
 
 ```
@@ -274,7 +250,7 @@ npm test          # vitest
 
 The dashboard embeds the real `hermes --tui` — **not** a rewrite.  See `hermes_cli/pty_bridge.py` + the `@app.websocket("/api/pty")` endpoint in `hermes_cli/web_server.py`.
 
-- Browser loads `apps/dashboard/src/pages/ChatPage.tsx`, which mounts xterm.js's `Terminal` with the WebGL renderer, `@xterm/addon-fit` for container-driven resize, and `@xterm/addon-unicode11` for modern wide-character widths.
+- Browser loads `web/src/pages/ChatPage.tsx`, which mounts xterm.js's `Terminal` with the WebGL renderer, `@xterm/addon-fit` for container-driven resize, and `@xterm/addon-unicode11` for modern wide-character widths.
 - `/api/pty?token=…` upgrades to a WebSocket; auth uses the same ephemeral `_SESSION_TOKEN` as REST, via query param (browsers can't set `Authorization` on WS upgrade).
 - The server spawns whatever `hermes --tui` would spawn, through `ptyprocess` (POSIX PTY — WSL works, native Windows does not).
 - Frames: raw PTY bytes each direction; resize via `\x1b[RESIZE:<cols>;<rows>]` intercepted on the server and applied with `TIOCSWINSZ`.
@@ -333,29 +309,6 @@ The registry handles schema collection, dispatch, availability checking, and err
 
 ---
 
-## Dependency Pinning Policy
-
-All dependencies must have upper bounds to limit supply-chain attack surface.
-This policy was established after the litellm compromise (PR #2796, #2810) and
-reinforced after the Mini Shai-Hulud worm campaign (May 2026).
-
-| Source type | Treatment | Example |
-|---|---|---|
-| PyPI package | `>=floor,<next_major` | `"httpx>=0.28.1,<1"` |
-| Git URL | Commit SHA | `git+https://...@<40-char-sha>` |
-| GitHub Actions | Commit SHA + comment | `uses: actions/checkout@<sha>  # v4` |
-| CI-only pip | `==exact` | `pyyaml==6.0.2` |
-
-**When adding a new dependency to `pyproject.toml`:**
-1. Pin to `>=current_version,<next_major` for post-1.0 (e.g. `>=1.5.0,<2`).
-2. For pre-1.0 packages, use `<0.(current_minor + 2)` (e.g. `>=0.29,<0.32`).
-3. Never commit a bare `>=X.Y.Z` without a ceiling — CI and reviewers will reject it.
-4. Run `uv lock` to regenerate `uv.lock` with hashes.
-
-Reference: #2810 (bounds pass), #9801 (SHA pinning + audit CI).
-
----
-
 ## Adding Configuration
 
 ### config.yaml options:
@@ -560,17 +513,6 @@ generic plugin surface (new hook, new ctx method) — never hardcode
 plugin-specific logic into core. PR #5295 removed 95 lines of hardcoded
 honcho argparse from `main.py` for exactly this reason.
 
-**No new in-tree memory providers (policy, May 2026):** the set of
-built-in memory providers under `plugins/memory/` is closed. New memory
-backends must ship as **standalone plugin repos** that users install
-into `~/.hermes/plugins/` (or via pip entry points) — they implement
-the same `MemoryProvider` ABC, register through the same discovery
-path, and integrate via `hermes memory setup` / `post_setup()` without
-landing in this tree. PRs that add a new directory under
-`plugins/memory/` will be closed with a pointer to publish the
-provider as its own repo. Existing in-tree providers stay; bug fixes
-to them are welcome.
-
 ### Model-provider plugins (`plugins/model-providers/<name>/`)
 
 Every inference backend (openrouter, anthropic, gmi, deepseek, nvidia, …)
@@ -638,86 +580,6 @@ during setup, injected at load time).
 Top-level `tags:` and `category:` are also accepted and mirrored from
 `metadata.hermes.*` by the loader.
 
-### Skill authoring standards (HARDLINE)
-
-Every new or modernized skill — bundled, optional, or contributed —
-must meet these standards before merge. Reviewers reject PRs that
-violate them.
-
-1. **`description` ≤ 60 characters, one sentence, ends with a period.**
-   Long descriptions bloat skill listings and dilute the model's
-   attention when many skills are loaded. State the capability, not
-   the implementation. No marketing words ("powerful",
-   "comprehensive", "seamless", "advanced"). Don't repeat the skill
-   name. Verify with:
-   ```python
-   import re, pathlib
-   m = re.search(r'^description: (.*)$',
-                 pathlib.Path('skills/<cat>/<name>/SKILL.md').read_text(),
-                 re.MULTILINE)
-   assert len(m.group(1)) <= 60, len(m.group(1))
-   ```
-
-2. **Tools referenced in SKILL.md prose must be native Hermes tools or
-   MCP servers the skill explicitly expects.** When the skill needs a
-   capability, point at the proper tool by name in backticks
-   (`` `terminal` ``, `` `web_extract` ``, `` `read_file` ``,
-   `` `patch` ``, `` `search_files` ``, `` `vision_analyze` ``,
-   `` `browser_navigate` ``, `` `delegate_task` ``, etc.). Do NOT
-   name shell utilities the agent already has wrapped — `grep` →
-   `search_files`, `cat`/`head`/`tail` → `read_file`, `sed`/`awk` →
-   `patch`, `find`/`ls` → `search_files target='files'`. If the skill
-   depends on an MCP server, name the MCP server and document the
-   expected setup in `## Prerequisites`. Anything else (third-party
-   CLIs, shell pipelines, etc.) is fair game inside script files but
-   should not be the headline interaction surface in the prose.
-
-3. **`platforms:` gating audited against actual script imports.**
-   Skills that use POSIX-only primitives (`fcntl`, `termios`,
-   `os.setsid`, `os.kill(pid, 0)` for liveness, `/proc`, `/tmp`
-   hardcoded, `signal.SIGKILL`, bash heredocs, `osascript`, `apt`,
-   `systemctl`) must declare their supported platforms. Default
-   posture: try to fix it cross-platform first — `tempfile.gettempdir`,
-   `pathlib.Path`, `psutil.pid_exists`, Python-level filtering instead
-   of `grep`. Gate to a narrower set only when the dependency is
-   genuinely platform-bound.
-
-4. **`author` credits the human contributor first.** For external
-   contributions, the contributor's real name + GitHub handle goes
-   first; "Hermes Agent" is the secondary collaborator. If the
-   contributor's commit shows "Hermes Agent" as author (because they
-   used Hermes to draft the skill), replace it with their actual name
-   — credit the human, not the tool.
-
-5. **SKILL.md body uses the modern section order.** `# <Skill> Skill`
-   title, 2-3 sentence intro stating what it does and doesn't do,
-   `## When to Use`, `## Prerequisites`, `## How to Run`,
-   `## Quick Reference`, `## Procedure`, `## Pitfalls`,
-   `## Verification`. Target ~200 lines for a complex skill,
-   ~100 lines for a simple one. Cut redundant intro fluff, marketing
-   prose, and re-explanations of env vars already in
-   `## Prerequisites`.
-
-6. **Scripts go in `scripts/`, references in `references/`,
-   templates in `templates/`.** Don't expect the model to inline-write
-   parsers, XML walkers, or non-trivial logic every call — ship a
-   helper script. Reference it from SKILL.md by path relative to the
-   skill directory.
-
-7. **Tests live at `tests/skills/test_<skill>_skill.py`** and use only
-   stdlib + pytest + `unittest.mock`. No live network calls. Run via
-   `scripts/run_tests.sh tests/skills/test_<skill>_skill.py -q`.
-
-8. **`.env.example` additions are isolated to a clearly delimited
-   block.** Don't touch the surrounding file — contributor-supplied
-   `.env.example` versions are usually stale and edits outside the
-   skill's own block must be dropped during salvage.
-
-The full salvage / modernization checklist for external skill PRs
-lives in the `hermes-agent-dev` skill at
-`references/new-skill-pr-salvage.md` — load it before polishing
-contributor skill PRs.
-
 ---
 
 ## Toolsets

CONTRIBUTING.md

@@ -49,24 +49,6 @@ If your skill is specialized, community-contributed, or niche, it's better suite
 
 ---
 
-## Memory Providers: Ship as a Standalone Plugin
-
-**We are no longer accepting new memory providers into this repo.** The set of built-in providers under `plugins/memory/` (honcho, mem0, supermemory, byterover, hindsight, holographic, openviking, retaindb) is closed. If you want to add a new memory backend, publish it as a **standalone plugin repo** that users install into `~/.hermes/plugins/` (or via a pip entry point).
-
-Standalone memory plugins:
-
-- Implement the same `MemoryProvider` ABC (`agent/memory_provider.py`) — `sync_turn`, `prefetch`, `shutdown`, and optionally `post_setup(hermes_home, config)` for setup-wizard integration
-- Use the same discovery system — `discover_memory_providers()` picks them up from user/project plugin directories and pip entry points
-- Integrate with `hermes memory setup` via `post_setup()` — no need to touch core code
-- Can register their own CLI subcommands via `register_cli(subparser)` in a `cli.py` file
-- Get all the same lifecycle hooks and config plumbing as in-tree providers
-
-PRs that add a new directory under `plugins/memory/` will be closed with a pointer to publish the provider as its own repo. Existing in-tree providers stay; bug fixes to them are welcome.
-
-This isn't a quality bar — it's a coupling-and-maintenance decision. Memory providers are the most common plugin type and they shouldn't all live in this tree.
-
----
-
 ## Development Setup
 
 ### Prerequisites
@@ -91,6 +73,9 @@ export VIRTUAL_ENV="$(pwd)/venv"
 # Install with all extras (messaging, cron, CLI menus, dev tools)
 uv pip install -e ".[all,dev]"
 
+# Optional: RL training submodule
+# git submodule update --init tinker-atropos && uv pip install -e "./tinker-atropos"
+
 # Optional: browser tools
 npm install
 ```
@@ -193,6 +178,7 @@ hermes-agent/
 │
 ├── skills/                   # Bundled skills (copied to ~/.hermes/skills/ on install)
 ├── optional-skills/          # Official optional skills (discoverable via hub, not activated by default)
+├── environments/             # RL training environments (Atropos integration)
 ├── tests/                    # Test suite
 ├── website/                  # Documentation site (hermes-agent.nousresearch.com)
 │
@@ -475,58 +461,6 @@ Gateway and messaging sessions never collect secrets in-band; they instruct the
 
 See `skills/gifs/gif-search/` and `skills/email/himalaya/` for examples.
 
-### Skill authoring standards (HARDLINE)
-
-Every new or modernized skill — bundled, optional, or contributed — must meet these standards before merge. Reviewers reject PRs that violate them.
-
-1. **`description` ≤ 60 characters, one sentence, ends with a period.** Long descriptions bloat the skill listing UI and dilute the model's attention when many skills are loaded. State the capability, not the implementation. No marketing words ("powerful", "comprehensive", "seamless", "advanced"). Don't repeat the skill name. Verify with:
-   ```python
-   import re, pathlib
-   m = re.search(r'^description: (.*)$',
-                 pathlib.Path('skills/<cat>/<name>/SKILL.md').read_text(),
-                 re.MULTILINE)
-   assert len(m.group(1)) <= 60, len(m.group(1))
-   ```
-
-   Good: `Search arXiv papers by keyword, author, category, or ID.`
-   Bad: `A powerful and comprehensive skill that allows the agent to search arXiv for relevant academic papers using various criteria including keywords, authors, and categories.`
-
-2. **Tools referenced in SKILL.md prose must be native Hermes tools or MCP servers the skill explicitly expects.** When the skill needs a capability, point at the proper tool by name in backticks: `` `terminal` ``, `` `web_extract` ``, `` `web_search` ``, `` `read_file` ``, `` `write_file` ``, `` `patch` ``, `` `search_files` ``, `` `vision_analyze` ``, `` `browser_navigate` ``, `` `delegate_task` ``, `` `image_generate` ``, `` `text_to_speech` ``, `` `cronjob` ``, `` `memory` ``, `` `skill_view` ``, `` `todo` ``, `` `execute_code` ``.
-
-   Do NOT name shell utilities the agent already has wrapped:
-
-   | Don't say | Say |
-   |---|---|
-   | `grep`, `rg` | `search_files` |
-   | `cat`, `head`, `tail` | `read_file` |
-   | `sed`, `awk` | `patch` |
-   | `find`, `ls` | `search_files` (with `target='files'`) |
-   | `curl` for content extraction | `web_extract` |
-   | `echo > file`, `cat <<EOF` | `write_file` |
-
-   If the skill depends on an MCP server, name the MCP server and document its setup in `## Prerequisites`. Third-party CLIs (e.g. `ffmpeg`, `gh`, a specific SDK) are fine to invoke from inside script files, but the prose should frame the interaction as "invoke through the `terminal` tool", not as a manual shell session.
-
-3. **`platforms:` gating audited against actual script imports.** Skills that use POSIX-only primitives (`fcntl`, `termios`, `os.setsid`, `os.kill(pid, 0)` for liveness, `/proc`, hardcoded `/tmp` paths, `signal.SIGKILL`, bash heredocs, `osascript`, `apt`, `systemctl`) must declare their supported platforms via the `platforms:` frontmatter. Default posture is to fix it cross-platform first — `tempfile.gettempdir()`, `pathlib.Path`, `psutil.pid_exists()`, Python-level filtering instead of `grep`. Gate to a narrower set only when the dependency is genuinely platform-bound (e.g. `osascript` is macOS-only, `/proc` is Linux-only).
-
-4. **`author` credits the human contributor first.** For external contributions, the contributor's real name + GitHub handle goes first (`Jane Doe (jane-doe)`); "Hermes Agent" is the secondary collaborator. If the contributor's commit shows "Hermes Agent" as author because they used Hermes to draft the skill, replace it with their actual name — credit the human, not the tool.
-
-5. **SKILL.md body uses the modern section order.** `# <Skill> Skill` title, 2-3 sentence intro stating what it does and what it doesn't do, then:
-   - `## When to Use` — trigger conditions
-   - `## Prerequisites` — env vars, install steps, MCP setup, API key sourcing
-   - `## How to Run` — canonical invocation through the `terminal` tool
-   - `## Quick Reference` — flat command/API reference
-   - `## Procedure` — numbered steps with copy-paste commands
-   - `## Pitfalls` — known limits, rate limits, things that look broken but aren't
-   - `## Verification` — single command that proves the skill works
-
-   Target ~200 lines for a complex skill, ~100 lines for a simple one. Cut redundant intro fluff, marketing prose, and re-explanations of env vars already documented in `## Prerequisites`.
-
-6. **Scripts go in `scripts/`, references in `references/`, templates in `templates/`.** Don't expect the model to inline-write parsers, XML walkers, or non-trivial logic every call — ship a helper script. Reference scripts from SKILL.md by path relative to the skill directory.
-
-7. **Tests live at `tests/skills/test_<skill>_skill.py`** and use only stdlib + pytest + `unittest.mock`. No live network calls. Run via `scripts/run_tests.sh tests/skills/test_<skill>_skill.py -q`. Must pass under the hermetic CI env (no API keys leaking through). Use `monkeypatch` and `tmp_path` for any env-var or filesystem dependencies.
-
-8. **`.env.example` additions are isolated to a clearly delimited block.** Don't touch the surrounding file — contributor-supplied `.env.example` versions are usually stale, and edits outside the skill's own block will be dropped during salvage. Comment all values with `#` (it's documentation, not live config).
-
 ### Skill guidelines
 
 - **No external dependencies unless absolutely necessary.** Prefer stdlib Python, curl, and existing Hermes tools (`web_extract`, `terminal`, `read_file`).
@@ -800,47 +734,6 @@ Hermes has terminal access. Security matters.
 
 If your PR affects security, note it explicitly in the description.
 
-### Dependency pinning policy (supply chain hardening)
-
-After the [litellm supply chain compromise](https://github.com/BerriAI/litellm/issues/24512) in March 2026 and the [Mini Shai-Hulud worm campaign](https://socket.dev/blog/tanstack-npm-packages-compromised-mini-shai-hulud-supply-chain-attack) in May 2026, all dependencies must follow these rules:
-
-| Source type | Required treatment | Rationale |
-|---|---|---|
-| **PyPI package** | `>=floor,<next_major` | PyPI versions are immutable once published, but new versions can be pushed into your range. A `<next_major` ceiling stops a 1.x install from upgrading to a malicious 2.0.0. |
-| **Git URL** (atroposlib, tinker, yc-bench, Baileys) | Full commit SHA | Branches and tags are mutable refs; SHA is content-addressed. |
-| **GitHub Actions** | Full commit SHA + version comment | Action tags are mutable refs (e.g. tj-actions/changed-files March 2025). Pin as `uses: owner/action@<sha>  # vX.Y.Z` |
-| **CI-only pip installs** | `==exact` | Hermetic CI builds; churn is acceptable. |
-
-**Every new PyPI dependency in a PR must have a `<next_major` upper bound.** PRs adding unbounded `>=X.Y.Z` specs will be rejected by reviewers. The `supply-chain-audit.yml` CI workflow also flags dependency manifest changes for manual review.
-
-**How to determine the ceiling:**
-- If the package is at version `1.x.y`, use `<2`.
-- If the package is at version `0.x.y` (pre-1.0), use `<0.(current_minor + 2)` — e.g. if current is `0.29.x`, use `<0.32`. This gives ~2 minor versions of headroom while keeping the window small enough that a hostile takeover version is unlikely to land inside it.
-- Exception: packages with very stable APIs (e.g. `aiohttp-socks`) can use `<1` at reviewer discretion.
-
-**Examples:**
-```toml
-# ✅ Correct — post-1.0
-"openai>=2.21.0,<3"
-"pydantic>=2.12.5,<3"
-
-# ✅ Correct — pre-1.0 (tight minor window)
-"asyncpg>=0.29,<0.32"
-"aiosqlite>=0.20,<0.23"
-"hindsight-client>=0.4.22,<0.5"
-
-# ❌ Rejected — no upper bound
-"some-package>=1.2.3"
-
-# ❌ Rejected — too tight (blocks legitimate patches)
-"some-package==1.2.3"
-
-# ❌ Rejected — too loose for pre-1.0 (allows 80 minor versions)
-"some-package>=0.20,<1"
-```
-
-**Reference PRs:** #2796 (litellm removal), #2810 (upper bounds pass), #9801 (SHA pinning + supply-chain-audit CI).
-
 ---
 
 ## Pull Request Process

Dockerfile

@@ -94,13 +94,9 @@ RUN cd web && npm run build && \
 # hermes_cli/main.py succeeds (see #18800). /opt/hermes/web is build-time
 # only (HERMES_WEB_DIST points at hermes_cli/web_dist) and is intentionally
 # not chowned here.
-# The .venv MUST be hermes-writable so lazy_deps.py can install platform
-# packages (discord.py, telegram, slack, etc.) at first gateway boot.
-# Without this, `uv pip install` fails with EACCES and all messaging
-# adapters silently fail to load.  See tools/lazy_deps.py.
 USER root
 RUN chmod -R a+rX /opt/hermes && \
-    chown -R hermes:hermes /opt/hermes/.venv /opt/hermes/ui-tui /opt/hermes/node_modules
+    chown -R hermes:hermes /opt/hermes/ui-tui /opt/hermes/node_modules
 # Start as root so the entrypoint can usermod/groupmod + gosu.
 # If HERMES_UID is unset, the entrypoint drops to the default hermes user (10000).
 

README.md

@@ -14,7 +14,7 @@
 
 **The self-improving AI agent built by [Nous Research](https://nousresearch.com).** It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who you are across sessions. Run it on a $5 VPS, a GPU cluster, or serverless infrastructure that costs nearly nothing when idle. It's not tied to your laptop — talk to it from Telegram while it works on a cloud VM.
 
-Use any model you want — [Nous Portal](https://portal.nousresearch.com), [OpenRouter](https://openrouter.ai) (200+ models), [NovitaAI](https://novita.ai) (AI-native cloud for Model API, Agent Sandbox, and GPU Cloud), [NVIDIA NIM](https://build.nvidia.com) (Nemotron), [Xiaomi MiMo](https://platform.xiaomimimo.com), [z.ai/GLM](https://z.ai), [Kimi/Moonshot](https://platform.moonshot.ai), [MiniMax](https://www.minimax.io), [Hugging Face](https://huggingface.co), OpenAI, or your own endpoint. Switch with `hermes model` — no code changes, no lock-in.
+Use any model you want — [Nous Portal](https://portal.nousresearch.com), [OpenRouter](https://openrouter.ai) (200+ models), [NVIDIA NIM](https://build.nvidia.com) (Nemotron), [Xiaomi MiMo](https://platform.xiaomimimo.com), [z.ai/GLM](https://z.ai), [Kimi/Moonshot](https://platform.moonshot.ai), [MiniMax](https://www.minimax.io), [Hugging Face](https://huggingface.co), OpenAI, or your own endpoint. Switch with `hermes model` — no code changes, no lock-in.
 
 <table>
 <tr><td><b>A real terminal interface</b></td><td>Full TUI with multiline editing, slash-command autocomplete, conversation history, interrupt-and-redirect, and streaming tool output.</td></tr>
@@ -23,7 +23,7 @@ Use any model you want — [Nous Portal](https://portal.nousresearch.com), [Open
 <tr><td><b>Scheduled automations</b></td><td>Built-in cron scheduler with delivery to any platform. Daily reports, nightly backups, weekly audits — all in natural language, running unattended.</td></tr>
 <tr><td><b>Delegates and parallelizes</b></td><td>Spawn isolated subagents for parallel workstreams. Write Python scripts that call tools via RPC, collapsing multi-step pipelines into zero-context-cost turns.</td></tr>
 <tr><td><b>Runs anywhere, not just your laptop</b></td><td>Seven terminal backends — local, Docker, SSH, Singularity, Modal, Daytona, and Vercel Sandbox. Daytona and Modal offer serverless persistence — your agent's environment hibernates when idle and wakes on demand, costing nearly nothing between sessions. Run it on a $5 VPS or a GPU cluster.</td></tr>
-<tr><td><b>Research-ready</b></td><td>Batch trajectory generation, trajectory compression for training the next generation of tool-calling models.</td></tr>
+<tr><td><b>Research-ready</b></td><td>Batch trajectory generation, Atropos RL environments, trajectory compression for training the next generation of tool-calling models.</td></tr>
 </table>
 
 ---
@@ -175,6 +175,8 @@ uv pip install -e ".[all,dev]"
 scripts/run_tests.sh
 ```
 
+> **RL Training (optional):** The RL/Atropos integration (`environments/`) — see [`CONTRIBUTING.md`](https://github.com/NousResearch/hermes-agent/blob/main/CONTRIBUTING.md#development-setup) for the full setup.
+
 ---
 
 ## Community

README.zh-CN.md

@@ -23,7 +23,7 @@
 <tr><td><b>定时自动化</b></td><td>内置 cron 调度器，支持向任何平台投递。日报、夜间备份、周审计——全部用自然语言描述，无人值守运行。</td></tr>
 <tr><td><b>委派与并行</b></td><td>生成隔离子代理处理并行工作流。编写 Python 脚本通过 RPC 调用工具，将多步管道压缩为零上下文开销的轮次。</td></tr>
 <tr><td><b>随处运行</b></td><td>六种终端后端——本地、Docker、SSH、Daytona、Singularity 和 Modal。Daytona 和 Modal 提供 Serverless 持久化——代理环境空闲时休眠、按需唤醒，空闲期间几乎零成本。$5 VPS 或 GPU 集群都能跑。</td></tr>
-<tr><td><b>研究就绪</b></td><td>批量轨迹生成、轨迹压缩——用于训练下一代工具调用模型。</td></tr>
+<tr><td><b>研究就绪</b></td><td>批量轨迹生成、Atropos RL 环境、轨迹压缩——用于训练下一代工具调用模型。</td></tr>
 </table>
 
 ---
@@ -161,6 +161,12 @@ uv pip install -e ".[all,dev]"
 python -m pytest tests/ -q
 ```
 
+> **RL 训练（可选）：** 如需参与 RL/Tinker-Atropos 集成开发：
+> ```bash
+> git submodule update --init tinker-atropos
+> uv pip install -e "./tinker-atropos"
+> ```
+
 ---
 
 ## 社区

RELEASE_v0.14.0.md

@@ -1,477 +0,0 @@
-# Hermes Agent v0.14.0 (v2026.5.16)
-
-**Release Date:** May 16, 2026
-**Since v0.13.0:** 808 commits · 633 merged PRs · 1393 files changed · 165,061 insertions · 545 issues closed (12 P0, 50 P1) · 215 community contributors (including co-authors)
-
-> The Foundation Release — Hermes Agent installs and runs anywhere now. Native Windows ships in early beta with a full PowerShell installer story, a `pip install hermes-agent` wheel lands on PyPI, lazy-deps reshape what `pip install hermes-agent` actually pulls down, the supply-chain checker scans every install/upgrade for unsafe versions, and a new OpenAI-compatible local proxy lets Codex / Aider / Cline talk to OAuth-only providers (Claude Pro, ChatGPT Pro, SuperGrok). The cold-start wave shaves ~19 seconds off `hermes` launch, browser-tool CDP calls run 180x faster, and `hermes tools` All-Platforms drops from 14s to under 1.5s. Two new messaging platforms (LINE and SimpleX Chat) and a Microsoft Graph foundation (Teams pipeline + webhook adapter) land alongside `/handoff` that finally transfers sessions live, `vision_analyze` passing pixels through to vision-capable models, `x_search` as a first-class tool, LSP semantic diagnostics on every `write_file` / `patch`, a unified pluggable `video_generate`, a `computer_use` cua-driver backend, cross-session 1-hour Claude prompt caching, a per-turn file-mutation verifier, plus 9 new optional skills. 50+ P1 closures, 12 P0 closures.
-
----
-
-## ✨ Highlights
-
-- **Native Windows support (early beta)** — full PowerShell installer, native subprocess/PTY paths, taskkill-based process management, MinGit auto-install, Microsoft Store python stub detection, foreground Ctrl+C preservation, taskkill+ps2 fallback, npm prefix handling, and ~40 follow-up Windows-only fixes across CLI / gateway / TUI / curator / tools. Hermes finally runs natively on `cmd.exe` and PowerShell, no WSL required. ([#21561](https://github.com/NousResearch/hermes-agent/pull/21561), [#22130](https://github.com/NousResearch/hermes-agent/pull/22130), [#22752](https://github.com/NousResearch/hermes-agent/pull/22752), [#26618](https://github.com/NousResearch/hermes-agent/pull/26618), and many more)
-
-- **`pip install hermes-agent && hermes`** — Hermes Agent is now a real PyPI package. One command, no clone, no git, no shell installer. Wheel includes the Ink TUI bundle and shell launcher. (salvage of [#26350](https://github.com/NousResearch/hermes-agent/pull/26350)) ([#26593](https://github.com/NousResearch/hermes-agent/pull/26593))
-
-- **Cold-start performance wave — ~19s off `hermes` launch** — skills cache, lazy Feishu import, no Nous HTTP at startup, plus PEP-562 lazy adapter imports (QQ, Yuanbao, Teams, Google Chat), deferred `fal_client` / `google-cloud` / `httpx` loads, models.dev disk-cache-first lookup, parallel doctor API checks, eager-skip plugin discovery on built-in subcommands, `hermes tools` All-Platforms drops from 14s to <1.5s, welcome banner skipped on `chat -q`. ([#22138](https://github.com/NousResearch/hermes-agent/pull/22138), [#22120](https://github.com/NousResearch/hermes-agent/pull/22120), [#22681](https://github.com/NousResearch/hermes-agent/pull/22681), [#22790](https://github.com/NousResearch/hermes-agent/pull/22790), [#22808](https://github.com/NousResearch/hermes-agent/pull/22808), [#22831](https://github.com/NousResearch/hermes-agent/pull/22831), [#22859](https://github.com/NousResearch/hermes-agent/pull/22859), [#22904](https://github.com/NousResearch/hermes-agent/pull/22904), [#22766](https://github.com/NousResearch/hermes-agent/pull/22766), [#25341](https://github.com/NousResearch/hermes-agent/pull/25341))
-
-- **180x faster `browser_console` evaluations** — routed through the supervisor's persistent CDP WebSocket instead of spawning a fresh DevTools session per call. Real-world page interactions feel instant. ([#23226](https://github.com/NousResearch/hermes-agent/pull/23226))
-
-- **Supply-chain advisory checker + lazy-deps framework + tiered install fallback** — every `pip install` / `hermes update` scans dependencies against an advisory list, lazy-deps replace heavy import-time loads with first-use installs, and the installer falls back through extras tiers when a wheel rejects on the target platform. ([#24220](https://github.com/NousResearch/hermes-agent/pull/24220))
-
-- **OpenAI-compatible local proxy** — `hermes proxy` exposes any OAuth-authed provider (Claude Pro, ChatGPT Pro, SuperGrok) as an OpenAI-compatible endpoint that Codex / Aider / Cline / VS Code Continue can hit. Your subscription, your tools. ([#25969](https://github.com/NousResearch/hermes-agent/pull/25969))
-
-- **Cross-session 1-hour Claude prompt cache** — Anthropic / OpenRouter / Nous Portal now share a 1h prefix cache across sessions for Claude models. Fast resume, fast `/new`, lower cost on repeat work. ([#23828](https://github.com/NousResearch/hermes-agent/pull/23828))
-
-- **Two new messaging platforms — LINE + SimpleX Chat** — LINE Messaging API lands as a first-class platform, SimpleX Chat salvages #2558 onto the modern adapter spec. Hermes is now on 22 platforms. ([#23197](https://github.com/NousResearch/hermes-agent/pull/23197), [#26232](https://github.com/NousResearch/hermes-agent/pull/26232))
-
-- **Microsoft Graph foundation — Teams pipeline + webhook adapter** — `msgraph` auth/client foundation, webhook listener platform, Teams pipeline plugin runtime, and Teams outbound delivery via the existing adapter — Hermes can now read and post to Teams. (salvages of #21408–#21411) ([#21922](https://github.com/NousResearch/hermes-agent/pull/21922), [#21969](https://github.com/NousResearch/hermes-agent/pull/21969), [#22007](https://github.com/NousResearch/hermes-agent/pull/22007), [#22024](https://github.com/NousResearch/hermes-agent/pull/22024))
-
-- **`/handoff` actually transfers the session live** — the agent's active session moves to a different model / persona / profile mid-conversation, with messages, tool history, and context preserved. ([#23395](https://github.com/NousResearch/hermes-agent/pull/23395))
-
-- **`x_search` — first-class X (Twitter) search tool** — gated tool with OAuth-or-API-key auth, no skill needed to query the timeline. ([#26763](https://github.com/NousResearch/hermes-agent/pull/26763))
-
-- **`vision_analyze` returns pixels to vision-capable models** — when the active model can see, `vision_analyze` now hands the image straight through instead of falling back to a text description. ([#22955](https://github.com/NousResearch/hermes-agent/pull/22955))
-
-- **LSP semantic diagnostics on every write** — `write_file` and `patch` now run real language-server diagnostics on the post-edit file (delta-only) and surface real errors before they ship downstream. ([#24168](https://github.com/NousResearch/hermes-agent/pull/24168), [#25978](https://github.com/NousResearch/hermes-agent/pull/25978))
-
-- **Per-turn file-mutation verifier footer** — after every turn that wrote files, the agent gets a verifier footer summarizing what actually changed on disk — catches silent overwrites and "wrote it but it didn't land" bugs. ([#24498](https://github.com/NousResearch/hermes-agent/pull/24498))
-
-- **Unified `video_generate` with pluggable provider backends** — single tool, any backend. Drop in a new video provider as a plugin, no core changes. ([#25126](https://github.com/NousResearch/hermes-agent/pull/25126))
-
-- **`computer_use` cua-driver backend** — proper focus-safe ops, non-Anthropic provider support, refresh on `hermes update`. Computer-use is no longer locked to a single SDK. (re-salvage of #16936) ([#21967](https://github.com/NousResearch/hermes-agent/pull/21967), [#24063](https://github.com/NousResearch/hermes-agent/pull/24063))
-
-- **xAI Grok OAuth provider — SuperGrok via subscription** — sign in with your xAI account, talk to Grok models from Hermes. ([#26534](https://github.com/NousResearch/hermes-agent/pull/26534))
-
-- **Clarify with buttons — native inline keyboards on Telegram + Discord** — the `clarify` tool renders multi-choice prompts as platform-native buttons instead of typed responses. ([#24199](https://github.com/NousResearch/hermes-agent/pull/24199), [#25485](https://github.com/NousResearch/hermes-agent/pull/25485))
-
-- **Discord channel history backfill (default on)** — Hermes reads recent channel history when joining a thread so it actually knows what's been said. ([#25984](https://github.com/NousResearch/hermes-agent/pull/25984))
-
-- **Watchers skill — RSS / HTTP JSON / GitHub polling via cron `no_agent` mode** — skill recipes that wire change-detection sources directly into cron's script-only watchdog mode. ([#21881](https://github.com/NousResearch/hermes-agent/pull/21881))
-
-- **Zed ACP Registry integration + uvx distribution** — Hermes is in the Zed registry, installable via `uvx` (no npm). Plus `hermes acp --setup-browser` bootstraps browser tools for registry installs. (salvage of [#25908](https://github.com/NousResearch/hermes-agent/pull/25908)) ([#26079](https://github.com/NousResearch/hermes-agent/pull/26079), [#26120](https://github.com/NousResearch/hermes-agent/pull/26120), [#26234](https://github.com/NousResearch/hermes-agent/pull/26234))
-
-- **OpenRouter Pareto Code router** — wire a new OpenRouter router with `min_coding_score` knob. Pick the cheapest model that meets your quality bar. ([#22838](https://github.com/NousResearch/hermes-agent/pull/22838))
-
-- **Optional codex app-server runtime for OpenAI/Codex models** — drives the OpenAI Codex CLI under the hood for OpenAI/Codex paths, with session reuse, wedge retirement, and OAuth refresh classification. ([#24182](https://github.com/NousResearch/hermes-agent/pull/24182), [#25769](https://github.com/NousResearch/hermes-agent/pull/25769))
-
-- **`hermes-skills/huggingface` as a trusted default tap** — community skills index from huggingface.co/skills is available by default in the Skills Hub. ([#26219](https://github.com/NousResearch/hermes-agent/pull/26219))
-
-- **9 new optional skills** — Hyperliquid (perp/spot trading via SDK + REST) (@kshitijk4poor & Hermes), Yahoo Finance market data, api-testing (REST/GraphQL debug), unified EVM multi-chain skill (folds #25291 + #2010 + base/), darwinian-evolver, osint-investigation (closes #355), pinggy-tunnel, watchers (RSS/HTTP/GitHub via cron), Notion overhaul for the Developer Platform (May 2026). ([#23582](https://github.com/NousResearch/hermes-agent/pull/23582), [#23583](https://github.com/NousResearch/hermes-agent/pull/23583), [#23590](https://github.com/NousResearch/hermes-agent/pull/23590), [#25299](https://github.com/NousResearch/hermes-agent/pull/25299), [#26760](https://github.com/NousResearch/hermes-agent/pull/26760), [#26729](https://github.com/NousResearch/hermes-agent/pull/26729), [#26765](https://github.com/NousResearch/hermes-agent/pull/26765), [#21881](https://github.com/NousResearch/hermes-agent/pull/21881), [#26612](https://github.com/NousResearch/hermes-agent/pull/26612))
-
-- **API server exposes run approval events** — long-running runs surface approval requests over the API stream, no more silent stalls. (salvage of [#20311](https://github.com/NousResearch/hermes-agent/pull/20311)) ([#21899](https://github.com/NousResearch/hermes-agent/pull/21899))
-
-- **`/subgoal` — user-added criteria appended to active `/goal`** — layer extra success criteria onto a running goal loop. The judge sees them in the prompt, no behavior change when subgoals are empty. ([#25449](https://github.com/NousResearch/hermes-agent/pull/25449))
-
-- **Plugins can run any LLM call via `ctx.llm`** — plugins get a first-class hook to make their own LLM requests through the active provider/credentials, no manual wiring. Plus `tool_override` flag for replacing built-in tools. ([#23194](https://github.com/NousResearch/hermes-agent/pull/23194), [#26759](https://github.com/NousResearch/hermes-agent/pull/26759))
-
-- **Brave Search (free tier) + DuckDuckGo (DDGS) as web-search providers** — two new free search backends alongside Tavily / SearXNG / Exa. ([#21337](https://github.com/NousResearch/hermes-agent/pull/21337))
-
-- **Sudo brute-force block + sudo-stdin/askpass DANGEROUS classification** — closes the `sudo -S` brute-force avenue; approval gates classify stdin-fed and askpass-stripped sudo invocations as dangerous. (salvages of #22194 + #21128) ([#23736](https://github.com/NousResearch/hermes-agent/pull/23736))
-
-- **Provider rename — Alibaba Cloud → Qwen Cloud, picker reorder** — matches what the world calls it. Existing config keys still work. ([#24835](https://github.com/NousResearch/hermes-agent/pull/24835))
-
-
----
-
-## 🪟 Windows — Native Support (Early Beta)
-
-### Bootstrap & installer
-- **Native Windows support (early beta)** — first-class native Windows path across CLI / gateway / TUI / tools ([#21561](https://github.com/NousResearch/hermes-agent/pull/21561))
-- **PyPI wheel packaging — `pip install hermes-agent && hermes`** (salvage of #26350) ([#26593](https://github.com/NousResearch/hermes-agent/pull/26593))
-- **Recognise Shift+Enter as a newline key** + Windows docs (salvage #21545) ([#22130](https://github.com/NousResearch/hermes-agent/pull/22130))
-- **Preserve Ctrl+C for Windows foreground runs** (@helix4u) ([#22752](https://github.com/NousResearch/hermes-agent/pull/22752))
-- **Stop spamming cwd-missing + tirith-spawn warnings on every terminal call** ([#26618](https://github.com/NousResearch/hermes-agent/pull/26618))
-- **Use `--extra all` not `--all-extras`; drop lazy-covered extras from `[all]`** ([#24515](https://github.com/NousResearch/hermes-agent/pull/24515))
-
-### Windows-specific fixes (40+ across cli / tools / gateway / curator / TUI)
-A long tail of native-Windows fixes shipped alongside the beta — taskkill-based subprocess management, MinGit auto-install, Microsoft Store python stub detection, npm prefix handling, native PTY paths, signal handling differences, foreground process management, ANSI sequence handling, path normalization, file-locking semantics, and many more. Full list in commit log under `fix(windows)` / `feat(windows)` / `windows`.
-
----
-
-## 🚀 Performance Wave
-
-### Cold start
-- **Cut ~19s from `hermes` cold start** — skills cache + lazy Feishu + no Nous HTTP at startup ([#22138](https://github.com/NousResearch/hermes-agent/pull/22138))
-- **Skip eager plugin discovery on known built-in subcommands** ([#22120](https://github.com/NousResearch/hermes-agent/pull/22120))
-- **Cache Nous auth + .env loads** — `hermes tools` All Platforms from 14s to <1.5s ([#25341](https://github.com/NousResearch/hermes-agent/pull/25341))
-- **Skip welcome banner on `chat -q` single-query mode** ([#22904](https://github.com/NousResearch/hermes-agent/pull/22904))
-- **Defer heavy google-cloud imports in google_chat to first adapter use** ([#22681](https://github.com/NousResearch/hermes-agent/pull/22681))
-- **Defer QQAdapter and YuanbaoAdapter imports via PEP 562** ([#22790](https://github.com/NousResearch/hermes-agent/pull/22790))
-- **Defer httpx import in teams to first webhook call** ([#22831](https://github.com/NousResearch/hermes-agent/pull/22831))
-- **Defer fal_client import to first generation request** ([#22859](https://github.com/NousResearch/hermes-agent/pull/22859))
-- **models.dev cache-first lookup, skip network when disk cache is fresh** ([#22808](https://github.com/NousResearch/hermes-agent/pull/22808))
-- **Parallelize API connectivity checks in `hermes doctor` and disable IMDS** ([#22766](https://github.com/NousResearch/hermes-agent/pull/22766))
-
-### Runtime
-- **180x faster `browser_console` evaluations** — route through supervisor's persistent CDP WebSocket ([#23226](https://github.com/NousResearch/hermes-agent/pull/23226))
-- **Tune Telegram cadence + adaptive fast-path for short replies** (salvage of #10388) ([#23587](https://github.com/NousResearch/hermes-agent/pull/23587))
-- **Accumulate length-continuation prefix via list+join** ([#26237](https://github.com/NousResearch/hermes-agent/pull/26237))
-
-### Prompt caching
-- **Cross-session 1h prefix cache for Claude on Anthropic / OpenRouter / Nous Portal** ([#23828](https://github.com/NousResearch/hermes-agent/pull/23828))
-- **Hit prefix cache in background review fork** (salvage #17276 + #25427) ([#25434](https://github.com/NousResearch/hermes-agent/pull/25434))
-
----
-
-## 📦 Installation & Distribution
-
-### PyPI + supply-chain
-- **PyPI wheel packaging — `pip install hermes-agent && hermes`** (salvage of #26350) ([#26593](https://github.com/NousResearch/hermes-agent/pull/26593))
-- **Supply-chain advisory checker + lazy-install framework + tiered install fallback** ([#24220](https://github.com/NousResearch/hermes-agent/pull/24220))
-- **Use `--extra all` not `--all-extras`; drop lazy-covered extras from `[all]`** ([#24515](https://github.com/NousResearch/hermes-agent/pull/24515))
-- **Skip browser download when system chromium exists** (@helix4u) ([#25317](https://github.com/NousResearch/hermes-agent/pull/25317))
-
-### Nix
-- **`extraDependencyGroups` for sealed venv extras** (@alt-glitch) ([#21817](https://github.com/NousResearch/hermes-agent/pull/21817))
-- **Refresh npm lockfile hashes** — keeps Nix flake builds reproducible
-
-### Docker
-- **Bootstrap auth.json from env on first boot** ([#21880](https://github.com/NousResearch/hermes-agent/pull/21880))
-- **Drop manual @hermes/ink build, rely on esbuild bundle** — slimmer image
-
-### ACP / Zed
-- **Zed ACP Registry integration** (salvage of #25908) ([#26079](https://github.com/NousResearch/hermes-agent/pull/26079))
-- **Switch to uvx distribution, drop npm launcher** ([#26120](https://github.com/NousResearch/hermes-agent/pull/26120))
-- **`hermes acp --setup-browser` bootstraps browser tools for registry installs** ([#26234](https://github.com/NousResearch/hermes-agent/pull/26234))
-
----
-
-## 🏗️ Core Agent & Architecture
-
-### Sessions & handoff
-- **`/handoff` actually transfers the session live** ([#23395](https://github.com/NousResearch/hermes-agent/pull/23395))
-- **Expose `HERMES_SESSION_ID` env var to agent tools** (@alt-glitch) ([#23847](https://github.com/NousResearch/hermes-agent/pull/23847))
-
-### Goals (Ralph loop)
-- **`/subgoal` — user-added criteria appended to active `/goal`** ([#25449](https://github.com/NousResearch/hermes-agent/pull/25449))
-- **`/goal` checklist + /subgoal user controls** ([#23456](https://github.com/NousResearch/hermes-agent/pull/23456)) — rolled back in window ([#23813](https://github.com/NousResearch/hermes-agent/pull/23813)); /subgoal returned in simpler form via #25449
-
-### Compression
-- **Make `protect_first_n` configurable** ([#25447](https://github.com/NousResearch/hermes-agent/pull/25447))
-
-### Verification
-- **Per-turn file-mutation verifier footer** ([#24498](https://github.com/NousResearch/hermes-agent/pull/24498))
-
-### Stream retry
-- **Log inner cause, upstream headers, bytes/elapsed on every drop** ([#23005](https://github.com/NousResearch/hermes-agent/pull/23005))
-
----
-
-## 🤖 Models & Providers
-
-### New providers
-- **xAI Grok OAuth (SuperGrok Subscription) provider** ([#26534](https://github.com/NousResearch/hermes-agent/pull/26534))
-- **NovitaAI provider** (salvage #7219) (@kshitijk4poor) ([#25507](https://github.com/NousResearch/hermes-agent/pull/25507))
-- **NVIDIA NIM billing origin header** (salvage #25211) ([#26585](https://github.com/NousResearch/hermes-agent/pull/26585))
-
-### Provider work
-- **OpenRouter Pareto Code router with `min_coding_score` knob** ([#22838](https://github.com/NousResearch/hermes-agent/pull/22838))
-- **Optional codex app-server runtime for OpenAI/Codex models** ([#24182](https://github.com/NousResearch/hermes-agent/pull/24182))
-- **Codex-runtime: retire wedged sessions + post-tool watchdog + OAuth refresh classify** ([#25769](https://github.com/NousResearch/hermes-agent/pull/25769))
-- **Codex-runtime: skip unavailable plugins during migration** ([#25437](https://github.com/NousResearch/hermes-agent/pull/25437))
-- **Codex-runtime: de-dup `[plugins.X]` tables and stop leaking HERMES_HOME into config.toml** (#26250) (@kshitijk4poor) ([#26260](https://github.com/NousResearch/hermes-agent/pull/26260))
-- **Pass `reasoning.effort` to xAI Responses API** ([#22807](https://github.com/NousResearch/hermes-agent/pull/22807))
-- **Custom provider: prompt and persist explicit `api_mode`** ([#25068](https://github.com/NousResearch/hermes-agent/pull/25068))
-- **Rename Alibaba Cloud → Qwen Cloud, reorder picker** ([#24835](https://github.com/NousResearch/hermes-agent/pull/24835))
-- **Restore gpt-5.3-codex-spark for ChatGPT Pro** (salvage #18286 + #19530, fixes #16172) (@kshitijk4poor) ([#22991](https://github.com/NousResearch/hermes-agent/pull/22991))
-- **Inject tool-use enforcement for GLM models** ([#24715](https://github.com/NousResearch/hermes-agent/pull/24715))
-- **Use Nous Portal as model metadata authority** (@rob-maron) ([#24502](https://github.com/NousResearch/hermes-agent/pull/24502))
-- **Unified `client=hermes-client-v<version>` tag on every Portal request** ([#24779](https://github.com/NousResearch/hermes-agent/pull/24779))
-- **Prevent stale Ollama credentials after provider switch** (@kshitijk4poor) ([#21703](https://github.com/NousResearch/hermes-agent/pull/21703))
-- **Auxiliary client: rotate pooled auth after quota failures** (salvage #22779) ([#22792](https://github.com/NousResearch/hermes-agent/pull/22792))
-- **Auxiliary client: skip providers without credentials immediately** (#25395) ([#25487](https://github.com/NousResearch/hermes-agent/pull/25487))
-- **Auth: send Nous refresh token via header** (@shannonsands) ([#21578](https://github.com/NousResearch/hermes-agent/pull/21578))
-- **MiniMax: harden OAuth dashboard and runtime** ([#24165](https://github.com/NousResearch/hermes-agent/pull/24165))
-
-### OpenAI-compatible proxy
-- **Local OpenAI-compatible proxy for OAuth providers** — Codex / Aider / Cline can hit Claude Pro, ChatGPT Pro, SuperGrok ([#25969](https://github.com/NousResearch/hermes-agent/pull/25969))
-
----
-
-## 📱 Messaging Platforms (Gateway)
-
-### New platforms
-- **LINE Messaging API platform plugin** ([#23197](https://github.com/NousResearch/hermes-agent/pull/23197))
-- **SimpleX Chat platform plugin** (salvages #2558) ([#26232](https://github.com/NousResearch/hermes-agent/pull/26232))
-
-### Microsoft Graph foundation
-- **msgraph: add auth and client foundation** (salvage of #21408) ([#21922](https://github.com/NousResearch/hermes-agent/pull/21922))
-- **msgraph: add webhook listener platform** (salvage of #21409) ([#21969](https://github.com/NousResearch/hermes-agent/pull/21969))
-- **teams-pipeline: add plugin runtime and operator cli** (salvage of #21410) ([#22007](https://github.com/NousResearch/hermes-agent/pull/22007))
-- **teams: add pipeline outbound delivery via existing adapter** (salvage of #21411) ([#22024](https://github.com/NousResearch/hermes-agent/pull/22024))
-
-### Cross-platform
-- **Per-platform admin/user split for slash commands** (salvage of #4443) ([#23373](https://github.com/NousResearch/hermes-agent/pull/23373))
-- **Forensics on signal handling — non-blocking diag, per-phase timing, stale-unit warning** ([#23285](https://github.com/NousResearch/hermes-agent/pull/23285))
-- **Keep gateway running when platforms fail; add per-platform circuit breaker + `/platform`** ([#26600](https://github.com/NousResearch/hermes-agent/pull/26600))
-- **Wire `clarify` tool with inline keyboard buttons on Telegram** ([#24199](https://github.com/NousResearch/hermes-agent/pull/24199))
-- **Add `chat_id` to `hook_ctx` for message source tracking** ([#24710](https://github.com/NousResearch/hermes-agent/pull/24710))
-
-### Telegram
-- **Native draft streaming via `sendMessageDraft` (Bot API 9.5+)** (salvage of #3412) ([#23512](https://github.com/NousResearch/hermes-agent/pull/23512))
-- **Stream Telegram edits safely** — salvage of #22264 (@kshitijk4poor) ([#22518](https://github.com/NousResearch/hermes-agent/pull/22518))
-- **Telegram notification mode** (salvage #22772) ([#22793](https://github.com/NousResearch/hermes-agent/pull/22793))
-- **Telegram guest mention mode** (@kshitijk4poor) ([#22759](https://github.com/NousResearch/hermes-agent/pull/22759))
-- **Split-and-deliver oversized edits instead of silent truncation** (salvage of #19537) ([#23576](https://github.com/NousResearch/hermes-agent/pull/23576))
-- **Preserve DM topic routing via reply fallback** (salvage #22053) (@kshitijk4poor) ([#22410](https://github.com/NousResearch/hermes-agent/pull/22410))
-- **Pass `source.thread_id` explicitly on auto-reset notice** (carve-out of #7404) ([#23440](https://github.com/NousResearch/hermes-agent/pull/23440))
-
-### Discord
-- **Render clarify choices as buttons** ([#25485](https://github.com/NousResearch/hermes-agent/pull/25485))
-- **Channel history backfill — default on, broadened scope** ([#25984](https://github.com/NousResearch/hermes-agent/pull/25984))
-- **`thread_require_mention` for multi-bot threads** (salvage #25313) ([#25445](https://github.com/NousResearch/hermes-agent/pull/25445))
-
-### Slack
-- **Support `!cmd` as alternate prefix for slash commands in threads** ([#25355](https://github.com/NousResearch/hermes-agent/pull/25355))
-
-### WhatsApp
-- **Surface quoted reply metadata from Baileys** (#25398) ([#25489](https://github.com/NousResearch/hermes-agent/pull/25489))
-
-### Feishu / Google Chat / others
-- **Feishu: native update prompt cards** (@kshitijk4poor) ([#22448](https://github.com/NousResearch/hermes-agent/pull/22448))
-- **Google Chat: repair setup prompt imports** (@helix4u) ([#22038](https://github.com/NousResearch/hermes-agent/pull/22038))
-- **Google Chat: honor relay-declared sender_type** (salvage of #22107) (@kshitijk4poor) ([#22432](https://github.com/NousResearch/hermes-agent/pull/22432))
-- **LINE: use `build_source` instead of nonexistent `create_source`** ([#24717](https://github.com/NousResearch/hermes-agent/pull/24717))
-- **Add `weixin, and more` to gateway docs** (salvage of #21063 by @wuwuzhijing)
-
----
-
-## 🖥️ CLI & TUI
-
-### CLI
-- **Show YOLO mode warning in banner and status bar** ([#26238](https://github.com/NousResearch/hermes-agent/pull/26238))
-- **Confirm prompt for destructive slash commands** (#4069) ([#22687](https://github.com/NousResearch/hermes-agent/pull/22687))
-- **`docker_extra_args` + `display.timestamps`** ([#23599](https://github.com/NousResearch/hermes-agent/pull/23599))
-- **Delegate tool: show user's actual concurrency / spawn-depth limits in description** ([#22694](https://github.com/NousResearch/hermes-agent/pull/22694))
-
-### TUI
-- **`/sessions` slash command for browsing and resuming previous sessions** (@austinpickett) ([#20805](https://github.com/NousResearch/hermes-agent/pull/20805))
-- **Segment turns with rule above non-first user msgs; trim ticker dead space** (@OutThisLife) ([#21846](https://github.com/NousResearch/hermes-agent/pull/21846))
-- **Support attaching to an existing gateway** (@OutThisLife) ([#21978](https://github.com/NousResearch/hermes-agent/pull/21978))
-- **Resolve markdown links to readable page titles** (@OutThisLife) ([#24013](https://github.com/NousResearch/hermes-agent/pull/24013))
-- **Width-aware markdown table rendering with vertical fallback** (@alt-glitch) ([#26195](https://github.com/NousResearch/hermes-agent/pull/26195))
-- **Keep Ink displayCursor in sync with fast-echo writes so cursor stops drifting** (@OutThisLife) ([#26717](https://github.com/NousResearch/hermes-agent/pull/26717))
-- **Allow transcript scroll + Esc during approval/clarify/confirm prompts** (@OutThisLife) ([#26414](https://github.com/NousResearch/hermes-agent/pull/26414))
-- **Preserve session when switching personality** (@austinpickett) ([#20942](https://github.com/NousResearch/hermes-agent/pull/20942))
-- **Skip native safety net on OSC52-capable terminals** (@benbarclay) ([#20954](https://github.com/NousResearch/hermes-agent/pull/20954))
-
-### Dashboard / GUI
-- **Route embedded TUI through dashboard gateway** (@OutThisLife) ([#21979](https://github.com/NousResearch/hermes-agent/pull/21979))
-- **Hide token/cost analytics behind config flag (default off)** ([#25438](https://github.com/NousResearch/hermes-agent/pull/25438))
-- **Fix Langfuse observability — trace I/O, tool outputs, placeholder credentials** (closes #22342, #22763) (@kshitijk4poor) ([#26320](https://github.com/NousResearch/hermes-agent/pull/26320))
-- **MiniMax 'Login' button launched Claude OAuth** (salvage #22849) ([#24058](https://github.com/NousResearch/hermes-agent/pull/24058))
-- **Update cron modals** (@austinpickett) ([#25985](https://github.com/NousResearch/hermes-agent/pull/25985))
-- **Analytics: prevent silent token loss and add Claude 4.5–4.7 pricing** (@austinpickett) ([#21455](https://github.com/NousResearch/hermes-agent/pull/21455))
-
----
-
-## 🔧 Tools & Capabilities
-
-### Vision & video
-- **`vision_analyze` returns pixels to vision-capable models** ([#22955](https://github.com/NousResearch/hermes-agent/pull/22955))
-- **Unified `video_generate` with pluggable provider backends** ([#25126](https://github.com/NousResearch/hermes-agent/pull/25126))
-- **`image_gen`: actionable setup message when no FAL backend is reachable** ([#26222](https://github.com/NousResearch/hermes-agent/pull/26222))
-
-### Computer use
-- **`computer_use` cua-driver backend + focus-safe ops + non-Anthropic provider fix** (re-salvage #16936) ([#21967](https://github.com/NousResearch/hermes-agent/pull/21967))
-- **Refresh cua-driver on `hermes update` + add `install --upgrade`** ([#24063](https://github.com/NousResearch/hermes-agent/pull/24063))
-
-### LSP & write-time diagnostics
-- **Semantic diagnostics from real language servers in `write_file`/`patch`** ([#24168](https://github.com/NousResearch/hermes-agent/pull/24168))
-- **Shift baseline diagnostics into post-edit coordinates** ([#25978](https://github.com/NousResearch/hermes-agent/pull/25978))
-
-### Search & web
-- **Brave Search (free tier) and DDGS search providers** ([#21337](https://github.com/NousResearch/hermes-agent/pull/21337))
-- **Bearer auth header for Tavily `/crawl` endpoint** ([#24658](https://github.com/NousResearch/hermes-agent/pull/24658))
-
-### X (Twitter)
-- **Gated `x_search` tool with OAuth-or-API-key auth** ([#26763](https://github.com/NousResearch/hermes-agent/pull/26763))
-
-### Browser
-- **Route `browser_console` eval through supervisor's persistent CDP WS (180x faster)** ([#23226](https://github.com/NousResearch/hermes-agent/pull/23226))
-- **Support externally managed Camofox sessions** ([#24499](https://github.com/NousResearch/hermes-agent/pull/24499))
-
-### MCP
-- **`supports_parallel_tool_calls` for MCP servers** (salvage of #9944) ([#26825](https://github.com/NousResearch/hermes-agent/pull/26825))
-- **Codex preset for Codex CLI MCP server** (salvage #22663) ([#22679](https://github.com/NousResearch/hermes-agent/pull/22679))
-- **Stop retrying initial MCP auth failures** (#25624) ([#25776](https://github.com/NousResearch/hermes-agent/pull/25776))
-
-### Google Workspace
-- **Drive write ops + Docs/Sheets create/append** ([#21895](https://github.com/NousResearch/hermes-agent/pull/21895))
-
-### Per-turn verifier
-- **Per-turn file-mutation verifier footer** ([#24498](https://github.com/NousResearch/hermes-agent/pull/24498))
-
----
-
-## 🧩 Kanban (Multi-Agent)
-
-- **`specify` — auxiliary LLM fleshes out triage tasks** ([#21435](https://github.com/NousResearch/hermes-agent/pull/21435))
-- **Orchestrator board tools — `kanban_list` + `kanban_unblock`** (carve-out of #20568) ([#23012](https://github.com/NousResearch/hermes-agent/pull/23012))
-- **`stranded_in_ready` diagnostic for unclaimed tasks** ([#23578](https://github.com/NousResearch/hermes-agent/pull/23578))
-- **Dashboard batch QOL upgrade** (salvage of #23240) ([#23550](https://github.com/NousResearch/hermes-agent/pull/23550))
-- **Tooltips and docs link across dashboard** ([#21541](https://github.com/NousResearch/hermes-agent/pull/21541))
-- **Dedupe notifier delivery via atomic claim + rewind on failure** (salvage #22558) ([#23401](https://github.com/NousResearch/hermes-agent/pull/23401))
-- **Keep notifier subscriptions alive across retry cycles** (salvage #21398) ([#23423](https://github.com/NousResearch/hermes-agent/pull/23423))
-- **Drop caller-controlled author override in `kanban_comment`** (salvage of #22109) (@kshitijk4poor) ([#22435](https://github.com/NousResearch/hermes-agent/pull/22435))
-- **Sanitize comment author rendering in `build_worker_context`** ([#22769](https://github.com/NousResearch/hermes-agent/pull/22769))
-
----
-
-## 🧠 Plugins & Extension
-
-### Plugin surface
-- **Run any LLM call from inside a plugin via `ctx.llm`** ([#23194](https://github.com/NousResearch/hermes-agent/pull/23194))
-- **`tool_override` flag for replacing built-in tools** (closes #11049) ([#26759](https://github.com/NousResearch/hermes-agent/pull/26759))
-- **`standalone_sender_fn` for out-of-process cron delivery** (@kshitijk4poor) ([#22461](https://github.com/NousResearch/hermes-agent/pull/22461))
-- **`HERMES_PLUGINS_DEBUG=1` surfaces plugin discovery logs** ([#22684](https://github.com/NousResearch/hermes-agent/pull/22684))
-- **Hindsight-client as optional dependency** (@alt-glitch) ([#21818](https://github.com/NousResearch/hermes-agent/pull/21818))
-
-### Profile & distribution
-- **Shareable profile distributions via git** ([#20831](https://github.com/NousResearch/hermes-agent/pull/20831))
-
----
-
-## ⏰ Cron
-
-- **Routing intent — `deliver=all` fans out to every connected channel** ([#21495](https://github.com/NousResearch/hermes-agent/pull/21495))
-- **Support name-based lookup for job operations** ([#26231](https://github.com/NousResearch/hermes-agent/pull/26231))
-- **Blank Cron dashboard tab + partial-record crashes** (salvage #21042 + #22330) (@kshitijk4poor) ([#22389](https://github.com/NousResearch/hermes-agent/pull/22389))
-- **Do not seed `HERMES_SESSION_*` contextvars from cron origin** (salvage of #22356) (@kshitijk4poor) ([#22382](https://github.com/NousResearch/hermes-agent/pull/22382))
-- **Scan assembled prompt including skill content for prompt injection** (#3968)
-
----
-
-## 🧩 Skills Ecosystem
-
-### Skills Hub
-- **`hermes-skills/huggingface` as a trusted default tap** (closes #2549) ([#26219](https://github.com/NousResearch/hermes-agent/pull/26219))
-- **Show per-skill pages in the left sidebar** ([#26646](https://github.com/NousResearch/hermes-agent/pull/26646))
-- **Richer info panels on the Skills Hub** ([#22905](https://github.com/NousResearch/hermes-agent/pull/22905))
-- **Refuse `skill_view` name collisions instead of guessing** (closes #6136 @polkn)
-
-### Curator
-- **Show rename map in user-visible summary** ([#22910](https://github.com/NousResearch/hermes-agent/pull/22910))
-- **Hint at `hermes curator pin` in the rename block** ([#23212](https://github.com/NousResearch/hermes-agent/pull/23212))
-
-### New optional skills
-- **Hyperliquid** — perp/spot trading via SDK + REST (salvage of #1952) ([#23583](https://github.com/NousResearch/hermes-agent/pull/23583))
-- **Yahoo Finance** market data ([#23590](https://github.com/NousResearch/hermes-agent/pull/23590))
-- **api-testing** (REST/GraphQL debug, salvages #1800) ([#23582](https://github.com/NousResearch/hermes-agent/pull/23582))
-- **Unified EVM multi-chain skill** (salvages #25291 + #2010 + folds in base/) ([#25299](https://github.com/NousResearch/hermes-agent/pull/25299))
-- **darwinian-evolver** ([#26760](https://github.com/NousResearch/hermes-agent/pull/26760))
-- **osint-investigation** (closes #355) ([#26729](https://github.com/NousResearch/hermes-agent/pull/26729))
-- **pinggy-tunnel** ([#26765](https://github.com/NousResearch/hermes-agent/pull/26765))
-- **watchers** — RSS / HTTP JSON / GitHub polling via cron no-agent ([#21881](https://github.com/NousResearch/hermes-agent/pull/21881))
-- **Notion overhaul for the Developer Platform** (May 2026) ([#26612](https://github.com/NousResearch/hermes-agent/pull/26612))
-
----
-
-## 🔒 Security & Reliability
-
-### Security hardening
-- **Sudo brute-force block + sudo-stdin/askpass DANGEROUS** (salvage of #22194 + #21128) (@kshitijk4poor) ([#23736](https://github.com/NousResearch/hermes-agent/pull/23736))
-- **Drop caller-controlled author override in `kanban_comment`** (salvage of #22109) (@kshitijk4poor) ([#22435](https://github.com/NousResearch/hermes-agent/pull/22435))
-- **Cover remaining SSRF fetch paths in skills-hub** (salvage #22804) ([#22843](https://github.com/NousResearch/hermes-agent/pull/22843))
-- **Use credential_pool for custom endpoint model listing probes** (salvage #22810) ([#22842](https://github.com/NousResearch/hermes-agent/pull/22842))
-- **Require dashboard auth for plugin API routes** (salvage #19541) ([#23220](https://github.com/NousResearch/hermes-agent/pull/23220))
-- **Sanitize env and redact output in quick commands + remove write-only `_pending_messages`** ([#23584](https://github.com/NousResearch/hermes-agent/pull/23584))
-- **Reduce unnecessary `shell=True` in subprocess calls** ([#25149](https://github.com/NousResearch/hermes-agent/pull/25149))
-- **Sanitize Google Chat sender_type from relay** (salvage of #22107) (@kshitijk4poor) ([#22432](https://github.com/NousResearch/hermes-agent/pull/22432))
-- **Supply-chain advisory checker** ([#24220](https://github.com/NousResearch/hermes-agent/pull/24220))
-- **Rewrite security policy around OS-level isolation as the boundary** (@jquesnelle) ([#20317](https://github.com/NousResearch/hermes-agent/pull/20317))
-- **Remove public security advisory page** ([#24253](https://github.com/NousResearch/hermes-agent/pull/24253))
-
-### Reliability — notable bug closures
-- **SQLite: fall back to `journal_mode=DELETE` on NFS/SMB/FUSE** (fixes `/resume` on network mounts) (@kshitijk4poor) ([#22043](https://github.com/NousResearch/hermes-agent/pull/22043))
-- **Codex-runtime: retire wedged sessions + post-tool watchdog + OAuth refresh classify** ([#25769](https://github.com/NousResearch/hermes-agent/pull/25769))
-- **Codex-runtime: de-dup `[plugins.X]` tables and stop leaking HERMES_HOME** (#26250) (@kshitijk4poor) ([#26260](https://github.com/NousResearch/hermes-agent/pull/26260))
-- **Daytona: migrate legacy-sandbox lookup to cursor-based `list()`** ([#24587](https://github.com/NousResearch/hermes-agent/pull/24587))
-- **MCP: stop retrying initial MCP auth failures** (#25624) ([#25776](https://github.com/NousResearch/hermes-agent/pull/25776))
-- **Gateway: enable text-intercept for multi-choice clarify fallback** (#25587) ([#25778](https://github.com/NousResearch/hermes-agent/pull/25778))
-- **Gateway: keep running when platforms fail; per-platform circuit breaker + `/platform`** ([#26600](https://github.com/NousResearch/hermes-agent/pull/26600))
-- **Delegate: salvage #21933 JSON-string batch + diagnostic logging** (@kshitijk4poor) ([#22436](https://github.com/NousResearch/hermes-agent/pull/22436))
-- **Profiles+banner: exclude infrastructure from `--clone-all` + fix stale update-check repo resolution** (@kshitijk4poor) ([#22475](https://github.com/NousResearch/hermes-agent/pull/22475))
-- **ACP: inline file attachment resources** (salvage #21400 + image support) ([#21407](https://github.com/NousResearch/hermes-agent/pull/21407))
-- **CI: unblock shared PR checks** (@stephenschoettler) ([#21012](https://github.com/NousResearch/hermes-agent/pull/21012), [#25957](https://github.com/NousResearch/hermes-agent/pull/25957))
-
-### Notable reverts in window
-- **`/goal` checklist + /subgoal feature stack** — rolled back ([#23813](https://github.com/NousResearch/hermes-agent/pull/23813)); `/subgoal` returned in simpler form via [#25449](https://github.com/NousResearch/hermes-agent/pull/25449)
-- **Scrollback box width clamp** (#25975) rolled back to restore full-width borders ([#26163](https://github.com/NousResearch/hermes-agent/pull/26163))
-- **`fix(cli): tolerate unreadable dirs when building systemd PATH`** rolled back
-
----
-
-## 🌍 i18n
-
-- **Localize all gateway commands + web dashboard, add 8 new locales (16 total)** ([#22914](https://github.com/NousResearch/hermes-agent/pull/22914))
-
----
-
-## 📚 Documentation
-
-- **Repair Voice & TTS provider table** (@nightcityblade, fixes #24101) ([#24138](https://github.com/NousResearch/hermes-agent/pull/24138))
-- **Show per-skill pages in the left sidebar** ([#26646](https://github.com/NousResearch/hermes-agent/pull/26646))
-- **Mention Weixin in gateway help and docstrings** (salvage of #21063 by @wuwuzhijing)
-- **Richer info panels on the Skills Hub** ([#22905](https://github.com/NousResearch/hermes-agent/pull/22905))
-- Many more doc updates across providers, platforms, skills, Windows install paths, and dashboard.
-
----
-
-## 🧪 Testing & CI
-
-- **Unblock shared PR checks** (@stephenschoettler) ([#21012](https://github.com/NousResearch/hermes-agent/pull/21012))
-- **Stabilize shared test state after 21012** (@stephenschoettler) ([#25957](https://github.com/NousResearch/hermes-agent/pull/25957))
-- A long tail of test additions for platforms, providers, plugins, and edge cases — 8 explicit `test:` PRs plus ~250 fix PRs that also added regression coverage.
-
----
-
-## 👥 Contributors
-
-### Core
-- @teknium1 — release lead, architecture, ~406 PRs merged in window
-
-### Top community contributors
-- **@kshitijk4poor** — 38 PRs · Telegram cadence/streaming/topic routing, security hardening (sudo, SSRF, kanban_comment, dashboard auth), codex-runtime hygiene, NovitaAI provider, profile/banner fixes, Feishu update cards, gateway QOL across the board
-- **@alt-glitch** — 13 PRs · Markdown-table TUI rendering, `HERMES_SESSION_ID` env var, hindsight-client optional dep, Nix `extraDependencyGroups`
-- **@OutThisLife** (Brooklyn Nicholson) — 12 PRs · TUI turn segmentation, attach-to-gateway, markdown link titles, embedded TUI via dashboard gateway, Ink cursor sync, scroll/Esc during prompts
-- **@austinpickett** — 8 PRs · `/sessions` slash command, personality switching preserves session, cron modals, dashboard analytics
-- **@helix4u** — 5 PRs · Google Chat setup, browser install skip on system chromium, Windows Ctrl+C preservation
-- **@rob-maron** — 4 PRs · Nous Portal as model metadata authority, provider polish
-- **@stephenschoettler** — 3 PRs · CI stabilization
-- **@ethernet8023** — 3 PRs · platform/gateway work
-
-### All contributors (alphabetical)
-
-@02356abc, @0xbyt4, @0xharryriddle, @1000Delta, @1RB, @29206394, @A-kamal, @aashizpoudel, @Abd0r,
-@adybag14-cyber, @AgentArcLab, @ahmedbadr3, @AhmetArif0, @alblez, @Alex-yang00, @ALIYILD, @AllynSheep,
-@alt-glitch, @am423, @amathxbt, @amethystani, @ArecaNon, @Arkmusn, @askclaw-vesper, @AsoTora, @austinpickett,
-@aydnOktay, @ayushere, @baocin, @Bartok9, @benbarclay, @BennetYrWang, @Bihruze, @binhnt92, @briandevans,
-@brooklynnicholson, @btorresgil, @buntingszn, @CalmProton, @chrisworksai, @CoinTheHat, @dandacompany, @Dangooy,
-@DanielLSM, @David-0x221Eight, @ddupont808, @dhruv-saxena, @diablozzc, @dlkakbs, @dmahan93, @dmnkhorvath,
-@domtriola, @donrhmexe, @Dusk1e, @eloklam, @emozilla, @ephron-ren, @erenkarakus, @EthanGuo-coder,
-@ethernet8023, @evgyur, @explainanalyze, @fahdad, @fr33d3m0n, @Freeman-Consulting, @freqyfreqy, @Frowtek,
-@fu576, @github-actions[bot], @gnanirahulnutakki, @GodsBoy, @guglielmofonda, @Gutslabs, @hanzckernel,
-@heathley, @hekaru-agent, @helix4u, @HenkDz, @HiddenPuppy, @hllqkb, @hrygo, @HuangYuChuh, @Hugo-SEQUIER, @HxT9,
-@iacker, @InB4DevOps, @isaachuangGMICLOUD, @iuyup, @Jaaneek, @jackey8616, @jackjin1997, @Jaggia, @jak983464779,
-@jelrod27, @jethac, @JithendraNara, @johnisag, @Julientalbot, @Jwd-gity, @kallidean, @keyuyuan, @kfa-ai,
-@kidonng, @KiraKatana, @kjames2001, @konsisumer, @Korkyzer, @kshitijk4poor, @KvnGz, @lars-hagen, @leehack,
-@leepoweii, @LeonSGP43, @li0near, @libo1106, @liquidchen, @littlewwwhite, @liuhao1024, @liyoungc, @luandiasrj,
-@luoyuctl, @luyao618, @magic524, @mbac, @McClean, @memosr, @Mibayy, @ming1523, @mizgyo, @mrshu, @ms-alan,
-@MustafaKara7, @nederev, @nicoechaniz, @nidhi-singh02, @nightcityblade, @nik1t7n, @Ninso112, @NivOO5,
-@novax635, @nv-kasikritc, @oferlaor, @oswaldb22, @outdoorsea, @oxngon, @PaTTeeL, @pearjelly, @pefontana,
-@perng, @PhilipAD, @phuongvm, @polkn, @Prasanna28Devadiga, @princepal9120, @pty819, @purzbeats, @Quarkex,
-@quocanh261997, @qWaitCrypto, @Qwinty, @rahimsais, @raymaylee, @ReqX, @rewbs, @RhombusMaximus, @rob-maron,
-@Ruzzgar, @ryptotalent, @Sanjays2402, @shannonsands, @shaun0927, @SiliconID, @silv-mt-holdings, @simpolism,
-@smwbev, @soichiyo, @sprmn24, @steezkelly, @stephenschoettler, @Sylw3ster, @szymonclawd, @teyrebaz33,
-@Tianyu199509, @Tranquil-Flow, @TreyDong, @TurgutKural, @tw2818, @tymrtn, @uzunkuyruk, @v1b3coder,
-@vanthinh6886, @VinceZcrikl, @vKongv, @vominh1919, @voteblake, @VTRiot, @wali-reheman, @wesleysimplicio,
-@wilsen0, @WorldWriter, @worlldz, @wuli666, @wuwuzhijing, @Wysie, @XiaoXiao0221, @xieNniu, @xxxigm, @yehuosi,
-@ygd58, @yifengingit, @yuga-hashimoto, @zccyman, @ZeterMordio, @Zhekinmaksim, @zhengyn0001
-
-Also: @Nagatha (Claude Opus 4.7).
-
----
-
-**Full Changelog**: [v2026.5.7...v2026.5.16](https://github.com/NousResearch/hermes-agent/compare/v2026.5.7...v2026.5.16)

acp_adapter/auth.py

@@ -1,11 +1,8 @@
-"""ACP auth helpers — detect and advertise Hermes authentication methods."""
+"""ACP auth helpers — detect the currently configured Hermes provider."""
 
 from __future__ import annotations
 
-from typing import Any, Optional
-
-
-TERMINAL_SETUP_AUTH_METHOD_ID = "hermes-setup"
+from typing import Optional
 
 
 def detect_provider() -> Optional[str]:
@@ -25,44 +22,3 @@ def detect_provider() -> Optional[str]:
 def has_provider() -> bool:
     """Return True if Hermes can resolve any runtime provider credentials."""
     return detect_provider() is not None
-
-
-def build_auth_methods() -> list[Any]:
-    """Return registry-compatible ACP auth methods for Hermes.
-
-    The official ACP registry validates that agents advertise at least one
-    usable auth method during the initial handshake. A fresh Zed install may
-    not have Hermes provider credentials configured yet, so Hermes always
-    advertises a terminal setup method. When credentials are already present,
-    it also advertises the resolved provider as the default agent-managed
-    runtime credential method.
-    """
-    from acp.schema import AuthMethodAgent, TerminalAuthMethod
-
-    methods: list[Any] = []
-    provider = detect_provider()
-    if provider:
-        methods.append(
-            AuthMethodAgent(
-                id=provider,
-                name=f"{provider} runtime credentials",
-                description=(
-                    "Authenticate Hermes using the currently configured "
-                    f"{provider} runtime credentials."
-                ),
-            )
-        )
-
-    methods.append(
-        TerminalAuthMethod(
-            id=TERMINAL_SETUP_AUTH_METHOD_ID,
-            name="Configure Hermes provider",
-            description=(
-                "Open Hermes' interactive model/provider setup in a terminal. "
-                "Use this when Hermes has not been configured on this machine yet."
-            ),
-            type="terminal",
-            args=["--setup"],
-        )
-    )
-    return methods

acp_adapter/bootstrap/bootstrap_browser_tools.ps1

@@ -1,288 +0,0 @@
-# bootstrap_browser_tools.ps1 — install agent-browser + Playwright Chromium
-# into ~/.hermes/node/ for use by Hermes Agent's browser tools on Windows.
-#
-# Targets the registry-install path: users who got Hermes via
-# `uvx --from 'hermes-agent[acp]==X' hermes-acp` don't have a repo clone,
-# so the install.ps1 `npm install`-in-repo flow doesn't apply. This script
-# is a self-contained, idempotent slice of install.ps1's browser block.
-#
-# Usage:
-#   .\bootstrap_browser_tools.ps1                # use defaults
-#   .\bootstrap_browser_tools.ps1 -Yes           # accept Chromium download
-#   .\bootstrap_browser_tools.ps1 -SkipChromium  # Node + agent-browser only
-#
-# Idempotent: re-running this is safe and fast.
-
-[CmdletBinding()]
-param(
-    [switch]$Yes,
-    [switch]$SkipChromium
-)
-
-$ErrorActionPreference = "Stop"
-$NodeVersion = "22"
-
-# ─────────────────────────────────────────────────────────────────────────
-# Logging
-# ─────────────────────────────────────────────────────────────────────────
-
-function Write-Info    { param([string]$msg) Write-Host "[*] $msg" -ForegroundColor Cyan    }
-function Write-Success { param([string]$msg) Write-Host "[+] $msg" -ForegroundColor Green   }
-function Write-Warn    { param([string]$msg) Write-Host "[!] $msg" -ForegroundColor Yellow  }
-function Write-Err     { param([string]$msg) Write-Host "[x] $msg" -ForegroundColor Red     }
-
-# ─────────────────────────────────────────────────────────────────────────
-# Paths
-# ─────────────────────────────────────────────────────────────────────────
-
-$HermesHome = $env:HERMES_HOME
-if (-not $HermesHome) {
-    $HermesHome = Join-Path $env:USERPROFILE ".hermes"
-}
-$NodePrefix = Join-Path $HermesHome "node"
-
-# ─────────────────────────────────────────────────────────────────────────
-# Step 1: Node.js
-# ─────────────────────────────────────────────────────────────────────────
-
-function Resolve-NpmExe {
-    # Same gotcha as install.ps1: prefer npm.cmd over npm.ps1 so the
-    # PowerShell execution policy doesn't block us.
-    $cmd = Get-Command npm -ErrorAction SilentlyContinue
-    if (-not $cmd) { return $null }
-    $npmExe = $cmd.Source
-    if ($npmExe -like "*.ps1") {
-        $sibling = Join-Path (Split-Path $npmExe -Parent) "npm.cmd"
-        if (Test-Path $sibling) { return $sibling }
-    }
-    return $npmExe
-}
-
-function Resolve-NpxExe {
-    $cmd = Get-Command npx -ErrorAction SilentlyContinue
-    if (-not $cmd) { return $null }
-    $npxExe = $cmd.Source
-    if ($npxExe -like "*.ps1") {
-        $sibling = Join-Path (Split-Path $npxExe -Parent) "npx.cmd"
-        if (Test-Path $sibling) { return $sibling }
-    }
-    return $npxExe
-}
-
-function Ensure-Node {
-    # System Node on PATH?
-    $sysNode = Get-Command node -ErrorAction SilentlyContinue
-    if ($sysNode) {
-        try {
-            $v = & $sysNode.Source --version
-            $major = [int]($v -replace '^v(\d+).*', '$1')
-            if ($major -ge 20) {
-                Write-Success "Node.js $v found on PATH"
-                return
-            }
-            Write-Warn "Node.js $v is older than v20 — installing managed Node."
-        } catch {
-            Write-Warn "Failed to query Node version: $_"
-        }
-    }
-
-    # Hermes-managed Node?
-    $managedNode = Join-Path $NodePrefix "node.exe"
-    if (Test-Path $managedNode) {
-        $v = & $managedNode --version
-        Write-Success "Node.js $v found (Hermes-managed at $NodePrefix)"
-        # Prepend to current-process PATH so subsequent npm/npx calls find it.
-        $env:PATH = "$NodePrefix;$env:PATH"
-        return
-    }
-
-    Write-Info "Installing Node.js $NodeVersion LTS into $NodePrefix ..."
-
-    $arch = if ([Environment]::Is64BitOperatingSystem) { "x64" } else { "x86" }
-    $indexUrl = "https://nodejs.org/dist/latest-v${NodeVersion}.x/"
-
-    try {
-        $indexPage = Invoke-WebRequest -Uri $indexUrl -UseBasicParsing
-        $matches = [regex]::Matches($indexPage.Content, "node-v${NodeVersion}\.\d+\.\d+-win-${arch}\.zip")
-        if ($matches.Count -eq 0) {
-            Write-Err "Could not locate Node.js $NodeVersion zip for win-$arch"
-            throw "no tarball"
-        }
-        $zipName = $matches[0].Value
-        $zipUrl = "$indexUrl$zipName"
-
-        $tmpDir = Join-Path $env:TEMP "hermes-node-$([guid]::NewGuid().ToString('N'))"
-        New-Item -ItemType Directory -Force -Path $tmpDir | Out-Null
-        $zipPath = Join-Path $tmpDir $zipName
-
-        Write-Info "Downloading $zipName ..."
-        Invoke-WebRequest -Uri $zipUrl -OutFile $zipPath -UseBasicParsing
-
-        Expand-Archive -Path $zipPath -DestinationPath $tmpDir -Force
-        $extracted = Get-ChildItem -Path $tmpDir -Directory | Where-Object { $_.Name -like "node-v*" } | Select-Object -First 1
-
-        if (-not $extracted) { Write-Err "Node.js extraction failed"; throw "extract" }
-
-        if (Test-Path $NodePrefix) { Remove-Item -Recurse -Force $NodePrefix }
-        New-Item -ItemType Directory -Force -Path $HermesHome | Out-Null
-        Move-Item -Path $extracted.FullName -Destination $NodePrefix
-
-        Remove-Item -Recurse -Force $tmpDir -ErrorAction SilentlyContinue
-
-        $env:PATH = "$NodePrefix;$env:PATH"
-        $v = & "$NodePrefix\node.exe" --version
-        Write-Success "Node.js $v installed to $NodePrefix"
-    } catch {
-        Write-Err "Node.js install failed: $_"
-        Write-Info "Install Node 20+ manually from https://nodejs.org/en/download/ and re-run."
-        throw
-    }
-}
-
-# ─────────────────────────────────────────────────────────────────────────
-# Step 2: agent-browser
-# ─────────────────────────────────────────────────────────────────────────
-
-function Ensure-AgentBrowser {
-    $npmExe = Resolve-NpmExe
-    if (-not $npmExe) {
-        Write-Err "npm not on PATH after Node install — aborting"
-        throw "npm missing"
-    }
-
-    # Already installed?
-    $existing = Get-Command agent-browser -ErrorAction SilentlyContinue
-    if ($existing) {
-        Write-Success "agent-browser already installed at $($existing.Source)"
-        return
-    }
-
-    # When the user has system Node (winget / installer-based), `npm install
-    # -g` writes to a directory that may require admin rights. Force the
-    # prefix to the user-writable Hermes-managed Node directory so we never
-    # need elevation and the agent can always find the result. Mirrors the
-    # bash bootstrap's `--prefix $NODE_PREFIX` strategy.
-    New-Item -ItemType Directory -Force -Path $NodePrefix | Out-Null
-
-    Write-Info "Installing agent-browser (npm, prefix=$NodePrefix)..."
-    & $npmExe install -g --prefix $NodePrefix --silent `
-        "agent-browser@^0.26.0" "@askjo/camofox-browser@^1.5.2"
-    if ($LASTEXITCODE -ne 0) {
-        Write-Err "npm install -g agent-browser failed (exit $LASTEXITCODE)"
-        throw "npm install"
-    }
-
-    # Windows npm global installs drop shims at $NodePrefix\ root (not bin/).
-    # Prepend to PATH so any subsequent npx call resolves them.
-    $env:PATH = "$NodePrefix;$env:PATH"
-
-    Write-Success "agent-browser installed to $NodePrefix"
-}
-
-# ─────────────────────────────────────────────────────────────────────────
-# Step 3: Playwright Chromium
-# ─────────────────────────────────────────────────────────────────────────
-
-function Find-SystemBrowser {
-    $candidates = @(
-        "C:\Program Files\Google\Chrome\Application\chrome.exe",
-        "C:\Program Files (x86)\Google\Chrome\Application\chrome.exe",
-        "C:\Program Files\Chromium\Application\chromium.exe",
-        "${env:LOCALAPPDATA}\Google\Chrome\Application\chrome.exe",
-        "${env:LOCALAPPDATA}\Chromium\Application\chromium.exe"
-    )
-    foreach ($p in $candidates) {
-        if (Test-Path $p) { return $p }
-    }
-    # Edge — Chromium-based, agent-browser can use it
-    foreach ($p in @(
-        "C:\Program Files (x86)\Microsoft\Edge\Application\msedge.exe",
-        "C:\Program Files\Microsoft\Edge\Application\msedge.exe"
-    )) {
-        if (Test-Path $p) { return $p }
-    }
-    return $null
-}
-
-function Write-BrowserEnv {
-    param([string]$BrowserPath)
-    $envFile = Join-Path $HermesHome ".env"
-    New-Item -ItemType Directory -Force -Path $HermesHome | Out-Null
-    if (Test-Path $envFile) {
-        $existing = Get-Content $envFile -Raw -ErrorAction SilentlyContinue
-        if ($existing -and ($existing -match "(?m)^AGENT_BROWSER_EXECUTABLE_PATH=")) {
-            return
-        }
-    }
-    Add-Content -Path $envFile -Value ""
-    Add-Content -Path $envFile -Value "# Hermes Agent browser tools — use the system Chrome/Chromium/Edge binary."
-    Add-Content -Path $envFile -Value "AGENT_BROWSER_EXECUTABLE_PATH=$BrowserPath"
-    Write-Success "Configured browser tools to use $BrowserPath"
-}
-
-function Confirm-ChromiumDownload {
-    if ($Yes) { return $true }
-    if (-not [Environment]::UserInteractive) {
-        Write-Warn "Non-interactive shell — skipping Chromium prompt."
-        Write-Info "Re-run with -Yes to install Chromium (~400 MB download)."
-        return $false
-    }
-    $reply = Read-Host "Install Playwright Chromium (~400 MB download)? [y/N]"
-    return ($reply -match "^(y|yes)$")
-}
-
-function Ensure-Chromium {
-    if ($SkipChromium) {
-        Write-Info "Skipping Chromium install (-SkipChromium)"
-        return
-    }
-
-    # agent-browser on Windows expects a Playwright-managed Chromium under
-    # %LOCALAPPDATA%\ms-playwright. The system-browser shortcut from the
-    # Linux/macOS path doesn't apply the same way on Windows — Playwright's
-    # default launch path won't pick up a stock Chrome install without an
-    # explicit AGENT_BROWSER_EXECUTABLE_PATH. We still offer it as a
-    # fallback when the user doesn't want the download.
-
-    if (-not (Confirm-ChromiumDownload)) {
-        $sys = Find-SystemBrowser
-        if ($sys) {
-            Write-Info "Using system browser at $sys (Chromium download skipped)."
-            Write-BrowserEnv -BrowserPath $sys
-        } else {
-            Write-Info "Chromium install skipped. Browser tools won't launch until"
-            Write-Info "Chromium is installed or AGENT_BROWSER_EXECUTABLE_PATH is set."
-        }
-        return
-    }
-
-    $npxExe = Resolve-NpxExe
-    if (-not $npxExe) {
-        Write-Err "npx not on PATH — cannot install Playwright Chromium"
-        throw "npx missing"
-    }
-
-    Write-Info "Installing Playwright Chromium (~400 MB) ..."
-    & $npxExe --yes playwright install chromium
-    if ($LASTEXITCODE -ne 0) {
-        Write-Err "Playwright Chromium install failed (exit $LASTEXITCODE)"
-        Write-Info "Try again later: npx --yes playwright install chromium"
-        throw "playwright"
-    }
-    Write-Success "Playwright Chromium installed"
-}
-
-# ─────────────────────────────────────────────────────────────────────────
-# Main
-# ─────────────────────────────────────────────────────────────────────────
-
-Write-Info "Hermes Agent: bootstrapping browser tools"
-Write-Info "  HERMES_HOME = $HermesHome"
-Write-Info "  OS          = Windows"
-
-Ensure-Node
-Ensure-AgentBrowser
-Ensure-Chromium
-
-Write-Success "Browser tools setup complete."
-Write-Info "Hermes Agent will pick up agent-browser from $NodePrefix on next launch."

acp_adapter/bootstrap/bootstrap_browser_tools.sh

@@ -1,399 +0,0 @@
-#!/usr/bin/env bash
-#
-# bootstrap_browser_tools.sh — install agent-browser + Playwright Chromium
-# into ~/.hermes/node/ for use by Hermes Agent's browser tools.
-#
-# Targets the registry-install path: users who got Hermes via
-# `uvx --from 'hermes-agent[acp]==X' hermes-acp` don't have a repo clone,
-# so the install.sh `npm install`-in-repo flow doesn't apply. This script
-# is a self-contained, idempotent slice of install.sh's browser block —
-# safe to run from `hermes-acp --setup-browser`, from a fresh terminal,
-# or from install.sh itself (it's a no-op when everything is already in place).
-#
-# Usage:
-#   bootstrap_browser_tools.sh           # use defaults
-#   bootstrap_browser_tools.sh --yes     # accept the ~400MB Chromium download
-#   bootstrap_browser_tools.sh --skip-chromium    # only install Node + agent-browser
-#   HERMES_HOME=/custom/path bootstrap_browser_tools.sh
-#
-# Idempotent: re-running this is safe and fast. Each step checks whether
-# the work is already done.
-
-set -euo pipefail
-
-# ─────────────────────────────────────────────────────────────────────────
-# Config
-# ─────────────────────────────────────────────────────────────────────────
-
-NODE_VERSION="22"
-HERMES_HOME="${HERMES_HOME:-$HOME/.hermes}"
-NODE_PREFIX="$HERMES_HOME/node"
-
-SKIP_CHROMIUM=false
-ASSUME_YES=false
-
-# ─────────────────────────────────────────────────────────────────────────
-# Logging
-# ─────────────────────────────────────────────────────────────────────────
-
-if [ -t 1 ]; then
-    C_GREEN='\033[0;32m'
-    C_YELLOW='\033[0;33m'
-    C_BLUE='\033[0;34m'
-    C_RED='\033[0;31m'
-    C_RESET='\033[0m'
-else
-    C_GREEN='' ; C_YELLOW='' ; C_BLUE='' ; C_RED='' ; C_RESET=''
-fi
-
-log_info()    { printf "${C_BLUE}[*]${C_RESET} %s\n"  "$*"; }
-log_success() { printf "${C_GREEN}[✓]${C_RESET} %s\n" "$*"; }
-log_warn()    { printf "${C_YELLOW}[!]${C_RESET} %s\n" "$*" >&2; }
-log_error()   { printf "${C_RED}[✗]${C_RESET} %s\n"   "$*" >&2; }
-
-# ─────────────────────────────────────────────────────────────────────────
-# Arg parsing
-# ─────────────────────────────────────────────────────────────────────────
-
-while [ $# -gt 0 ]; do
-    case "$1" in
-        --skip-chromium) SKIP_CHROMIUM=true ;;
-        --yes|-y)        ASSUME_YES=true ;;
-        -h|--help)
-            cat <<EOF
-Bootstrap Hermes Agent browser tools.
-
-Installs Node.js (into ~/.hermes/node/), the agent-browser npm package,
-and the Playwright Chromium browser engine.
-
-Options:
-  --skip-chromium   Install Node + agent-browser but skip Chromium download
-  --yes, -y         Accept the ~400 MB Chromium download without prompting
-  -h, --help        Show this help
-
-Environment:
-  HERMES_HOME       Override Hermes data dir (default: \$HOME/.hermes)
-EOF
-            exit 0
-            ;;
-        *)
-            log_error "Unknown option: $1"
-            exit 2
-            ;;
-    esac
-    shift
-done
-
-# ─────────────────────────────────────────────────────────────────────────
-# OS / arch detection
-# ─────────────────────────────────────────────────────────────────────────
-
-OS="unknown"
-case "$(uname -s)" in
-    Linux*)  OS="linux"  ;;
-    Darwin*) OS="macos"  ;;
-    *)
-        log_error "Unsupported OS: $(uname -s)"
-        log_info "Windows users: run scripts/bootstrap_browser_tools.ps1 in PowerShell."
-        exit 1
-        ;;
-esac
-
-NODE_ARCH=""
-case "$(uname -m)" in
-    x86_64)         NODE_ARCH="x64"    ;;
-    aarch64|arm64)  NODE_ARCH="arm64"  ;;
-    armv7l)         NODE_ARCH="armv7l" ;;
-    *)
-        log_error "Unsupported architecture: $(uname -m)"
-        exit 1
-        ;;
-esac
-
-NODE_OS=""
-case "$OS" in
-    linux) NODE_OS="linux"  ;;
-    macos) NODE_OS="darwin" ;;
-esac
-
-DISTRO=""
-if [ -f /etc/os-release ]; then
-    # shellcheck disable=SC1091
-    . /etc/os-release
-    DISTRO="${ID:-}"
-fi
-
-# ─────────────────────────────────────────────────────────────────────────
-# Step 1: Node.js
-# ─────────────────────────────────────────────────────────────────────────
-
-ensure_node() {
-    # Already on PATH and recent enough?
-    if command -v node >/dev/null 2>&1; then
-        local found_ver major
-        found_ver=$(node --version 2>/dev/null)
-        major=$(echo "$found_ver" | sed -E 's/^v([0-9]+).*/\1/')
-        if [ -n "$major" ] && [ "$major" -ge 20 ]; then
-            log_success "Node.js $found_ver found on PATH"
-            return 0
-        fi
-        log_warn "Node.js $found_ver is older than v20 — installing managed Node."
-    fi
-
-    if [ -x "$NODE_PREFIX/bin/node" ]; then
-        local found_ver
-        found_ver=$("$NODE_PREFIX/bin/node" --version 2>/dev/null || echo "?")
-        export PATH="$NODE_PREFIX/bin:$PATH"
-        log_success "Node.js $found_ver found (Hermes-managed at $NODE_PREFIX)"
-        return 0
-    fi
-
-    log_info "Installing Node.js $NODE_VERSION LTS into $NODE_PREFIX ..."
-
-    local index_url="https://nodejs.org/dist/latest-v${NODE_VERSION}.x/"
-    local tarball_name
-    tarball_name=$(curl -fsSL "$index_url" \
-        | grep -oE "node-v${NODE_VERSION}\.[0-9]+\.[0-9]+-${NODE_OS}-${NODE_ARCH}\.tar\.xz" \
-        | head -1)
-
-    if [ -z "$tarball_name" ]; then
-        tarball_name=$(curl -fsSL "$index_url" \
-            | grep -oE "node-v${NODE_VERSION}\.[0-9]+\.[0-9]+-${NODE_OS}-${NODE_ARCH}\.tar\.gz" \
-            | head -1)
-    fi
-
-    if [ -z "$tarball_name" ]; then
-        log_error "Could not locate Node.js $NODE_VERSION tarball for $NODE_OS-$NODE_ARCH"
-        log_info "Install Node 20+ manually: https://nodejs.org/en/download/"
-        return 1
-    fi
-
-    local tmp_dir
-    tmp_dir=$(mktemp -d)
-    trap 'rm -rf "$tmp_dir"' RETURN
-
-    log_info "Downloading $tarball_name ..."
-    if ! curl -fsSL "${index_url}${tarball_name}" -o "$tmp_dir/$tarball_name"; then
-        log_error "Node.js download failed"
-        return 1
-    fi
-
-    if [[ "$tarball_name" == *.tar.xz ]]; then
-        tar xf "$tmp_dir/$tarball_name" -C "$tmp_dir"
-    else
-        tar xzf "$tmp_dir/$tarball_name" -C "$tmp_dir"
-    fi
-
-    local extracted_dir
-    extracted_dir=$(ls -d "$tmp_dir"/node-v* 2>/dev/null | head -1)
-    if [ ! -d "$extracted_dir" ]; then
-        log_error "Node.js extraction failed"
-        return 1
-    fi
-
-    mkdir -p "$HERMES_HOME"
-    rm -rf "$NODE_PREFIX"
-    mv "$extracted_dir" "$NODE_PREFIX"
-
-    export PATH="$NODE_PREFIX/bin:$PATH"
-
-    local installed_ver
-    installed_ver=$("$NODE_PREFIX/bin/node" --version 2>/dev/null || echo "?")
-    log_success "Node.js $installed_ver installed to $NODE_PREFIX"
-}
-
-# ─────────────────────────────────────────────────────────────────────────
-# Step 2: agent-browser + @askjo/camofox-browser via global npm install
-# ─────────────────────────────────────────────────────────────────────────
-
-ensure_agent_browser() {
-    if ! command -v npm >/dev/null 2>&1; then
-        log_error "npm not on PATH after Node install — aborting"
-        return 1
-    fi
-
-    # _find_agent_browser() in tools/browser_tool.py walks ~/.hermes/node/bin
-    # plus a few standard prefixes, so installing globally into the managed
-    # Node prefix is enough — no PATH manipulation needed from the agent side.
-    if [ -x "$NODE_PREFIX/bin/agent-browser" ] || command -v agent-browser >/dev/null 2>&1; then
-        log_success "agent-browser already installed"
-        return 0
-    fi
-
-    # When the system's `npm` resolves to a root-owned prefix (e.g.
-    # /usr/lib/node_modules), `npm install -g` fails with EACCES without
-    # sudo. Force the prefix to the user-writable Hermes-managed Node
-    # directory so we never need sudo and the agent can always find the
-    # result. If we installed Node ourselves above, this is a no-op
-    # (managed Node already uses $NODE_PREFIX). If the user has system
-    # Node, we still drop agent-browser under $NODE_PREFIX/bin/ — which
-    # is exactly where _browser_candidate_path_dirs() looks first.
-    mkdir -p "$NODE_PREFIX"
-
-    log_info "Installing agent-browser (npm, prefix=$NODE_PREFIX)..."
-    if ! npm install -g --prefix "$NODE_PREFIX" --silent \
-            agent-browser@^0.26.0 \
-            "@askjo/camofox-browser@^1.5.2"; then
-        log_error "npm install -g agent-browser failed"
-        return 1
-    fi
-
-    # macOS/Linux global installs place the shim into $NODE_PREFIX/bin/.
-    # Add it to PATH for any subsequent steps (npx playwright).
-    export PATH="$NODE_PREFIX/bin:$PATH"
-
-    log_success "agent-browser installed to $NODE_PREFIX/bin/"
-}
-
-# ─────────────────────────────────────────────────────────────────────────
-# Step 3: Playwright Chromium
-# ─────────────────────────────────────────────────────────────────────────
-
-confirm_chromium_download() {
-    if [ "$ASSUME_YES" = true ]; then return 0; fi
-    if [ ! -t 0 ]; then
-        log_warn "Non-interactive shell — skipping Chromium prompt."
-        log_info "Re-run with --yes to install Chromium (~400 MB download)."
-        return 1
-    fi
-    printf "Install Playwright Chromium (~400 MB download)? [y/N] "
-    local reply=""
-    read -r reply || reply=""
-    case "$reply" in
-        y|Y|yes|YES) return 0 ;;
-        *) return 1 ;;
-    esac
-}
-
-# Detect a usable system Chrome/Chromium. agent-browser's Chrome engine can
-# use it instead of downloading Playwright's bundled Chromium, saving the
-# download cost. Returns the path or empty string.
-find_system_browser() {
-    local candidate
-    for candidate in google-chrome google-chrome-stable chromium chromium-browser chrome; do
-        if command -v "$candidate" >/dev/null 2>&1; then
-            command -v "$candidate"
-            return 0
-        fi
-    done
-    # macOS app-bundle locations
-    if [ "$OS" = "macos" ]; then
-        for candidate in \
-            "/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" \
-            "/Applications/Chromium.app/Contents/MacOS/Chromium" ; do
-            if [ -x "$candidate" ]; then
-                echo "$candidate"
-                return 0
-            fi
-        done
-    fi
-    return 1
-}
-
-write_browser_env() {
-    local browser_path="$1"
-    local env_file="$HERMES_HOME/.env"
-    mkdir -p "$HERMES_HOME"
-    if [ -f "$env_file" ] && grep -q "^AGENT_BROWSER_EXECUTABLE_PATH=" "$env_file"; then
-        return 0
-    fi
-    {
-        echo ""
-        echo "# Hermes Agent browser tools — use the system Chrome/Chromium binary."
-        echo "AGENT_BROWSER_EXECUTABLE_PATH=$browser_path"
-    } >> "$env_file"
-    log_success "Configured browser tools to use $browser_path"
-}
-
-ensure_chromium() {
-    if [ "$SKIP_CHROMIUM" = true ]; then
-        log_info "Skipping Chromium install (--skip-chromium)"
-        return 0
-    fi
-
-    local system_browser
-    system_browser="$(find_system_browser 2>/dev/null || true)"
-    if [ -n "$system_browser" ]; then
-        log_success "Found system browser: $system_browser"
-        log_info "Skipping Playwright Chromium download; agent-browser will use it."
-        write_browser_env "$system_browser"
-        return 0
-    fi
-
-    if ! confirm_chromium_download; then
-        log_info "Chromium install skipped. Browser tools will only work if you"
-        log_info "set AGENT_BROWSER_EXECUTABLE_PATH or install Chromium later."
-        return 0
-    fi
-
-    if ! command -v npx >/dev/null 2>&1; then
-        log_error "npx not on PATH — cannot install Playwright Chromium"
-        return 1
-    fi
-
-    log_info "Installing Playwright Chromium (~400 MB) ..."
-
-    # On apt-based distros, --with-deps requires sudo. Try non-interactively
-    # only — never prompt — and fall back to the bare browser-only install.
-    local installed=false
-    if [ "$OS" = "linux" ]; then
-        case "$DISTRO" in
-            ubuntu|debian|raspbian|pop|linuxmint|elementary|zorin|kali|parrot)
-                if [ "$(id -u)" -eq 0 ] || (command -v sudo >/dev/null 2>&1 && sudo -n true 2>/dev/null); then
-                    log_info "Installing system deps with --with-deps (sudo available)"
-                    if npx --yes playwright install --with-deps chromium; then
-                        installed=true
-                    fi
-                else
-                    log_warn "sudo not available non-interactively — installing Chromium without system deps."
-                    log_info "If browser tools fail to launch, an administrator should run:"
-                    log_info "  sudo npx playwright install-deps chromium"
-                fi
-                ;;
-            arch|manjaro|cachyos|endeavouros|garuda)
-                log_info "Arch-family system dependencies are not auto-installed."
-                log_info "If launch fails, run: sudo pacman -S nss atk at-spi2-core cups libdrm libxkbcommon mesa pango cairo alsa-lib"
-                ;;
-            fedora|rhel|centos|rocky|alma)
-                log_info "Fedora/RHEL system dependencies are not auto-installed."
-                log_info "If launch fails, run: sudo dnf install nss atk at-spi2-core cups-libs libdrm libxkbcommon mesa-libgbm pango cairo alsa-lib"
-                ;;
-            opensuse*|sles)
-                log_info "openSUSE system dependencies are not auto-installed."
-                ;;
-        esac
-    fi
-
-    if [ "$installed" = false ]; then
-        if npx --yes playwright install chromium; then
-            installed=true
-        fi
-    fi
-
-    if [ "$installed" = true ]; then
-        log_success "Playwright Chromium installed"
-    else
-        log_error "Playwright Chromium install failed"
-        log_info "Try again later: npx --yes playwright install chromium"
-        return 1
-    fi
-}
-
-# ─────────────────────────────────────────────────────────────────────────
-# Main
-# ─────────────────────────────────────────────────────────────────────────
-
-main() {
-    log_info "Hermes Agent: bootstrapping browser tools"
-    log_info "  HERMES_HOME = $HERMES_HOME"
-    log_info "  OS / arch   = $NODE_OS-$NODE_ARCH ${DISTRO:+($DISTRO)}"
-
-    ensure_node
-    ensure_agent_browser
-    ensure_chromium
-
-    log_success "Browser tools setup complete."
-    log_info "Hermes Agent will pick up agent-browser from $NODE_PREFIX/bin/ on next launch."
-}
-
-main

acp_adapter/entry.py

@@ -24,7 +24,6 @@ except ModuleNotFoundError:
     # means UTF-8 stdio setup is skipped on Windows; POSIX is unaffected.
     pass
 
-import argparse
 import asyncio
 import logging
 import sys
@@ -108,150 +107,8 @@ def _load_env() -> None:
         )
 
 
-def _parse_args(argv: list[str] | None = None) -> argparse.Namespace:
-    parser = argparse.ArgumentParser(
-        prog="hermes-acp",
-        description="Run Hermes Agent as an ACP stdio server.",
-    )
-    parser.add_argument("--version", action="store_true", help="Print Hermes version and exit")
-    parser.add_argument(
-        "--check",
-        action="store_true",
-        help="Verify ACP dependencies and adapter imports, then exit",
-    )
-    parser.add_argument(
-        "--setup",
-        action="store_true",
-        help="Run interactive Hermes provider/model setup for ACP terminal auth",
-    )
-    parser.add_argument(
-        "--setup-browser",
-        action="store_true",
-        help="Install agent-browser + Playwright Chromium into ~/.hermes/node/ "
-             "for browser tool support. Idempotent.",
-    )
-    parser.add_argument(
-        "--yes",
-        "-y",
-        action="store_true",
-        dest="assume_yes",
-        help="Accept all prompts (currently used by --setup-browser to skip the "
-             "~400 MB Chromium download confirmation).",
-    )
-    return parser.parse_args(argv)
-
-
-def _print_version() -> None:
-    from hermes_cli import __version__ as hermes_version
-
-    print(hermes_version)
-
-
-def _run_check() -> None:
-    import acp  # noqa: F401
-    from acp_adapter.server import HermesACPAgent  # noqa: F401
-
-    print("Hermes ACP check OK")
-
-
-def _run_setup() -> None:
-    from hermes_cli.main import main as hermes_main
-
-    old_argv = sys.argv[:]
-    try:
-        sys.argv = [old_argv[0] if old_argv else "hermes", "model"]
-        hermes_main()
-    finally:
-        sys.argv = old_argv
-
-    # Offer browser-tools install as a follow-up. The terminal auth method
-    # is the one supported first-run UX for registry installs, so this is
-    # the natural moment to ask. Skip silently if stdin isn't a TTY (the
-    # answer can't be collected anyway).
-    if not sys.stdin.isatty():
-        return
-    try:
-        reply = input(
-            "\nInstall browser tools? Downloads agent-browser (npm) and "
-            "optionally Playwright Chromium (~400 MB). [y/N] "
-        ).strip().lower()
-    except (EOFError, KeyboardInterrupt):
-        return
-    if reply in {"y", "yes"}:
-        _run_setup_browser(assume_yes=False)
-
-
-def _run_setup_browser(assume_yes: bool = False) -> int:
-    """Bootstrap agent-browser + Playwright Chromium for the registry-install path.
-
-    Shells out to the bundled platform-specific bootstrap script
-    (acp_adapter/bootstrap/bootstrap_browser_tools.{sh,ps1}) so the install
-    logic lives in one place — readable, debuggable, and shareable with
-    install.sh / install.ps1 if we ever want to call it from there too.
-
-    Returns the script's exit code (0 on success).
-    """
-    import platform
-    import subprocess
-
-    bootstrap_dir = Path(__file__).resolve().parent / "bootstrap"
-
-    if platform.system() == "Windows":
-        script = bootstrap_dir / "bootstrap_browser_tools.ps1"
-        if not script.is_file():
-            print(
-                f"Bootstrap script not found at {script} — wheel may be incomplete.",
-                file=sys.stderr,
-            )
-            return 1
-        cmd = [
-            "powershell.exe",
-            "-NoProfile",
-            "-ExecutionPolicy", "Bypass",
-            "-File", str(script),
-        ]
-        if assume_yes:
-            cmd.append("-Yes")
-    else:
-        script = bootstrap_dir / "bootstrap_browser_tools.sh"
-        if not script.is_file():
-            print(
-                f"Bootstrap script not found at {script} — wheel may be incomplete.",
-                file=sys.stderr,
-            )
-            return 1
-        cmd = ["bash", str(script)]
-        if assume_yes:
-            cmd.append("--yes")
-
-    # stdio is inherited so the user sees the bootstrap's progress live.
-    try:
-        result = subprocess.run(cmd, check=False)
-    except FileNotFoundError as exc:
-        # bash / powershell.exe not on PATH
-        print(f"Could not launch browser bootstrap: {exc}", file=sys.stderr)
-        return 1
-    return result.returncode
-
-
-def main(argv: list[str] | None = None) -> None:
+def main() -> None:
     """Entry point: load env, configure logging, run the ACP agent."""
-    args = _parse_args(argv)
-    if args.version:
-        _print_version()
-        return
-    if args.check:
-        _run_check()
-        return
-    if args.setup:
-        _run_setup()
-        return
-    if args.setup_browser:
-        rc = _run_setup_browser(assume_yes=args.assume_yes)
-        if rc != 0:
-            sys.exit(rc)
-        return
-
     _setup_logging()
     _load_env()
 

acp_adapter/events.py

@@ -14,7 +14,6 @@ from collections import deque
 from typing import Any, Callable, Deque, Dict
 
 import acp
-from acp.schema import AgentPlanUpdate, PlanEntry
 
 from .tools import (
     build_tool_complete,
@@ -25,65 +24,6 @@ from .tools import (
 logger = logging.getLogger(__name__)
 
 
-def _json_loads_maybe_prefix(value: str) -> Any:
-    """Parse a JSON object even when Hermes appended a human hint after it."""
-    text = value.strip()
-    try:
-        return json.loads(text)
-    except Exception:
-        decoder = json.JSONDecoder()
-        data, _ = decoder.raw_decode(text)
-        return data
-
-
-def _build_plan_update_from_todo_result(result: Any) -> AgentPlanUpdate | None:
-    """Translate Hermes' todo tool result into ACP's native plan update.
-
-    Zed renders ``sessionUpdate: plan`` as its first-class task/todo panel. The
-    Hermes agent already maintains task state through the ``todo`` tool, so the
-    ACP adapter should expose that state natively instead of only as a generic
-    tool-call transcript block.
-    """
-    if not isinstance(result, str) or not result.strip():
-        return None
-
-    try:
-        data = _json_loads_maybe_prefix(result)
-    except Exception:
-        return None
-
-    if not isinstance(data, dict) or not isinstance(data.get("todos"), list):
-        return None
-
-    todos = data["todos"]
-    if not todos:
-        return AgentPlanUpdate(session_update="plan", entries=[])
-
-    status_map = {
-        "pending": "pending",
-        "in_progress": "in_progress",
-        "completed": "completed",
-        # ACP plans only support pending/in_progress/completed. Preserve
-        # cancelled tasks as terminal entries instead of dropping them and
-        # making the client's full-list replacement lose visible context.
-        "cancelled": "completed",
-    }
-    entries: list[PlanEntry] = []
-    for item in todos:
-        if not isinstance(item, dict):
-            continue
-        content = str(item.get("content") or item.get("id") or "").strip()
-        if not content:
-            continue
-        raw_status = str(item.get("status") or "pending").strip()
-        status = status_map.get(raw_status, "pending")
-        if raw_status == "cancelled":
-            content = f"[cancelled] {content}"
-        entries.append(PlanEntry(content=content, priority="medium", status=status))
-
-    return AgentPlanUpdate(session_update="plan", entries=entries)
-
-
 def _send_update(
     conn: acp.Client,
     session_id: str,
@@ -91,17 +31,10 @@ def _send_update(
     update: Any,
 ) -> None:
     """Fire-and-forget an ACP session update from a worker thread."""
-    from agent.async_utils import safe_schedule_threadsafe
-
-    future = safe_schedule_threadsafe(
-        conn.session_update(session_id, update),
-        loop,
-        logger=logger,
-        log_message="Failed to send ACP update",
-    )
-    if future is None:
-        return
     try:
+        future = asyncio.run_coroutine_threadsafe(
+            conn.session_update(session_id, update), loop
+        )
         future.result(timeout=5)
     except Exception:
         logger.debug("Failed to send ACP update", exc_info=True)
@@ -235,10 +168,6 @@ def make_step_cb(
                         snapshot=meta.get("snapshot"),
                     )
                     _send_update(conn, session_id, loop, update)
-                    if tool_name == "todo":
-                        plan_update = _build_plan_update_from_todo_result(result)
-                        if plan_update is not None:
-                            _send_update(conn, session_id, loop, plan_update)
                     if not queue:
                         tool_call_ids.pop(tool_name, None)
 

acp_adapter/permissions.py

@@ -1,11 +1,10 @@
-"""ACP permission bridging for Hermes dangerous-command approvals."""
+"""ACP permission bridging — maps ACP approval requests to hermes approval callbacks."""
 
 from __future__ import annotations
 
 import asyncio
 import logging
 from concurrent.futures import TimeoutError as FutureTimeout
-from itertools import count
 from typing import Callable
 
 from acp.schema import (
@@ -15,87 +14,24 @@ from acp.schema import (
 
 logger = logging.getLogger(__name__)
 
-# Maps ACP permission option ids to Hermes approval result strings.
-# Option ids are stable across both the ``allow_permanent=True`` and
-# ``allow_permanent=False`` paths even though the option list differs.
-_OPTION_ID_TO_HERMES = {
+# Maps ACP PermissionOptionKind -> hermes approval result strings
+_KIND_TO_HERMES = {
     "allow_once": "once",
-    "allow_session": "session",
     "allow_always": "always",
-    "deny": "deny",
+    "reject_once": "deny",
+    "reject_always": "deny",
 }
 
-_PERMISSION_REQUEST_IDS = count(1)
-
-
-def _build_permission_options(*, allow_permanent: bool) -> list[PermissionOption]:
-    """Return ACP options that match Hermes approval semantics."""
-    options = [
-        PermissionOption(option_id="allow_once", kind="allow_once", name="Allow once"),
-        PermissionOption(
-            option_id="allow_session",
-            # ACP has no session-scoped kind, so use the closest persistent
-            # hint while keeping Hermes semantics in the option id.
-            kind="allow_always",
-            name="Allow for session",
-        ),
-    ]
-    if allow_permanent:
-        options.append(
-            PermissionOption(
-                option_id="allow_always",
-                kind="allow_always",
-                name="Allow always",
-            ),
-        )
-    options.append(PermissionOption(option_id="deny", kind="reject_once", name="Deny"))
-    return options
-
-
-def _build_permission_tool_call(command: str, description: str):
-    """Return the ACP tool-call update attached to a permission request.
-
-    ``request_permission`` expects a ``ToolCallUpdate`` payload — produced
-    by ``_acp.update_tool_call`` — not a ``ToolCallStart``. Each request
-    gets a unique ``perm-check-N`` id so concurrent requests don't collide.
-    """
-    import acp as _acp
-
-    tool_call_id = f"perm-check-{next(_PERMISSION_REQUEST_IDS)}"
-    return _acp.update_tool_call(
-        tool_call_id,
-        title=description,
-        kind="execute",
-        status="pending",
-        content=[_acp.tool_content(_acp.text_block(f"$ {command}"))],
-        raw_input={"command": command, "description": description},
-    )
-
-
-def _map_outcome_to_hermes(outcome: object, *, allowed_option_ids: set[str]) -> str:
-    """Map an ACP permission outcome into Hermes approval strings."""
-    if not isinstance(outcome, AllowedOutcome):
-        return "deny"
-
-    option_id = outcome.option_id
-    if option_id not in allowed_option_ids:
-        logger.warning("Permission request returned unknown option_id: %s", option_id)
-        return "deny"
-    return _OPTION_ID_TO_HERMES.get(option_id, "deny")
-
 
 def make_approval_callback(
     request_permission_fn: Callable,
     loop: asyncio.AbstractEventLoop,
     session_id: str,
     timeout: float = 60.0,
-) -> Callable[..., str]:
+) -> Callable[[str, str], str]:
     """
-    Return a Hermes-compatible approval callback that bridges to ACP.
-
-    The callback accepts ``command`` and ``description`` plus optional
-    keyword arguments such as ``allow_permanent`` used by
-    ``tools.approval.prompt_dangerous_approval()``.
+    Return a hermes-compatible ``approval_callback(command, description) -> str``
+    that bridges to the ACP client's ``request_permission`` call.
 
     Args:
         request_permission_fn: The ACP connection's ``request_permission`` coroutine.
@@ -104,45 +40,41 @@ def make_approval_callback(
         timeout: Seconds to wait for a response before auto-denying.
     """
 
-    def _callback(
-        command: str,
-        description: str,
-        *,
-        allow_permanent: bool = True,
-        **_: object,
-    ) -> str:
-        from agent.async_utils import safe_schedule_threadsafe
+    def _callback(command: str, description: str) -> str:
+        options = [
+            PermissionOption(option_id="allow_once", kind="allow_once", name="Allow once"),
+            PermissionOption(option_id="allow_always", kind="allow_always", name="Allow always"),
+            PermissionOption(option_id="deny", kind="reject_once", name="Deny"),
+        ]
+        import acp as _acp
 
-        options = _build_permission_options(allow_permanent=allow_permanent)
+        tool_call = _acp.start_tool_call("perm-check", command, kind="execute")
 
-        tool_call = _build_permission_tool_call(command, description)
         coro = request_permission_fn(
             session_id=session_id,
             tool_call=tool_call,
             options=options,
         )
-        future = safe_schedule_threadsafe(
-            coro, loop,
-            logger=logger,
-            log_message="Permission request: failed to schedule on loop",
-        )
-        if future is None:
-            return "deny"
 
         try:
+            future = asyncio.run_coroutine_threadsafe(coro, loop)
             response = future.result(timeout=timeout)
         except (FutureTimeout, Exception) as exc:
-            future.cancel()
             logger.warning("Permission request timed out or failed: %s", exc)
             return "deny"
 
         if response is None:
             return "deny"
 
-        allowed_option_ids = {option.option_id for option in options}
-        return _map_outcome_to_hermes(
-            response.outcome,
-            allowed_option_ids=allowed_option_ids,
-        )
+        outcome = response.outcome
+        if isinstance(outcome, AllowedOutcome):
+            option_id = outcome.option_id
+            # Look up the kind from our options list
+            for opt in options:
+                if opt.option_id == option_id:
+                    return _KIND_TO_HERMES.get(opt.kind, "deny")
+            return "once"  # fallback for unknown option_id
+        else:
+            return "deny"
 
     return _callback

acp_adapter/server.py

@@ -18,7 +18,6 @@ import acp
 from acp.schema import (
     AgentCapabilities,
     AgentMessageChunk,
-    AgentThoughtChunk,
     AuthenticateResponse,
     AvailableCommand,
     AvailableCommandsUpdate,
@@ -58,9 +57,14 @@ from acp.schema import (
     UserMessageChunk,
 )
 
-from acp_adapter.auth import TERMINAL_SETUP_AUTH_METHOD_ID, build_auth_methods, detect_provider
+# AuthMethodAgent was renamed from AuthMethod in agent-client-protocol 0.9.0
+try:
+    from acp.schema import AuthMethodAgent
+except ImportError:
+    from acp.schema import AuthMethod as AuthMethodAgent  # type: ignore[attr-defined]
+
+from acp_adapter.auth import detect_provider
 from acp_adapter.events import (
-    _build_plan_update_from_todo_result,
     make_message_cb,
     make_step_cb,
     make_thinking_cb,
@@ -740,7 +744,16 @@ class HermesACPAgent(acp.Agent):
         resolved_protocol_version = (
             protocol_version if isinstance(protocol_version, int) else acp.PROTOCOL_VERSION
         )
-        auth_methods = build_auth_methods()
+        provider = detect_provider()
+        auth_methods = None
+        if provider:
+            auth_methods = [
+                AuthMethodAgent(
+                    id=provider,
+                    name=f"{provider} runtime credentials",
+                    description=f"Authenticate Hermes using the currently configured {provider} runtime credentials.",
+                )
+            ]
 
         client_name = client_info.name if client_info else "unknown"
         logger.info(
@@ -771,38 +784,24 @@ class HermesACPAgent(acp.Agent):
         # server has provider credentials configured — harmless under
         # Hermes' threat model (ACP is stdio-only, local-trust), but poor
         # API hygiene and confusing if ACP ever grows multi-method auth.
-        if not isinstance(method_id, str):
-            return None
-        normalized_method = method_id.strip().lower()
         provider = detect_provider()
-
-        if normalized_method == TERMINAL_SETUP_AUTH_METHOD_ID:
-            # Terminal auth launches Hermes setup/model selection out-of-band.
-            # Only report success once that flow has produced usable runtime
-            # credentials for the normal ACP session.
-            return AuthenticateResponse() if provider else None
-
-        if not provider or normalized_method != provider:
+        if not provider:
+            return None
+        if not isinstance(method_id, str) or method_id.strip().lower() != provider:
             return None
         return AuthenticateResponse()
 
     # ---- Session management -------------------------------------------------
 
     @staticmethod
-    def _flatten_history_text(value: Any) -> str:
-        """Normalize a persisted text-or-text-parts value into a single string.
-
-        OpenAI-style assistant content (and provider reasoning fields) can arrive
-        as either a scalar string or a list of ``{"text": ...}`` /
-        ``{"type": "text", "content": ...}`` parts. Whitespace-only inputs
-        collapse to an empty string so callers can treat ``""`` as "nothing to
-        emit".
-        """
-        if isinstance(value, str):
-            return value.strip()
-        if isinstance(value, list):
+    def _history_message_text(message: dict[str, Any]) -> str:
+        """Extract displayable text from a persisted OpenAI-style message."""
+        content = message.get("content")
+        if isinstance(content, str):
+            return content.strip()
+        if isinstance(content, list):
             parts: list[str] = []
-            for item in value:
+            for item in content:
                 if isinstance(item, dict):
                     text = item.get("text")
                     if isinstance(text, str):
@@ -814,29 +813,6 @@ class HermesACPAgent(acp.Agent):
             return "\n".join(part.strip() for part in parts if part and part.strip()).strip()
         return ""
 
-    @classmethod
-    def _history_message_text(cls, message: dict[str, Any]) -> str:
-        """Extract displayable text from a persisted OpenAI-style message."""
-        return cls._flatten_history_text(message.get("content"))
-
-    @classmethod
-    def _history_reasoning_text(cls, message: dict[str, Any]) -> str:
-        """Extract displayable reasoning/thought text from a persisted assistant message.
-
-        Returns the first non-empty value among ``reasoning_content`` (the
-        canonical field used by DeepSeek / Moonshot and the post-#16892
-        chat-completions normalizer) and ``reasoning`` (used by the codex
-        event projector and several other transports). Both keys are
-        actively written by live code paths, so neither branch is
-        deprecated — they cover different transports rather than old vs.
-        new sessions.
-        """
-        for key in ("reasoning_content", "reasoning"):
-            text = cls._flatten_history_text(message.get(key))
-            if text:
-                return text
-        return ""
-
     @staticmethod
     def _history_message_update(
         *,
@@ -857,11 +833,6 @@ class HermesACPAgent(acp.Agent):
             )
         return None
 
-    @staticmethod
-    def _history_thought_update(text: str) -> AgentThoughtChunk:
-        """Build an ACP history replay update for an assistant thought."""
-        return acp.update_agent_thought_text(text)
-
     @staticmethod
     def _history_tool_call_name_args(tool_call: dict[str, Any]) -> tuple[str, dict[str, Any]]:
         """Extract function name/arguments from an OpenAI-style tool_call."""
@@ -889,17 +860,13 @@ class HermesACPAgent(acp.Agent):
         ).strip()
 
     async def _replay_session_history(self, state: SessionState) -> None:
-        """Replay persisted user/assistant history during session/load or session/resume.
+        """Send persisted user/assistant history to clients during session/load.
 
-        Invoked inline (``await``) from both ``load_session`` and
-        ``resume_session`` so that spec-compliant ACP clients receive the
-        full transcript within the request's lifetime — see the comment at
-        the call sites for the rationale and prior-art citations.
-
-        Replays the conversation as user/assistant chunks, thinking-mode
-        thought chunks, plus reconstructed tool-call start/completion
-        notifications. Merely restoring server-side state makes Hermes
-        remember context, but leaves the editor looking like a clean thread.
+        Zed's ACP history UI calls ``session/load`` after the user picks an item
+        from the Agents sidebar. The agent must then replay the full conversation
+        as user/assistant chunks plus reconstructed tool-call start/completion
+        notifications; merely restoring server-side state makes Hermes remember
+        context, but leaves the editor looking like a clean thread.
         """
         if not self._conn or not state.history:
             return
@@ -921,37 +888,24 @@ class HermesACPAgent(acp.Agent):
         for message in state.history:
             role = str(message.get("role") or "")
 
-            if role == "user":
-                text = self._history_message_text(message)
-                if text:
-                    update = self._history_message_update(role=role, text=text)
-                    if update is not None and not await _send(update):
-                        return
-                continue
-
-            if role == "assistant":
-                thought = self._history_reasoning_text(message)
-                if thought and not await _send(self._history_thought_update(thought)):
-                    return
-
+            if role in {"user", "assistant"}:
                 text = self._history_message_text(message)
                 if text:
                     update = self._history_message_update(role=role, text=text)
                     if update is not None and not await _send(update):
                         return
 
-                tool_calls = message.get("tool_calls")
-                if isinstance(tool_calls, list):
-                    for tool_call in tool_calls:
-                        if not isinstance(tool_call, dict):
-                            continue
-                        tool_call_id = self._history_tool_call_id(tool_call)
-                        if not tool_call_id:
-                            continue
-                        tool_name, args = self._history_tool_call_name_args(tool_call)
-                        active_tool_calls[tool_call_id] = (tool_name, args)
-                        if not await _send(build_tool_start(tool_call_id, tool_name, args)):
-                            return
+            if role == "assistant" and isinstance(message.get("tool_calls"), list):
+                for tool_call in message["tool_calls"]:
+                    if not isinstance(tool_call, dict):
+                        continue
+                    tool_call_id = self._history_tool_call_id(tool_call)
+                    if not tool_call_id:
+                        continue
+                    tool_name, args = self._history_tool_call_name_args(tool_call)
+                    active_tool_calls[tool_call_id] = (tool_name, args)
+                    if not await _send(build_tool_start(tool_call_id, tool_name, args)):
+                        return
                 continue
 
             if role == "tool":
@@ -963,20 +917,15 @@ class HermesACPAgent(acp.Agent):
                 if not tool_call_id or not tool_name:
                     continue
                 result = message.get("content")
-                result_text = result if isinstance(result, str) else None
                 if not await _send(
                     build_tool_complete(
                         tool_call_id,
                         tool_name,
-                        result=result_text,
+                        result=result if isinstance(result, str) else None,
                         function_args=function_args,
                     )
                 ):
                     return
-                if tool_name == "todo":
-                    plan_update = _build_plan_update_from_todo_result(result_text)
-                    if plan_update is not None and not await _send(plan_update):
-                        return
 
     async def new_session(
         self,
@@ -994,6 +943,18 @@ class HermesACPAgent(acp.Agent):
             models=self._build_model_state(state),
         )
 
+    def _schedule_history_replay(self, state: SessionState) -> None:
+        """Replay persisted history after session/load or session/resume returns.
+
+        Zed only attaches streamed transcript/tool updates once the load/resume
+        response has completed. Sending replay notifications while the request is
+        still in-flight can make the server look correct in logs while the editor
+        drops or fails to attach the tool-call history.
+        """
+        loop = asyncio.get_running_loop()
+        replay_coro = self._replay_session_history(state)
+        loop.call_soon(asyncio.create_task, replay_coro)
+
     async def load_session(
         self,
         cwd: str,
@@ -1007,30 +968,7 @@ class HermesACPAgent(acp.Agent):
             return None
         await self._register_session_mcp_servers(state, mcp_servers)
         logger.info("Loaded session %s", session_id)
-        # Per ACP spec, `session/load` must stream the prior conversation back
-        # to the client via `session/update` notifications BEFORE responding,
-        # so the client receives the full transcript within the load request's
-        # lifetime. Awaiting the replay here matches Codex / Claude Code /
-        # OpenCode / Pi and the Zed client (which registers the session-update
-        # routing entry before awaiting the loadSession RPC specifically so
-        # in-call history replay updates can find the thread). Deferring this
-        # via `loop.call_soon` (as we did briefly in May 2026) broke every
-        # spec-compliant ACP client that measures notifications synchronously
-        # against the load response — see #12285 follow-up.
-        try:
-            await self._replay_session_history(state)
-        except Exception:
-            # Replay is best-effort — a corrupted or unexpected message shape
-            # must not turn a successful session/load into a JSON-RPC error
-            # response. Per-notification failures are already caught inside
-            # ``_replay_session_history``; this outer guard covers anything
-            # raised by the helpers themselves before reaching ``_send``.
-            logger.warning(
-                "ACP history replay raised during session/load for %s — "
-                "load will still succeed, partial transcript may be missing",
-                session_id,
-                exc_info=True,
-            )
+        self._schedule_history_replay(state)
         self._schedule_available_commands_update(session_id)
         self._schedule_usage_update(state)
         return LoadSessionResponse(models=self._build_model_state(state))
@@ -1048,18 +986,7 @@ class HermesACPAgent(acp.Agent):
             state = self.session_manager.create_session(cwd=cwd)
         await self._register_session_mcp_servers(state, mcp_servers)
         logger.info("Resumed session %s", state.session_id)
-        # See `load_session` above for the spec rationale — replay must
-        # complete before the response so clients receive the full transcript
-        # within the request's lifetime.
-        try:
-            await self._replay_session_history(state)
-        except Exception:
-            logger.warning(
-                "ACP history replay raised during session/resume for %s — "
-                "resume will still succeed, partial transcript may be missing",
-                state.session_id,
-                exc_info=True,
-            )
+        self._schedule_history_replay(state)
         self._schedule_available_commands_update(state.session_id)
         self._schedule_usage_update(state)
         return ResumeSessionResponse(models=self._build_model_state(state))

acp_registry/agent.json

@@ -1,16 +1,12 @@
 {
-  "id": "hermes-agent",
-  "name": "Hermes Agent",
-  "version": "0.13.0",
-  "description": "Self-improving open-source AI agent by Nous Research with ACP editor integration, persistent memory, skills, and rich tool support.",
-  "repository": "https://github.com/NousResearch/hermes-agent",
-  "website": "https://hermes-agent.nousresearch.com/docs/user-guide/features/acp",
-  "authors": ["Nous Research"],
-  "license": "MIT",
+  "schema_version": 1,
+  "name": "hermes-agent",
+  "display_name": "Hermes Agent",
+  "description": "AI agent by Nous Research with 90+ tools, persistent memory, and multi-platform support",
+  "icon": "icon.svg",
   "distribution": {
-    "uvx": {
-      "package": "hermes-agent[acp]==0.13.0",
-      "args": ["hermes-acp"]
-    }
+    "type": "command",
+    "command": "hermes",
+    "args": ["acp"]
   }
 }

acp_registry/icon.svg

@@ -1,8 +1,25 @@
-<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 16 16" width="16" height="16" fill="none">
-  <path d="M8 1.5v13" stroke="currentColor" stroke-width="1.5" stroke-linecap="round"/>
-  <path d="M8 3.25c-2.35-1.4-4.7-.95-6.25.35 1.85-.2 3.8.2 5.55 1.55" stroke="currentColor" stroke-width="1.1" stroke-linecap="round" stroke-linejoin="round"/>
-  <path d="M8 3.25c2.35-1.4 4.7-.95 6.25.35-1.85-.2-3.8.2-5.55 1.55" stroke="currentColor" stroke-width="1.1" stroke-linecap="round" stroke-linejoin="round"/>
-  <path d="M8 13.25c-2.3-1-3.05-2.65-1.35-4.15-2 .8-2.35 2.95-.35 4" stroke="currentColor" stroke-width="1.1" stroke-linecap="round" stroke-linejoin="round"/>
-  <path d="M8 13.25c2.3-1 3.05-2.65 1.35-4.15 2 .8 2.35 2.95.35 4" stroke="currentColor" stroke-width="1.1" stroke-linecap="round" stroke-linejoin="round"/>
-  <circle cx="8" cy="1.8" r="1.1" fill="currentColor"/>
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 64 64" width="64" height="64">
+  <defs>
+    <linearGradient id="gold" x1="0%" y1="0%" x2="0%" y2="100%">
+      <stop offset="0%" style="stop-color:#F5C542;stop-opacity:1" />
+      <stop offset="100%" style="stop-color:#D4961C;stop-opacity:1" />
+    </linearGradient>
+  </defs>
+  <!-- Staff -->
+  <rect x="30" y="10" width="4" height="46" rx="2" fill="url(#gold)" />
+  <!-- Wings (left) -->
+  <path d="M30 18 C24 14, 14 14, 10 18 C14 16, 22 16, 28 20" fill="#F5C542" opacity="0.9" />
+  <path d="M30 22 C26 19, 18 19, 14 22 C18 20, 24 20, 28 24" fill="#D4961C" opacity="0.8" />
+  <!-- Wings (right) -->
+  <path d="M34 18 C40 14, 50 14, 54 18 C50 16, 42 16, 36 20" fill="#F5C542" opacity="0.9" />
+  <path d="M34 22 C38 19, 46 19, 50 22 C46 20, 40 20, 36 24" fill="#D4961C" opacity="0.8" />
+  <!-- Left serpent -->
+  <path d="M32 48 C22 44, 20 38, 26 34 C20 36, 18 42, 24 46 C18 40, 22 30, 30 28 C24 32, 22 38, 28 42"
+        fill="none" stroke="#F5C542" stroke-width="2.5" stroke-linecap="round" />
+  <!-- Right serpent -->
+  <path d="M32 48 C42 44, 44 38, 38 34 C44 36, 46 42, 40 46 C46 40, 42 30, 34 28 C40 32, 42 38, 36 42"
+        fill="none" stroke="#D4961C" stroke-width="2.5" stroke-linecap="round" />
+  <!-- Orb at top -->
+  <circle cx="32" cy="10" r="4" fill="#F5C542" />
+  <circle cx="32" cy="10" r="2" fill="#FFF8E1" opacity="0.7" />
 </svg>

agent/anthropic_adapter.py

@@ -1060,12 +1060,10 @@ def _generate_pkce() -> tuple:
 
 def run_hermes_oauth_login_pure() -> Optional[Dict[str, Any]]:
     """Run Hermes-native OAuth PKCE flow and return credential state."""
-    import secrets
     import time
     import webbrowser
 
     verifier, challenge = _generate_pkce()
-    oauth_state = secrets.token_urlsafe(32)
 
     params = {
         "code": "true",
@@ -1075,7 +1073,7 @@ def run_hermes_oauth_login_pure() -> Optional[Dict[str, Any]]:
         "scope": _OAUTH_SCOPES,
         "code_challenge": challenge,
         "code_challenge_method": "S256",
-        "state": oauth_state,
+        "state": verifier,
     }
     from urllib.parse import urlencode
 
@@ -1112,12 +1110,7 @@ def run_hermes_oauth_login_pure() -> Optional[Dict[str, Any]]:
 
     splits = auth_code.split("#")
     code = splits[0]
-    received_state = splits[1] if len(splits) > 1 else ""
-
-    # Validate state to prevent CSRF (RFC 6749 §10.12)
-    if received_state != oauth_state:
-        logger.warning("OAuth state mismatch — possible CSRF, aborting")
-        return None
+    state = splits[1] if len(splits) > 1 else ""
 
     try:
         import urllib.request
@@ -1126,7 +1119,7 @@ def run_hermes_oauth_login_pure() -> Optional[Dict[str, Any]]:
             "grant_type": "authorization_code",
             "client_id": _OAUTH_CLIENT_ID,
             "code": code,
-            "state": received_state,
+            "state": state,
             "redirect_uri": _OAUTH_REDIRECT_URI,
             "code_verifier": verifier,
         }).encode()
@@ -1312,8 +1305,9 @@ def convert_tools_to_anthropic(tools: List[Dict]) -> List[Dict]:
             ),
         }
         # Forward cache_control marker when present on the OpenAI-format
-        # tool dict. Anthropic's tools array supports cache_control on the
-        # last tool to cache the entire schema cross-session.
+        # tool dict (set by ``mark_tools_for_long_lived_cache``). Anthropic's
+        # tools array supports cache_control on the last tool to cache the
+        # entire schema cross-session.
         cache_control = t.get("cache_control")
         if isinstance(cache_control, dict):
             anthropic_tool["cache_control"] = dict(cache_control)

agent/async_utils.py

@@ -1,68 +0,0 @@
-"""Async/sync bridging helpers.
-
-The codebase has ~30 sites that schedule a coroutine onto an event loop from a
-worker thread via :func:`asyncio.run_coroutine_threadsafe`.  That function can
-raise :class:`RuntimeError` (e.g. the loop was closed during a shutdown race),
-and when it does the coroutine object is never awaited and never closed —
-which triggers a ``"coroutine '<name>' was never awaited"`` RuntimeWarning and
-leaks the coroutine's frame until GC.
-
-:func:`safe_schedule_threadsafe` wraps the call, closes the coroutine on
-scheduling failure, and returns ``None`` (instead of a half-formed future) so
-callers can branch cleanly:
-
-    fut = safe_schedule_threadsafe(coro, loop)
-    if fut is None:
-        return  # or fallback behavior
-    fut.result(timeout=5)
-
-The helper deliberately does NOT also handle ``future.result()`` failures —
-that is a separate concern.  Once the loop has accepted the coroutine, its
-lifecycle belongs to the loop, not the scheduling thread.
-"""
-from __future__ import annotations
-
-import asyncio
-import logging
-from concurrent.futures import Future
-from typing import Any, Coroutine, Optional
-
-
-_DEFAULT_LOGGER = logging.getLogger(__name__)
-
-
-def safe_schedule_threadsafe(
-    coro: Coroutine[Any, Any, Any],
-    loop: Optional[asyncio.AbstractEventLoop],
-    *,
-    logger: Optional[logging.Logger] = None,
-    log_message: str = "Failed to schedule coroutine on loop",
-    log_level: int = logging.DEBUG,
-) -> Optional[Future]:
-    """Schedule ``coro`` on ``loop`` from a sync context, leak-safe.
-
-    Returns the :class:`concurrent.futures.Future` on success, or ``None`` if
-    the loop is missing or :func:`asyncio.run_coroutine_threadsafe` raised
-    (e.g. the loop was closed during a shutdown race).  In all failure paths
-    the coroutine is :meth:`close`-d so it does not trigger
-    ``"coroutine was never awaited"`` warnings or leak its frame.
-
-    Callers retain full control over what to do with the returned future
-    (call ``.result(timeout=...)``, attach ``add_done_callback``, ignore it
-    fire-and-forget, etc.).
-    """
-    log = logger if logger is not None else _DEFAULT_LOGGER
-
-    if loop is None:
-        if asyncio.iscoroutine(coro):
-            coro.close()
-        log.log(log_level, "%s: loop is None", log_message)
-        return None
-
-    try:
-        return asyncio.run_coroutine_threadsafe(coro, loop)
-    except Exception as exc:
-        if asyncio.iscoroutine(coro):
-            coro.close()
-        log.log(log_level, "%s: %s", log_message, exc)
-        return None

agent/auxiliary_client.py

@@ -369,21 +369,6 @@ def build_or_headers(or_config: dict | None = None) -> dict:
 
     return headers
 
-
-# NVIDIA NIM cloud billing attribution.  Keep this host-gated because the
-# nvidia provider also supports local/on-prem NIM endpoints via NVIDIA_BASE_URL.
-_NVIDIA_NIM_CLOUD_HEADERS = {
-    "X-BILLING-INVOKE-ORIGIN": "HermesAgent",
-}
-
-
-def build_nvidia_nim_headers(base_url: str | None) -> dict:
-    """Return NVIDIA NIM cloud attribution headers for build.nvidia.com traffic."""
-    if base_url_host_matches(str(base_url or ""), "integrate.api.nvidia.com"):
-        return dict(_NVIDIA_NIM_CLOUD_HEADERS)
-    return {}
-
-
 # Vercel AI Gateway app attribution headers. HTTP-Referer maps to
 # referrerUrl and X-Title maps to appName in the gateway's analytics.
 from hermes_cli import __version__ as _HERMES_VERSION
@@ -397,28 +382,7 @@ _AI_GATEWAY_HEADERS = {
 # Nous Portal extra_body for product attribution.
 # Callers should pass this as extra_body in chat.completions.create()
 # when the auxiliary client is backed by Nous Portal.
-#
-# The tags are computed from agent.portal_tags so the client= marker stays
-# in lockstep with hermes_cli.__version__ across every Portal call site
-# (main loop, aux, compression, web_extract). Do not inline a literal here;
-# see agent/portal_tags.py for the rationale.
-from agent.portal_tags import nous_portal_tags as _nous_portal_tags
-
-
-def _nous_extra_body() -> dict:
-    """Return a fresh Nous Portal ``extra_body`` dict.
-
-    Computed at call time so a hot-reloaded ``hermes_cli.__version__`` is
-    reflected without restarting long-running processes.
-    """
-    return {"tags": _nous_portal_tags()}
-
-
-# Backwards-compatible module attribute. Some callers (tests, third-party
-# plugins) read ``NOUS_EXTRA_BODY`` directly; keep it as a snapshot of the
-# current tags. Callers that need the freshest value should call
-# ``_nous_extra_body()`` or import ``nous_portal_tags`` directly.
-NOUS_EXTRA_BODY = _nous_extra_body()
+NOUS_EXTRA_BODY = {"tags": ["product=hermes-agent", "client=aux"]}
 
 # Set at resolve time — True if the auxiliary client points to Nous Portal
 auxiliary_is_nous: bool = False
@@ -1269,58 +1233,6 @@ def _resolve_nous_runtime_api(*, force_refresh: bool = False) -> Optional[tuple[
     return api_key, base_url
 
 
-def _resolve_xai_oauth_for_aux() -> Optional[Tuple[str, str]]:
-    """Resolve a fresh xAI OAuth (api_key, base_url) for auxiliary clients.
-
-    Prefer the credential pool, matching the main runtime/provider status
-    path.  Some xAI OAuth logins live only as pool entries; falling straight
-    to the singleton auth-store resolver would make auxiliary tasks such as
-    compression report "no provider configured" even though ``hermes auth
-    status`` shows xAI OAuth as logged in.
-
-    Falls back to ``hermes_cli.auth``'s singleton runtime resolver for older
-    auth-store-only logins. Returns ``None`` if the user is not authenticated
-    with xAI Grok OAuth.
-    """
-    try:
-        from hermes_cli.auth import DEFAULT_XAI_OAUTH_BASE_URL
-
-        pool = load_pool("xai-oauth")
-        if pool and pool.has_credentials():
-            entry = pool.select()
-            if entry is not None:
-                api_key = str(
-                    getattr(entry, "runtime_api_key", None)
-                    or getattr(entry, "access_token", "")
-                    or ""
-                ).strip()
-                base_url = str(
-                    os.getenv("HERMES_XAI_BASE_URL", "").strip().rstrip("/")
-                    or os.getenv("XAI_BASE_URL", "").strip().rstrip("/")
-                    or getattr(entry, "runtime_base_url", None)
-                    or getattr(entry, "base_url", None)
-                    or DEFAULT_XAI_OAUTH_BASE_URL
-                ).strip().rstrip("/")
-                if api_key and base_url:
-                    return api_key, base_url
-    except Exception as exc:
-        logger.debug("Auxiliary xAI OAuth pool credential resolution failed: %s", exc)
-
-    try:
-        from hermes_cli.auth import resolve_xai_oauth_runtime_credentials
-
-        creds = resolve_xai_oauth_runtime_credentials()
-    except Exception as exc:
-        logger.debug("Auxiliary xAI OAuth runtime credential resolution failed: %s", exc)
-        return None
-
-    api_key = str(creds.get("api_key") or "").strip()
-    base_url = str(creds.get("base_url") or "").strip().rstrip("/")
-    if not api_key or not base_url:
-        return None
-    return api_key, base_url
-
-
 def _read_codex_access_token() -> Optional[str]:
     """Read a valid, non-expired Codex OAuth access token from Hermes auth store.
 
@@ -1415,8 +1327,6 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
                 from hermes_cli.models import copilot_default_headers
 
                 extra["default_headers"] = copilot_default_headers()
-            elif base_url_host_matches(base_url, "integrate.api.nvidia.com"):
-                extra["default_headers"] = build_nvidia_nim_headers(base_url)
             else:
                 try:
                     from providers import get_provider_profile as _gpf_aux
@@ -1452,8 +1362,6 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
             from hermes_cli.models import copilot_default_headers
 
             extra["default_headers"] = copilot_default_headers()
-        elif base_url_host_matches(base_url, "integrate.api.nvidia.com"):
-            extra["default_headers"] = build_nvidia_nim_headers(base_url)
         else:
             try:
                 from providers import get_provider_profile as _gpf_aux2
@@ -1478,7 +1386,6 @@ def _try_openrouter(explicit_api_key: str = None) -> Tuple[Optional[OpenAI], Opt
     if pool_present:
         or_key = explicit_api_key or _pool_runtime_api_key(entry)
         if not or_key:
-            _mark_provider_unhealthy("openrouter", ttl=60)
             return None, None
         base_url = _pool_runtime_base_url(entry, OPENROUTER_BASE_URL) or OPENROUTER_BASE_URL
         logger.debug("Auxiliary client: OpenRouter via pool")
@@ -1487,7 +1394,6 @@ def _try_openrouter(explicit_api_key: str = None) -> Tuple[Optional[OpenAI], Opt
 
     or_key = explicit_api_key or os.getenv("OPENROUTER_API_KEY")
     if not or_key:
-        _mark_provider_unhealthy("openrouter", ttl=60)
         return None, None
     logger.debug("Auxiliary client: OpenRouter")
     return OpenAI(api_key=or_key, base_url=OPENROUTER_BASE_URL,
@@ -1519,7 +1425,6 @@ def _try_nous(vision: bool = False) -> Tuple[Optional[OpenAI], Optional[str]]:
                 "Auxiliary: skipping Nous Portal (rate-limited, resets in %.0fs)",
                 _remaining,
             )
-            _mark_provider_unhealthy("nous", ttl=_remaining)
             return None, None
     except Exception:
         pass
@@ -1527,21 +1432,7 @@ def _try_nous(vision: bool = False) -> Tuple[Optional[OpenAI], Optional[str]]:
     nous = _read_nous_auth()
     runtime = _resolve_nous_runtime_api(force_refresh=False)
     if runtime is None and not nous:
-        logger.warning(
-            "Auxiliary Nous client unavailable: no Nous authentication found "
-            "(run: hermes auth)."
-        )
-        _mark_provider_unhealthy("nous", ttl=60)
         return None, None
-    if runtime is None and nous:
-        # Runtime credential mint failed but stored Nous auth is still present.
-        # Falls back to the raw stored token below; surface a debug line so
-        # operators investigating expired/invalid sessions have a breadcrumb,
-        # without blocking the fallback path the rest of this function relies on.
-        logger.debug(
-            "Auxiliary Nous: runtime credential mint failed; falling back to "
-            "stored auth.json token."
-        )
     global auxiliary_is_nous
     auxiliary_is_nous = True
     logger.debug("Auxiliary client: Nous Portal")
@@ -1815,32 +1706,6 @@ def _try_custom_endpoint() -> Tuple[Optional[Any], Optional[str]]:
     return _fallback_client, model
 
 
-def _build_xai_oauth_aux_client(model: str) -> Tuple[Optional[Any], Optional[str]]:
-    """Build a CodexAuxiliaryClient for an xAI Grok OAuth-authenticated session.
-
-    xAI's ``/v1/responses`` endpoint speaks the OpenAI Responses API, so we
-    wrap a plain ``OpenAI`` client in ``CodexAuxiliaryClient`` to translate
-    ``chat.completions.create()`` calls into ``responses.stream()`` requests.
-
-    The caller must pass an explicit model — pinning a default for Grok
-    would silently rot when xAI's allowlist drifts.  Returns ``(None, None)``
-    when the user has not authenticated with xAI Grok OAuth.
-    """
-    if not model:
-        logger.warning(
-            "Auxiliary client: xai-oauth requested without a model; "
-            "pass model explicitly (auxiliary.<task>.model in config.yaml)."
-        )
-        return None, None
-    resolved = _resolve_xai_oauth_for_aux()
-    if resolved is None:
-        return None, None
-    api_key, base_url = resolved
-    logger.debug("Auxiliary client: xAI OAuth (%s via Responses API)", model)
-    real_client = OpenAI(api_key=api_key, base_url=base_url)
-    return CodexAuxiliaryClient(real_client, model), model
-
-
 def _build_codex_client(model: str) -> Tuple[Optional[Any], Optional[str]]:
     """Build a CodexAuxiliaryClient for an explicitly-requested model.
 
@@ -2737,8 +2602,6 @@ def _to_async_client(sync_client, model: str, is_vision: bool = False):
         )
     elif base_url_host_matches(sync_base_url, "api.kimi.com"):
         async_kwargs["default_headers"] = {"User-Agent": "claude-code/0.1.0"}
-    elif base_url_host_matches(sync_base_url, "integrate.api.nvidia.com"):
-        async_kwargs["default_headers"] = build_nvidia_nim_headers(sync_base_url)
     else:
         # Fall back to profile.default_headers for providers that declare
         # client-level headers on their ProviderProfile (e.g. attribution
@@ -2950,26 +2813,6 @@ def resolve_provider_client(
         return (_to_async_client(client, final_model, is_vision=is_vision) if async_mode
                 else (client, final_model))
 
-    # ── xAI Grok OAuth (loopback PKCE → Responses API) ───────────────
-    # Without this branch, an xai-oauth main provider falls through to the
-    # generic ``oauth_external`` arm below and returns ``(None, None)``,
-    # silently re-routing every auxiliary task (compression, web extract,
-    # session search, curator, etc.) to whatever Step-2 fallback the user
-    # has configured.  Users on xAI Grok OAuth would then see surprise
-    # OpenRouter / Nous bills for side tasks they thought were running on
-    # their xAI subscription.
-    if provider == "xai-oauth":
-        client, default = _build_xai_oauth_aux_client(model)
-        if client is None:
-            logger.warning(
-                "resolve_provider_client: xai-oauth requested but no xAI "
-                "OAuth token found (run: hermes model -> xAI Grok OAuth — SuperGrok Subscription)"
-            )
-            return None, None
-        final_model = _normalize_resolved_model(model or default, provider)
-        return (_to_async_client(client, final_model, is_vision=is_vision) if async_mode
-                else (client, final_model))
-
     # ── Custom endpoint (OPENAI_BASE_URL + OPENAI_API_KEY) ───────────
     if provider == "custom":
         if explicit_base_url:
@@ -3000,8 +2843,6 @@ def resolve_provider_client(
                 extra["default_headers"] = copilot_request_headers(
                     is_agent_turn=True, is_vision=is_vision
                 )
-            elif base_url_host_matches(custom_base, "integrate.api.nvidia.com"):
-                extra["default_headers"] = build_nvidia_nim_headers(custom_base)
             else:
                 # Fall back to profile.default_headers for providers that
                 # declare client-level attribution headers on their profile.
@@ -3200,8 +3041,6 @@ def resolve_provider_client(
             headers.update(copilot_request_headers(
                 is_agent_turn=True, is_vision=is_vision
             ))
-        elif base_url_host_matches(base_url, "integrate.api.nvidia.com"):
-            headers.update(build_nvidia_nim_headers(base_url))
         else:
             # Fall back to profile.default_headers for providers that declare
             # client-level attribution headers on their profile (e.g. GMI
@@ -3324,8 +3163,6 @@ def resolve_provider_client(
             return resolve_provider_client("nous", model, async_mode)
         if provider == "openai-codex":
             return resolve_provider_client("openai-codex", model, async_mode)
-        if provider == "xai-oauth":
-            return resolve_provider_client("xai-oauth", model, async_mode)
         # Other OAuth providers not directly supported
         logger.warning("resolve_provider_client: OAuth provider %s not "
                        "directly supported, try 'auto'", provider)
@@ -3600,7 +3437,7 @@ def get_auxiliary_extra_body() -> dict:
     Includes Nous Portal product tags when the auxiliary client is backed
     by Nous Portal. Returns empty dict otherwise.
     """
-    return _nous_extra_body() if auxiliary_is_nous else {}
+    return dict(NOUS_EXTRA_BODY) if auxiliary_is_nous else {}
 
 
 def auxiliary_max_tokens_param(value: int) -> dict:
@@ -3991,7 +3828,7 @@ def _resolve_task_provider_model(
             # (e.g. OPENROUTER_API_KEY) instead of locking into "custom".
             return cfg_provider, resolved_model, cfg_base_url, None, resolved_api_mode
         if cfg_provider and cfg_provider != "auto":
-            return cfg_provider, resolved_model, cfg_base_url, cfg_api_key, resolved_api_mode
+            return cfg_provider, resolved_model, None, None, resolved_api_mode
 
         return "auto", resolved_model, None, None, resolved_api_mode
 
@@ -4189,7 +4026,7 @@ def _build_call_kwargs(
     # Provider-specific extra_body
     merged_extra = dict(extra_body or {})
     if provider == "nous" or auxiliary_is_nous:
-        merged_extra.setdefault("tags", []).extend(_nous_portal_tags())
+        merged_extra.setdefault("tags", []).extend(NOUS_EXTRA_BODY["tags"])
     if merged_extra:
         kwargs["extra_body"] = merged_extra
 
@@ -4574,7 +4411,7 @@ def extract_content_or_reasoning(response) -> str:
       1. ``message.content`` — strip inline think/reasoning blocks, check for
          remaining non-whitespace text.
       2. ``message.reasoning`` / ``message.reasoning_content`` — direct
-         structured reasoning fields (DeepSeek, Moonshot, NovitaAI, etc.).
+         structured reasoning fields (DeepSeek, Moonshot, Novita, etc.).
       3. ``message.reasoning_details`` — OpenRouter unified array format.
 
     Returns the best available text, or ``""`` if nothing found.

agent/codex_responses_adapter.py

@@ -244,21 +244,8 @@ def _normalize_responses_message_status(value: Any, *, default: str = "completed
     return default
 
 
-def _chat_messages_to_responses_input(
-    messages: List[Dict[str, Any]],
-    *,
-    is_xai_responses: bool = False,
-) -> List[Dict[str, Any]]:
-    """Convert internal chat-style messages to Responses input items.
-
-    ``is_xai_responses=True`` strips ``encrypted_content`` from replayed
-    reasoning items.  xAI's OAuth/SuperGrok ``/v1/responses`` surface
-    rejects encrypted reasoning blobs minted by prior turns: the request
-    streams an ``error`` SSE frame before ``response.created`` and the
-    OpenAI SDK collapses it into a generic stream-ordering error.  Native
-    Codex (chatgpt.com backend-api) DOES accept replayed encrypted_content
-    — keep the default off.
-    """
+def _chat_messages_to_responses_input(messages: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
+    """Convert internal chat-style messages to Responses input items."""
     items: List[Dict[str, Any]] = []
     seen_item_ids: set = set()
 
@@ -284,17 +271,9 @@ def _chat_messages_to_responses_input(
             if role == "assistant":
                 # Replay encrypted reasoning items from previous turns
                 # so the API can maintain coherent reasoning chains.
-                #
-                # xAI OAuth (SuperGrok/Premium) rejects replayed
-                # ``encrypted_content`` reasoning items minted by prior
-                # turns — see _chat_messages_to_responses_input docstring.
-                # When ``is_xai_responses`` is set we drop the replay
-                # entirely; Grok still reasons on each turn server-side,
-                # we just don't try to thread the prior turn's encrypted
-                # blob back in.
                 codex_reasoning = msg.get("codex_reasoning_items")
                 has_codex_reasoning = False
-                if isinstance(codex_reasoning, list) and not is_xai_responses:
+                if isinstance(codex_reasoning, list):
                     for ri in codex_reasoning:
                         if isinstance(ri, dict) and ri.get("encrypted_content"):
                             item_id = ri.get("id")
@@ -747,7 +726,7 @@ def _preflight_codex_api_kwargs(
         "model", "instructions", "input", "tools", "store",
         "reasoning", "include", "max_output_tokens", "temperature",
         "tool_choice", "parallel_tool_calls", "prompt_cache_key", "service_tier",
-        "extra_headers", "extra_body",
+        "extra_headers",
     }
     normalized: Dict[str, Any] = {
         "model": model,
@@ -797,19 +776,6 @@ def _preflight_codex_api_kwargs(
         if normalized_headers:
             normalized["extra_headers"] = normalized_headers
 
-    extra_body = api_kwargs.get("extra_body")
-    if extra_body is not None:
-        if not isinstance(extra_body, dict):
-            raise ValueError("Codex Responses request 'extra_body' must be an object.")
-        # Pass extra_body through verbatim — used by xAI Responses to
-        # carry `prompt_cache_key` as a body-level field (the documented
-        # cache-routing surface on /v1/responses). The openai SDK
-        # serializes extra_body into the JSON body without per-field
-        # type checks, so it survives Responses.stream() kwarg-signature
-        # changes that would otherwise raise TypeError before the wire.
-        if extra_body:
-            normalized["extra_body"] = dict(extra_body)
-
     if allow_stream:
         stream = api_kwargs.get("stream")
         if stream is not None and stream is not True:

agent/context_compressor.py

@@ -1185,26 +1185,6 @@ The user has requested that this compaction PRIORITISE preserving all informatio
             idx += 1
         return idx
 
-    def _protect_head_size(self, messages: List[Dict[str, Any]]) -> int:
-        """Total count of head messages to protect.
-
-        ``protect_first_n`` is defined as *additional* messages protected
-        beyond the system prompt.  The system prompt (if present at index 0)
-        is always implicitly protected — it's load-bearing context that
-        must never be summarised away.  This keeps semantics stable across
-        call paths where the system prompt may or may not be included in
-        the ``messages`` list (e.g. the gateway ``/compress`` handler
-        strips it before calling compress()).
-
-        Examples:
-          protect_first_n=0 → system prompt only (or nothing if no system msg)
-          protect_first_n=3 → system + first 3 non-system messages
-        """
-        head = 0
-        if messages and messages[0].get("role") == "system":
-            head = 1
-        return head + self.protect_first_n
-
     def _align_boundary_backward(self, messages: List[Dict[str, Any]], idx: int) -> int:
         """Pull a compress-end boundary backward to avoid splitting a
         tool_call / result group.
@@ -1363,7 +1343,7 @@ The user has requested that this compaction PRIORITISE preserving all informatio
         skip the LLM call when the transcript is still entirely inside
         the protected head/tail.
         """
-        compress_start = self._align_boundary_forward(messages, self._protect_head_size(messages))
+        compress_start = self._align_boundary_forward(messages, self.protect_first_n)
         compress_end = self._find_tail_cut_by_tokens(messages, compress_start)
         return compress_start < compress_end
 
@@ -1399,7 +1379,7 @@ The user has requested that this compaction PRIORITISE preserving all informatio
         self._last_aux_model_failure_model = None
         n_messages = len(messages)
         # Only need head + 3 tail messages minimum (token budget decides the real tail size)
-        _min_for_compress = self._protect_head_size(messages) + 3 + 1
+        _min_for_compress = self.protect_first_n + 3 + 1
         if n_messages <= _min_for_compress:
             if not self.quiet_mode:
                 logger.warning(
@@ -1419,7 +1399,7 @@ The user has requested that this compaction PRIORITISE preserving all informatio
             logger.info("Pre-compression: pruned %d old tool result(s)", pruned_count)
 
         # Phase 2: Determine boundaries
-        compress_start = self._protect_head_size(messages)
+        compress_start = self.protect_first_n
         compress_start = self._align_boundary_forward(messages, compress_start)
 
         # Use token-budget tail protection instead of fixed message count
@@ -1429,23 +1409,15 @@ The user has requested that this compaction PRIORITISE preserving all informatio
             return messages
 
         turns_to_summarize = messages[compress_start:compress_end]
-        # A persisted handoff summary can sit in the protected head after a
-        # resume (commonly immediately after the system prompt). Search from
-        # the first non-system message through the compression window so we can
-        # rehydrate iterative-summary state without serializing that handoff as
-        # a new turn. Protected messages after the handoff remain live context,
-        # so only summarize messages that are both after the handoff and inside
-        # the current compression window.
-        summary_search_start = 1 if messages and messages[0].get("role") == "system" else 0
         summary_idx, summary_body = self._find_latest_context_summary(
             messages,
-            summary_search_start,
+            compress_start,
             compress_end,
         )
         if summary_idx is not None:
             if summary_body and not self._previous_summary:
                 self._previous_summary = summary_body
-            turns_to_summarize = messages[max(compress_start, summary_idx + 1):compress_end]
+            turns_to_summarize = messages[summary_idx + 1:compress_end]
 
         if not self.quiet_mode:
             logger.info(

agent/context_engine.py

@@ -55,11 +55,6 @@ class ContextEngine(ABC):
     # These control the preflight compression check.  Subclasses may
     # override via __init__ or property; defaults are sensible for most
     # engines.
-    #
-    # protect_first_n semantics (since PR #13754): count of non-system head
-    # messages always preserved verbatim, IN ADDITION to the system prompt
-    # which is always implicitly protected.  Default 3 keeps the
-    # historical "system + first 3 non-system messages" head shape.
 
     threshold_percent: float = 0.75
     protect_first_n: int = 3

agent/copilot_acp_client.py

@@ -30,28 +30,6 @@ _DEFAULT_TIMEOUT_SECONDS = 900.0
 _TOOL_CALL_BLOCK_RE = re.compile(r"<tool_call>\s*(\{.*?\})\s*</tool_call>", re.DOTALL)
 _TOOL_CALL_JSON_RE = re.compile(r"\{\s*\"id\"\s*:\s*\"[^\"]+\"\s*,\s*\"type\"\s*:\s*\"function\"\s*,\s*\"function\"\s*:\s*\{.*?\}\s*\}", re.DOTALL)
 
-# Stderr fingerprint of the deprecated `gh copilot` CLI extension
-# (https://github.blog/changelog/2025-09-25-upcoming-deprecation-of-gh-copilot-cli-extension).
-# We require BOTH the literal product name ("gh-copilot") AND a deprecation
-# marker, so generic stderr from the NEW `@github/copilot` CLI — whose repo
-# is github.com/github/copilot-cli and which legitimately mentions "copilot-cli"
-# in its own banners and error messages — doesn't get misclassified as the
-# deprecated extension.
-_DEPRECATION_REQUIRED = ("gh-copilot",)
-_DEPRECATION_MARKERS = (
-    "has been deprecated",
-    "no commands will be executed",
-)
-
-
-def _is_gh_copilot_deprecation_message(stderr_text: str) -> bool:
-    """True iff stderr looks like the deprecated gh-copilot extension's banner."""
-
-    lower = stderr_text.lower()
-    if not any(req in lower for req in _DEPRECATION_REQUIRED):
-        return False
-    return any(marker in lower for marker in _DEPRECATION_MARKERS)
-
 
 def _resolve_command() -> str:
     return (
@@ -528,21 +506,6 @@ class CopilotACPClient:
 
             stderr_text = "\n".join(stderr_tail).strip()
             if proc.poll() is not None and stderr_text:
-                if _is_gh_copilot_deprecation_message(stderr_text):
-                    raise RuntimeError(
-                        "Hermes ACP mode requires the NEW GitHub Copilot CLI "
-                        "(github.com/github/copilot-cli), but the binary it just "
-                        "spawned is the deprecated `gh copilot` extension.\n\n"
-                        "Install the new CLI:\n"
-                        "  npm install -g @github/copilot\n"
-                        "  # then verify with: copilot --help\n\n"
-                        "If `copilot` already resolves to the new CLI but you still see this,\n"
-                        "point Hermes at it explicitly:\n"
-                        "  export HERMES_COPILOT_ACP_COMMAND=/path/to/new/copilot\n\n"
-                        "Alternative: use the `copilot` provider (no ACP, hits the Copilot API\n"
-                        "directly with a Copilot subscription token) via `hermes setup`.\n\n"
-                        f"Original error:\n{stderr_text}"
-                    )
                 raise RuntimeError(f"Copilot ACP process exited early: {stderr_text}")
             raise TimeoutError(f"Timed out waiting for Copilot ACP response to {method}.")
 

agent/credential_pool.py

@@ -29,7 +29,6 @@ from hermes_cli.auth import (
     _resolve_zai_base_url,
     _save_auth_store,
     _save_provider_state,
-    _store_provider_state,
     read_credential_pool,
     write_credential_pool,
 )
@@ -540,64 +539,6 @@ class CredentialPool:
             logger.debug("Failed to sync Codex entry from auth.json: %s", exc)
         return entry
 
-    def _sync_xai_oauth_entry_from_auth_store(self, entry: PooledCredential) -> PooledCredential:
-        """Sync an xAI OAuth pool entry from auth.json if tokens differ.
-
-        xAI OAuth refresh tokens are single-use.  When another Hermes process
-        (or another profile sharing the same auth.json) refreshes the token,
-        it writes the new pair to ``providers["xai-oauth"]["tokens"]`` under
-        ``_auth_store_lock``.  Without this resync, our in-memory pool entry
-        keeps the consumed refresh_token and the next ``_refresh_entry`` call
-        would replay it and get a ``refresh_token_reused``-style 4xx.
-
-        Only applies to entries seeded from the singleton (``loopback_pkce``);
-        manually added entries (``manual:xai_pkce``) are independent
-        credentials with their own refresh-token lifecycle.
-        """
-        if self.provider != "xai-oauth" or entry.source != "loopback_pkce":
-            return entry
-        try:
-            with _auth_store_lock():
-                auth_store = _load_auth_store()
-                state = _load_provider_state(auth_store, "xai-oauth")
-            if not isinstance(state, dict):
-                return entry
-            tokens = state.get("tokens")
-            if not isinstance(tokens, dict):
-                return entry
-            store_access = tokens.get("access_token", "")
-            store_refresh = tokens.get("refresh_token", "")
-            entry_access = entry.access_token or ""
-            entry_refresh = entry.refresh_token or ""
-            if store_access and (
-                store_access != entry_access
-                or (store_refresh and store_refresh != entry_refresh)
-            ):
-                logger.debug(
-                    "Pool entry %s: syncing xAI OAuth tokens from auth.json "
-                    "(refreshed by another process)",
-                    entry.id,
-                )
-                field_updates: Dict[str, Any] = {
-                    "access_token": store_access,
-                    "refresh_token": store_refresh or entry.refresh_token,
-                    "last_status": None,
-                    "last_status_at": None,
-                    "last_error_code": None,
-                    "last_error_reason": None,
-                    "last_error_message": None,
-                    "last_error_reset_at": None,
-                }
-                if state.get("last_refresh"):
-                    field_updates["last_refresh"] = state["last_refresh"]
-                updated = replace(entry, **field_updates)
-                self._replace_entry(entry, updated)
-                self._persist()
-                return updated
-        except Exception as exc:
-            logger.debug("Failed to sync xAI OAuth entry from auth.json: %s", exc)
-        return entry
-
     def _sync_nous_entry_from_auth_store(self, entry: PooledCredential) -> PooledCredential:
         """Sync a Nous pool entry from auth.json if tokens differ.
 
@@ -663,22 +604,9 @@ class CredentialPool:
         re-seeding a consumed single-use refresh token.
 
         Applies to any OAuth provider whose singleton lives in auth.json
-        (currently Nous, OpenAI Codex, and xAI Grok OAuth).
-
-        ``set_active=False`` on every write: a pool sync-back is a
-        token-rotation side effect, not the user choosing a provider.
-        Using ``_save_provider_state`` (which sets ``active_provider``)
-        here would mean every Nous/Codex/xAI refresh in a multi-provider
-        setup silently flips the ``active_provider`` flag — the next
-        ``hermes`` invocation that defaults to the active provider
-        (e.g. setup wizard, ``hermes auth status``) would land on
-        whatever provider happened to refresh last, not whatever the
-        user actually chose.
+        (currently Nous and OpenAI Codex).
         """
-        # Only sync entries that were seeded *from* a singleton.  Manually
-        # added pool entries (source="manual:*") are independent credentials
-        # and must not write back to the singleton.
-        if entry.source not in {"device_code", "loopback_pkce"}:
+        if entry.source != "device_code":
             return
         try:
             with _auth_store_lock():
@@ -704,7 +632,7 @@ class CredentialPool:
                             state[extra_key] = val
                     if entry.inference_base_url:
                         state["inference_base_url"] = entry.inference_base_url
-                    _store_provider_state(auth_store, "nous", state, set_active=False)
+                    _save_provider_state(auth_store, "nous", state)
 
                 elif self.provider == "openai-codex":
                     state = _load_provider_state(auth_store, "openai-codex")
@@ -718,21 +646,7 @@ class CredentialPool:
                         tokens["refresh_token"] = entry.refresh_token
                     if entry.last_refresh:
                         state["last_refresh"] = entry.last_refresh
-                    _store_provider_state(auth_store, "openai-codex", state, set_active=False)
-
-                elif self.provider == "xai-oauth":
-                    state = _load_provider_state(auth_store, "xai-oauth")
-                    if not isinstance(state, dict):
-                        return
-                    tokens = state.get("tokens")
-                    if not isinstance(tokens, dict):
-                        return
-                    tokens["access_token"] = entry.access_token
-                    if entry.refresh_token:
-                        tokens["refresh_token"] = entry.refresh_token
-                    if entry.last_refresh:
-                        state["last_refresh"] = entry.last_refresh
-                    _store_provider_state(auth_store, "xai-oauth", state, set_active=False)
+                    _save_provider_state(auth_store, "openai-codex", state)
 
                 else:
                     return
@@ -785,25 +699,6 @@ class CredentialPool:
                     refresh_token=refreshed["refresh_token"],
                     last_refresh=refreshed.get("last_refresh"),
                 )
-            elif self.provider == "xai-oauth":
-                # Adopt fresher tokens from auth.json before spending the
-                # refresh_token — single-use tokens consumed by another
-                # process (or another profile sharing the singleton) would
-                # otherwise trigger ``refresh_token_reused`` on the next
-                # POST.  Only meaningful for singleton-seeded entries.
-                synced = self._sync_xai_oauth_entry_from_auth_store(entry)
-                if synced is not entry:
-                    entry = synced
-                refreshed = auth_mod.refresh_xai_oauth_pure(
-                    entry.access_token,
-                    entry.refresh_token,
-                )
-                updated = replace(
-                    entry,
-                    access_token=refreshed["access_token"],
-                    refresh_token=refreshed["refresh_token"],
-                    last_refresh=refreshed.get("last_refresh"),
-                )
             elif self.provider == "nous":
                 synced = self._sync_nous_entry_from_auth_store(entry)
                 if synced is not entry:
@@ -882,30 +777,6 @@ class CredentialPool:
                     # Credentials file had a valid (non-expired) token — use it directly
                     logger.debug("Credentials file has valid token, using without refresh")
                     return synced
-            # For xai-oauth: same race as nous — another process may have
-            # consumed the refresh token between our proactive sync and the
-            # HTTP call.  Re-check auth.json and adopt the fresh tokens if
-            # they have rotated since.  Only meaningful for singleton-seeded
-            # (loopback_pkce) entries; manual entries don't share state with
-            # the singleton.
-            if self.provider == "xai-oauth":
-                synced = self._sync_xai_oauth_entry_from_auth_store(entry)
-                if synced.refresh_token != entry.refresh_token:
-                    logger.debug(
-                        "xAI OAuth refresh failed but auth.json has newer tokens — adopting"
-                    )
-                    updated = replace(
-                        synced,
-                        last_status=STATUS_OK,
-                        last_status_at=None,
-                        last_error_code=None,
-                        last_error_reason=None,
-                        last_error_message=None,
-                        last_error_reset_at=None,
-                    )
-                    self._replace_entry(synced, updated)
-                    self._persist()
-                    return updated
             # For nous: another process may have consumed the refresh token
             # between our proactive sync and the HTTP call.  Re-sync from
             # auth.json and adopt the fresh tokens if available.
@@ -958,11 +829,6 @@ class CredentialPool:
                 entry.access_token,
                 CODEX_ACCESS_TOKEN_REFRESH_SKEW_SECONDS,
             )
-        if self.provider == "xai-oauth":
-            return auth_mod._xai_access_token_is_expiring(
-                entry.access_token,
-                auth_mod.XAI_ACCESS_TOKEN_REFRESH_SKEW_SECONDS,
-            )
         if self.provider == "nous":
             # Nous refresh/mint can require network access and should happen when
             # runtime credentials are actually resolved, not merely when the pool
@@ -1017,17 +883,6 @@ class CredentialPool:
                 if synced is not entry:
                     entry = synced
                     cleared_any = True
-            # For xai-oauth singleton-seeded entries, identical pattern:
-            # an entry frozen as exhausted may simply be holding stale
-            # tokens that another process (or a fresh `hermes model` ->
-            # xAI Grok OAuth login) has since rotated in auth.json.
-            if (self.provider == "xai-oauth"
-                    and entry.source == "loopback_pkce"
-                    and entry.last_status == STATUS_EXHAUSTED):
-                synced = self._sync_xai_oauth_entry_from_auth_store(entry)
-                if synced is not entry:
-                    entry = synced
-                    cleared_any = True
             if entry.last_status == STATUS_EXHAUSTED:
                 exhausted_until = _exhausted_until(entry)
                 if exhausted_until is not None and now < exhausted_until:
@@ -1539,37 +1394,6 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
                 },
             )
 
-    elif provider == "xai-oauth":
-        # When the user logs in via ``hermes model`` -> xAI Grok OAuth,
-        # tokens are written to the auth.json singleton
-        # (``providers["xai-oauth"]``).  Surface them in the pool too so
-        # ``hermes auth list`` reflects the logged-in state and so the pool
-        # is the single source of truth for refresh during runtime resolution.
-        if _is_suppressed(provider, "loopback_pkce"):
-            return changed, active_sources
-
-        state = _load_provider_state(auth_store, "xai-oauth")
-        tokens = state.get("tokens") if isinstance(state, dict) else None
-        if isinstance(tokens, dict) and tokens.get("access_token"):
-            active_sources.add("loopback_pkce")
-            from hermes_cli.auth import DEFAULT_XAI_OAUTH_BASE_URL
-
-            base_url = DEFAULT_XAI_OAUTH_BASE_URL
-            changed |= _upsert_entry(
-                entries,
-                provider,
-                "loopback_pkce",
-                {
-                    "source": "loopback_pkce",
-                    "auth_type": AUTH_TYPE_OAUTH,
-                    "access_token": tokens.get("access_token", ""),
-                    "refresh_token": tokens.get("refresh_token"),
-                    "base_url": base_url,
-                    "last_refresh": state.get("last_refresh"),
-                    "label": label_from_token(tokens.get("access_token", ""), "loopback_pkce"),
-                },
-            )
-
     return changed, active_sources
 
 

agent/credential_sources.py

@@ -265,31 +265,6 @@ def _remove_minimax_oauth(provider: str, removed) -> RemovalResult:
     return result
 
 
-def _remove_xai_oauth_loopback_pkce(provider: str, removed) -> RemovalResult:
-    """xAI OAuth tokens live in auth.json providers.xai-oauth — clear them.
-
-    Without this step, ``hermes auth remove xai-oauth <N>`` silently undoes
-    itself: the central dispatcher only removes the in-memory pool entry,
-    leaves ``providers.xai-oauth`` in auth.json intact, and on the next
-    ``load_pool("xai-oauth")`` call ``_seed_from_singletons`` re-seeds the
-    entry from the still-present singleton — credentials reappear with no
-    user feedback. Clearing the singleton in step with the suppression set
-    by the central dispatcher makes the removal stick.
-
-    Belt-and-braces against the manual entry path: ``hermes auth add
-    xai-oauth`` produces a ``manual:xai_pkce`` entry whose removal step
-    falls through to "unregistered → nothing to clean up" (correct —
-    manual entries are pool-only).
-    """
-    result = RemovalResult()
-    if _clear_auth_store_provider(provider):
-        result.cleaned.append(f"Cleared {provider} OAuth tokens from auth store")
-    result.hints.append(
-        "Run `hermes model` → xAI Grok OAuth (SuperGrok Subscription) to re-authenticate if needed."
-    )
-    return result
-
-
 def _remove_codex_device_code(provider: str, removed) -> RemovalResult:
     """Codex tokens live in TWO places: our auth store AND ~/.codex/auth.json.
 
@@ -422,11 +397,6 @@ def _register_all_sources() -> None:
         remove_fn=_remove_codex_device_code,
         description="auth.json providers.openai-codex + ~/.codex/auth.json",
     ))
-    register(RemovalStep(
-        provider="xai-oauth", source_id="loopback_pkce",
-        remove_fn=_remove_xai_oauth_loopback_pkce,
-        description="auth.json providers.xai-oauth",
-    ))
     register(RemovalStep(
         provider="qwen-oauth", source_id="qwen-cli",
         remove_fn=_remove_qwen_cli,

agent/display.py

@@ -14,7 +14,6 @@ from difflib import unified_diff
 from pathlib import Path
 
 from utils import safe_json_loads
-from agent.tool_result_classification import file_mutation_result_landed
 
 # ANSI escape codes for coloring tool failure indicators
 _RED = "\033[31m"
@@ -240,6 +239,21 @@ def build_tool_preview(tool_name: str, args: dict, max_len: int | None = None) -
             msg = msg[:17] + "..."
         return f"to {target}: \"{msg}\""
 
+    if tool_name.startswith("rl_"):
+        rl_previews = {
+            "rl_list_environments": "listing envs",
+            "rl_select_environment": args.get("name", ""),
+            "rl_get_current_config": "reading config",
+            "rl_edit_config": f"{args.get('field', '')}={args.get('value', '')}",
+            "rl_start_training": "starting",
+            "rl_check_status": args.get("run_id", "")[:16],
+            "rl_stop_training": f"stopping {args.get('run_id', '')[:16]}",
+            "rl_get_results": args.get("run_id", "")[:16],
+            "rl_list_runs": "listing runs",
+            "rl_test_inference": f"{args.get('num_steps', 3)} steps",
+        }
+        return rl_previews.get(tool_name)
+
     key = primary_args.get(tool_name)
     if not key:
         for fallback_key in ("query", "text", "command", "path", "name", "prompt", "code", "goal"):
@@ -796,8 +810,6 @@ def _detect_tool_failure(tool_name: str, result: str | None) -> tuple[bool, str]
     """
     if result is None:
         return False, ""
-    if file_mutation_result_landed(tool_name, result):
-        return False, ""
 
     if tool_name == "terminal":
         data = safe_json_loads(result)
@@ -966,6 +978,15 @@ def get_cute_tool_message(
         if action == "list":
             return _wrap(f"┊ ⏰ cron      listing  {dur}")
         return _wrap(f"┊ ⏰ cron      {action} {args.get('job_id', '')}  {dur}")
+    if tool_name.startswith("rl_"):
+        rl = {
+            "rl_list_environments": "list envs", "rl_select_environment": f"select {args.get('name', '')}",
+            "rl_get_current_config": "get config", "rl_edit_config": f"set {args.get('field', '?')}",
+            "rl_start_training": "start training", "rl_check_status": f"status {args.get('run_id', '?')[:12]}",
+            "rl_stop_training": f"stop {args.get('run_id', '?')[:12]}", "rl_get_results": f"results {args.get('run_id', '?')[:12]}",
+            "rl_list_runs": "list runs", "rl_test_inference": "test inference",
+        }
+        return _wrap(f"┊ 🧪 rl        {rl.get(tool_name, tool_name.replace('rl_', ''))}  {dur}")
     if tool_name == "execute_code":
         code = args.get("code", "")
         first_line = code.strip().split("\n")[0] if code.strip() else ""

agent/gemini_cloudcode_adapter.py

@@ -450,13 +450,7 @@ def _make_stream_chunk(
     finish_reason: Optional[str] = None,
     reasoning: str = "",
 ) -> _GeminiStreamChunk:
-    delta_kwargs: Dict[str, Any] = {
-        "role": "assistant",
-        "content": None,
-        "tool_calls": None,
-        "reasoning": None,
-        "reasoning_content": None,
-    }
+    delta_kwargs: Dict[str, Any] = {"role": "assistant"}
     if content:
         delta_kwargs["content"] = content
     if tool_call_delta is not None:

agent/image_gen_registry.py

@@ -77,17 +77,6 @@ def get_active_provider() -> Optional[ImageGenProvider]:
 
     Reads ``image_gen.provider`` from config.yaml; falls back per the
     module docstring.
-
-    **Availability semantics** (mirrors :mod:`agent.web_search_registry`):
-
-    - When ``image_gen.provider`` is explicitly set, the configured
-      provider is returned even if :meth:`ImageGenProvider.is_available`
-      reports False — the dispatcher surfaces a precise "X_API_KEY is not
-      set" error rather than silently switching backends.
-    - When ``image_gen.provider`` is unset, the fallback path (single-
-      provider shortcut and the FAL legacy preference) is filtered by
-      ``is_available()`` so we don't pick a provider the user has no
-      credentials for.
     """
     configured: Optional[str] = None
     try:
@@ -105,17 +94,6 @@ def get_active_provider() -> Optional[ImageGenProvider]:
     with _lock:
         snapshot = dict(_providers)
 
-    def _is_available_safe(p: ImageGenProvider) -> bool:
-        """Wrap ``is_available()`` so a buggy provider doesn't kill resolution."""
-        try:
-            return bool(p.is_available())
-        except Exception as exc:  # noqa: BLE001
-            logger.debug("image_gen provider %s.is_available() raised %s", p.name, exc)
-            return False
-
-    # 1. Explicit config wins — return regardless of is_available() so the
-    #    user gets a precise downstream error message rather than a silent
-    #    backend switch.
     if configured:
         provider = snapshot.get(configured)
         if provider is not None:
@@ -125,16 +103,13 @@ def get_active_provider() -> Optional[ImageGenProvider]:
             configured,
         )
 
-    # 2. Fallback: single registered provider — but only if it's actually
-    #    available (no credentials = don't surface it as "active").
-    available = [p for p in snapshot.values() if _is_available_safe(p)]
-    if len(available) == 1:
-        return available[0]
+    # Fallback: single-provider case
+    if len(snapshot) == 1:
+        return next(iter(snapshot.values()))
 
-    # 3. Fallback: prefer legacy FAL for backward compat, when available.
-    fal = snapshot.get("fal")
-    if fal is not None and _is_available_safe(fal):
-        return fal
+    # Fallback: prefer legacy FAL for backward compat
+    if "fal" in snapshot:
+        return snapshot["fal"]
 
     return None
 

agent/lsp/__init__.py

@@ -1,106 +0,0 @@
-"""Language Server Protocol (LSP) integration for Hermes Agent.
-
-Hermes runs full language servers (pyright, gopls, rust-analyzer,
-typescript-language-server, etc.) as subprocesses and pipes their
-``textDocument/publishDiagnostics`` output into the post-write lint
-delta filter used by ``write_file`` and ``patch``.
-
-LSP is **gated on git workspace detection** — if the agent's cwd is
-inside a git repository, LSP runs against that workspace; otherwise the
-file_operations layer falls back to its existing in-process syntax
-checks.  This keeps users on user-home cwd's (e.g. Telegram gateway
-chats) from spawning daemons they don't need.
-
-Public API:
-
-    from agent.lsp import get_service
-
-    svc = get_service()
-    if svc and svc.enabled_for(path):
-        await svc.touch_file(path)
-        diags = svc.diagnostics_for(path)
-
-The bulk of the wiring is internal — most callers only need the layer
-in :func:`tools.file_operations.FileOperations._check_lint_delta`,
-which is already wired (see that module).
-
-Architecture is documented in ``website/docs/user-guide/features/lsp.md``.
-"""
-from __future__ import annotations
-
-import atexit
-import logging
-import threading
-from typing import Optional
-
-from agent.lsp.manager import LSPService
-
-logger = logging.getLogger("agent.lsp")
-
-_service: Optional[LSPService] = None
-_atexit_registered = False
-_service_lock = threading.Lock()
-
-
-def get_service() -> Optional[LSPService]:
-    """Return the process-wide LSP service singleton, or None when disabled.
-
-    The service is created lazily on first call.  ``None`` is returned
-    when LSP is disabled in config, when no workspace can be detected,
-    or when the platform doesn't support subprocess-based LSP servers.
-
-    On first creation, registers an :mod:`atexit` handler that tears
-    down spawned language servers on Python exit so a long-running
-    CLI or gateway session doesn't leak pyright/gopls/etc. processes
-    when it terminates.
-    """
-    global _service, _atexit_registered
-    if _service is not None:
-        return _service if _service.is_active() else None
-    with _service_lock:
-        if _service is not None:
-            return _service if _service.is_active() else None
-        _service = LSPService.create_from_config()
-        if not _atexit_registered:
-            # ``atexit`` handlers run in LIFO order on normal Python
-            # exit and on SystemExit, but NOT on os._exit() or
-            # uncaught signals.  Language servers are stateless
-            # subprocesses — losing them on SIGKILL is fine; they'll
-            # be reaped by the kernel along with their parent.  We
-            # care about clean exits where Python flushes stdio
-            # before terminating; without this hook every
-            # ``hermes chat`` exit would leak pyright processes that
-            # outlive the parent for a few seconds while their
-            # stdout buffers drain.
-            atexit.register(_atexit_shutdown)
-            _atexit_registered = True
-    return _service if (_service is not None and _service.is_active()) else None
-
-
-def shutdown_service() -> None:
-    """Tear down the LSP service if one was started.
-
-    Safe to call multiple times; safe to call when no service was created.
-    """
-    global _service
-    with _service_lock:
-        svc = _service
-        _service = None
-    if svc is not None:
-        try:
-            svc.shutdown()
-        except Exception as e:  # noqa: BLE001
-            logger.debug("LSP shutdown error: %s", e)
-
-
-def _atexit_shutdown() -> None:
-    """atexit-registered wrapper.  Logs at debug because by the time
-    atexit fires the user has already seen the agent's final output —
-    a noisy shutdown line on top of that is just clutter."""
-    try:
-        shutdown_service()
-    except Exception as e:  # noqa: BLE001
-        logger.debug("atexit LSP shutdown failed: %s", e)
-
-
-__all__ = ["get_service", "shutdown_service", "LSPService"]

agent/lsp/range_shift.py

@@ -1,149 +0,0 @@
-"""Diff-aware line-shift map for cross-edit LSP delta filtering.
-
-When an edit deletes or inserts lines in the middle of a file, every
-diagnostic below the edit point shifts to a new line number.  The
-LSPService delta filter subtracts the pre-edit baseline from the
-post-edit diagnostics keyed on ``(severity, code, source, message,
-range)`` — without an adjustment, the shifted-but-otherwise-identical
-diagnostics look brand-new and the agent gets flooded with noise.
-
-The fix used here is the same trick git's blame and unified diff use:
-build a piecewise-linear map from pre-edit line numbers to post-edit
-line numbers, then apply that map to baseline diagnostics before the
-set-difference.  Diagnostics whose pre-edit line is in a region the
-edit deleted return ``None`` and are dropped from the baseline (they
-genuinely no longer apply).
-
-Trade-off vs. dropping range from the key entirely (the previous
-fix): preserves the "new instance of an identical error at a
-different line" signal — if the model introduces a second instance
-of the same error class at a different location, that one will be
-surfaced as new instead of swallowed by content-only dedup.
-
-The map is derived from ``difflib.SequenceMatcher.get_opcodes()`` and
-exposed as a single callable so callers don't have to reason about
-diff regions.
-"""
-from __future__ import annotations
-
-import difflib
-from typing import Any, Callable, Dict, List, Optional
-
-
-def build_line_shift(pre_text: str, post_text: str) -> Callable[[int], Optional[int]]:
-    """Build a function mapping pre-edit line numbers to post-edit line numbers.
-
-    Lines are 0-indexed to match the LSP wire format
-    (``range.start.line`` is 0-indexed).
-
-    The returned callable takes a pre-edit 0-indexed line number and
-    returns the corresponding post-edit 0-indexed line number, or
-    ``None`` if that line was deleted by the edit (no post-edit
-    counterpart exists).
-
-    Cost: one ``SequenceMatcher.get_opcodes()`` call up front; the
-    returned closure is O(log n) per call (binary search over opcode
-    regions).  Cheap enough to call once per write/patch and apply to
-    every baseline diagnostic.
-    """
-    pre_lines = pre_text.splitlines() if pre_text else []
-    post_lines = post_text.splitlines() if post_text else []
-
-    # Trivial case: identical content or no content — identity map.
-    if pre_lines == post_lines:
-        return lambda line: line
-
-    # SequenceMatcher.get_opcodes() returns a list of
-    # (tag, i1, i2, j1, j2) where tag is 'equal', 'replace', 'delete',
-    # or 'insert'.  i1:i2 is the range in pre, j1:j2 is the range in
-    # post.  We build a list of (i1, i2, j1, j2, tag) tuples and
-    # binary-search by i for each lookup.
-    sm = difflib.SequenceMatcher(a=pre_lines, b=post_lines, autojunk=False)
-    opcodes = sm.get_opcodes()
-
-    def shift(line: int) -> Optional[int]:
-        # Find the opcode region whose i1 <= line < i2.
-        # Linear scan is fine — typical opcode count is small (single
-        # digits for a typical patch-tool edit).
-        for tag, i1, i2, j1, j2 in opcodes:
-            if i1 <= line < i2:
-                if tag == "equal":
-                    # Pre-line N → post-line (N - i1 + j1).
-                    return line - i1 + j1
-                if tag == "delete":
-                    # Pre-line is in a deleted region — no post counterpart.
-                    return None
-                if tag == "replace":
-                    # Replace == delete + insert; the pre-line has no
-                    # post counterpart in any meaningful sense.  Drop.
-                    return None
-                # 'insert' has i1 == i2 so line < i2 can't be hit.
-            if line < i1:
-                # Past the relevant region — handled in earlier iteration.
-                break
-        # Past the last opcode region (line >= len(pre_lines)).
-        # Anchor at end of post.
-        return max(0, len(post_lines) - 1) if post_lines else None
-
-    return shift
-
-
-def shift_diagnostic_range(diag: Dict[str, Any],
-                           shift: Callable[[int], Optional[int]]) -> Optional[Dict[str, Any]]:
-    """Return a copy of ``diag`` with its line range remapped through ``shift``.
-
-    Returns ``None`` if the diagnostic's start line maps to ``None``
-    (the line was deleted by the edit) — caller drops it from the
-    baseline since the diagnostic no longer applies.
-
-    Both ``start.line`` and ``end.line`` are remapped independently;
-    when only the end maps to ``None`` (rare, multi-line diagnostic
-    straddling the edit boundary) we collapse to a single-line range
-    at the shifted start to keep the diagnostic in the baseline.
-
-    The original ``diag`` is not mutated.
-    """
-    rng = diag.get("range") or {}
-    start = rng.get("start") or {}
-    end = rng.get("end") or {}
-
-    pre_start_line = int(start.get("line", 0))
-    pre_end_line = int(end.get("line", pre_start_line))
-
-    new_start_line = shift(pre_start_line)
-    if new_start_line is None:
-        return None
-
-    new_end_line = shift(pre_end_line)
-    if new_end_line is None:
-        # Diagnostic straddled the deletion — collapse to start.
-        new_end_line = new_start_line
-
-    shifted = dict(diag)
-    shifted["range"] = {
-        "start": {
-            "line": new_start_line,
-            "character": int(start.get("character", 0)),
-        },
-        "end": {
-            "line": new_end_line,
-            "character": int(end.get("character", 0)),
-        },
-    }
-    return shifted
-
-
-def shift_baseline(baseline: List[Dict[str, Any]],
-                   shift: Callable[[int], Optional[int]]) -> List[Dict[str, Any]]:
-    """Apply ``shift`` to every diagnostic in ``baseline``, dropping deleted entries."""
-    out: List[Dict[str, Any]] = []
-    for d in baseline:
-        if not isinstance(d, dict):
-            continue
-        shifted = shift_diagnostic_range(d, shift)
-        if shifted is not None:
-            out.append(shifted)
-    return out
-
-
-__all__ = ["build_line_shift", "shift_diagnostic_range", "shift_baseline"]

agent/model_metadata.py

@@ -10,7 +10,7 @@ import os
 import re
 import time
 from pathlib import Path
-from typing import Any, Dict, List, Optional, Tuple
+from typing import Any, Dict, List, Optional
 from urllib.parse import urlparse
 
 import requests
@@ -47,7 +47,7 @@ def _resolve_requests_verify() -> bool | str:
 _PROVIDER_PREFIXES: frozenset[str] = frozenset({
     "openrouter", "nous", "openai-codex", "copilot", "copilot-acp",
     "gemini", "ollama-cloud", "zai", "kimi-coding", "kimi-coding-cn", "stepfun", "minimax", "minimax-oauth", "minimax-cn", "anthropic", "deepseek",
-    "opencode-zen", "opencode-go", "ai-gateway", "kilocode", "alibaba", "novita",
+    "opencode-zen", "opencode-go", "ai-gateway", "kilocode", "alibaba",
     "qwen-oauth",
     "xiaomi",
     "arcee",
@@ -66,7 +66,7 @@ _PROVIDER_PREFIXES: frozenset[str] = frozenset({
     "gmi-cloud", "gmicloud",
     "xai", "x-ai", "x.ai", "grok",
     "nvidia", "nim", "nvidia-nim", "nemotron",
-    "qwen-portal", "novita-ai", "novitaai",
+    "qwen-portal",
 })
 
 
@@ -104,8 +104,6 @@ def _strip_provider_prefix(model: str) -> str:
 
 _model_metadata_cache: Dict[str, Dict[str, Any]] = {}
 _model_metadata_cache_time: float = 0
-_novita_metadata_cache: Dict[str, Dict[str, Any]] = {}
-_novita_metadata_cache_time: float = 0
 _MODEL_CACHE_TTL = 3600
 _endpoint_model_metadata_cache: Dict[str, Dict[str, Dict[str, Any]]] = {}
 _endpoint_model_metadata_cache_time: Dict[str, float] = {}
@@ -213,7 +211,6 @@ DEFAULT_CONTEXT_LENGTHS = {
     "grok-2-vision": 8192,      # grok-2-vision, -1212, -latest
     "grok-4-fast": 2000000,     # grok-4-fast-(non-)reasoning
     "grok-4.20": 2000000,       # grok-4.20-0309-(non-)reasoning, -multi-agent-0309
-    "grok-4.3": 1000000,        # grok-4.3, grok-4.3-latest — 1M context per docs.x.ai
     "grok-4": 256000,           # grok-4, grok-4-0709
     "grok-3": 131072,           # grok-3, grok-3-mini, grok-3-fast, grok-3-mini-fast
     "grok-2": 131072,           # grok-2, grok-2-1212, grok-2-latest
@@ -288,7 +285,6 @@ def grok_supports_reasoning_effort(model: str) -> bool:
 _CONTEXT_LENGTH_KEYS = (
     "context_length",
     "context_window",
-    "context_size",
     "max_context_length",
     "max_position_embeddings",
     "max_model_len",
@@ -358,12 +354,6 @@ _URL_TO_PROVIDER: Dict[str, str] = {
     "api.deepseek.com": "deepseek",
     "api.githubcopilot.com": "copilot",
     "models.github.ai": "copilot",
-    # GitHub Models free tier (Azure-hosted prototyping endpoint) — same
-    # canonical provider as the Copilot API.  Hard per-request token cap
-    # (often 8K) makes it unusable for Hermes' system prompt, but mapping
-    # it here lets us recognize the endpoint and emit a targeted hint
-    # instead of falling through the unknown-custom-endpoint path.
-    "models.inference.ai.azure.com": "copilot",
     "api.fireworks.ai": "fireworks",
     "opencode.ai": "opencode-go",
     "api.x.ai": "xai",
@@ -371,7 +361,6 @@ _URL_TO_PROVIDER: Dict[str, str] = {
     "api.xiaomimimo.com": "xiaomi",
     "xiaomimimo.com": "xiaomi",
     "api.gmi-serving.com": "gmi",
-    "api.novita.ai": "novita",
     "tokenhub.tencentmaas.com": "tencent-tokenhub",
     "ollama.com": "ollama-cloud",
 }
@@ -568,16 +557,6 @@ def _extract_max_completion_tokens(payload: Dict[str, Any]) -> Optional[int]:
 
 
 def _extract_pricing(payload: Dict[str, Any]) -> Dict[str, Any]:
-    novita_input = payload.get("input_token_price_per_m")
-    novita_output = payload.get("output_token_price_per_m")
-    if novita_input is not None or novita_output is not None:
-        pricing: Dict[str, Any] = {}
-        if novita_input is not None:
-            pricing["prompt"] = str(float(novita_input) / 10_000 / 1_000_000)
-        if novita_output is not None:
-            pricing["completion"] = str(float(novita_output) / 10_000 / 1_000_000)
-        return pricing
-
     alias_map = {
         "prompt": ("prompt", "input", "input_cost_per_token", "prompt_token_cost"),
         "completion": ("completion", "output", "output_cost_per_token", "completion_token_cost"),
@@ -1351,40 +1330,21 @@ def _resolve_codex_oauth_context_length(
     return None
 
 
-def _resolve_nous_context_length(
-    model: str,
-    base_url: str = "",
-    api_key: str = "",
-) -> Tuple[Optional[int], str]:
-    """Resolve Nous Portal model context length.
+def _resolve_nous_context_length(model: str) -> Optional[int]:
+    """Resolve Nous Portal model context length via OpenRouter metadata.
 
-    Tries the live Nous inference endpoint first (authoritative), then falls
-    back to OpenRouter metadata with suffix/version matching.
-
-    Nous model IDs are bare after prefix-stripping (e.g. 'qwen3.6-plus',
-    'claude-opus-4-6') while OpenRouter uses prefixed IDs (e.g.
-    'qwen/qwen3.6-plus', 'anthropic/claude-opus-4.6').  Version
-    normalization (dot↔dash) is applied to handle name drifts.
-
-    Returns ``(context_length, source)`` where ``source`` is one of:
-      - ``"portal"``    — live /v1/models response (authoritative)
-      - ``"openrouter"`` — OpenRouter cache fallback (non-authoritative;
-        callers must NOT persist this to the on-disk cache or a single
-        portal blip will freeze the wrong value in forever)
-      - ``""``           — could not resolve
+    Nous model IDs are bare (e.g. 'claude-opus-4-6') while OpenRouter uses
+    prefixed IDs (e.g. 'anthropic/claude-opus-4.6'). Try suffix matching
+    with version normalization (dot↔dash).
     """
-    # Portal first — the Nous /models endpoint is authoritative for what our
-    # infrastructure enforces and may differ from OR (e.g. OR reports 1M for
-    # qwen3.6-plus; the portal correctly says 262144).  Fall back to the OR
-    # catalog only if the portal doesn't list the model.
-    if base_url:
-        portal_ctx = _resolve_endpoint_context_length(model, base_url, api_key=api_key)
-        if portal_ctx is not None:
-            return portal_ctx, "portal"
-
-    metadata = fetch_model_metadata()
+    metadata = fetch_model_metadata()  # OpenRouter cache
 
     def _safe_ctx(or_id: str, entry: dict) -> Optional[int]:
+        """Return context length, but reject stale 32k values for Kimi models.
+
+        Apply the same guard used for the generic OpenRouter path (step 6 in 
+        resolve_context_length) so the Nous portal path does not short-circuit it.
+        """
         ctx = entry.get("context_length")
         if ctx is None:
             return None
@@ -1397,20 +1357,19 @@ def _resolve_nous_context_length(
             return None
         return ctx
 
+    # Exact match first
     if model in metadata:
-        ctx = _safe_ctx(model, metadata[model])
-        if ctx is not None:
-            return ctx, "openrouter"
+        return _safe_ctx(model, metadata[model])
 
     normalized = _normalize_model_version(model).lower()
 
     for or_id, entry in metadata.items():
         bare = or_id.split("/", 1)[1] if "/" in or_id else or_id
         if bare.lower() == model.lower() or _normalize_model_version(bare).lower() == normalized:
-            ctx = _safe_ctx(or_id, entry)
-            if ctx is not None:
-                return ctx, "openrouter"
+            return _safe_ctx(or_id, entry)
 
+    # Partial prefix match for cases like gemini-3-flash → gemini-3-flash-preview
+    # Require match to be at a word boundary (followed by -, :, or end of string)
     model_lower = model.lower()
     for or_id, entry in metadata.items():
         bare = or_id.split("/", 1)[1] if "/" in or_id else or_id
@@ -1418,11 +1377,9 @@ def _resolve_nous_context_length(
             if candidate.startswith(query) and (
                 len(candidate) == len(query) or candidate[len(query)] in "-:."
             ):
-                ctx = _safe_ctx(or_id, entry)
-                if ctx is not None:
-                    return ctx, "openrouter"
+                return _safe_ctx(or_id, entry)
 
-    return None, ""
+    return None
 
 
 def get_model_context_length(
@@ -1437,18 +1394,14 @@ def get_model_context_length(
 
     Resolution order:
     0. Explicit config override (model.context_length or custom_providers per-model)
-    1. Persistent cache (previously discovered via probing).  Nous URLs
-       bypass the cache here so step 5b can always reconcile against
-       the authoritative portal /v1/models response.
+    1. Persistent cache (previously discovered via probing)
     1b. AWS Bedrock static table (must precede custom-endpoint probe)
     2. Active endpoint metadata (/models for explicit custom endpoints)
     3. Local server query (for local endpoints)
     4. Anthropic /v1/models API (API-key users only, not OAuth)
     5. Provider-aware lookups (before generic OpenRouter cache):
        a. Copilot live /models API
-       b. Nous: live /v1/models probe first (authoritative), then OR
-          cache fallback with suffix/version normalisation.  Only
-          portal-derived values are persisted to disk.
+       b. Nous suffix-match via OpenRouter cache
        c. Codex OAuth /models probe
        d. GMI /models endpoint
        e. Ollama native /api/show probe (any base_url, provider-agnostic)
@@ -1511,20 +1464,6 @@ def get_model_context_length(
                     model, base_url, f"{cached:,}",
                 )
                 _invalidate_cached_context_length(model, base_url)
-            # Nous Portal: the portal /v1/models endpoint is authoritative.
-            # Bypass the persistent cache so step 5b can always reconcile
-            # against it — this corrects pre-fix entries seeded from the
-            # OR catalog (the same OR underreport class that the Kimi/Qwen
-            # DEFAULT_CONTEXT_LENGTHS overrides exist to mitigate) without
-            # touching the on-disk file when the portal is unreachable.
-            # The in-memory 300s endpoint metadata cache makes the per-call
-            # cost amortise to ~0 within a process.
-            elif _infer_provider_from_url(base_url) == "nous":
-                logger.debug(
-                    "Bypassing persistent cache for %s@%s (Nous portal authoritative)",
-                    model, base_url,
-                )
-                # Fall through; step 5b reconciles and overwrites if portal responds.
             else:
                 return cached
 
@@ -1548,13 +1487,6 @@ def get_model_context_length(
         except ImportError:
             pass  # boto3 not installed — fall through to generic resolution
 
-    if provider == "novita" or (base_url and base_url_host_matches(base_url, "api.novita.ai")):
-        ctx = _resolve_endpoint_context_length(model, base_url or "https://api.novita.ai/openai/v1", api_key=api_key)
-        if ctx is not None:
-            if base_url:
-                save_context_length(model, base_url, ctx)
-            return ctx
-
     # 2. Active endpoint metadata for truly custom/unknown endpoints.
     # Known providers (Copilot, OpenAI, Anthropic, etc.) skip this — their
     # /models endpoint may report a provider-imposed limit (e.g. Copilot
@@ -1623,18 +1555,8 @@ def get_model_context_length(
             pass  # Fall through to models.dev
 
     if effective_provider == "nous":
-        ctx, source = _resolve_nous_context_length(
-            model, base_url=base_url or "", api_key=api_key or ""
-        )
+        ctx = _resolve_nous_context_length(model)
         if ctx:
-            # Persist ONLY portal-derived values.  Caching an OR-fallback
-            # value here would freeze in a wrong number on the first portal
-            # blip / auth glitch and step-1 would short-circuit it forever.
-            # OR's catalog is community-maintained and is precisely why the
-            # Kimi/Qwen DEFAULT_CONTEXT_LENGTHS overrides exist — we don't
-            # want it leaking into the persistent cache for Nous URLs.
-            if base_url and source == "portal":
-                save_context_length(model, base_url, ctx)
             return ctx
     if effective_provider == "openai-codex":
         # Codex OAuth enforces lower context limits than the direct OpenAI

agent/models_dev.py

@@ -141,7 +141,6 @@ class ProviderInfo:
 # Hermes provider names → models.dev provider IDs
 PROVIDER_TO_MODELS_DEV: Dict[str, str] = {
     "openrouter": "openrouter",
-    "novita": "novita-ai",
     "anthropic": "anthropic",
     "openai": "openai",
     "openai-codex": "openai",

agent/portal_tags.py

@@ -1,64 +0,0 @@
-"""Centralized Nous Portal request tags.
-
-Every Hermes request that hits the Nous Portal — main agent loop, auxiliary
-client (compression / titles / vision / web_extract / session_search / etc.),
-and any future code path — must carry the same product-attribution tags so
-Nous can attribute usage to Hermes Agent and bucket it by client release.
-
-Tag shape (sent in OpenAI-compatible ``extra_body['tags']``):
-
-    [
-        "product=hermes-agent",
-        "client=hermes-client-v<__version__>",
-    ]
-
-The version is sourced live from ``hermes_cli.__version__`` so it auto-aligns
-to whatever release is installed; the release script
-(``scripts/release.py``) regex-bumps that single string, and every Portal
-request picks up the new tag on the next process start.
-
-Why one helper instead of inlining the literal at each site:
-* Four call sites (main loop profile, aux client, run_agent compression
-  fallback, web_tools fallback) used to drift apart — see PR #24194 which
-  only got the aux site, leaving the main loop sending a different tag set.
-* Tests should assert the same tag list everywhere; centralizing makes that
-  assertion a one-liner against this module.
-
-Do NOT pre-compute these as module-level constants in the consumers. The
-version can change at runtime (editable installs, hot-reload tooling), and
-``hermes_cli.__version__`` is the canonical source of truth.
-"""
-
-from __future__ import annotations
-
-from typing import List
-
-
-def _hermes_version() -> str:
-    """Return the current Hermes release version, e.g. ``"0.13.0"``.
-
-    Falls back to ``"unknown"`` if ``hermes_cli`` cannot be imported (should
-    never happen in a real install — guarded for defensive testing).
-    """
-    try:
-        from hermes_cli import __version__
-        return __version__
-    except Exception:
-        return "unknown"
-
-
-def hermes_client_tag() -> str:
-    """Return the ``client=...`` tag for Nous Portal requests.
-
-    Format: ``client=hermes-client-v<MAJOR>.<MINOR>.<PATCH>``.
-    """
-    return f"client=hermes-client-v{_hermes_version()}"
-
-
-def nous_portal_tags() -> List[str]:
-    """Return the canonical list of Nous Portal product tags.
-
-    Always returns a fresh list so callers can mutate it freely
-    (e.g. ``merged_extra.setdefault("tags", []).extend(nous_portal_tags())``).
-    """
-    return ["product=hermes-agent", hermes_client_tag()]

agent/prompt_builder.py

@@ -268,7 +268,7 @@ TOOL_USE_ENFORCEMENT_GUIDANCE = (
 
 # Model name substrings that trigger tool-use enforcement guidance.
 # Add new patterns here when a model family needs explicit steering.
-TOOL_USE_ENFORCEMENT_MODELS = ("gpt", "codex", "gemini", "gemma", "grok", "glm")
+TOOL_USE_ENFORCEMENT_MODELS = ("gpt", "codex", "gemini", "gemma", "grok")
 
 # OpenAI GPT/Codex-specific execution guidance.  Addresses known failure modes
 # where GPT models abandon work on partial results, skip prerequisite lookups,

agent/prompt_caching.py

@@ -1,15 +1,25 @@
-"""Anthropic prompt caching strategy.
+"""Anthropic prompt caching strategies.
 
-Single layout: ``system_and_3``. 4 cache_control breakpoints — system
-prompt + last 3 non-system messages, all at the same TTL (5m or 1h).
-Reduces input token costs by ~75% on multi-turn conversations within a
-single session.
+Two layouts:
+
+* ``system_and_3`` (default, used everywhere except the long-lived path):
+  4 cache_control breakpoints — system prompt + last 3 non-system messages.
+  All at the same TTL (5m or 1h). Reduces input token costs by ~75% on
+  multi-turn conversations within a single session.
+
+* ``prefix_and_2`` (Claude on Anthropic / OpenRouter / Nous Portal):
+  4 breakpoints split across two TTL tiers — tools[-1] (1h) +
+  stable system prefix (1h) + last 2 non-system messages (5m). The
+  long-lived prefix is byte-stable across sessions for a given user
+  config, so every fresh session reads the cached system+tools instead
+  of re-paying for them. Within-session rolling window shrinks from 3
+  messages to 2 to free the breakpoint budget.
 
 Pure functions -- no class state, no AIAgent dependency.
 """
 
 import copy
-from typing import Any, Dict, List
+from typing import Any, Dict, List, Optional
 
 
 def _apply_cache_marker(msg: dict, cache_marker: dict, native_anthropic: bool = False) -> None:
@@ -77,3 +87,115 @@ def apply_anthropic_cache_control(
         _apply_cache_marker(messages[idx], marker, native_anthropic=native_anthropic)
 
     return messages
+
+
+def _mark_system_stable_block(
+    messages: List[Dict[str, Any]],
+    long_lived_marker: Dict[str, str],
+) -> bool:
+    """Mark the *first* content block of the system message with the 1h marker.
+
+    The system message is expected to have been split into multiple content
+    blocks beforehand by the caller — block[0] is the cross-session-stable
+    prefix, subsequent blocks carry context files + volatile suffix.
+    Falls back to marking the whole system message as a single block when
+    the message hasn't been split (preserves correctness on the fallback path).
+
+    Returns True when a marker was placed.
+    """
+    if not messages or messages[0].get("role") != "system":
+        return False
+
+    sys_msg = messages[0]
+    content = sys_msg.get("content")
+
+    # Already a list of blocks → mark the first block.
+    if isinstance(content, list) and content:
+        first = content[0]
+        if isinstance(first, dict):
+            first["cache_control"] = long_lived_marker
+            return True
+        return False
+
+    # String content (no split) → cannot place a stable-prefix breakpoint
+    # without changing the byte content.  Caller is responsible for
+    # splitting; if they didn't, fall through to envelope marker so we still
+    # cache *something* for this turn.
+    if isinstance(content, str) and content:
+        sys_msg["content"] = [
+            {"type": "text", "text": content, "cache_control": long_lived_marker}
+        ]
+        return True
+
+    return False
+
+
+def apply_anthropic_cache_control_long_lived(
+    api_messages: List[Dict[str, Any]],
+    long_lived_ttl: str = "1h",
+    rolling_ttl: str = "5m",
+    native_anthropic: bool = False,
+) -> List[Dict[str, Any]]:
+    """Apply prefix_and_2 caching: long-lived stable prefix + rolling window.
+
+    Layout (4 breakpoints total):
+      * Stable system prefix (block[0]) → ``long_lived_ttl`` TTL
+      * Last 2 non-system messages → ``rolling_ttl`` TTL each
+
+    NOTE: this function does NOT mark the tools array. Tools cache_control
+    is attached separately (see ``mark_tools_for_long_lived_cache``) because
+    tools live outside the messages list in the API payload.
+
+    The caller MUST have split the system message into ordered content
+    blocks where block[0] is the cross-session-stable portion. If the system
+    message is still a single string, it is wrapped into a single block and
+    marked — this is correct, just less effective (the volatile suffix is
+    not isolated, so the prefix invalidates per-session).
+
+    Returns:
+        Deep copy of messages with cache_control breakpoints injected.
+    """
+    messages = copy.deepcopy(api_messages)
+    if not messages:
+        return messages
+
+    long_marker = _build_marker(long_lived_ttl)
+    rolling_marker = _build_marker(rolling_ttl)
+
+    placed_prefix = _mark_system_stable_block(messages, long_marker)
+
+    # Reserve 1 breakpoint for the system prefix (when placed); spend the
+    # remaining 3 on the rolling tail.  Anthropic max is 4 total —
+    # tools[-1] (when marked) consumes the 4th, so we cap rolling at 2 here.
+    rolling_budget = 2 if placed_prefix else 3
+    non_sys = [i for i in range(len(messages)) if messages[i].get("role") != "system"]
+    for idx in non_sys[-rolling_budget:]:
+        _apply_cache_marker(messages[idx], rolling_marker, native_anthropic=native_anthropic)
+
+    return messages
+
+
+def mark_tools_for_long_lived_cache(
+    tools: Optional[List[Dict[str, Any]]],
+    long_lived_ttl: str = "1h",
+) -> Optional[List[Dict[str, Any]]]:
+    """Attach cache_control to the last tool in the OpenAI-format tools list.
+
+    Anthropic prefix-cache order is ``tools → system → messages``.  Marking
+    the last tool dict caches the entire tools array (Anthropic's docs:
+    "the marker is placed on the last block you want included in the cached
+    prefix").  Marker is preserved across the OpenAI-wire boundary on
+    OpenRouter and Nous Portal (which proxies to OpenRouter); on native
+    Anthropic the marker is forwarded by ``convert_tools_to_anthropic``.
+
+    Returns a deep copy of the tools list with the marker attached, or the
+    input unchanged when tools is empty/None.  Pure function — does not
+    mutate the input.
+    """
+    if not tools:
+        return tools
+    out = copy.deepcopy(tools)
+    last = out[-1]
+    if isinstance(last, dict):
+        last["cache_control"] = _build_marker(long_lived_ttl)
+    return out

agent/tool_guardrails.py

@@ -14,7 +14,6 @@ from dataclasses import dataclass, field
 from typing import Any, Mapping
 
 from utils import safe_json_loads
-from agent.tool_result_classification import file_mutation_result_landed
 
 
 IDEMPOTENT_TOOL_NAMES = frozenset(
@@ -197,8 +196,6 @@ def classify_tool_failure(tool_name: str, result: str | None) -> tuple[bool, str
     """
     if result is None:
         return False, ""
-    if file_mutation_result_landed(tool_name, result):
-        return False, ""
 
     if tool_name == "terminal":
         data = safe_json_loads(result)

agent/tool_result_classification.py

@@ -1,26 +0,0 @@
-"""Shared helpers for classifying tool result payloads."""
-
-from __future__ import annotations
-
-import json
-from typing import Any
-
-
-FILE_MUTATING_TOOL_NAMES = frozenset({"write_file", "patch"})
-
-
-def file_mutation_result_landed(tool_name: str, result: Any) -> bool:
-    """Return True when a file mutation result proves the write landed."""
-    if tool_name not in FILE_MUTATING_TOOL_NAMES or not isinstance(result, str):
-        return False
-    try:
-        data = json.loads(result.strip())
-    except Exception:
-        return False
-    if not isinstance(data, dict) or data.get("error"):
-        return False
-    if tool_name == "write_file":
-        return "bytes_written" in data
-    if tool_name == "patch":
-        return data.get("success") is True
-    return False

agent/transports/codex.py

@@ -24,10 +24,7 @@ class ResponsesApiTransport(ProviderTransport):
     def convert_messages(self, messages: List[Dict[str, Any]], **kwargs) -> Any:
         """Convert OpenAI chat messages to Responses API input items."""
         from agent.codex_responses_adapter import _chat_messages_to_responses_input
-        return _chat_messages_to_responses_input(
-            messages,
-            is_xai_responses=bool(kwargs.get("is_xai_responses")),
-        )
+        return _chat_messages_to_responses_input(messages)
 
     def convert_tools(self, tools: List[Dict[str, Any]]) -> Any:
         """Convert OpenAI tool schemas to Responses API function definitions."""
@@ -92,38 +89,24 @@ class ResponsesApiTransport(ProviderTransport):
         _effort_clamp = {"minimal": "low"}
         reasoning_effort = _effort_clamp.get(reasoning_effort, reasoning_effort)
 
-        response_tools = _responses_tools(tools)
         kwargs = {
             "model": model,
             "instructions": instructions,
-            "input": _chat_messages_to_responses_input(
-                payload_messages,
-                is_xai_responses=is_xai_responses,
-            ),
-            "tools": response_tools,
+            "input": _chat_messages_to_responses_input(payload_messages),
+            "tools": _responses_tools(tools),
+            "tool_choice": "auto",
+            "parallel_tool_calls": True,
             "store": False,
         }
-        if response_tools:
-            kwargs["tool_choice"] = "auto"
-            kwargs["parallel_tool_calls"] = True
 
         session_id = params.get("session_id")
-        # xAI Responses takes prompt_cache_key in extra_body (set further
-        # down); GitHub Models opts out of cache-key routing entirely.
-        if not is_github_responses and not is_xai_responses and session_id:
+        if not is_github_responses and session_id:
             kwargs["prompt_cache_key"] = session_id
 
         if reasoning_enabled and is_xai_responses:
             from agent.model_metadata import grok_supports_reasoning_effort
 
-            # NOTE: Hermes does NOT ask xAI to return ``reasoning.encrypted_content``
-            # any more.  xAI's OAuth/SuperGrok ``/v1/responses`` surface rejects
-            # replayed encrypted reasoning items on turn 2+ — see
-            # _chat_messages_to_responses_input docstring.  Requesting the field
-            # back would just have us cache something we then must strip.  Grok
-            # still reasons natively each turn; coherence across turns rides on
-            # the visible message text alone.
-            kwargs["include"] = []
+            kwargs["include"] = ["reasoning.encrypted_content"]
             # xAI rejects `reasoning.effort` on grok-4 / grok-4-fast / grok-3
             # / grok-code-fast / grok-4.20-0309-* with HTTP 400 even though
             # those models reason natively. Only send the effort dial when
@@ -182,17 +165,6 @@ class ResponsesApiTransport(ProviderTransport):
             merged_extra_headers["x-grok-conv-id"] = session_id
             kwargs["extra_headers"] = merged_extra_headers
 
-            # xAI Responses cache-routing — body-level field per
-            # https://docs.x.ai/developers/advanced-api-usage/prompt-caching/maximizing-cache-hits.
-            # Sent via extra_body (not the typed kwarg) so it survives openai
-            # SDK builds whose Responses.stream() signature has dropped the field.
-            existing_extra_body = kwargs.get("extra_body")
-            merged_extra_body: Dict[str, Any] = {}
-            if isinstance(existing_extra_body, dict):
-                merged_extra_body.update(existing_extra_body)
-            merged_extra_body.setdefault("prompt_cache_key", session_id)
-            kwargs["extra_body"] = merged_extra_body
-
         return kwargs
 
     def normalize_response(self, response: Any, **kwargs) -> NormalizedResponse:

agent/transports/codex_app_server.py

@@ -1,368 +0,0 @@
-"""Codex app-server JSON-RPC client.
-
-Speaks the protocol documented in codex-rs/app-server/README.md (codex 0.125+).
-Transport is newline-delimited JSON-RPC 2.0 over stdio: spawn `codex app-server`,
-do an `initialize` handshake, then drive `thread/start` + `turn/start` and
-consume streaming `item/*` notifications until `turn/completed`.
-
-This module is the wire-level speaker only. Higher-level concerns (event
-projection into Hermes' display, approval bridging, transcript projection into
-AIAgent.messages, plugin migration) live in sibling modules.
-
-Status: optional opt-in runtime gated behind `model.openai_runtime ==
-"codex_app_server"`. Hermes' default tool dispatch is unchanged when this
-runtime is not selected.
-"""
-
-from __future__ import annotations
-
-import json
-import os
-import queue
-import subprocess
-import threading
-import time
-from dataclasses import dataclass, field
-from typing import Any, Callable, Optional
-
-# Default minimum codex version we test against. The PR sets this from the
-# `codex --version` parsed at install time; bumping is a one-line change here.
-MIN_CODEX_VERSION = (0, 125, 0)
-
-
-@dataclass
-class CodexAppServerError(RuntimeError):
-    """Raised on JSON-RPC errors from the app-server."""
-
-    code: int
-    message: str
-    data: Optional[Any] = None
-
-    def __str__(self) -> str:  # pragma: no cover - trivial
-        return f"codex app-server error {self.code}: {self.message}"
-
-
-@dataclass
-class _Pending:
-    queue: queue.Queue
-    method: str
-    sent_at: float = field(default_factory=time.time)
-
-
-class CodexAppServerClient:
-    """Minimal JSON-RPC 2.0 client for `codex app-server` over stdio.
-
-    Threading model:
-      - Spawning thread (caller) drives request/response pairs synchronously.
-      - One reader thread parses stdout, dispatches replies to the right
-        pending future, and routes notifications + server-initiated requests
-        to bounded queues that the caller drains on their own cadence.
-      - One reader thread captures stderr for diagnostics; codex emits
-        tracing logs there at RUST_LOG-controlled levels.
-
-    Intentionally NOT async. AIAgent.run_conversation() is synchronous and
-    runs on the main thread; layering asyncio just to drive a stdio child
-    creates surprising interrupt semantics. We use blocking queues with
-    timeouts and rely on `turn/interrupt` for cancellation.
-    """
-
-    def __init__(
-        self,
-        codex_bin: str = "codex",
-        codex_home: Optional[str] = None,
-        extra_args: Optional[list[str]] = None,
-        env: Optional[dict[str, str]] = None,
-    ) -> None:
-        self._codex_bin = codex_bin
-        cmd = [codex_bin, "app-server"] + list(extra_args or [])
-        spawn_env = os.environ.copy()
-        if env:
-            spawn_env.update(env)
-        if codex_home:
-            spawn_env["CODEX_HOME"] = codex_home
-        # Codex emits tracing to stderr; default WARN keeps it quiet for users.
-        spawn_env.setdefault("RUST_LOG", "warn")
-
-        self._proc = subprocess.Popen(
-            cmd,
-            stdin=subprocess.PIPE,
-            stdout=subprocess.PIPE,
-            stderr=subprocess.PIPE,
-            bufsize=0,
-            env=spawn_env,
-        )
-        self._next_id = 1
-        self._pending: dict[int, _Pending] = {}
-        self._pending_lock = threading.Lock()
-        self._notifications: queue.Queue = queue.Queue()
-        self._server_requests: queue.Queue = queue.Queue()
-        self._stderr_lines: list[str] = []
-        self._stderr_lock = threading.Lock()
-        self._closed = False
-        self._initialized = False
-
-        self._reader = threading.Thread(target=self._read_stdout, daemon=True)
-        self._reader.start()
-        self._stderr_reader = threading.Thread(target=self._read_stderr, daemon=True)
-        self._stderr_reader.start()
-
-    # ---------- lifecycle ----------
-
-    def initialize(
-        self,
-        client_name: str = "hermes",
-        client_title: str = "Hermes Agent",
-        client_version: str = "0.1",
-        capabilities: Optional[dict] = None,
-        timeout: float = 10.0,
-    ) -> dict:
-        """Send `initialize` + `initialized` handshake. Returns the server's
-        InitializeResponse (userAgent, codexHome, platformFamily, platformOs)."""
-        if self._initialized:
-            raise RuntimeError("already initialized")
-        params = {
-            "clientInfo": {
-                "name": client_name,
-                "title": client_title,
-                "version": client_version,
-            },
-            "capabilities": capabilities or {},
-        }
-        result = self.request("initialize", params, timeout=timeout)
-        self.notify("initialized")
-        self._initialized = True
-        return result
-
-    def close(self, timeout: float = 3.0) -> None:
-        """Close stdin and wait for the subprocess to exit, escalating to kill."""
-        if self._closed:
-            return
-        self._closed = True
-        try:
-            if self._proc.stdin and not self._proc.stdin.closed:
-                self._proc.stdin.close()
-        except Exception:
-            pass
-        try:
-            self._proc.terminate()
-            self._proc.wait(timeout=timeout)
-        except subprocess.TimeoutExpired:
-            try:
-                self._proc.kill()
-                self._proc.wait(timeout=1.0)
-            except Exception:
-                pass
-
-    def __enter__(self) -> "CodexAppServerClient":
-        return self
-
-    def __exit__(self, *exc: Any) -> None:
-        self.close()
-
-    # ---------- send/receive ----------
-
-    def request(
-        self,
-        method: str,
-        params: Optional[dict] = None,
-        timeout: float = 30.0,
-    ) -> dict:
-        """Send a JSON-RPC request and block on the response. Returns `result`,
-        raises CodexAppServerError on `error`."""
-        rid = self._take_id()
-        q: queue.Queue = queue.Queue(maxsize=1)
-        with self._pending_lock:
-            self._pending[rid] = _Pending(queue=q, method=method)
-        self._send({"id": rid, "method": method, "params": params or {}})
-        try:
-            msg = q.get(timeout=timeout)
-        except queue.Empty:
-            with self._pending_lock:
-                self._pending.pop(rid, None)
-            raise TimeoutError(
-                f"codex app-server method {method!r} timed out after {timeout}s"
-            )
-        if "error" in msg:
-            err = msg["error"]
-            raise CodexAppServerError(
-                code=err.get("code", -1),
-                message=err.get("message", ""),
-                data=err.get("data"),
-            )
-        return msg.get("result", {})
-
-    def notify(self, method: str, params: Optional[dict] = None) -> None:
-        """Send a JSON-RPC notification (no id, no response expected)."""
-        self._send({"method": method, "params": params or {}})
-
-    def respond(self, request_id: Any, result: dict) -> None:
-        """Reply to a server-initiated request (e.g. approval prompts)."""
-        self._send({"id": request_id, "result": result})
-
-    def respond_error(
-        self, request_id: Any, code: int, message: str, data: Optional[Any] = None
-    ) -> None:
-        """Reply to a server-initiated request with an error."""
-        err: dict[str, Any] = {"code": code, "message": message}
-        if data is not None:
-            err["data"] = data
-        self._send({"id": request_id, "error": err})
-
-    def take_notification(self, timeout: float = 0.0) -> Optional[dict]:
-        """Pop the next streaming notification, or return None on timeout.
-
-        timeout=0.0 means non-blocking. Use small positive timeouts inside the
-        AIAgent turn loop to interleave reads with interrupt checks."""
-        try:
-            if timeout <= 0:
-                return self._notifications.get_nowait()
-            return self._notifications.get(timeout=timeout)
-        except queue.Empty:
-            return None
-
-    def take_server_request(self, timeout: float = 0.0) -> Optional[dict]:
-        """Pop the next server-initiated request (e.g. exec/applyPatch approval)."""
-        try:
-            if timeout <= 0:
-                return self._server_requests.get_nowait()
-            return self._server_requests.get(timeout=timeout)
-        except queue.Empty:
-            return None
-
-    # ---------- diagnostics ----------
-
-    def stderr_tail(self, n: int = 20) -> list[str]:
-        """Return last n lines of codex's stderr (for error reports)."""
-        with self._stderr_lock:
-            return list(self._stderr_lines[-n:])
-
-    def is_alive(self) -> bool:
-        return self._proc.poll() is None
-
-    # ---------- internals ----------
-
-    def _take_id(self) -> int:
-        # JSON-RPC ids only need to be unique per-connection. A simple
-        # monotonically increasing int is the common choice and matches what
-        # codex's own clients use.
-        rid = self._next_id
-        self._next_id += 1
-        return rid
-
-    def _send(self, obj: dict) -> None:
-        if self._closed:
-            raise RuntimeError("codex app-server client is closed")
-        if self._proc.stdin is None:
-            raise RuntimeError("codex app-server stdin not available")
-        try:
-            self._proc.stdin.write((json.dumps(obj) + "\n").encode("utf-8"))
-            self._proc.stdin.flush()
-        except (BrokenPipeError, ValueError) as exc:
-            raise RuntimeError(
-                f"codex app-server stdin closed unexpectedly: {exc}"
-            ) from exc
-
-    def _read_stdout(self) -> None:
-        if self._proc.stdout is None:
-            return
-        try:
-            for line in iter(self._proc.stdout.readline, b""):
-                if not line:
-                    break
-                line = line.strip()
-                if not line:
-                    continue
-                try:
-                    msg = json.loads(line)
-                except json.JSONDecodeError:
-                    # Non-JSON output is unexpected on stdout; tracing belongs
-                    # on stderr. Surface it via stderr buffer for diagnostics.
-                    with self._stderr_lock:
-                        self._stderr_lines.append(
-                            f"<non-json on stdout> {line[:200]!r}"
-                        )
-                    continue
-                self._dispatch(msg)
-        except Exception as exc:
-            with self._stderr_lock:
-                self._stderr_lines.append(f"<stdout reader error> {exc}")
-
-    def _dispatch(self, msg: dict) -> None:
-        # Reply (has id + result/error, no method)
-        if "id" in msg and ("result" in msg or "error" in msg):
-            with self._pending_lock:
-                pending = self._pending.pop(msg["id"], None)
-            if pending is not None:
-                try:
-                    pending.queue.put_nowait(msg)
-                except queue.Full:  # pragma: no cover - defensive
-                    pass
-            return
-        # Server-initiated request (has id + method)
-        if "id" in msg and "method" in msg:
-            self._server_requests.put(msg)
-            return
-        # Notification (no id)
-        if "method" in msg:
-            self._notifications.put(msg)
-
-    def _read_stderr(self) -> None:
-        if self._proc.stderr is None:
-            return
-        try:
-            for line in iter(self._proc.stderr.readline, b""):
-                if not line:
-                    break
-                with self._stderr_lock:
-                    self._stderr_lines.append(
-                        line.decode("utf-8", "replace").rstrip()
-                    )
-                    # Bound memory: keep last 500 lines.
-                    if len(self._stderr_lines) > 500:
-                        self._stderr_lines = self._stderr_lines[-500:]
-        except Exception:  # pragma: no cover
-            pass
-
-
-def parse_codex_version(output: str) -> Optional[tuple[int, int, int]]:
-    """Parse `codex --version` output. Returns (major, minor, patch) or None."""
-    # Output format: "codex-cli 0.130.0" possibly followed by metadata.
-    import re
-
-    match = re.search(r"(\d+)\.(\d+)\.(\d+)", output or "")
-    if not match:
-        return None
-    return (int(match.group(1)), int(match.group(2)), int(match.group(3)))
-
-
-def check_codex_binary(
-    codex_bin: str = "codex", min_version: tuple[int, int, int] = MIN_CODEX_VERSION
-) -> tuple[bool, str]:
-    """Verify codex CLI is installed and meets minimum version.
-
-    Returns (ok, message). Used by setup wizard and runtime startup."""
-    try:
-        proc = subprocess.run(
-            [codex_bin, "--version"],
-            capture_output=True,
-            text=True,
-            timeout=10,
-        )
-    except FileNotFoundError:
-        return False, (
-            f"codex CLI not found at {codex_bin!r}. Install with: "
-            f"npm i -g @openai/codex"
-        )
-    except subprocess.TimeoutExpired:
-        return False, "codex --version timed out"
-    if proc.returncode != 0:
-        return False, f"codex --version exited {proc.returncode}: {proc.stderr.strip()}"
-    version = parse_codex_version(proc.stdout)
-    if version is None:
-        return False, f"could not parse codex version from: {proc.stdout!r}"
-    if version < min_version:
-        return False, (
-            f"codex {'.'.join(map(str, version))} is older than required "
-            f"{'.'.join(map(str, min_version))}. Run: npm i -g @openai/codex"
-        )
-    return True, ".".join(map(str, version))

agent/transports/codex_app_server_session.py

@@ -1,810 +0,0 @@
-"""Session adapter for codex app-server runtime.
-
-Owns one Codex thread per Hermes session. Drives `turn/start`, consumes
-streaming notifications via CodexEventProjector, handles server-initiated
-approval requests (apply_patch, exec command), translates cancellation,
-and returns a clean turn result that AIAgent.run_conversation() can splice
-into its `messages` list.
-
-Lifecycle:
-    session = CodexAppServerSession(cwd="/home/x/proj")
-    session.ensure_started()                              # spawns + handshake + thread/start
-    result = session.run_turn(user_input="hello")         # blocks until turn/completed
-    # result.final_text          → assistant text returned to caller
-    # result.projected_messages  → list of {role, content, ...} for messages list
-    # result.tool_iterations     → how many tool-shaped items completed (skill nudge counter)
-    # result.interrupted         → True if Ctrl+C / interrupt_requested fired mid-turn
-    session.close()                                       # tears down subprocess
-
-Threading model: the adapter is single-threaded from the caller's perspective.
-The underlying CodexAppServerClient owns its own reader threads but exposes
-blocking-with-timeout queues that this adapter polls in a loop, so the run_turn
-call is synchronous and behaves like AIAgent's existing chat_completions loop.
-"""
-
-from __future__ import annotations
-
-import logging
-import os
-import threading
-import time
-from dataclasses import dataclass, field
-from typing import Any, Callable, Optional
-
-from agent.redact import redact_sensitive_text
-from agent.transports.codex_app_server import (
-    CodexAppServerClient,
-    CodexAppServerError,
-)
-from agent.transports.codex_event_projector import CodexEventProjector
-
-logger = logging.getLogger(__name__)
-
-
-# How many tailing stderr lines from the codex subprocess to attach to a
-# user-facing error when we don't have a more specific classification (OAuth,
-# wedge watchdog, etc.). Small enough to keep error messages legible, large
-# enough to surface a config/provider/auth diagnostic.
-_STDERR_TAIL_LINES = 12
-
-
-# Permission profile mapping mirrors the docstring in PR proposal:
-# Hermes' tools.terminal.security_mode → Codex's permissions profile id.
-# Defaults if config is missing → workspace-write (matches Codex's own default).
-_HERMES_TO_CODEX_PERMISSION_PROFILE = {
-    "auto": "workspace-write",
-    "approval-required": "read-only-with-approval",
-    "unrestricted": "full-access",
-    # Backstop alias used by some skills/tests.
-    "yolo": "full-access",
-}
-
-
-@dataclass
-class TurnResult:
-    """Result of one user→assistant→tool turn through the codex app-server."""
-
-    final_text: str = ""
-    projected_messages: list[dict] = field(default_factory=list)
-    tool_iterations: int = 0
-    interrupted: bool = False
-    error: Optional[str] = None  # Set if turn ended in a non-recoverable error
-    turn_id: Optional[str] = None
-    thread_id: Optional[str] = None
-    # Hint to the caller that the underlying codex subprocess is likely
-    # wedged (turn-level timeout fired, post-tool watchdog tripped, or
-    # token-refresh failure killed the child). The caller should retire
-    # the session so the next turn respawns codex from scratch instead
-    # of riding a CPU-spinning or auth-broken process. Mirrors openclaw
-    # beta.8's "retire timed-out app-server clients" fix.
-    should_retire: bool = False
-
-
-# Markers we accept as terminal even when codex never emits turn/completed.
-# Some codex versions stream `<turn_aborted>` as raw text in agentMessage
-# items when an interrupt or upstream error tears the turn down before the
-# normal completion path fires. Mirrors openclaw beta.8 fix.
-_TURN_ABORTED_MARKERS = ("<turn_aborted>", "<turn_aborted/>")
-
-
-# Substrings in codex stderr / JSON-RPC error messages that signal the
-# subprocess died because its OAuth credentials are no longer valid.
-# Kept conservative: we only redirect users to `codex login` when we're
-# reasonably sure that's the actual failure, otherwise we surface the
-# original error verbatim. Mirrors openclaw beta.8's auth-refresh
-# classification.
-_OAUTH_REFRESH_FAILURE_HINTS = (
-    "invalid_grant",
-    "invalid grant",
-    "refresh token",
-    "refresh_token",
-    "token refresh",
-    "token_refresh",
-    "token has expired",
-    "expired_token",
-    "expired token",
-    "not authenticated",
-    "unauthenticated",
-    "unauthorized",
-    "401 unauthorized",
-    "re-authenticate",
-    "reauthenticate",
-    "please log in",
-    "please login",
-    "auth profile",
-    "no auth profile",
-    "oauth",
-)
-
-
-def _classify_oauth_failure(*parts: str) -> Optional[str]:
-    """Return a user-friendly re-auth hint if any of the provided strings
-    look like a codex OAuth/token-refresh failure; otherwise None.
-
-    Used for both `turn/start` JSON-RPC errors and post-mortem stderr
-    inspection when the subprocess exits unexpectedly. Conservative on
-    purpose — we only redirect users to `codex login` when the signal
-    is strong, so unrelated runtime failures still surface verbatim.
-    """
-    haystack = " ".join(p for p in parts if p).lower()
-    if not haystack:
-        return None
-    for needle in _OAUTH_REFRESH_FAILURE_HINTS:
-        if needle in haystack:
-            return (
-                "Codex authentication failed — your ChatGPT/Codex login "
-                "looks expired or invalid. Run `codex login` to refresh, "
-                "then retry. (Fall back to default runtime with "
-                "`/codex-runtime auto` if the issue persists.)"
-            )
-    return None
-
-
-@dataclass
-class _ServerRequestRouting:
-    """Default policies for codex-side approval requests when no interactive
-    callback is wired in. These are only used by tests + cron / non-interactive
-    contexts; the live CLI path passes an approval_callback that defers to
-    tools.approval.prompt_dangerous_approval()."""
-
-    auto_approve_exec: bool = False
-    auto_approve_apply_patch: bool = False
-
-
-class CodexAppServerSession:
-    """One Codex thread per Hermes session, lifetime owned by AIAgent.
-
-    Not thread-safe — one caller drives it at a time, matching how AIAgent's
-    run_conversation() loop is structured today. The codex client itself can
-    handle interleaved reads/writes via its own threads, but the adapter's
-    state (projector, thread_id, turn counter) is owned by the caller thread.
-    """
-
-    def __init__(
-        self,
-        *,
-        cwd: Optional[str] = None,
-        codex_bin: str = "codex",
-        codex_home: Optional[str] = None,
-        permission_profile: Optional[str] = None,
-        approval_callback: Optional[Callable[..., str]] = None,
-        on_event: Optional[Callable[[dict], None]] = None,
-        request_routing: Optional[_ServerRequestRouting] = None,
-        client_factory: Optional[Callable[..., CodexAppServerClient]] = None,
-    ) -> None:
-        self._cwd = cwd or os.getcwd()
-        self._codex_bin = codex_bin
-        self._codex_home = codex_home
-        self._permission_profile = (
-            permission_profile or _HERMES_TO_CODEX_PERMISSION_PROFILE.get(
-                os.environ.get("HERMES_TERMINAL_SECURITY_MODE", "auto"),
-                "workspace-write",
-            )
-        )
-        self._approval_callback = approval_callback
-        self._on_event = on_event  # Display hook (kawaii spinner ticks etc.)
-        self._routing = request_routing or _ServerRequestRouting()
-        self._client_factory = client_factory or CodexAppServerClient
-
-        self._client: Optional[CodexAppServerClient] = None
-        self._thread_id: Optional[str] = None
-        self._interrupt_event = threading.Event()
-        # Pending file-change items, keyed by item id. Populated on
-        # item/started for fileChange items; consumed by the approval
-        # bridge when codex sends item/fileChange/requestApproval. The
-        # approval params don't carry the changeset, so we cache here
-        # to surface a real summary in the approval prompt (quirk #4).
-        self._pending_file_changes: dict[str, str] = {}
-        self._closed = False
-
-    # ---------- lifecycle ----------
-
-    def ensure_started(self) -> str:
-        """Spawn the subprocess, do the initialize handshake, and start a
-        thread. Returns the codex thread id. Idempotent — repeated calls
-        return the same thread id."""
-        if self._thread_id is not None:
-            return self._thread_id
-        if self._client is None:
-            self._client = self._client_factory(
-                codex_bin=self._codex_bin, codex_home=self._codex_home
-            )
-        self._client.initialize(
-            client_name="hermes",
-            client_title="Hermes Agent",
-            client_version=_get_hermes_version(),
-        )
-        # Permission selection is intentionally NOT sent on thread/start.
-        # Two reasons (live-tested against codex 0.130.0):
-        #   1. `thread/start.permissions` is gated behind the experimentalApi
-        #      capability on this codex version — we'd have to opt in during
-        #      initialize and accept the unstable surface.
-        #   2. Even with experimentalApi declared and the correct shape
-        #      (`{"type": "profile", "id": "..."}`, not `{"profileId": ...}`),
-        #      codex requires a matching `[permissions]` table in
-        #      ~/.codex/config.toml or it fails the request with
-        #      'default_permissions requires a [permissions] table'.
-        # Letting codex pick its default (`:read-only` unless the user has
-        # configured otherwise in their codex config.toml) is the standard
-        # codex CLI workflow and avoids fighting codex's own validation.
-        # Users who want a write-capable profile configure it in their
-        # ~/.codex/config.toml the same way they would for any codex usage.
-        params: dict[str, Any] = {"cwd": self._cwd}
-        result = self._client.request("thread/start", params, timeout=15)
-        # Cross-fill thread.id/sessionId — different codex versions have
-        # serialized this under either key. Mirrors openclaw beta.8's
-        # tolerance fix so future codex drops/renames don't KeyError us
-        # at handshake time.
-        thread_obj = result.get("thread") or {}
-        thread_id = (
-            thread_obj.get("id")
-            or thread_obj.get("sessionId")
-            or result.get("sessionId")
-            or result.get("threadId")
-        )
-        if not thread_id:
-            raise CodexAppServerError(
-                code=-32603,
-                message=(
-                    "codex thread/start returned no thread id "
-                    f"(payload keys: {sorted(result.keys())})"
-                ),
-            )
-        self._thread_id = thread_id
-        logger.info(
-            "codex app-server thread started: id=%s profile=%s cwd=%s",
-            self._thread_id[:8],
-            self._permission_profile,
-            self._cwd,
-        )
-        return self._thread_id
-
-    def close(self) -> None:
-        if self._closed:
-            return
-        self._closed = True
-        if self._client is not None:
-            try:
-                self._client.close()
-            except Exception:  # pragma: no cover - best-effort cleanup
-                pass
-            self._client = None
-        self._thread_id = None
-
-    def __enter__(self) -> "CodexAppServerSession":
-        return self
-
-    def __exit__(self, *exc: Any) -> None:
-        self.close()
-
-    # ---------- interrupt ----------
-
-    def request_interrupt(self) -> None:
-        """Idempotent: signal the active turn loop to issue turn/interrupt
-        and unwind. Called by AIAgent's _interrupt_requested path."""
-        self._interrupt_event.set()
-
-    # ---------- diagnostics ----------
-
-    def _format_error_with_stderr(
-        self,
-        prefix: str,
-        exc: Any = "",
-        *,
-        tail_lines: int = _STDERR_TAIL_LINES,
-    ) -> str:
-        """Build a user-facing error string for codex failures.
-
-        Appends the last few lines of codex's stderr buffer when available,
-        passed through agent.redact with force=True so secrets in provider
-        error responses (auth headers, query-string tokens, sk-* keys) never
-        leak into chat output or trajectories. The codex CLI's own error
-        text ('Internal error', 'turn/start failed: ...') is otherwise
-        opaque and forces users to re-run with verbose flags to diagnose
-        config / provider / auth-bridge problems.
-
-        Use this for the generic / catch-all branches. Specific
-        classifications (OAuth via _classify_oauth_failure, post-tool wedge
-        watchdog) already produce a clean hint and should be used instead.
-        """
-        exc_str = str(exc) if exc != "" and exc is not None else ""
-        base = f"{prefix}: {exc_str}" if exc_str else prefix
-        if self._client is None:
-            return base
-        try:
-            tail = self._client.stderr_tail(tail_lines)
-        except Exception:  # pragma: no cover - diagnostic best-effort
-            return base
-        if not tail:
-            return base
-        joined = "\n".join(line.rstrip() for line in tail if line)
-        if not joined.strip():
-            return base
-        redacted = redact_sensitive_text(joined, force=True)
-        return f"{base}\ncodex stderr (last {len(tail)} lines):\n{redacted}"
-
-    # ---------- per-turn ----------
-
-    def run_turn(
-        self,
-        user_input: str,
-        *,
-        turn_timeout: float = 600.0,
-        notification_poll_timeout: float = 0.25,
-        post_tool_quiet_timeout: float = 90.0,
-    ) -> TurnResult:
-        """Send a user message and block until turn/completed, while
-        forwarding server-initiated approval requests and projecting items
-        into Hermes' messages shape.
-
-        post_tool_quiet_timeout: if codex emits a tool completion and then
-        goes quiet for this many seconds without emitting another item or
-        `turn/completed`, fast-fail and mark the session for retirement.
-        Mirrors openclaw beta.8's post-tool completion watchdog (#81697)
-        so a wedged codex doesn't burn the full turn deadline.
-        """
-        # Pre-create the result so startup failures (codex subprocess can't
-        # spawn, initialize handshake rejects, thread/start blows up) surface
-        # the same way per-turn failures do — with a TurnResult.error string
-        # the caller can render — instead of bubbling raw codex exceptions
-        # up to AIAgent.run_conversation.
-        result = TurnResult()
-        try:
-            self.ensure_started()
-        except (CodexAppServerError, TimeoutError) as exc:
-            result.error = self._format_error_with_stderr(
-                "codex app-server startup failed", exc
-            )
-            # Subprocess almost certainly unhealthy — retire so the next
-            # turn re-spawns cleanly.
-            result.should_retire = True
-            return result
-        assert self._client is not None and self._thread_id is not None
-        result.thread_id = self._thread_id
-
-        self._interrupt_event.clear()
-        projector = CodexEventProjector()
-
-        # Send turn/start with the user input. Text-only for now (codex
-        # supports rich content but Hermes' text path is the common case).
-        try:
-            ts = self._client.request(
-                "turn/start",
-                {
-                    "threadId": self._thread_id,
-                    "input": [{"type": "text", "text": user_input}],
-                },
-                timeout=10,
-            )
-        except CodexAppServerError as exc:
-            # Classify auth/refresh failures so the user gets a clear
-            # `codex login` pointer instead of a raw RPC error string.
-            stderr_blob = "\n".join(self._client.stderr_tail(40))
-            hint = _classify_oauth_failure(exc.message, stderr_blob)
-            if hint is not None:
-                result.error = hint
-                # Subprocess is fine on a JSON-RPC level here, but the
-                # token store is broken — retire so the next turn does a
-                # clean handshake (and the user has a chance to re-auth
-                # via `codex login` between turns).
-                result.should_retire = True
-            else:
-                result.error = self._format_error_with_stderr(
-                    "turn/start failed", exc
-                )
-            return result
-        except TimeoutError as exc:
-            # turn/start hanging is a strong signal the subprocess is wedged.
-            stderr_blob = "\n".join(self._client.stderr_tail(40))
-            hint = _classify_oauth_failure(stderr_blob)
-            result.error = hint or self._format_error_with_stderr(
-                "turn/start timed out", exc
-            )
-            result.should_retire = True
-            return result
-
-        result.turn_id = (ts.get("turn") or {}).get("id")
-        deadline = time.time() + turn_timeout
-        turn_complete = False
-        # Post-tool watchdog state. last_tool_completion_at is set whenever
-        # a tool-shaped item completes; if no further notification arrives
-        # within post_tool_quiet_timeout and the turn hasn't completed, we
-        # fast-fail and retire the session.
-        last_tool_completion_at: Optional[float] = None
-
-        while time.time() < deadline and not turn_complete:
-            if self._interrupt_event.is_set():
-                self._issue_interrupt(result.turn_id)
-                result.interrupted = True
-                break
-
-            # Detect a dead subprocess between iterations. If codex exited
-            # (e.g. crashed, segfaulted, or its auth refresh thread killed
-            # the process), we won't get any more notifications — bail out
-            # rather than waiting for the full turn deadline.
-            if not self._client.is_alive():
-                stderr_blob = "\n".join(self._client.stderr_tail(60))
-                hint = _classify_oauth_failure(stderr_blob)
-                if hint is not None:
-                    result.error = hint
-                else:
-                    result.error = self._format_error_with_stderr(
-                        "codex app-server subprocess exited unexpectedly",
-                        tail_lines=20,
-                    )
-                result.should_retire = True
-                break
-
-            # Post-tool watchdog: if a tool completion was the most recent
-            # signal and codex has been silent past the quiet timeout, give
-            # up on this turn instead of waiting for the outer deadline.
-            if (
-                last_tool_completion_at is not None
-                and (time.time() - last_tool_completion_at)
-                    > post_tool_quiet_timeout
-            ):
-                self._issue_interrupt(result.turn_id)
-                result.interrupted = True
-                result.error = (
-                    f"codex went silent for "
-                    f"{post_tool_quiet_timeout:.0f}s after a tool result; "
-                    f"retiring app-server session."
-                )
-                result.should_retire = True
-                break
-
-            # Drain any server-initiated requests (approvals) before
-            # reading notifications, so the codex side isn't blocked.
-            sreq = self._client.take_server_request(timeout=0)
-            if sreq is not None:
-                # Drain any pending notifications first so per-turn state
-                # (e.g. _pending_file_changes for fileChange approvals) is
-                # up to date when we make the approval decision. Bounded
-                # to avoid starving the server-request response.
-                for _ in range(8):
-                    pending = self._client.take_notification(timeout=0)
-                    if pending is None:
-                        break
-                    self._track_pending_file_change(pending)
-                    proj = projector.project(pending)
-                    if proj.messages:
-                        result.projected_messages.extend(proj.messages)
-                    if proj.is_tool_iteration:
-                        result.tool_iterations += 1
-                        last_tool_completion_at = time.time()
-                    if proj.final_text is not None:
-                        result.final_text = proj.final_text
-                        if _has_turn_aborted_marker(proj.final_text):
-                            turn_complete = True
-                            result.interrupted = True
-                            result.error = (
-                                result.error
-                                or "codex reported turn_aborted"
-                            )
-                self._handle_server_request(sreq)
-                # Activity counts as live signal — reset the post-tool
-                # quiet timer so an approval round-trip doesn't trip it.
-                last_tool_completion_at = None
-                continue
-
-            note = self._client.take_notification(
-                timeout=notification_poll_timeout
-            )
-            if note is None:
-                continue
-
-            method = note.get("method", "")
-            if self._on_event is not None:
-                try:
-                    self._on_event(note)
-                except Exception:  # pragma: no cover - display callback
-                    logger.debug("on_event callback raised", exc_info=True)
-
-            # Track in-progress fileChange items so the approval bridge
-            # can surface a real change summary when codex requests
-            # approval (the approval params themselves don't carry the
-            # changeset). Quirk #4 fix.
-            self._track_pending_file_change(note)
-
-            # Project into messages
-            projection = projector.project(note)
-            if projection.messages:
-                result.projected_messages.extend(projection.messages)
-            if projection.is_tool_iteration:
-                result.tool_iterations += 1
-                # Arm/refresh the post-tool quiet watchdog whenever a
-                # tool-shaped item completes.
-                last_tool_completion_at = time.time()
-            else:
-                # Any non-tool projected activity (assistant message,
-                # status update, etc.) means codex is still producing
-                # output — clear the quiet timer so we don't fast-fail.
-                if projection.messages or projection.final_text is not None:
-                    last_tool_completion_at = None
-            if projection.final_text is not None:
-                # Codex can emit multiple agentMessage items in one turn
-                # (e.g. partial then final). Take the last one as canonical.
-                result.final_text = projection.final_text
-                # Some codex builds tear a turn down by emitting a
-                # `<turn_aborted>` marker in the agent message text and
-                # never sending turn/completed. Treat the marker itself
-                # as terminal so we don't burn the full deadline.
-                if _has_turn_aborted_marker(projection.final_text):
-                    turn_complete = True
-                    result.interrupted = True
-                    result.error = (
-                        result.error or "codex reported turn_aborted"
-                    )
-
-            if method == "turn/completed":
-                turn_complete = True
-                turn_status = (
-                    (note.get("params") or {}).get("turn") or {}
-                ).get("status")
-                if turn_status and turn_status not in ("completed", "interrupted"):
-                    err_obj = (
-                        (note.get("params") or {}).get("turn") or {}
-                    ).get("error")
-                    if err_obj:
-                        err_msg = err_obj.get("message") or str(err_obj)
-                        # If the turn failed for an auth/refresh reason,
-                        # rewrite the error into a re-auth hint AND mark
-                        # the session for retirement.
-                        stderr_blob = "\n".join(
-                            self._client.stderr_tail(40)
-                        )
-                        hint = _classify_oauth_failure(err_msg, stderr_blob)
-                        if hint is not None:
-                            result.error = hint
-                            result.should_retire = True
-                        else:
-                            result.error = self._format_error_with_stderr(
-                                f"turn ended status={turn_status}", err_msg
-                            )
-
-        if not turn_complete and not result.interrupted:
-            # Hit the deadline. Issue interrupt to stop wasted compute, and
-            # tell the caller to retire the session — a turn that never
-            # finished is a strong sign codex is wedged in a way the next
-            # turn shouldn't inherit.
-            self._issue_interrupt(result.turn_id)
-            result.interrupted = True
-            if not result.error:
-                result.error = self._format_error_with_stderr(
-                    f"turn timed out after {turn_timeout}s"
-                )
-            result.should_retire = True
-
-        return result
-
-    # ---------- internals ----------
-
-    def _issue_interrupt(self, turn_id: Optional[str]) -> None:
-        if self._client is None or self._thread_id is None or turn_id is None:
-            return
-        try:
-            self._client.request(
-                "turn/interrupt",
-                {"threadId": self._thread_id, "turnId": turn_id},
-                timeout=5,
-            )
-        except CodexAppServerError as exc:
-            # "no active turn to interrupt" is fine — already done.
-            logger.debug("turn/interrupt non-fatal: %s", exc)
-        except TimeoutError:
-            logger.warning("turn/interrupt timed out")
-
-    def _handle_server_request(self, req: dict) -> None:
-        """Translate a codex server request (approval) into Hermes' approval
-        flow, then send the response.
-
-        Method names verified live against codex 0.130.0 (Apr 2026):
-          item/commandExecution/requestApproval — exec approvals
-          item/fileChange/requestApproval       — apply_patch approvals
-          item/permissions/requestApproval      — permissions changes
-                                                  (we decline; user controls
-                                                  permission profile in
-                                                  ~/.codex/config.toml).
-        """
-        if self._client is None:
-            return
-        method = req.get("method", "")
-        rid = req.get("id")
-        params = req.get("params") or {}
-
-        if method == "item/commandExecution/requestApproval":
-            decision = self._decide_exec_approval(params)
-            self._client.respond(rid, {"decision": decision})
-        elif method == "item/fileChange/requestApproval":
-            decision = self._decide_apply_patch_approval(params)
-            self._client.respond(rid, {"decision": decision})
-        elif method == "item/permissions/requestApproval":
-            # Codex sometimes asks to escalate permissions mid-turn. We
-            # always decline — the user already chose their permission
-            # profile in ~/.codex/config.toml and surprise escalations
-            # shouldn't be silently accepted.
-            self._client.respond(rid, {"decision": "decline"})
-        elif method == "mcpServer/elicitation/request":
-            # Codex's MCP layer asks the user for structured input on
-            # behalf of an MCP server (e.g. tool-call confirmation,
-            # OAuth, form data). For our own hermes-tools callback we
-            # auto-accept — the user already approved Hermes' tools
-            # by enabling the runtime, and we never expose anything
-            # codex's built-in shell can't already do. For other MCP
-            # servers we decline so the user explicitly opts in via
-            # codex's own auth flow.
-            server_name = params.get("serverName") or ""
-            if server_name == "hermes-tools":
-                self._client.respond(
-                    rid,
-                    {"action": "accept", "content": None, "_meta": None},
-                )
-            else:
-                self._client.respond(
-                    rid,
-                    {"action": "decline", "content": None, "_meta": None},
-                )
-        else:
-            # Unknown server request — codex can extend this surface. Reject
-            # cleanly so codex doesn't hang waiting for us.
-            logger.warning("Unknown codex server request: %s", method)
-            self._client.respond_error(
-                rid, code=-32601, message=f"Unsupported method: {method}"
-            )
-
-    def _decide_exec_approval(self, params: dict) -> str:
-        if self._routing.auto_approve_exec:
-            return "accept"
-        command = params.get("command") or ""
-        # Codex's CommandExecutionRequestApprovalParams has cwd as Optional —
-        # fall back to the session's cwd when codex doesn't include it so the
-        # approval prompt is never empty (quirk #10 fix).
-        cwd = params.get("cwd") or self._cwd or "<unknown>"
-        reason = params.get("reason")
-        description = f"Codex requests exec in {cwd}"
-        if reason:
-            description += f" — {reason}"
-        if self._approval_callback is not None:
-            try:
-                choice = self._approval_callback(
-                    command, description, allow_permanent=False
-                )
-                return _approval_choice_to_codex_decision(choice)
-            except Exception:
-                logger.exception("approval_callback raised on exec request")
-                return "decline"
-        return "decline"  # fail-closed when no callback wired
-
-    def _decide_apply_patch_approval(self, params: dict) -> str:
-        if self._routing.auto_approve_apply_patch:
-            return "accept"
-        if self._approval_callback is not None:
-            # FileChangeRequestApprovalParams gives us reason + grantRoot.
-            # The actual changeset lives on the corresponding fileChange
-            # item which the projector has already cached for us — look it
-            # up by item_id so the user sees what's actually changing.
-            reason = params.get("reason")
-            grant_root = params.get("grantRoot")
-            item_id = params.get("itemId") or ""
-            change_summary = self._lookup_pending_file_change(item_id)
-            description_parts = []
-            if reason:
-                description_parts.append(reason)
-            if change_summary:
-                description_parts.append(change_summary)
-            if grant_root:
-                description_parts.append(f"grants write to {grant_root}")
-            description = (
-                "; ".join(description_parts)
-                if description_parts
-                else "Codex requests to apply a patch"
-            )
-            command_label = (
-                f"apply_patch: {change_summary}" if change_summary
-                else f"apply_patch: {reason}" if reason
-                else "apply_patch"
-            )
-            try:
-                choice = self._approval_callback(
-                    command_label,
-                    description,
-                    allow_permanent=False,
-                )
-                return _approval_choice_to_codex_decision(choice)
-            except Exception:
-                logger.exception("approval_callback raised on apply_patch")
-                return "decline"
-        return "decline"
-
-    def _track_pending_file_change(self, note: dict) -> None:
-        """Maintain self._pending_file_changes from item/started + item/completed
-        notifications. Lets the apply_patch approval prompt show what's
-        actually changing — codex's approval params don't carry the data."""
-        method = note.get("method", "")
-        params = note.get("params") or {}
-        item = params.get("item") or {}
-        if item.get("type") != "fileChange":
-            return
-        item_id = item.get("id") or ""
-        if not item_id:
-            return
-        if method == "item/started":
-            changes = item.get("changes") or []
-            if not changes:
-                self._pending_file_changes[item_id] = "1 change pending"
-                return
-            kinds: dict[str, int] = {}
-            paths: list[str] = []
-            for ch in changes:
-                if not isinstance(ch, dict):
-                    continue
-                kind = (ch.get("kind") or {}).get("type") or "update"
-                kinds[kind] = kinds.get(kind, 0) + 1
-                p = ch.get("path") or ""
-                if p:
-                    paths.append(p)
-            counts = ", ".join(f"{n} {k}" for k, n in sorted(kinds.items()))
-            preview = ", ".join(paths[:3])
-            if len(paths) > 3:
-                preview += f", +{len(paths) - 3} more"
-            self._pending_file_changes[item_id] = (
-                f"{counts}: {preview}" if preview else counts
-            )
-        elif method == "item/completed":
-            self._pending_file_changes.pop(item_id, None)
-
-    def _lookup_pending_file_change(self, item_id: str) -> Optional[str]:
-        """Look up an in-progress fileChange item by id and summarize its
-        changes for the approval prompt. Returns None when we don't have
-        the item cached (e.g. approval arrived before item/started, or
-        fileChange item content not tracked yet)."""
-        if not item_id:
-            return None
-        cached = self._pending_file_changes.get(item_id)
-        if not cached:
-            return None
-        return cached
-
-
-def _approval_choice_to_codex_decision(choice: str) -> str:
-    """Map Hermes approval choices onto codex's CommandExecutionApprovalDecision
-    / FileChangeApprovalDecision wire values.
-
-    Hermes returns 'once', 'session', 'always', or 'deny'.
-    Codex expects 'accept', 'acceptForSession', 'decline', or 'cancel'
-    (verified against codex-rs/app-server-protocol/src/protocol/v2/item.rs
-    on codex 0.130.0).
-    """
-    if choice in ("once",):
-        return "accept"
-    if choice in ("session", "always"):
-        return "acceptForSession"
-    return "decline"
-
-
-def _has_turn_aborted_marker(text: str) -> bool:
-    """Return True if `text` contains any of the raw markers codex uses
-    to signal a turn was aborted without emitting `turn/completed`.
-
-    Codex emits `<turn_aborted>` (and sometimes `<turn_aborted/>`) as raw
-    text inside agentMessage items when an interrupt or upstream error
-    tears the turn down before the normal completion path fires. Mirrors
-    openclaw beta.8's terminal-marker fix so we don't burn the full turn
-    deadline waiting for a turn/completed that never comes.
-    """
-    if not text:
-        return False
-    for marker in _TURN_ABORTED_MARKERS:
-        if marker in text:
-            return True
-    return False
-
-
-def _get_hermes_version() -> str:
-    """Best-effort Hermes version string for codex's userAgent line."""
-    try:
-        from importlib.metadata import version
-
-        return version("hermes-agent")
-    except Exception:  # pragma: no cover
-        return "0.0.0"

agent/transports/codex_event_projector.py

@@ -1,312 +0,0 @@
-"""Projects codex app-server events into Hermes' messages list.
-
-The translator that lets Hermes' memory/skill review keep working under the
-Codex runtime: it converts Codex `item/*` notifications into the standard
-OpenAI-shaped `{role, content, tool_calls, tool_call_id}` entries that
-`agent/curator.py` already knows how to read.
-
-Codex emits items with a discriminator field `type`:
-  - userMessage         → {role: "user", content}
-  - agentMessage        → {role: "assistant", content}
-  - reasoning           → stashed in the assistant's "reasoning" field
-  - commandExecution    → assistant tool_call(name="exec") + tool result
-  - fileChange          → assistant tool_call(name="apply_patch") + tool result
-  - mcpToolCall         → assistant tool_call(name=f"mcp.{server}.{tool}") + tool result
-  - dynamicToolCall     → assistant tool_call(name=tool) + tool result
-  - plan/hookPrompt/collabAgentToolCall → recorded as opaque assistant notes
-
-Each item maps to AT MOST one assistant entry + one tool entry, preserving
-Hermes' message-alternation invariants (system → user → assistant → user/tool
-→ assistant → ...). Multiple Codex tool calls within one Codex turn produce
-multiple consecutive (assistant, tool) pairs, which is the same shape Hermes
-already produces for parallel tool calls.
-
-Counters tracked alongside projection:
-  - tool_iterations: ticks once per completed tool-shaped item. Used by
-    AIAgent._iters_since_skill (skill nudge gate, default threshold 10).
-"""
-
-from __future__ import annotations
-
-import hashlib
-import json
-from dataclasses import dataclass, field
-from typing import Any, Optional
-
-
-def _deterministic_call_id(item_type: str, item_id: str) -> str:
-    """Stable id for tool_call message correlation.
-
-    Uses the codex item id directly when present (already a uuid); falls back
-    to a content hash so replay produces the same id across sessions and
-    prefix caches stay valid. See AGENTS.md Pitfall #16 (deterministic IDs in
-    tool call history)."""
-    if item_id:
-        return f"codex_{item_type}_{item_id}"
-    digest = hashlib.sha256(f"{item_type}".encode()).hexdigest()[:16]
-    return f"codex_{item_type}_{digest}"
-
-
-def _format_tool_args(d: dict) -> str:
-    """Format a dict as JSON the way Hermes' existing tool_calls path does."""
-    return json.dumps(d, ensure_ascii=False, sort_keys=True)
-
-
-@dataclass
-class ProjectionResult:
-    """Output of projecting one Codex item.
-
-    `messages` is a list because some Codex items produce two messages
-    (assistant tool_call + tool result). Empty list = item ignored (e.g. a
-    streaming `outputDelta` that doesn't materialize into messages until the
-    `item/completed` event)."""
-
-    messages: list[dict] = field(default_factory=list)
-    is_tool_iteration: bool = False
-    final_text: Optional[str] = None  # Set when an agentMessage completes
-
-
-class CodexEventProjector:
-    """Stateful projector consuming Codex notifications in arrival order.
-
-    Owns the in-progress reasoning content (codex emits reasoning as separate
-    items but Hermes stashes it on the next assistant message)."""
-
-    def __init__(self) -> None:
-        self._pending_reasoning: list[str] = []
-
-    def project(self, notification: dict) -> ProjectionResult:
-        """Project a single notification. Idempotent for non-completion events;
-        only `item/completed` and `turn/completed` materialize messages."""
-        method = notification.get("method", "")
-        params = notification.get("params", {}) or {}
-
-        # We only materialize messages on `item/completed`. Streaming deltas
-        # (`item/<type>/outputDelta`, `item/<type>/delta`) are display-only and
-        # don't enter the messages list — same way Hermes already only writes
-        # the assistant message after the streaming completion event.
-        if method != "item/completed":
-            return ProjectionResult()
-
-        item = params.get("item") or {}
-        item_type = item.get("type") or ""
-        item_id = item.get("id") or ""
-
-        if item_type == "agentMessage":
-            return self._project_agent_message(item)
-        if item_type == "reasoning":
-            self._pending_reasoning.extend(item.get("summary") or [])
-            self._pending_reasoning.extend(item.get("content") or [])
-            return ProjectionResult()
-        if item_type == "commandExecution":
-            return self._project_command(item, item_id)
-        if item_type == "fileChange":
-            return self._project_file_change(item, item_id)
-        if item_type == "mcpToolCall":
-            return self._project_mcp_tool_call(item, item_id)
-        if item_type == "dynamicToolCall":
-            return self._project_dynamic_tool_call(item, item_id)
-        if item_type == "userMessage":
-            return self._project_user_message(item)
-
-        # Unknown / rare items (plan, hookPrompt, collabAgentToolCall, etc.)
-        # — record as opaque assistant note so memory review can still see
-        # *something* happened, but don't fabricate tool_call structure.
-        return self._project_opaque(item, item_type)
-
-    # ---------- per-type projections ----------
-
-    def _project_agent_message(self, item: dict) -> ProjectionResult:
-        text = item.get("text") or ""
-        msg: dict[str, Any] = {"role": "assistant", "content": text}
-        if self._pending_reasoning:
-            msg["reasoning"] = "\n".join(self._pending_reasoning)
-            self._pending_reasoning = []
-        return ProjectionResult(messages=[msg], final_text=text)
-
-    def _project_user_message(self, item: dict) -> ProjectionResult:
-        # codex's userMessage content is a list of UserInput variants. For
-        # projection purposes we flatten any text fragments and ignore
-        # non-text parts (images, etc.) — Hermes' messages store text only.
-        text_parts: list[str] = []
-        for fragment in item.get("content") or []:
-            if isinstance(fragment, dict):
-                if fragment.get("type") == "text":
-                    text_parts.append(fragment.get("text") or "")
-                elif "text" in fragment:
-                    text_parts.append(str(fragment["text"]))
-        return ProjectionResult(
-            messages=[{"role": "user", "content": "\n".join(text_parts)}]
-        )
-
-    def _project_command(self, item: dict, item_id: str) -> ProjectionResult:
-        call_id = _deterministic_call_id("exec", item_id)
-        args = {
-            "command": item.get("command") or "",
-            "cwd": item.get("cwd") or "",
-        }
-        assistant_msg = {
-            "role": "assistant",
-            "content": None,
-            "tool_calls": [
-                {
-                    "id": call_id,
-                    "type": "function",
-                    "function": {
-                        "name": "exec_command",
-                        "arguments": _format_tool_args(args),
-                    },
-                }
-            ],
-        }
-        if self._pending_reasoning:
-            assistant_msg["reasoning"] = "\n".join(self._pending_reasoning)
-            self._pending_reasoning = []
-        output = item.get("aggregatedOutput") or ""
-        exit_code = item.get("exitCode")
-        if exit_code is not None and exit_code != 0:
-            output = f"[exit {exit_code}]\n{output}"
-        tool_msg = {
-            "role": "tool",
-            "tool_call_id": call_id,
-            "content": output,
-        }
-        return ProjectionResult(
-            messages=[assistant_msg, tool_msg], is_tool_iteration=True
-        )
-
-    def _project_file_change(self, item: dict, item_id: str) -> ProjectionResult:
-        call_id = _deterministic_call_id("apply_patch", item_id)
-        # Reduce the codex changes array to a digest the agent loop will
-        # find readable. We record per-file change kinds (Add/Update/Delete)
-        # without inlining full file contents — those can be huge.
-        changes_summary = []
-        for change in item.get("changes") or []:
-            kind = (change.get("kind") or {}).get("type") or "update"
-            path = change.get("path") or ""
-            changes_summary.append({"kind": kind, "path": path})
-        args = {"changes": changes_summary}
-        assistant_msg = {
-            "role": "assistant",
-            "content": None,
-            "tool_calls": [
-                {
-                    "id": call_id,
-                    "type": "function",
-                    "function": {
-                        "name": "apply_patch",
-                        "arguments": _format_tool_args(args),
-                    },
-                }
-            ],
-        }
-        if self._pending_reasoning:
-            assistant_msg["reasoning"] = "\n".join(self._pending_reasoning)
-            self._pending_reasoning = []
-        status = item.get("status") or "unknown"
-        n = len(changes_summary)
-        tool_msg = {
-            "role": "tool",
-            "tool_call_id": call_id,
-            "content": f"apply_patch status={status}, {n} change(s)",
-        }
-        return ProjectionResult(
-            messages=[assistant_msg, tool_msg], is_tool_iteration=True
-        )
-
-    def _project_mcp_tool_call(self, item: dict, item_id: str) -> ProjectionResult:
-        server = item.get("server") or "mcp"
-        tool = item.get("tool") or "unknown"
-        call_id = _deterministic_call_id(f"mcp_{server}_{tool}", item_id)
-        args = item.get("arguments") or {}
-        if not isinstance(args, dict):
-            args = {"arguments": args}
-        assistant_msg = {
-            "role": "assistant",
-            "content": None,
-            "tool_calls": [
-                {
-                    "id": call_id,
-                    "type": "function",
-                    "function": {
-                        "name": f"mcp.{server}.{tool}",
-                        "arguments": _format_tool_args(args),
-                    },
-                }
-            ],
-        }
-        if self._pending_reasoning:
-            assistant_msg["reasoning"] = "\n".join(self._pending_reasoning)
-            self._pending_reasoning = []
-        result = item.get("result")
-        error = item.get("error")
-        if error:
-            content = f"[error] {json.dumps(error, ensure_ascii=False)[:1000]}"
-        elif result is not None:
-            content = json.dumps(result, ensure_ascii=False)[:4000]
-        else:
-            content = ""
-        tool_msg = {
-            "role": "tool",
-            "tool_call_id": call_id,
-            "content": content,
-        }
-        return ProjectionResult(
-            messages=[assistant_msg, tool_msg], is_tool_iteration=True
-        )
-
-    def _project_dynamic_tool_call(
-        self, item: dict, item_id: str
-    ) -> ProjectionResult:
-        tool = item.get("tool") or "unknown"
-        call_id = _deterministic_call_id(f"dyn_{tool}", item_id)
-        args = item.get("arguments") or {}
-        if not isinstance(args, dict):
-            args = {"arguments": args}
-        assistant_msg = {
-            "role": "assistant",
-            "content": None,
-            "tool_calls": [
-                {
-                    "id": call_id,
-                    "type": "function",
-                    "function": {
-                        "name": tool,
-                        "arguments": _format_tool_args(args),
-                    },
-                }
-            ],
-        }
-        if self._pending_reasoning:
-            assistant_msg["reasoning"] = "\n".join(self._pending_reasoning)
-            self._pending_reasoning = []
-        content_items = item.get("contentItems") or []
-        if isinstance(content_items, list) and content_items:
-            content = json.dumps(content_items, ensure_ascii=False)[:4000]
-        else:
-            success = item.get("success")
-            content = f"success={success}"
-        tool_msg = {
-            "role": "tool",
-            "tool_call_id": call_id,
-            "content": content,
-        }
-        return ProjectionResult(
-            messages=[assistant_msg, tool_msg], is_tool_iteration=True
-        )
-
-    def _project_opaque(self, item: dict, item_type: str) -> ProjectionResult:
-        # Record the existence of the item without inventing tool_calls.
-        # Memory review will see this and may or may not save anything.
-        try:
-            payload = json.dumps(item, ensure_ascii=False)[:1500]
-        except (TypeError, ValueError):
-            payload = repr(item)[:1500]
-        return ProjectionResult(
-            messages=[
-                {
-                    "role": "assistant",
-                    "content": f"[codex {item_type}] {payload}",
-                }
-            ]
-        )

agent/transports/hermes_tools_mcp_server.py

@@ -1,233 +0,0 @@
-"""Hermes-tools-as-MCP server for the codex_app_server runtime.
-
-When the user runs `openai/*` turns through the codex app-server, codex
-owns the loop and builds its own tool list. By default, that means
-Hermes' richer tool surface — web search, browser automation,
-delegate_task subagents, vision analysis, persistent memory, skills,
-cross-session search, image generation, TTS — is unreachable.
-
-This module exposes a curated subset of those Hermes tools to the
-spawned codex subprocess via stdio MCP. Codex registers it as a normal
-MCP server (per `~/.codex/config.toml [mcp_servers.hermes-tools]`) and
-the user gets full Hermes capability inside a Codex turn.
-
-Scope (what we expose):
-  - web_search, web_extract              — Firecrawl, no codex equivalent
-  - browser_navigate / _click / _type /  — Camofox/Browserbase automation
-    _snapshot / _scroll / _back / _press /
-    _get_images / _console / _vision
-  - vision_analyze                       — image inspection by vision model
-  - image_generate                       — image generation
-  - skill_view, skills_list              — Hermes' skill library
-  - text_to_speech                       — TTS
-  - kanban_* (complete/block/comment/    — kanban worker + orchestrator
-    heartbeat/show/list/create/            handoff (stateless: read env var,
-    unblock/link)                          write ~/.hermes/kanban.db)
-
-What we DO NOT expose:
-  - terminal / shell                     — codex's own shell tool
-  - read_file / write_file / patch       — codex's apply_patch + shell
-  - search_files / process               — codex's shell
-  - clarify                              — codex's own UX
-  - delegate_task / memory /             — `_AGENT_LOOP_TOOLS` in Hermes
-    session_search / todo                  (model_tools.py). They require
-                                           the running AIAgent context to
-                                           dispatch (mid-loop state), so a
-                                           stateless MCP callback can't
-                                           drive them. See the inline
-                                           comment on EXPOSED_TOOLS below.
-
-Run with: python -m agent.transports.hermes_tools_mcp_server
-Spawned by: CodexAppServerSession.ensure_started() when the runtime is
-            active and config opts in.
-"""
-
-from __future__ import annotations
-
-import json
-import logging
-import os
-import sys
-from typing import Any, Optional
-
-logger = logging.getLogger(__name__)
-
-
-# Tools we expose. Each name MUST match a registered Hermes tool that
-# `model_tools.handle_function_call()` can dispatch.
-#
-# What we deliberately DO NOT expose:
-#   - terminal / shell / read_file / write_file / patch / search_files /
-#     process — codex's built-ins cover these and approval routes through
-#     codex's own UI.
-#   - delegate_task / memory / session_search / todo — these are
-#     `_AGENT_LOOP_TOOLS` in Hermes (model_tools.py:493). They require
-#     the running AIAgent context to dispatch (mid-loop state), so a
-#     stateless MCP callback can't drive them. Hermes' default runtime
-#     keeps these working; the codex_app_server runtime cannot.
-EXPOSED_TOOLS: tuple[str, ...] = (
-    "web_search",
-    "web_extract",
-    "browser_navigate",
-    "browser_click",
-    "browser_type",
-    "browser_press",
-    "browser_snapshot",
-    "browser_scroll",
-    "browser_back",
-    "browser_get_images",
-    "browser_console",
-    "browser_vision",
-    "vision_analyze",
-    "image_generate",
-    "skill_view",
-    "skills_list",
-    "text_to_speech",
-    # Kanban worker handoff tools — gated on HERMES_KANBAN_TASK env var
-    # (set by the kanban dispatcher when spawning a worker). Without these
-    # in the callback, a worker spawned with openai_runtime=codex_app_server
-    # could do the work but couldn't report completion back to the kernel,
-    # making it hang until timeout. Stateless dispatch — they just read
-    # the env var and write to ~/.hermes/kanban.db.
-    "kanban_complete",
-    "kanban_block",
-    "kanban_comment",
-    "kanban_heartbeat",
-    "kanban_show",
-    "kanban_list",
-    # NOTE: kanban_create / kanban_unblock / kanban_link are orchestrator-
-    # only — the kanban tool gates them on HERMES_KANBAN_TASK being unset.
-    # They're exposed here for orchestrator agents running on the codex
-    # runtime that need to dispatch new tasks.
-    "kanban_create",
-    "kanban_unblock",
-    "kanban_link",
-)
-
-
-def _build_server() -> Any:
-    """Create the FastMCP server with Hermes tools attached. Lazy imports
-    so the module can be imported without the mcp package installed
-    (we degrade to a clear error only when actually run)."""
-    try:
-        from mcp.server.fastmcp import FastMCP
-    except ImportError as exc:  # pragma: no cover - install hint
-        raise ImportError(
-            f"hermes-tools MCP server requires the 'mcp' package: {exc}"
-        ) from exc
-
-    # Discover Hermes tools so dispatch works.
-    from model_tools import (
-        get_tool_definitions,
-        handle_function_call,
-    )
-
-    mcp = FastMCP(
-        "hermes-tools",
-        instructions=(
-            "Hermes Agent's tool surface, exposed for use inside a Codex "
-            "session. Use these for capabilities Codex's built-in toolset "
-            "doesn't cover: web search/extract, browser automation, "
-            "subagent delegation, vision, image generation, persistent "
-            "memory, skills, and cross-session search."
-        ),
-    )
-
-    # Pull authoritative Hermes tool schemas for the ones we expose, so
-    # MCP clients see the same parameter docs Hermes gives the model.
-    all_defs = {
-        td["function"]["name"]: td["function"]
-        for td in (get_tool_definitions(quiet_mode=True) or [])
-        if isinstance(td, dict) and td.get("type") == "function"
-    }
-
-    exposed_count = 0
-
-    for name in EXPOSED_TOOLS:
-        spec = all_defs.get(name)
-        if spec is None:
-            logger.debug(
-                "skipping %s — not registered in this Hermes process", name
-            )
-            continue
-
-        description = spec.get("description") or f"Hermes {name} tool"
-        params_schema = spec.get("parameters") or {"type": "object", "properties": {}}
-
-        # FastMCP wants a Python callable. Build a closure that takes the
-        # arguments dict, dispatches via handle_function_call, and returns
-        # the result string. We use add_tool() for full control over the
-        # input schema (FastMCP's @tool() decorator inspects type hints,
-        # which we can't get from a JSON schema at runtime).
-        def _make_handler(tool_name: str):
-            def _dispatch(**kwargs: Any) -> str:
-                try:
-                    return handle_function_call(tool_name, kwargs or {})
-                except Exception as exc:
-                    logger.exception("tool %s raised", tool_name)
-                    return json.dumps({"error": str(exc), "tool": tool_name})
-            _dispatch.__name__ = tool_name
-            _dispatch.__doc__ = description
-            return _dispatch
-
-        try:
-            mcp.add_tool(
-                _make_handler(name),
-                name=name,
-                description=description,
-                # FastMCP accepts JSON schema directly via the
-                # input_schema parameter on newer versions; older
-                # versions use parameters_schema. Try both for compat.
-            )
-        except TypeError:
-            # Older mcp SDK signature — fall back to decorator-style.
-            handler = _make_handler(name)
-            handler = mcp.tool(name=name, description=description)(handler)
-
-        exposed_count += 1
-
-    logger.info(
-        "hermes-tools MCP server registered %d/%d tools",
-        exposed_count,
-        len(EXPOSED_TOOLS),
-    )
-    return mcp
-
-
-def main(argv: Optional[list[str]] = None) -> int:
-    """Entry point for `python -m agent.transports.hermes_tools_mcp_server`."""
-    argv = argv or sys.argv[1:]
-    verbose = "--verbose" in argv or "-v" in argv
-
-    log_level = logging.INFO if verbose else logging.WARNING
-    logging.basicConfig(
-        level=log_level,
-        stream=sys.stderr,  # MCP uses stdio for protocol — logs MUST go to stderr
-        format="%(asctime)s [%(levelname)s] %(name)s: %(message)s",
-    )
-
-    # Quiet mode: keep Hermes' own banners off stdout (which is the MCP wire).
-    os.environ.setdefault("HERMES_QUIET", "1")
-    os.environ.setdefault("HERMES_REDACT_SECRETS", "true")
-
-    try:
-        server = _build_server()
-    except ImportError as exc:
-        sys.stderr.write(f"hermes-tools MCP server cannot start: {exc}\n")
-        return 2
-
-    # FastMCP runs with stdio transport by default when launched as a
-    # subprocess.
-    try:
-        server.run()
-    except KeyboardInterrupt:
-        return 0
-    except Exception as exc:
-        logger.exception("hermes-tools MCP server crashed")
-        sys.stderr.write(f"hermes-tools MCP server error: {exc}\n")
-        return 1
-    return 0
-
-
-if __name__ == "__main__":
-    sys.exit(main())

agent/usage_pricing.py

@@ -370,17 +370,6 @@ _OFFICIAL_DOCS_PRICING: Dict[tuple[str, str], PricingEntry] = {
         source_url="https://api-docs.deepseek.com/quick_start/pricing",
         pricing_version="deepseek-pricing-2026-03-16",
     ),
-    (
-        "deepseek",
-        "deepseek-v4-pro",
-    ): PricingEntry(
-        input_cost_per_million=Decimal("1.74"),
-        output_cost_per_million=Decimal("3.48"),
-        cache_read_cost_per_million=Decimal("0.0145"),
-        source="official_docs_snapshot",
-        source_url="https://api-docs.deepseek.com/quick_start/pricing",
-        pricing_version="deepseek-pricing-2026-05-12",
-    ),
     # Google Gemini
     (
         "google",

agent/video_gen_provider.py

@@ -1,299 +0,0 @@
-"""
-Video Generation Provider ABC
-=============================
-
-Defines the pluggable-backend interface for video generation. Providers register
-instances via ``PluginContext.register_video_gen_provider()``; the active one
-(selected via ``video_gen.provider`` in ``config.yaml``) services every
-``video_generate`` tool call.
-
-Providers live in ``<repo>/plugins/video_gen/<name>/`` (built-in, auto-loaded
-as ``kind: backend``) or ``~/.hermes/plugins/video_gen/<name>/`` (user, opt-in
-via ``plugins.enabled``).
-
-Mirrors the ``image_gen`` provider design (``agent/image_gen_provider.py``) so
-the two surfaces stay learnable together.
-
-Unified surface
----------------
-One tool — ``video_generate`` — covers **text-to-video** and **image-to-video**.
-The router is the presence of ``image_url``: if it's set, the provider routes
-to its image-to-video endpoint; if it's omitted, the provider routes to
-text-to-video. Users pick one **model family** (e.g. Pixverse v6, Veo 3.1,
-Kling O3 Standard); the provider handles which underlying FAL/xAI endpoint
-to hit.
-
-Video edit and video extend are intentionally NOT exposed in this surface —
-the inconsistency across backends is too large for one unified tool. If
-those use cases warrant attention later they can ship as separate tools.
-
-Response shape
---------------
-All providers return a dict built by :func:`success_response` /
-:func:`error_response`. Keys:
-
-    success         bool
-    video           str | None      URL or absolute file path
-    model           str             provider-specific model identifier
-    prompt          str             echoed prompt
-    modality        str             "text" | "image" (which mode was used)
-    aspect_ratio    str             provider-native (e.g. "16:9") or ""
-    duration        int             seconds (0 if not applicable)
-    provider        str             provider name (for diagnostics)
-    error           str             only when success=False
-    error_type      str             only when success=False
-"""
-
-from __future__ import annotations
-
-import abc
-import base64
-import datetime
-import logging
-import uuid
-from pathlib import Path
-from typing import Any, Dict, List, Optional, Tuple
-
-logger = logging.getLogger(__name__)
-
-
-# Common aspect ratios across providers (Veo / Kling / xAI / Pixverse). The
-# tool schema advertises this set as an enum hint, but providers may accept
-# a narrower or wider set — they are responsible for clamping.
-COMMON_ASPECT_RATIOS: Tuple[str, ...] = ("16:9", "9:16", "1:1", "4:3", "3:4", "3:2", "2:3")
-DEFAULT_ASPECT_RATIO = "16:9"
-
-COMMON_RESOLUTIONS: Tuple[str, ...] = ("480p", "540p", "720p", "1080p")
-DEFAULT_RESOLUTION = "720p"
-
-
-# ---------------------------------------------------------------------------
-# ABC
-# ---------------------------------------------------------------------------
-
-
-class VideoGenProvider(abc.ABC):
-    """Abstract base class for a video generation backend.
-
-    Subclasses must implement :meth:`generate`. Everything else has sane
-    defaults — override only what your provider needs.
-    """
-
-    @property
-    @abc.abstractmethod
-    def name(self) -> str:
-        """Stable short identifier used in ``video_gen.provider`` config.
-
-        Lowercase, no spaces. Examples: ``xai``, ``fal``, ``google``.
-        """
-
-    @property
-    def display_name(self) -> str:
-        """Human-readable label shown in ``hermes tools``. Defaults to ``name.title()``."""
-        return self.name.title()
-
-    def is_available(self) -> bool:
-        """Return True when this provider can service calls.
-
-        Typically checks for a required API key and optional-dependency
-        import. Default: True.
-        """
-        return True
-
-    def list_models(self) -> List[Dict[str, Any]]:
-        """Return catalog entries for ``hermes tools`` model picker.
-
-        Each entry represents a **model family** that supports text-to-video
-        and/or image-to-video routing internally::
-
-            {
-                "id": "veo-3.1",                       # required
-                "display": "Veo 3.1",                  # optional; defaults to id
-                "speed": "~60s",                       # optional
-                "strengths": "...",                    # optional
-                "price": "$0.20/s",                    # optional
-                "modalities": ["text", "image"],       # optional, advisory
-            }
-
-        Default: empty list (provider has no user-selectable models).
-        """
-        return []
-
-    def get_setup_schema(self) -> Dict[str, Any]:
-        """Return provider metadata for the ``hermes tools`` picker."""
-        return {
-            "name": self.display_name,
-            "badge": "",
-            "tag": "",
-            "env_vars": [],
-        }
-
-    def default_model(self) -> Optional[str]:
-        """Return the default model id, or None if not applicable."""
-        models = self.list_models()
-        if models:
-            return models[0].get("id")
-        return None
-
-    def capabilities(self) -> Dict[str, Any]:
-        """Return what this provider supports.
-
-        Returned dict (all keys optional)::
-
-            {
-                "modalities": ["text", "image"],      # which inputs the backend accepts
-                "aspect_ratios": ["16:9", "9:16", ...],
-                "resolutions": ["720p", "1080p"],
-                "max_duration": 15,                   # seconds
-                "min_duration": 1,
-                "supports_audio": True,
-                "supports_negative_prompt": True,
-                "max_reference_images": 7,
-            }
-
-        Used by the tool layer for soft validation and by ``hermes tools``
-        for the picker. Default: text-only.
-        """
-        return {
-            "modalities": ["text"],
-            "aspect_ratios": list(COMMON_ASPECT_RATIOS),
-            "resolutions": list(COMMON_RESOLUTIONS),
-            "max_duration": 10,
-            "min_duration": 1,
-            "supports_audio": False,
-            "supports_negative_prompt": False,
-            "max_reference_images": 0,
-        }
-
-    @abc.abstractmethod
-    def generate(
-        self,
-        prompt: str,
-        *,
-        model: Optional[str] = None,
-        image_url: Optional[str] = None,
-        reference_image_urls: Optional[List[str]] = None,
-        duration: Optional[int] = None,
-        aspect_ratio: str = DEFAULT_ASPECT_RATIO,
-        resolution: str = DEFAULT_RESOLUTION,
-        negative_prompt: Optional[str] = None,
-        audio: Optional[bool] = None,
-        seed: Optional[int] = None,
-        **kwargs: Any,
-    ) -> Dict[str, Any]:
-        """Generate a video from a prompt (text-to-video) or animate an image
-        (image-to-video).
-
-        Routing: if ``image_url`` is provided, the provider should route to
-        its image-to-video endpoint; otherwise text-to-video. The plugin
-        is responsible for picking the right underlying endpoint within
-        the user's chosen model family.
-
-        Implementations should return the dict from :func:`success_response`
-        or :func:`error_response`. ``kwargs`` may contain forward-compat
-        parameters future versions of the schema will expose —
-        implementations MUST ignore unknown keys (no TypeError).
-        """
-
-
-# ---------------------------------------------------------------------------
-# Helpers
-# ---------------------------------------------------------------------------
-
-
-def _videos_cache_dir() -> Path:
-    """Return ``$HERMES_HOME/cache/videos/``, creating parents as needed."""
-    from hermes_constants import get_hermes_home
-
-    path = get_hermes_home() / "cache" / "videos"
-    path.mkdir(parents=True, exist_ok=True)
-    return path
-
-
-def save_b64_video(
-    b64_data: str,
-    *,
-    prefix: str = "video",
-    extension: str = "mp4",
-) -> Path:
-    """Decode base64 video data and write under ``$HERMES_HOME/cache/videos/``.
-
-    Returns the absolute :class:`Path` to the saved file.
-
-    Filename format: ``<prefix>_<YYYYMMDD_HHMMSS>_<short-uuid>.<ext>``.
-    """
-    raw = base64.b64decode(b64_data)
-    ts = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
-    short = uuid.uuid4().hex[:8]
-    path = _videos_cache_dir() / f"{prefix}_{ts}_{short}.{extension}"
-    path.write_bytes(raw)
-    return path
-
-
-def save_bytes_video(
-    raw: bytes,
-    *,
-    prefix: str = "video",
-    extension: str = "mp4",
-) -> Path:
-    """Write raw video bytes (e.g. an HTTP download body) to the cache."""
-    ts = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
-    short = uuid.uuid4().hex[:8]
-    path = _videos_cache_dir() / f"{prefix}_{ts}_{short}.{extension}"
-    path.write_bytes(raw)
-    return path
-
-
-def success_response(
-    *,
-    video: str,
-    model: str,
-    prompt: str,
-    modality: str = "text",
-    aspect_ratio: str = "",
-    duration: int = 0,
-    provider: str,
-    extra: Optional[Dict[str, Any]] = None,
-) -> Dict[str, Any]:
-    """Build a uniform success response dict.
-
-    ``video`` may be an HTTP URL or an absolute filesystem path.
-    ``modality`` is ``"text"`` (text-to-video) or ``"image"`` (image-to-video) —
-    indicates which endpoint was actually hit, useful for diagnostics.
-    """
-    payload: Dict[str, Any] = {
-        "success": True,
-        "video": video,
-        "model": model,
-        "prompt": prompt,
-        "modality": modality,
-        "aspect_ratio": aspect_ratio,
-        "duration": int(duration) if duration else 0,
-        "provider": provider,
-    }
-    if extra:
-        for k, v in extra.items():
-            payload.setdefault(k, v)
-    return payload
-
-
-def error_response(
-    *,
-    error: str,
-    error_type: str = "provider_error",
-    provider: str = "",
-    model: str = "",
-    prompt: str = "",
-    aspect_ratio: str = "",
-) -> Dict[str, Any]:
-    """Build a uniform error response dict."""
-    return {
-        "success": False,
-        "video": None,
-        "error": error,
-        "error_type": error_type,
-        "model": model,
-        "prompt": prompt,
-        "aspect_ratio": aspect_ratio,
-        "provider": provider,
-    }

agent/video_gen_registry.py

@@ -1,117 +0,0 @@
-"""
-Video Generation Provider Registry
-==================================
-
-Central map of registered providers. Populated by plugins at import-time via
-``PluginContext.register_video_gen_provider()``; consumed by the
-``video_generate`` tool to dispatch each call to the active backend.
-
-Active selection
-----------------
-The active provider is chosen by ``video_gen.provider`` in ``config.yaml``.
-If unset, :func:`get_active_provider` applies fallback logic:
-
-1. If exactly one provider is registered, use it.
-2. Otherwise return ``None`` (the tool surfaces a helpful error pointing
-   the user at ``hermes tools``).
-
-Mirrors ``agent/image_gen_registry.py`` so the two surfaces behave the
-same.
-"""
-
-from __future__ import annotations
-
-import logging
-import threading
-from typing import Dict, List, Optional
-
-from agent.video_gen_provider import VideoGenProvider
-
-logger = logging.getLogger(__name__)
-
-
-_providers: Dict[str, VideoGenProvider] = {}
-_lock = threading.Lock()
-
-
-def register_provider(provider: VideoGenProvider) -> None:
-    """Register a video generation provider.
-
-    Re-registration (same ``name``) overwrites the previous entry and logs
-    a debug message — this makes hot-reload scenarios (tests, dev loops)
-    behave predictably.
-    """
-    if not isinstance(provider, VideoGenProvider):
-        raise TypeError(
-            f"register_provider() expects a VideoGenProvider instance, "
-            f"got {type(provider).__name__}"
-        )
-    name = provider.name
-    if not isinstance(name, str) or not name.strip():
-        raise ValueError("Video gen provider .name must be a non-empty string")
-    with _lock:
-        existing = _providers.get(name)
-        _providers[name] = provider
-    if existing is not None:
-        logger.debug("Video gen provider '%s' re-registered (was %r)", name, type(existing).__name__)
-    else:
-        logger.debug("Registered video gen provider '%s' (%s)", name, type(provider).__name__)
-
-
-def list_providers() -> List[VideoGenProvider]:
-    """Return all registered providers, sorted by name."""
-    with _lock:
-        items = list(_providers.values())
-    return sorted(items, key=lambda p: p.name)
-
-
-def get_provider(name: str) -> Optional[VideoGenProvider]:
-    """Return the provider registered under *name*, or None."""
-    if not isinstance(name, str):
-        return None
-    with _lock:
-        return _providers.get(name.strip())
-
-
-def get_active_provider() -> Optional[VideoGenProvider]:
-    """Resolve the currently-active provider.
-
-    Reads ``video_gen.provider`` from config.yaml; falls back per the
-    module docstring.
-    """
-    configured: Optional[str] = None
-    try:
-        from hermes_cli.config import load_config
-
-        cfg = load_config()
-        section = cfg.get("video_gen") if isinstance(cfg, dict) else None
-        if isinstance(section, dict):
-            raw = section.get("provider")
-            if isinstance(raw, str) and raw.strip():
-                configured = raw.strip()
-    except Exception as exc:
-        logger.debug("Could not read video_gen.provider from config: %s", exc)
-
-    with _lock:
-        snapshot = dict(_providers)
-
-    if configured:
-        provider = snapshot.get(configured)
-        if provider is not None:
-            return provider
-        logger.debug(
-            "video_gen.provider='%s' configured but not registered; falling back",
-            configured,
-        )
-
-    # Fallback: single-provider case
-    if len(snapshot) == 1:
-        return next(iter(snapshot.values()))
-
-    return None
-
-
-def _reset_for_tests() -> None:
-    """Clear the registry. **Test-only.**"""
-    with _lock:
-        _providers.clear()

agent/web_search_provider.py

@@ -1,221 +0,0 @@
-"""
-Web Search Provider ABC
-=======================
-
-Defines the pluggable-backend interface for web search and content extraction.
-Providers register instances via ``PluginContext.register_web_search_provider()``;
-the active one (selected via ``web.search_backend`` / ``web.extract_backend`` /
-``web.backend`` in ``config.yaml``) services every ``web_search`` /
-``web_extract`` tool call.
-
-Providers live in ``<repo>/plugins/web/<name>/`` (built-in, auto-loaded as
-``kind: backend``) or ``~/.hermes/plugins/web/<name>/`` (user, opt-in via
-``plugins.enabled``).
-
-This ABC is the SINGLE plugin-facing surface for web providers — every
-provider in the tree (brave-free, ddgs, searxng, exa, parallel, tavily,
-firecrawl) implements it. The legacy in-tree ``tools.web_providers.base``
-ABCs were deleted in PR #25182 along with the per-vendor inline helpers
-in ``tools/web_tools.py``; the response-shape contract documented below
-is preserved bit-for-bit so the tool wrapper does not have to translate.
-
-Response shape (preserved from the legacy contract):
-
-Search results::
-
-    {
-        "success": True,
-        "data": {
-            "web": [
-                {"title": str, "url": str, "description": str, "position": int},
-                ...
-            ]
-        }
-    }
-
-Extract results::
-
-    {
-        "success": True,
-        "data": [
-            {"url": str, "title": str, "content": str,
-             "raw_content": str, "metadata": dict},
-            ...
-        ]
-    }
-
-On failure (either capability)::
-
-    {"success": False, "error": str}
-"""
-
-from __future__ import annotations
-
-import abc
-from typing import Any, Dict, List
-
-
-# ---------------------------------------------------------------------------
-# ABC
-# ---------------------------------------------------------------------------
-
-
-class WebSearchProvider(abc.ABC):
-    """Abstract base class for a web search/extract/crawl backend.
-
-    Subclasses must implement :meth:`is_available` and at least one of
-    :meth:`search` / :meth:`extract` / :meth:`crawl`. The
-    :meth:`supports_search` / :meth:`supports_extract` / :meth:`supports_crawl`
-    capability flags let the registry route each tool call to the right
-    provider, and let multi-capability providers (Firecrawl, Tavily, Exa,
-    …) advertise multiple capabilities from a single class.
-    """
-
-    @property
-    @abc.abstractmethod
-    def name(self) -> str:
-        """Stable short identifier used in ``web.search_backend`` /
-        ``web.extract_backend`` / ``web.backend`` config keys.
-
-        Lowercase, no spaces; hyphens permitted to preserve existing
-        user-visible names. Examples: ``brave-free``, ``ddgs``,
-        ``searxng``, ``firecrawl``.
-        """
-
-    @property
-    def display_name(self) -> str:
-        """Human-readable label shown in ``hermes tools``. Defaults to ``name``."""
-        return self.name
-
-    @abc.abstractmethod
-    def is_available(self) -> bool:
-        """Return True when this provider can service calls.
-
-        Typically a cheap check (env var present, optional Python dep
-        importable, instance URL set). Must NOT make network calls — this
-        runs at tool-registration time and on every ``hermes tools`` paint.
-        """
-
-    def supports_search(self) -> bool:
-        """Return True if this provider implements :meth:`search`."""
-        return True
-
-    def supports_extract(self) -> bool:
-        """Return True if this provider implements :meth:`extract`.
-
-        Both sync and async :meth:`extract` implementations are valid — the
-        dispatcher detects coroutine functions via
-        :func:`inspect.iscoroutinefunction` and awaits as needed. Sync
-        implementations that perform blocking I/O (HTTP, SDK calls) should
-        ideally wrap in :func:`asyncio.to_thread` at the call site; small
-        providers can keep their sync shape and let the dispatcher handle
-        threading.
-        """
-        return False
-
-    def supports_crawl(self) -> bool:
-        """Return True if this provider implements :meth:`crawl`.
-
-        Crawl differs from extract in that the agent provides a *seed URL*
-        and the provider walks linked pages on its own — useful for
-        documentation sites where the agent doesn't know all relevant
-        URLs upfront. Tavily is the only built-in backend that natively
-        crawls today; Firecrawl provides a similar capability that we
-        don't currently surface as a tool.
-
-        Providers that don't crawl should leave this as False; the
-        dispatcher in :func:`tools.web_tools.web_crawl_tool` will fall
-        back to its auxiliary-model summarization path.
-        """
-        return False
-
-    def search(self, query: str, limit: int = 5) -> Dict[str, Any]:
-        """Execute a web search.
-
-        Override when :meth:`supports_search` returns True. The default
-        raises NotImplementedError; callers should gate on
-        :meth:`supports_search` before calling.
-        """
-        raise NotImplementedError(
-            f"{self.name} does not support search (override supports_search)"
-        )
-
-    def extract(self, urls: List[str], **kwargs: Any) -> Any:
-        """Extract content from one or more URLs.
-
-        Override when :meth:`supports_extract` returns True. The default
-        raises NotImplementedError; callers should gate on
-        :meth:`supports_extract` before calling.
-
-        Return shape: a list of result dicts matching what the legacy
-        :func:`tools.web_tools.web_extract_tool` post-processing pipeline
-        expects::
-
-            [
-                {
-                    "url": str,
-                    "title": str,
-                    "content": str,
-                    "raw_content": str,
-                    "metadata": dict,           # optional
-                    "error": str,               # optional, only on per-URL failure
-                },
-                ...
-            ]
-
-        Implementations MAY be ``async def`` — the dispatcher detects
-        coroutines via :func:`inspect.iscoroutinefunction` and awaits.
-
-        ``kwargs`` may carry forward-compat fields (``format``, ``include_raw``,
-        ``max_chars``) — implementations should ignore unknown keys.
-        """
-        raise NotImplementedError(
-            f"{self.name} does not support extract (override supports_extract)"
-        )
-
-    def crawl(self, url: str, **kwargs: Any) -> Any:
-        """Crawl a seed URL and return results.
-
-        Override when :meth:`supports_crawl` returns True. The default
-        raises NotImplementedError; callers should gate on
-        :meth:`supports_crawl` before calling.
-
-        Return shape: ``{"results": [{"url": str, "title": str,
-        "content": str, ...}, ...]}`` matching what
-        :func:`tools.web_tools.web_crawl_tool` post-processing expects.
-
-        Implementations MAY be ``async def``.
-
-        ``kwargs`` may carry forward-compat fields (e.g. ``max_depth``,
-        ``include_domains``) — implementations should ignore unknown keys.
-        """
-        raise NotImplementedError(
-            f"{self.name} does not support crawl (override supports_crawl)"
-        )
-
-    def get_setup_schema(self) -> Dict[str, Any]:
-        """Return provider metadata for the ``hermes tools`` picker.
-
-        Used by ``hermes_cli/tools_config.py`` to inject this provider as a
-        row in the Web Search / Web Extract picker. Shape::
-
-            {
-                "name": "Brave Search (Free)",
-                "badge": "free",
-                "tag": "No paid tier needed — uses Brave's free API.",
-                "env_vars": [
-                    {"key": "BRAVE_SEARCH_API_KEY",
-                     "prompt": "Brave Search API key",
-                     "url": "https://brave.com/search/api/"},
-                ],
-            }
-
-        Default: minimal entry derived from ``display_name``. Override to
-        expose API key prompts, badges, and instance URL fields.
-        """
-        return {
-            "name": self.display_name,
-            "badge": "",
-            "tag": "",
-            "env_vars": [],
-        }

agent/web_search_registry.py

@@ -1,262 +0,0 @@
-"""
-Web Search Provider Registry
-============================
-
-Central map of registered web providers. Populated by plugins at import-time
-via :meth:`PluginContext.register_web_search_provider`; consumed by the
-``web_search`` and ``web_extract`` tool wrappers in :mod:`tools.web_tools` to
-dispatch each call to the active backend.
-
-Active selection
-----------------
-The active provider is chosen by configuration with this precedence:
-
-1. ``web.search_backend`` / ``web.extract_backend`` / ``web.crawl_backend``
-   (per-capability override).
-2. ``web.backend`` (shared fallback).
-3. If exactly one capability-eligible provider is registered AND available,
-   use it.
-4. Legacy preference order — ``firecrawl`` → ``parallel`` → ``tavily`` →
-   ``exa`` → ``searxng`` → ``brave-free`` → ``ddgs`` — filtered by
-   availability. Matches the historic ``tools.web_tools._get_backend()``
-   candidate order so installs that never set a config key keep landing
-   on the same provider they did before the plugin migration.
-5. Otherwise ``None`` — the tool surfaces a helpful error pointing at
-   ``hermes tools``.
-
-The capability filter (``supports_search`` / ``supports_extract`` /
-``supports_crawl``) is applied at every step so a search-only provider
-(``brave-free``) configured as ``web.extract_backend`` correctly falls
-through to an extract-capable backend.
-"""
-
-from __future__ import annotations
-
-import logging
-import threading
-from typing import Dict, List, Optional
-
-from agent.web_search_provider import WebSearchProvider
-
-logger = logging.getLogger(__name__)
-
-
-_providers: Dict[str, WebSearchProvider] = {}
-_lock = threading.Lock()
-
-
-def register_provider(provider: WebSearchProvider) -> None:
-    """Register a web search/extract provider.
-
-    Re-registration (same ``name``) overwrites the previous entry and logs
-    a debug message — makes hot-reload scenarios (tests, dev loops) behave
-    predictably.
-    """
-    if not isinstance(provider, WebSearchProvider):
-        raise TypeError(
-            f"register_provider() expects a WebSearchProvider instance, "
-            f"got {type(provider).__name__}"
-        )
-    name = provider.name
-    if not isinstance(name, str) or not name.strip():
-        raise ValueError("Web provider .name must be a non-empty string")
-    with _lock:
-        existing = _providers.get(name)
-        _providers[name] = provider
-    if existing is not None:
-        logger.debug(
-            "Web provider '%s' re-registered (was %r)",
-            name, type(existing).__name__,
-        )
-    else:
-        logger.debug(
-            "Registered web provider '%s' (%s)",
-            name, type(provider).__name__,
-        )
-
-
-def list_providers() -> List[WebSearchProvider]:
-    """Return all registered providers, sorted by name."""
-    with _lock:
-        items = list(_providers.values())
-    return sorted(items, key=lambda p: p.name)
-
-
-def get_provider(name: str) -> Optional[WebSearchProvider]:
-    """Return the provider registered under *name*, or None."""
-    if not isinstance(name, str):
-        return None
-    with _lock:
-        return _providers.get(name.strip())
-
-
-# ---------------------------------------------------------------------------
-# Active-provider resolution
-# ---------------------------------------------------------------------------
-
-
-def _read_config_key(*path: str) -> Optional[str]:
-    """Resolve a dotted config key from ``config.yaml``. Returns None on miss."""
-    try:
-        from hermes_cli.config import load_config
-
-        cfg = load_config()
-        cur = cfg
-        for segment in path:
-            if not isinstance(cur, dict):
-                return None
-            cur = cur.get(segment)
-        if isinstance(cur, str) and cur.strip():
-            return cur.strip()
-    except Exception as exc:
-        logger.debug("Could not read config %s: %s", ".".join(path), exc)
-    return None
-
-
-# Legacy preference order — preserves behaviour for users who set no
-# ``web.backend`` / ``web.<capability>_backend`` config key at all. Matches
-# the historic candidate order in :func:`tools.web_tools._get_backend`
-# (paid providers first so existing paid setups don't get downgraded to
-# a free tier on upgrade). Filtered by ``is_available()`` at walk time so
-# we don't surface a provider the user has no credentials for.
-_LEGACY_PREFERENCE = (
-    "firecrawl",
-    "parallel",
-    "tavily",
-    "exa",
-    "searxng",
-    "brave-free",
-    "ddgs",
-)
-
-
-def _resolve(configured: Optional[str], *, capability: str) -> Optional[WebSearchProvider]:
-    """Resolve the active provider for a capability ("search" | "extract" | "crawl").
-
-    Resolution rules (in order):
-
-    1. **Explicit config wins, ignoring availability.** If
-       ``web.{capability}_backend`` or ``web.backend`` names a registered
-       provider that supports *capability*, return it even if its
-       :meth:`is_available` returns False — the dispatcher will surface a
-       precise "X_API_KEY is not set" error to the user instead of silently
-       routing somewhere else. Matches legacy
-       :func:`tools.web_tools._get_backend` behavior for configured names.
-
-    2. **Single-provider shortcut.** When only one registered provider
-       supports *capability* AND ``is_available()`` reports True, return it.
-
-    3. **Legacy preference walk, filtered by availability.** Walk the
-       :data:`_LEGACY_PREFERENCE` order (firecrawl → parallel → tavily →
-       exa → searxng → brave-free → ddgs) looking for a provider whose
-       ``supports_<capability>()`` is True AND whose ``is_available()`` is
-       True. Matches the historic ``tools.web_tools._get_backend()``
-       candidate order so users with credentials but no explicit config
-       key keep landing on the same provider as pre-migration. This is
-       the path that fires when no config key is set — pick the
-       highest-priority backend the user actually has credentials for.
-
-    Returns None when no provider is configured AND no available provider
-    matches the legacy preference; the dispatcher then returns a "set up a
-    provider" error to the user.
-    """
-    with _lock:
-        snapshot = dict(_providers)
-
-    def _capable(p: WebSearchProvider) -> bool:
-        if capability == "search":
-            return bool(p.supports_search())
-        if capability == "extract":
-            return bool(p.supports_extract())
-        if capability == "crawl":
-            return bool(p.supports_crawl())
-        return False
-
-    def _is_available_safe(p: WebSearchProvider) -> bool:
-        """Wrap ``is_available()`` so a buggy provider doesn't kill resolution."""
-        try:
-            return bool(p.is_available())
-        except Exception as exc:  # noqa: BLE001
-            logger.debug("provider %s.is_available() raised %s", p.name, exc)
-            return False
-
-    # 1. Explicit config wins — return regardless of is_available() so the
-    #    user gets a precise downstream error message rather than a silent
-    #    backend switch. Matches _get_backend() in web_tools.py.
-    if configured:
-        provider = snapshot.get(configured)
-        if provider is not None and _capable(provider):
-            return provider
-        if provider is None:
-            logger.debug(
-                "web backend '%s' configured but not registered; falling back",
-                configured,
-            )
-        else:
-            logger.debug(
-                "web backend '%s' configured but does not support '%s'; falling back",
-                configured, capability,
-            )
-
-    # 2. + 3. Fallback path — filter by availability so we don't surface
-    #    a provider the user has no credentials for. Without this filter,
-    #    a registered-but-unconfigured provider could end up "active" on
-    #    a fresh install with no API keys at all.
-    eligible = [
-        p for p in snapshot.values()
-        if _capable(p) and _is_available_safe(p)
-    ]
-    if len(eligible) == 1:
-        return eligible[0]
-
-    for legacy in _LEGACY_PREFERENCE:
-        provider = snapshot.get(legacy)
-        if (
-            provider is not None
-            and _capable(provider)
-            and _is_available_safe(provider)
-        ):
-            return provider
-
-    return None
-
-
-def get_active_search_provider() -> Optional[WebSearchProvider]:
-    """Resolve the currently-active web search provider.
-
-    Reads ``web.search_backend`` (preferred) or ``web.backend`` (shared
-    fallback) from config.yaml; falls back per the module docstring.
-    """
-    explicit = _read_config_key("web", "search_backend") or _read_config_key("web", "backend")
-    return _resolve(explicit, capability="search")
-
-
-def get_active_extract_provider() -> Optional[WebSearchProvider]:
-    """Resolve the currently-active web extract provider.
-
-    Reads ``web.extract_backend`` (preferred) or ``web.backend`` (shared
-    fallback) from config.yaml; falls back per the module docstring.
-    """
-    explicit = _read_config_key("web", "extract_backend") or _read_config_key("web", "backend")
-    return _resolve(explicit, capability="extract")
-
-
-def get_active_crawl_provider() -> Optional[WebSearchProvider]:
-    """Resolve the currently-active web crawl provider.
-
-    Reads ``web.crawl_backend`` (preferred) or ``web.backend`` (shared
-    fallback) from config.yaml; falls back per the module docstring.
-
-    Crawl is a niche capability — among built-in providers only Tavily and
-    Firecrawl implement it. Callers should expect ``None`` and fall back to
-    a different strategy (e.g. summarize-via-LLM) when neither is
-    configured.
-    """
-    explicit = _read_config_key("web", "crawl_backend") or _read_config_key("web", "backend")
-    return _resolve(explicit, capability="crawl")
-
-
-def _reset_for_tests() -> None:
-    """Clear the registry. **Test-only.**"""
-    with _lock:
-        _providers.clear()

apps/dashboard/scripts/sync-assets.cjs

@@ -1,46 +0,0 @@
-#!/usr/bin/env node
-/**
- * Copy font and asset folders from @nous-research/ui into public/ for Vite.
- *
- * Locates @nous-research/ui by walking up from this script looking for
- * node_modules/@nous-research/ui — works whether the dep is co-located
- * (non-workspace layout) or hoisted to the repo root (npm workspaces).
- */
-const fs = require('node:fs')
-const path = require('node:path')
-
-const DASHBOARD_ROOT = path.resolve(__dirname, '..')
-
-function locateUiPackage() {
-  let dir = DASHBOARD_ROOT
-  const { root } = path.parse(dir)
-  while (true) {
-    const candidate = path.join(dir, 'node_modules', '@nous-research', 'ui')
-    if (fs.existsSync(path.join(candidate, 'package.json'))) {
-      return candidate
-    }
-    if (dir === root) break
-    dir = path.dirname(dir)
-  }
-  throw new Error(
-    '@nous-research/ui not found. Run `npm install` from the repo root.'
-  )
-}
-
-const uiRoot = locateUiPackage()
-const distRoot = path.join(uiRoot, 'dist')
-
-const mappings = [
-  ['fonts', path.join(DASHBOARD_ROOT, 'public', 'fonts')],
-  ['assets', path.join(DASHBOARD_ROOT, 'public', 'ds-assets')],
-]
-
-for (const [srcName, destPath] of mappings) {
-  const srcPath = path.join(distRoot, srcName)
-  if (!fs.existsSync(srcPath)) {
-    throw new Error(`Missing ${srcPath} in @nous-research/ui — rebuild that package.`)
-  }
-  fs.rmSync(destPath, { recursive: true, force: true })
-  fs.cpSync(srcPath, destPath, { recursive: true })
-  console.log(`synced ${path.relative(DASHBOARD_ROOT, destPath)}`)
-}

apps/dashboard/src/components/ui/checkbox.tsx

@@ -1,61 +0,0 @@
-import { cn } from "@/lib/utils";
-import { Check } from "lucide-react";
-
-interface CheckboxProps
-  extends Omit<React.InputHTMLAttributes<HTMLInputElement>, "type"> {
-  label?: React.ReactNode;
-}
-
-export function Checkbox({
-  className,
-  label,
-  id,
-  checked,
-  defaultChecked,
-  ...props
-}: CheckboxProps) {
-  // Support both controlled (checked prop) and uncontrolled (defaultChecked) usage.
-  // For visual rendering, prefer `checked` if provided; otherwise fall back to defaultChecked.
-  const isChecked = checked ?? defaultChecked ?? false;
-
-  return (
-    <label
-      htmlFor={id}
-      className={cn(
-        "group flex items-center gap-2.5 cursor-pointer select-none",
-        props.disabled && "cursor-not-allowed opacity-50",
-      )}
-    >
-      <span
-        className={cn(
-          "flex h-4 w-4 shrink-0 items-center justify-center transition-all",
-          "border bg-background/40",
-          // Focus-visible ring for keyboard accessibility
-          "group-has-[:focus-visible]:ring-2 group-has-[:focus-visible]:ring-ring group-has-[:focus-visible]:ring-offset-1",
-          isChecked
-            ? "border-foreground bg-foreground/20"
-            : "border-border group-hover:border-foreground/40",
-          className,
-        )}
-      >
-        <Check
-          className={cn(
-            "h-3 w-3 transition-opacity",
-            isChecked
-              ? "text-foreground opacity-100"
-              : "text-foreground opacity-0",
-          )}
-        />
-      </span>
-      <input
-        type="checkbox"
-        id={id}
-        checked={checked}
-        defaultChecked={checked === undefined ? defaultChecked : undefined}
-        className="sr-only"
-        {...props}
-      />
-      {label && <span className="text-sm">{label}</span>}
-    </label>
-  );
-}

apps/dashboard/src/hooks/useModalBehavior.ts

@@ -1,44 +0,0 @@
-import { useEffect, useRef } from "react";
-
-/**
- * Hook that adds standard modal behaviors when `open` is true:
- * - Escape key calls `onClose`
- * - Body scroll is locked
- * - Focus is restored to the previously focused element on close
- *
- * Returns a ref to attach to the modal container (for optional future focus trapping).
- */
-export function useModalBehavior({
-  open,
-  onClose,
-}: {
-  open: boolean;
-  onClose: () => void;
-}) {
-  const containerRef = useRef<HTMLDivElement>(null);
-
-  useEffect(() => {
-    if (!open) return;
-
-    const prevActive = document.activeElement as HTMLElement | null;
-
-    const onKey = (e: KeyboardEvent) => {
-      if (e.key === "Escape") {
-        e.preventDefault();
-        onClose();
-      }
-    };
-
-    document.addEventListener("keydown", onKey);
-    const prevOverflow = document.body.style.overflow;
-    document.body.style.overflow = "hidden";
-
-    return () => {
-      document.removeEventListener("keydown", onKey);
-      document.body.style.overflow = prevOverflow;
-      prevActive?.focus?.();
-    };
-  }, [open, onClose]);
-
-  return containerRef;
-}

apps/dashboard/src/lib/gatewayClient.ts

@@ -1,36 +0,0 @@
-import {
-  JsonRpcGatewayClient,
-  type ConnectionState,
-  type GatewayEvent,
-  type GatewayEventName,
-} from "@hermes/shared";
-
-export type { ConnectionState, GatewayEvent, GatewayEventName };
-
-/**
- * Browser wrapper for the shared tui_gateway JSON-RPC client.
- *
- * Dashboard resolves its token and host from the served page. Desktop uses the
- * same shared protocol client, but supplies an absolute wsUrl from Electron.
- */
-export class GatewayClient extends JsonRpcGatewayClient {
-  async connect(token?: string): Promise<void> {
-    const resolved = token ?? window.__HERMES_SESSION_TOKEN__ ?? "";
-    if (!resolved) {
-      throw new Error(
-        "Session token not available — page must be served by the Hermes dashboard",
-      );
-    }
-
-    const scheme = location.protocol === "https:" ? "wss:" : "ws:";
-    await super.connect(
-      `${scheme}//${location.host}/api/ws?token=${encodeURIComponent(resolved)}`,
-    );
-  }
-}
-
-declare global {
-  interface Window {
-    __HERMES_SESSION_TOKEN__?: string;
-  }
-}

apps/desktop/.prettierrc

@@ -1,11 +0,0 @@
-{
-  "arrowParens": "avoid",
-  "bracketSpacing": true,
-  "endOfLine": "auto",
-  "printWidth": 120,
-  "semi": false,
-  "singleQuote": true,
-  "tabWidth": 2,
-  "trailingComma": "none",
-  "useTabs": false
-}

apps/desktop/README.md

@@ -1,282 +0,0 @@
-# Hermes Desktop
-
-Native Electron shell for Hermes. It packages the desktop renderer, a bundled Hermes source payload, and installer targets for macOS and Windows.
-
-## Setup
-
-Install workspace dependencies from the repo root so `apps/desktop`, `apps/dashboard`, and `apps/shared` stay linked:
-
-```bash
-npm install
-```
-
-For Python, you have two options:
-
-**Option A — let the desktop provision it for you (recommended for first-time setup):** just run `npm run dev`. On first launch the desktop creates a venv at `HERMES_HOME/hermes-agent/venv` and runs `pip install -e .` against the resolved Hermes source automatically. Requires Python 3.11-3.13 on Windows.
-
-**Option B — share an existing CLI install:** if you already ran `scripts/install.ps1` / `scripts/install.sh`, that's the same layout the desktop uses. The desktop reuses your existing venv and editable install — no extra steps. See [Runtime Bootstrap](#runtime-bootstrap) below for details.
-
-If you're hacking on Hermes from a clone outside `HERMES_HOME/hermes-agent`, point the desktop at it explicitly:
-
-```bash
-HERMES_DESKTOP_HERMES_ROOT=/path/to/your/clone npm run dev
-```
-
-### Runtime prerequisites
-
-Hermes Desktop's baseline installer dependencies are:
-
-- **Python 3.11-3.13** — for the agent runtime, dashboard backend, and tool execution.
-- **Node.js 20+ LTS** — for browser tools and Node-backed capabilities.
-- **Git for Windows** — for Git Bash, which powers Hermes terminal commands on Windows.
-
-The packaged Windows installer (`Hermes-*.exe`) is intentionally barebones: it installs the GUI and offers to install Python 3.11, Node.js 20+, and Git for Windows via `winget` when possible. Python 3.14 is not accepted yet because several Hermes dependencies do not publish compatible wheels. On first launch, the GUI handles the Hermes-specific work: syncing the bundled agent payload, creating the virtualenv, installing Python dependencies, and showing progress in the onboarding UI. The MSI installer does not run the prerequisite page, so enterprise deploys should preinstall these dependencies out-of-band.
-
-For dev (`npm run dev`) the Python check happens at first launch via the Electron bootstrapper. Manual install commands you can run yourself:
-
-```powershell
-winget install -e --id Python.Python.3.11 --scope user
-winget install -e --id OpenJS.NodeJS.LTS
-winget install -e --id Git.Git
-```
-
-## Development
-
-```bash
-cd apps/desktop
-npm run dev
-```
-
-`npm run dev` starts Vite on `127.0.0.1:5174`, launches Electron, and lets Electron boot the Hermes backend (`hermes dashboard --no-open --tui`) on an open port in `9120-9199`. This path is for UI iteration and may still show Electron/dev identities in OS prompts.
-
-Useful overrides:
-
-```bash
-HERMES_DESKTOP_HERMES_ROOT=/path/to/hermes-agent npm run dev
-HERMES_DESKTOP_PYTHON=/path/to/python npm run dev
-HERMES_DESKTOP_CWD=/path/to/project npm run dev
-HERMES_DESKTOP_IGNORE_EXISTING=1 npm run dev
-HERMES_HOME=/tmp/throwaway-hermes-home npm run dev
-HERMES_DESKTOP_BOOT_FAKE=1 npm run dev
-HERMES_DESKTOP_BOOT_FAKE=1 HERMES_DESKTOP_BOOT_FAKE_STEP_MS=900 npm run dev
-```
-
-`HERMES_DESKTOP_IGNORE_EXISTING=1` skips any `hermes` CLI already on `PATH`, which is useful when testing the factory-image bootstrap path.
-
-`HERMES_HOME` overrides the install root (default: `%LOCALAPPDATA%\hermes` on Windows, `~/.hermes` elsewhere) — handy for sandboxed dev runs that shouldn't touch your real config.
-
-`HERMES_DESKTOP_BOOT_FAKE=1` adds deterministic per-phase delays to desktop startup so you can validate the startup overlay and progress bar. For convenience, `npm run dev:fake-boot` enables fake mode with defaults.
-
-On a fresh Hermes profile, Desktop shows a first-run setup overlay after boot. The overlay saves the minimum required provider credential (for example `OPENROUTER_API_KEY`, `ANTHROPIC_API_KEY`, or `OPENAI_API_KEY`) to the active Hermes `.env`, reloads the backend env, and then lets the user continue without opening Settings manually.
-
-## Dashboard Dev
-
-Run the Python dashboard backend with embedded chat enabled:
-
-```bash
-hermes dashboard --tui --no-open
-```
-
-For dashboard HMR, start Vite in another terminal:
-
-```bash
-cd apps/dashboard
-npm run dev
-```
-
-Open the Vite URL. The dev server proxies `/api`, `/api/pty`, and plugin assets to `http://127.0.0.1:9119` and fetches the live dashboard HTML so the ephemeral session token matches the running backend.
-
-## Build
-
-```bash
-npm run build
-npm run pack          # unpacked app at release/mac-<arch>/Hermes.app
-npm run dist:mac      # macOS DMG + zip
-npm run dist:mac:dmg  # DMG only
-npm run dist:mac:zip  # zip only
-npm run dist:win      # NSIS + MSI
-```
-
-Before packaging, `stage:hermes` copies the Python Hermes payload into `build/hermes-agent`. Electron Builder then ships it as `Contents/Resources/hermes-agent`.
-
-## Automated Releases
-
-Desktop installers are published by [`.github/workflows/desktop-release.yml`](../../.github/workflows/desktop-release.yml) with two channels:
-
-- **Stable:** runs on published GitHub releases and uploads signed artifacts to that release tag.
-- **Nightly:** runs on `main` pushes and updates the rolling `desktop-nightly` prerelease.
-
-The workflow injects a channel-aware desktop version at build time:
-
-- stable: derived from the release tag (for example `v2026.5.5` -> `2026.5.5`)
-- nightly: `0.0.0-nightly.YYYYMMDD.<sha>`
-
-Artifact names include channel, platform, and architecture:
-
-```text
-Hermes-<version>-<channel>-<platform>-<arch>.<ext>
-```
-
-Each run also publishes `SHA256SUMS-<platform>.txt` so installers can be verified.
-
-### Stable release gates
-
-Stable builds fail fast if signing credentials are missing:
-
-- macOS signing + notarization: `CSC_LINK`, `CSC_KEY_PASSWORD`, `APPLE_API_KEY`, `APPLE_API_KEY_ID`, `APPLE_API_ISSUER`
-- Windows signing: `WIN_CSC_LINK`, `WIN_CSC_KEY_PASSWORD`
-
-Stable macOS builds also validate stapling and Gatekeeper assessment in CI before upload.
-
-## Icons
-
-Desktop icons live in `assets/`:
-
-- `assets/icon.icns`
-- `assets/icon.ico`
-- `assets/icon.png`
-
-The builder config points at `assets/icon`. Replace these files directly if the app icon changes.
-
-## Testing Install Paths
-
-Use the package-local test scripts from this directory:
-
-```bash
-npm run test:desktop:all
-npm run test:desktop:existing
-npm run test:desktop:fresh
-npm run test:desktop:dmg
-npm run test:desktop:platforms
-```
-
-`test:desktop:existing` builds the packaged app and opens it normally. It should use an existing `hermes` CLI if one is on `PATH`, preserving the user’s real `~/.hermes` config.
-
-`test:desktop:fresh` builds the packaged app and launches it in a throwaway fresh-install sandbox. It sets `HERMES_DESKTOP_IGNORE_EXISTING=1`, points Electron `userData` at a temp dir, points `HERMES_HOME` at a temp dir, and launches through the factory-image bootstrap path without touching your real desktop runtime or `~/.hermes`.
-
-`test:desktop:dmg` builds and opens the DMG.
-
-`test:desktop:platforms` runs platform bootstrap-path assertions, including:
-- existing-CLI vs factory-image runtime path selection semantics
-- WSL2 protection against Windows `.exe/.cmd/.bat/.ps1` overrides
-- platform-specific runtime import checks (`winpty` vs `ptyprocess`)
-
-For fast reruns without rebuilding:
-
-```bash
-HERMES_DESKTOP_SKIP_BUILD=1 npm run test:desktop:fresh
-HERMES_DESKTOP_SKIP_BUILD=1 npm run test:desktop:existing
-HERMES_DESKTOP_SKIP_BUILD=1 npm run test:desktop:dmg
-```
-
-## Installing Locally
-
-```bash
-npm run dist:mac:dmg
-open release/Hermes-0.0.0-arm64.dmg
-```
-
-Drag `Hermes` to Applications. If testing repeated installs, replace the existing app.
-
-## Runtime Bootstrap
-
-Hermes Desktop shares its install layout with the CLI installers (`scripts/install.ps1`, `scripts/install.sh`) so a desktop-only user and a CLI-only user end up with the same files in the same places.
-
-### Where things live
-
-```text
-HERMES_HOME/                       # %LOCALAPPDATA%\hermes (Windows)
-                                   # ~/.hermes (macOS / Linux)
-├── hermes-agent/                  # ACTIVE_HERMES_ROOT — the canonical install
-│   ├── hermes_cli/, agent/, ...   # Python source
-│   ├── pyproject.toml             # source of truth for deps
-│   ├── venv/                      # virtualenv (Scripts\python.exe on Windows,
-│   │                              #             bin/python elsewhere)
-│   └── .hermes-desktop-runtime.json   # marker: schema version + pyproject hash
-├── config.yaml                    # user config
-├── .env                           # API keys
-└── logs/
-    ├── desktop.log                # Electron-side boot log
-    ├── agent.log
-    ├── errors.log
-    └── gateway.log
-```
-
-The factory image (`Contents/Resources/hermes-agent` on macOS, `resources\hermes-agent` on Windows) ships inside the `.app` / `.exe` and seeds `HERMES_HOME/hermes-agent` on first launch.
-
-### Resolution order
-
-The desktop resolves a Hermes backend in this order:
-
-1. `HERMES_DESKTOP_HERMES_ROOT` — explicit dev override.
-2. Existing `hermes` CLI on PATH (skipped when `HERMES_DESKTOP_IGNORE_EXISTING=1`).
-3. Repo source root — only when running `npm run dev` from a checkout. Takes precedence over `HERMES_HOME/hermes-agent` so devs always run their local edits.
-4. `HERMES_HOME/hermes-agent` if it already exists (CLI installer or prior desktop launch).
-5. Packaged + factory image present → sync factory → `HERMES_HOME/hermes-agent`, then use it.
-6. Pip-installed `hermes_cli` module via system Python.
-
-### First-launch flow on a packaged install
-
-1. Sync factory image → `HERMES_HOME/hermes-agent`. Skipped if a `.git` directory exists at the destination (developer install) — never overwrites a user's local repo.
-2. Create venv at `HERMES_HOME/hermes-agent/venv` using system Python (errors out with a Python-install hint if no supported Python is found).
-3. `pip install -e HERMES_HOME/hermes-agent` — `pyproject.toml` is the single source of truth for dependencies.
-4. Stamp `.hermes-desktop-runtime.json` with the schema version + pyproject hash + factory version.
-
-Subsequent launches compare the marker against the active `pyproject.toml` and skip venv/dependency work when nothing has changed.
-
-### Upgrades
-
-A new installer drops a new factory image. On next launch the marker mismatches → factory contents are copied over `HERMES_HOME/hermes-agent` (excluding `venv/`, `.git`, `__pycache__`, etc.), `pip install -e` re-runs to pick up new deps, the marker is re-stamped. The venv is preserved across upgrades to keep the upgrade fast when deps haven't moved.
-
-A user who installed via `scripts/install.ps1` / `scripts/install.sh` (so `HERMES_HOME/hermes-agent/.git` exists) is detected as a developer install and the desktop never overwrites their checkout — they keep using `hermes update` / `git pull` to update.
-
-## Debugging
-
-Desktop boot logs are written to:
-
-```text
-HERMES_HOME/logs/desktop.log     # %LOCALAPPDATA%\hermes\logs\desktop.log on Windows
-                                  # ~/.hermes/logs/desktop.log on macOS / Linux
-```
-
-If the UI reports `Desktop boot failed`, check that log first. It includes the backend command output and recent Python traceback context.
-
-To reset desktop runtime state (forces re-sync from the factory image and re-`pip install -e .` on next launch):
-
-```bash
-# macOS / Linux
-rm "$HOME/.hermes/hermes-agent/.hermes-desktop-runtime.json"
-
-# Windows (PowerShell)
-Remove-Item "$env:LOCALAPPDATA\hermes\hermes-agent\.hermes-desktop-runtime.json"
-```
-
-For a full reset of just the Python venv (rare — usually only needed if the venv is broken):
-
-```bash
-# macOS / Linux
-rm -rf "$HOME/.hermes/hermes-agent/venv"
-
-# Windows (PowerShell)
-Remove-Item -Recurse -Force "$env:LOCALAPPDATA\hermes\hermes-agent\venv"
-```
-
-To reset stale macOS microphone permission prompts:
-
-```bash
-tccutil reset Microphone com.github.Electron
-tccutil reset Microphone com.nousresearch.hermes
-```
-
-## Verification
-
-Run before handing off installer changes:
-
-```bash
-npm run fix
-npm run type-check
-npm run lint
-npm run test:desktop:all
-```
-
-Current lint may report existing warnings, but it should exit with no errors.

apps/desktop/components.json

@@ -1,21 +0,0 @@
-{
-  "$schema": "https://ui.shadcn.com/schema.json",
-  "style": "new-york",
-  "rsc": false,
-  "tsx": true,
-  "tailwind": {
-    "config": "",
-    "css": "src/styles.css",
-    "baseColor": "neutral",
-    "cssVariables": true,
-    "prefix": ""
-  },
-  "aliases": {
-    "components": "@/components",
-    "utils": "@/lib/utils",
-    "ui": "@/components/ui",
-    "lib": "@/lib",
-    "hooks": "@/hooks"
-  },
-  "iconLibrary": "lucide"
-}

apps/desktop/electron/bootstrap-platform.cjs

@@ -1,30 +0,0 @@
-function isWslEnvironment(env = process.env, platform = process.platform) {
-  if (platform !== 'linux') return false
-  return Boolean(env.WSL_DISTRO_NAME || env.WSL_INTEROP)
-}
-
-function isWindowsBinaryPathInWsl(filePath, options = {}) {
-  const isWsl = options.isWsl ?? isWslEnvironment(options.env, options.platform)
-  if (!isWsl) return false
-
-  const normalized = String(filePath || '')
-    .replace(/\\/g, '/')
-    .toLowerCase()
-
-  return (
-    normalized.endsWith('.exe') ||
-    normalized.endsWith('.cmd') ||
-    normalized.endsWith('.bat') ||
-    normalized.endsWith('.ps1')
-  )
-}
-
-function bundledRuntimeImportCheck(platform = process.platform) {
-  return platform === 'win32' ? 'import fastapi, uvicorn, winpty' : 'import fastapi, uvicorn, ptyprocess'
-}
-
-module.exports = {
-  bundledRuntimeImportCheck,
-  isWindowsBinaryPathInWsl,
-  isWslEnvironment
-}

apps/desktop/electron/bootstrap-platform.test.cjs

@@ -1,46 +0,0 @@
-const assert = require('node:assert/strict')
-const fs = require('node:fs')
-const path = require('node:path')
-const test = require('node:test')
-
-const { bundledRuntimeImportCheck, isWindowsBinaryPathInWsl, isWslEnvironment } = require('./bootstrap-platform.cjs')
-
-test('isWslEnvironment detects WSL2 env vars on linux', () => {
-  assert.equal(isWslEnvironment({ WSL_DISTRO_NAME: 'Ubuntu' }, 'linux'), true)
-  assert.equal(isWslEnvironment({ WSL_INTEROP: '/run/WSL/123_interop' }, 'linux'), true)
-  assert.equal(isWslEnvironment({}, 'linux'), false)
-  assert.equal(isWslEnvironment({ WSL_DISTRO_NAME: 'Ubuntu' }, 'darwin'), false)
-})
-
-test('isWindowsBinaryPathInWsl blocks Windows binary types on WSL', () => {
-  assert.equal(isWindowsBinaryPathInWsl('/mnt/c/Tools/hermes.exe', { isWsl: true }), true)
-  assert.equal(isWindowsBinaryPathInWsl('/mnt/c/Tools/hermes.cmd', { isWsl: true }), true)
-  assert.equal(isWindowsBinaryPathInWsl('/mnt/c/Tools/hermes.bat', { isWsl: true }), true)
-  assert.equal(isWindowsBinaryPathInWsl('/mnt/c/Tools/install.ps1', { isWsl: true }), true)
-  assert.equal(isWindowsBinaryPathInWsl('/usr/local/bin/hermes', { isWsl: true }), false)
-  assert.equal(isWindowsBinaryPathInWsl('/mnt/c/Tools/hermes.exe', { isWsl: false }), false)
-})
-
-test('bundledRuntimeImportCheck selects platform-specific import checks', () => {
-  assert.equal(bundledRuntimeImportCheck('win32'), 'import fastapi, uvicorn, winpty')
-  assert.equal(bundledRuntimeImportCheck('darwin'), 'import fastapi, uvicorn, ptyprocess')
-  assert.equal(bundledRuntimeImportCheck('linux'), 'import fastapi, uvicorn, ptyprocess')
-})
-
-test('packaged electron entrypoints do not require unpackaged npm modules', () => {
-  const electronDir = __dirname
-  const entrypoints = ['main.cjs', 'preload.cjs', 'bootstrap-platform.cjs']
-  const allowedBareRequires = new Set(['electron'])
-  const requirePattern = /require\(['"]([^'"]+)['"]\)/g
-
-  for (const entrypoint of entrypoints) {
-    const source = fs.readFileSync(path.join(electronDir, entrypoint), 'utf8')
-    const bareRequires = Array.from(source.matchAll(requirePattern))
-      .map(match => match[1])
-      .filter(specifier => !specifier.startsWith('node:'))
-      .filter(specifier => !specifier.startsWith('.'))
-      .filter(specifier => !allowedBareRequires.has(specifier))
-
-    assert.deepEqual(bareRequires, [], `${entrypoint} has unpackaged runtime requires`)
-  }
-})

apps/desktop/electron/entitlements.mac.inherit.plist

@@ -1,12 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
-<plist version="1.0">
-<dict>
-  <key>com.apple.security.cs.allow-jit</key>
-  <true/>
-  <key>com.apple.security.cs.allow-unsigned-executable-memory</key>
-  <true/>
-  <key>com.apple.security.cs.disable-library-validation</key>
-  <true/>
-</dict>
-</plist>

apps/desktop/electron/entitlements.mac.plist

@@ -1,14 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
-<plist version="1.0">
-<dict>
-  <key>com.apple.security.cs.allow-jit</key>
-  <true/>
-  <key>com.apple.security.cs.allow-unsigned-executable-memory</key>
-  <true/>
-  <key>com.apple.security.cs.disable-library-validation</key>
-  <true/>
-  <key>com.apple.security.device.audio-input</key>
-  <true/>
-</dict>
-</plist>

apps/desktop/electron/hardening.cjs

@@ -1,184 +0,0 @@
-const fs = require('node:fs')
-const path = require('node:path')
-const { fileURLToPath } = require('node:url')
-
-const DEFAULT_FETCH_TIMEOUT_MS = 15_000
-const DATA_URL_READ_MAX_BYTES = 16 * 1024 * 1024
-const TEXT_PREVIEW_SOURCE_MAX_BYTES = 64 * 1024 * 1024
-
-const SAFE_ENV_SUFFIXES = new Set(['dist', 'example', 'sample', 'template'])
-const SENSITIVE_EXTENSIONS = new Set(['.kdbx', '.p12', '.pem', '.pfx'])
-
-function resolveTimeoutMs(timeoutMs, fallbackMs = DEFAULT_FETCH_TIMEOUT_MS) {
-  const fallback =
-    Number.isFinite(fallbackMs) && Number(fallbackMs) > 0 ? Math.round(Number(fallbackMs)) : DEFAULT_FETCH_TIMEOUT_MS
-  const parsed = Number(timeoutMs)
-
-  if (Number.isFinite(parsed) && parsed > 0) {
-    return Math.round(parsed)
-  }
-
-  return fallback
-}
-
-function encryptDesktopSecret(value, safeStorageApi) {
-  const raw = String(value || '')
-
-  if (!raw) {
-    return null
-  }
-
-  let encryptionAvailable = false
-
-  try {
-    encryptionAvailable = Boolean(safeStorageApi?.isEncryptionAvailable?.())
-  } catch {
-    encryptionAvailable = false
-  }
-
-  if (!encryptionAvailable) {
-    throw new Error(
-      'Secure token storage is unavailable, so Hermes Desktop cannot save remote gateway tokens. ' +
-        'Set HERMES_DESKTOP_REMOTE_URL and HERMES_DESKTOP_REMOTE_TOKEN in your environment, or enable OS keychain access and try again.'
-    )
-  }
-
-  try {
-    return {
-      encoding: 'safeStorage',
-      value: safeStorageApi.encryptString(raw).toString('base64')
-    }
-  } catch (error) {
-    const detail = error instanceof Error && error.message ? ` (${error.message})` : ''
-    throw new Error(
-      `Failed to encrypt the remote gateway token for secure storage${detail}. ` +
-        'Set HERMES_DESKTOP_REMOTE_URL and HERMES_DESKTOP_REMOTE_TOKEN in your environment as a fallback.'
-    )
-  }
-}
-
-function sensitiveFileBlockReason(filePath) {
-  const normalized = String(filePath || '')
-    .replace(/\\/g, '/')
-    .toLowerCase()
-  const basename = path.basename(normalized)
-  const ext = path.extname(basename)
-
-  if (!basename) {
-    return null
-  }
-
-  if (normalized.includes('/.ssh/')) {
-    return 'SSH key/config files are blocked.'
-  }
-
-  if (normalized.includes('/.gnupg/')) {
-    return 'GPG key material is blocked.'
-  }
-
-  if (normalized.endsWith('/.aws/credentials')) {
-    return 'AWS credential files are blocked.'
-  }
-
-  if (basename === '.env') {
-    return '.env files are blocked because they commonly contain secrets.'
-  }
-
-  if (basename.startsWith('.env.')) {
-    const suffix = basename.slice('.env.'.length)
-    if (!SAFE_ENV_SUFFIXES.has(suffix)) {
-      return `${basename} is blocked because it appears to contain environment secrets.`
-    }
-  }
-
-  if (/^id_(rsa|dsa|ecdsa|ed25519)(?:\..+)?$/.test(basename) && !basename.endsWith('.pub')) {
-    return 'SSH private key files are blocked.'
-  }
-
-  if (SENSITIVE_EXTENSIONS.has(ext)) {
-    return `${ext} key/certificate files are blocked.`
-  }
-
-  if (basename === '.npmrc' || basename === '.netrc' || basename === '.pypirc') {
-    return `${basename} is blocked because it may include auth credentials.`
-  }
-
-  return null
-}
-
-function resolveRequestedFilePath(filePath, baseDir = process.cwd(), purpose = 'File read') {
-  const raw = String(filePath || '').trim()
-
-  if (!raw) {
-    throw new Error(`${purpose} failed: file path is required.`)
-  }
-
-  if (raw.includes('\0')) {
-    throw new Error(`${purpose} failed: file path is invalid.`)
-  }
-
-  if (/^file:/i.test(raw)) {
-    try {
-      return fileURLToPath(raw)
-    } catch {
-      throw new Error(`${purpose} failed: file URL is invalid.`)
-    }
-  }
-
-  const resolvedBase = path.resolve(String(baseDir || process.cwd()))
-  return path.resolve(resolvedBase, raw)
-}
-
-async function resolveReadableFileForIpc(filePath, options = {}) {
-  const purpose = String(options.purpose || 'File read')
-  const resolvedPath = resolveRequestedFilePath(filePath, options.baseDir, purpose)
-
-  if (options.blockSensitive !== false) {
-    const blockReason = sensitiveFileBlockReason(resolvedPath)
-    if (blockReason) {
-      throw new Error(`${purpose} blocked for sensitive file: ${blockReason}`)
-    }
-  }
-
-  let stat
-  try {
-    stat = await fs.promises.stat(resolvedPath)
-  } catch (error) {
-    const code = error && typeof error === 'object' ? error.code : ''
-    if (code === 'ENOENT' || code === 'ENOTDIR') {
-      throw new Error(`${purpose} failed: file does not exist.`)
-    }
-    throw new Error(`${purpose} failed: ${error instanceof Error ? error.message : String(error)}`)
-  }
-
-  if (stat.isDirectory()) {
-    throw new Error(`${purpose} failed: path points to a directory.`)
-  }
-
-  if (!stat.isFile()) {
-    throw new Error(`${purpose} failed: only regular files can be read.`)
-  }
-
-  const maxBytes = Number.isFinite(options.maxBytes) && Number(options.maxBytes) > 0 ? Number(options.maxBytes) : null
-  if (maxBytes && stat.size > maxBytes) {
-    throw new Error(`${purpose} failed: file is too large (${stat.size} bytes; limit ${maxBytes} bytes).`)
-  }
-
-  try {
-    await fs.promises.access(resolvedPath, fs.constants.R_OK)
-  } catch {
-    throw new Error(`${purpose} failed: file is not readable.`)
-  }
-
-  return { resolvedPath, stat }
-}
-
-module.exports = {
-  DATA_URL_READ_MAX_BYTES,
-  DEFAULT_FETCH_TIMEOUT_MS,
-  TEXT_PREVIEW_SOURCE_MAX_BYTES,
-  encryptDesktopSecret,
-  resolveReadableFileForIpc,
-  resolveTimeoutMs,
-  sensitiveFileBlockReason
-}

apps/desktop/electron/hardening.test.cjs

@@ -1,116 +0,0 @@
-const assert = require('node:assert/strict')
-const fs = require('node:fs')
-const os = require('node:os')
-const path = require('node:path')
-const test = require('node:test')
-const { pathToFileURL } = require('node:url')
-
-const {
-  DEFAULT_FETCH_TIMEOUT_MS,
-  encryptDesktopSecret,
-  resolveReadableFileForIpc,
-  resolveTimeoutMs,
-  sensitiveFileBlockReason
-} = require('./hardening.cjs')
-
-test('resolveTimeoutMs falls back to defaults and accepts overrides', () => {
-  assert.equal(resolveTimeoutMs(undefined), DEFAULT_FETCH_TIMEOUT_MS)
-  assert.equal(resolveTimeoutMs(0), DEFAULT_FETCH_TIMEOUT_MS)
-  assert.equal(resolveTimeoutMs(-25), DEFAULT_FETCH_TIMEOUT_MS)
-  assert.equal(resolveTimeoutMs('2750'), 2750)
-})
-
-test('encryptDesktopSecret requires available secure storage', () => {
-  assert.equal(
-    encryptDesktopSecret('', { isEncryptionAvailable: () => true, encryptString: () => Buffer.alloc(0) }),
-    null
-  )
-
-  assert.throws(
-    () => encryptDesktopSecret('token', { isEncryptionAvailable: () => false, encryptString: () => Buffer.alloc(0) }),
-    /Secure token storage is unavailable/
-  )
-})
-
-test('encryptDesktopSecret stores safeStorage base64 payload', () => {
-  const secret = encryptDesktopSecret('token-123', {
-    isEncryptionAvailable: () => true,
-    encryptString: value => Buffer.from(`enc:${value}`, 'utf8')
-  })
-
-  assert.deepEqual(secret, {
-    encoding: 'safeStorage',
-    value: Buffer.from('enc:token-123', 'utf8').toString('base64')
-  })
-})
-
-test('sensitiveFileBlockReason blocks obvious secret file patterns', () => {
-  assert.match(String(sensitiveFileBlockReason('/tmp/.env')), /\.env/)
-  assert.equal(sensitiveFileBlockReason('/tmp/.env.example'), null)
-  assert.match(String(sensitiveFileBlockReason('/Users/me/.ssh/id_ed25519')), /SSH/)
-  assert.match(String(sensitiveFileBlockReason('/tmp/server-cert.pem')), /\.pem/)
-})
-
-test('resolveReadableFileForIpc validates existence type size and sensitivity', async t => {
-  const tempDir = fs.mkdtempSync(path.join(os.tmpdir(), 'hermes-desktop-hardening-'))
-  t.after(() => fs.rmSync(tempDir, { recursive: true, force: true }))
-
-  const textPath = path.join(tempDir, 'notes.txt')
-  fs.writeFileSync(textPath, 'hello world', 'utf8')
-
-  const fromRelative = await resolveReadableFileForIpc('notes.txt', {
-    baseDir: tempDir,
-    maxBytes: 256,
-    purpose: 'File preview'
-  })
-  assert.equal(fromRelative.resolvedPath, textPath)
-  assert.equal(fromRelative.stat.size, 11)
-
-  const fromFileUrl = await resolveReadableFileForIpc(pathToFileURL(textPath).toString(), {
-    purpose: 'File preview'
-  })
-  assert.equal(fromFileUrl.resolvedPath, textPath)
-
-  await assert.rejects(
-    resolveReadableFileForIpc('missing.txt', {
-      baseDir: tempDir,
-      purpose: 'Text preview'
-    }),
-    /file does not exist/
-  )
-
-  const nestedDir = path.join(tempDir, 'directory')
-  fs.mkdirSync(nestedDir)
-  await assert.rejects(
-    resolveReadableFileForIpc(nestedDir, {
-      purpose: 'Text preview'
-    }),
-    /path points to a directory/
-  )
-
-  const largePath = path.join(tempDir, 'large.txt')
-  fs.writeFileSync(largePath, 'x'.repeat(40), 'utf8')
-  await assert.rejects(
-    resolveReadableFileForIpc(largePath, {
-      maxBytes: 8,
-      purpose: 'File preview'
-    }),
-    /file is too large/
-  )
-
-  const envPath = path.join(tempDir, '.env')
-  fs.writeFileSync(envPath, 'SECRET_TOKEN=123', 'utf8')
-  await assert.rejects(
-    resolveReadableFileForIpc(envPath, {
-      purpose: 'File preview'
-    }),
-    /blocked for sensitive file/
-  )
-
-  const envTemplatePath = path.join(tempDir, '.env.example')
-  fs.writeFileSync(envTemplatePath, 'EXAMPLE_TOKEN=value', 'utf8')
-  const envTemplate = await resolveReadableFileForIpc(envTemplatePath, {
-    purpose: 'File preview'
-  })
-  assert.equal(envTemplate.resolvedPath, envTemplatePath)
-})

apps/desktop/electron/preload.cjs

@@ -1,78 +0,0 @@
-const { contextBridge, ipcRenderer, webUtils } = require('electron')
-
-contextBridge.exposeInMainWorld('hermesDesktop', {
-  getConnection: () => ipcRenderer.invoke('hermes:connection'),
-  getBootProgress: () => ipcRenderer.invoke('hermes:boot-progress:get'),
-  getConnectionConfig: () => ipcRenderer.invoke('hermes:connection-config:get'),
-  saveConnectionConfig: payload => ipcRenderer.invoke('hermes:connection-config:save', payload),
-  applyConnectionConfig: payload => ipcRenderer.invoke('hermes:connection-config:apply', payload),
-  testConnectionConfig: payload => ipcRenderer.invoke('hermes:connection-config:test', payload),
-  api: request => ipcRenderer.invoke('hermes:api', request),
-  notify: payload => ipcRenderer.invoke('hermes:notify', payload),
-  requestMicrophoneAccess: () => ipcRenderer.invoke('hermes:requestMicrophoneAccess'),
-  readFileDataUrl: filePath => ipcRenderer.invoke('hermes:readFileDataUrl', filePath),
-  readFileText: filePath => ipcRenderer.invoke('hermes:readFileText', filePath),
-  selectPaths: options => ipcRenderer.invoke('hermes:selectPaths', options),
-  writeClipboard: text => ipcRenderer.invoke('hermes:writeClipboard', text),
-  saveImageFromUrl: url => ipcRenderer.invoke('hermes:saveImageFromUrl', url),
-  saveImageBuffer: (data, ext) => ipcRenderer.invoke('hermes:saveImageBuffer', { data, ext }),
-  saveClipboardImage: () => ipcRenderer.invoke('hermes:saveClipboardImage'),
-  getPathForFile: file => {
-    try {
-      return webUtils.getPathForFile(file) || ''
-    } catch {
-      return ''
-    }
-  },
-  normalizePreviewTarget: (target, baseDir) => ipcRenderer.invoke('hermes:normalizePreviewTarget', target, baseDir),
-  watchPreviewFile: url => ipcRenderer.invoke('hermes:watchPreviewFile', url),
-  stopPreviewFileWatch: id => ipcRenderer.invoke('hermes:stopPreviewFileWatch', id),
-  setTitleBarTheme: payload => ipcRenderer.send('hermes:titlebar-theme', payload),
-  setPreviewShortcutActive: active => ipcRenderer.send('hermes:previewShortcutActive', Boolean(active)),
-  openExternal: url => ipcRenderer.invoke('hermes:openExternal', url),
-  fetchLinkTitle: url => ipcRenderer.invoke('hermes:fetchLinkTitle', url),
-  readDir: dirPath => ipcRenderer.invoke('hermes:fs:readDir', dirPath),
-  gitRoot: startPath => ipcRenderer.invoke('hermes:fs:gitRoot', startPath),
-  onClosePreviewRequested: callback => {
-    const listener = () => callback()
-    ipcRenderer.on('hermes:close-preview-requested', listener)
-    return () => ipcRenderer.removeListener('hermes:close-preview-requested', listener)
-  },
-  onOpenUpdatesRequested: callback => {
-    const listener = () => callback()
-    ipcRenderer.on('hermes:open-updates', listener)
-    return () => ipcRenderer.removeListener('hermes:open-updates', listener)
-  },
-  onWindowStateChanged: callback => {
-    const listener = (_event, payload) => callback(payload)
-    ipcRenderer.on('hermes:window-state-changed', listener)
-    return () => ipcRenderer.removeListener('hermes:window-state-changed', listener)
-  },
-  onPreviewFileChanged: callback => {
-    const listener = (_event, payload) => callback(payload)
-    ipcRenderer.on('hermes:preview-file-changed', listener)
-    return () => ipcRenderer.removeListener('hermes:preview-file-changed', listener)
-  },
-  onBackendExit: callback => {
-    const listener = (_event, payload) => callback(payload)
-    ipcRenderer.on('hermes:backend-exit', listener)
-    return () => ipcRenderer.removeListener('hermes:backend-exit', listener)
-  },
-  onBootProgress: callback => {
-    const listener = (_event, payload) => callback(payload)
-    ipcRenderer.on('hermes:boot-progress', listener)
-    return () => ipcRenderer.removeListener('hermes:boot-progress', listener)
-  },
-  getVersion: () => ipcRenderer.invoke('hermes:version'),
-  updates: {
-    check: () => ipcRenderer.invoke('hermes:updates:check'),
-    apply: opts => ipcRenderer.invoke('hermes:updates:apply', opts),
-    getBranch: () => ipcRenderer.invoke('hermes:updates:branch:get'),
-    setBranch: name => ipcRenderer.invoke('hermes:updates:branch:set', name),
-    onProgress: callback => {
-      const listener = (_event, payload) => callback(payload)
-      ipcRenderer.on('hermes:updates:progress', listener)
-      return () => ipcRenderer.removeListener('hermes:updates:progress', listener)
-    }
-  }
-})

apps/desktop/eslint.config.mjs

@@ -1,122 +0,0 @@
-import js from '@eslint/js'
-import typescriptEslint from '@typescript-eslint/eslint-plugin'
-import typescriptParser from '@typescript-eslint/parser'
-import perfectionist from 'eslint-plugin-perfectionist'
-import reactPlugin from 'eslint-plugin-react'
-import reactCompiler from 'eslint-plugin-react-compiler'
-import hooksPlugin from 'eslint-plugin-react-hooks'
-import unusedImports from 'eslint-plugin-unused-imports'
-import globals from 'globals'
-
-const noopRule = {
-  meta: { schema: [], type: 'problem' },
-  create: () => ({})
-}
-
-const customRules = {
-  rules: {
-    'no-process-cwd': noopRule,
-    'no-process-env-top-level': noopRule,
-    'no-sync-fs': noopRule,
-    'no-top-level-dynamic-import': noopRule,
-    'no-top-level-side-effects': noopRule
-  }
-}
-
-export default [
-  {
-    ignores: ['**/node_modules/**', '**/dist/**', 'src/**/*.js']
-  },
-  js.configs.recommended,
-  {
-    files: ['**/*.{ts,tsx}'],
-    languageOptions: {
-      globals: {
-        ...globals.browser,
-        ...globals.node
-      },
-      parser: typescriptParser,
-      parserOptions: {
-        ecmaFeatures: { jsx: true },
-        ecmaVersion: 'latest',
-        sourceType: 'module'
-      }
-    },
-    plugins: {
-      '@typescript-eslint': typescriptEslint,
-      'custom-rules': customRules,
-      perfectionist,
-      react: reactPlugin,
-      'react-compiler': reactCompiler,
-      'react-hooks': hooksPlugin,
-      'unused-imports': unusedImports
-    },
-    rules: {
-      '@typescript-eslint/consistent-type-imports': ['error', { prefer: 'type-imports' }],
-      '@typescript-eslint/no-unused-vars': 'off',
-      curly: ['error', 'all'],
-      'no-fallthrough': ['error', { allowEmptyCase: true }],
-      'no-undef': 'off',
-      'no-unused-vars': 'off',
-      'padding-line-between-statements': [
-        1,
-        {
-          blankLine: 'always',
-          next: [
-            'block-like',
-            'block',
-            'return',
-            'if',
-            'class',
-            'continue',
-            'debugger',
-            'break',
-            'multiline-const',
-            'multiline-let'
-          ],
-          prev: '*'
-        },
-        {
-          blankLine: 'always',
-          next: '*',
-          prev: ['case', 'default', 'multiline-const', 'multiline-let', 'multiline-block-like']
-        },
-        { blankLine: 'never', next: ['block', 'block-like'], prev: ['case', 'default'] },
-        { blankLine: 'always', next: ['block', 'block-like'], prev: ['block', 'block-like'] },
-        { blankLine: 'always', next: ['empty'], prev: 'export' },
-        { blankLine: 'never', next: 'iife', prev: ['block', 'block-like', 'empty'] }
-      ],
-      'perfectionist/sort-exports': ['error', { order: 'asc', type: 'natural' }],
-      'perfectionist/sort-imports': [
-        'error',
-        {
-          groups: ['side-effect', 'builtin', 'external', 'internal', 'parent', 'sibling', 'index'],
-          order: 'asc',
-          type: 'natural'
-        }
-      ],
-      'perfectionist/sort-jsx-props': ['error', { order: 'asc', type: 'natural' }],
-      'perfectionist/sort-named-exports': ['error', { order: 'asc', type: 'natural' }],
-      'perfectionist/sort-named-imports': ['error', { order: 'asc', type: 'natural' }],
-      'react-compiler/react-compiler': 'warn',
-      'react-hooks/exhaustive-deps': 'warn',
-      'react-hooks/rules-of-hooks': 'error',
-      'unused-imports/no-unused-imports': 'error'
-    },
-    settings: {
-      react: { version: 'detect' }
-    }
-  },
-  {
-    files: ['**/*.js', '**/*.cjs'],
-    ignores: ['**/node_modules/**', '**/dist/**'],
-    languageOptions: {
-      ecmaVersion: 'latest',
-      globals: { ...globals.node },
-      sourceType: 'commonjs'
-    }
-  },
-  {
-    ignores: ['*.config.*']
-  }
-]

apps/desktop/index.html

@@ -1,14 +0,0 @@
-<!doctype html>
-<html lang="en">
-  <head>
-    <meta charset="UTF-8" />
-    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-    <link rel="icon" href="/apple-touch-icon.png" />
-    <link rel="apple-touch-icon" href="/apple-touch-icon.png" />
-    <title>Hermes</title>
-  </head>
-  <body>
-    <div id="root" class="scrollbar-dt"></div>
-    <script type="module" src="/src/main.tsx"></script>
-  </body>
-</html>

apps/desktop/installer/prereq-check.nsh

@@ -1,813 +0,0 @@
-; ============================================================================
-; Hermes Desktop installer — prerequisite detection page
-; ============================================================================
-;
-; A native NSIS Wizard page (using nsDialogs) inserted between the directory
-; selection page and the install-files page. Detects the baseline runtime
-; prerequisites (Python 3.11-3.13, Node.js 20+, and Git for Windows); offers to
-; install missing items via winget.
-;
-; Page sequence:
-;   Welcome → Directory → [PrereqPage] → InstFiles → Finish
-;
-; Hooks used:
-;   customInit               — open $TEMP\Hermes-Installer.log for diagnostics
-;   customPageAfterChangeDir — page declaration (electron-builder's hook for
-;                              inserting a page between Directory and InstFiles)
-;   customInstall            — execute winget for any prereqs the user
-;                              checked on the page; close the log file
-;
-; Diagnostics:
-;   $TEMP\Hermes-Installer.log captures every detection probe (command,
-;   exit code, captured output), the user's checkbox choices, and full
-;   winget stdout/stderr for Python installs. Node.js and Git installs go via
-;   ExecShellWait so UAC comes forward; for those we log start/end plus a
-;   post-install filesystem probe. Users hitting bugs should attach this file.
-;
-; The Function declarations live at top-level in this file so they're parsed
-; at include time; the customPageAfterChangeDir macro references them via
-; the Page directive so the optimizer doesn't strip them.
-;
-; UAC behavior:
-;   Python: --scope user, no UAC.
-;   Node.js: winget-managed install; installer package may request elevation.
-;   Git for Windows: winget-managed install; may request elevation.
-;
-; Detection:
-;   Python: try `py -3.11`/`-3.12`/`-3.13`. The Python launcher
-;     returns exit 0 only when that specific version is installed. The
-;     Microsoft Store "Python stub" doesn't install py.exe, so users with
-;     only the stub get correctly classified as not-installed.
-;   Node.js: require a modern Node (major >= 20). Check PATH first, then the
-;     Hermes-managed %LOCALAPPDATA%\hermes\node\node.exe if present.
-;   Git: check known Git Bash locations for Git for Windows / Hermes-managed Git.
-;   winget: `where winget` returns exit 0 on Win11 / Win10 1809+ with App
-;     Installer. If unavailable, the page shows manual download URLs.
-;
-; Required vs. recommended:
-;   Python, Node.js, and Git Bash are baseline dependencies. The GUI handles the
-;   Hermes source payload, virtualenv, and Python dependency install on first
-;   launch.
-;
-; Skip behaviors:
-;   - All three already detected → page is auto-skipped via Abort
-;   - Silent install (/S) → customInstall winget block skips
-;   - User unchecks all checkboxes → page advances without running winget
-; ============================================================================
-
-!include "LogicLib.nsh"
-!include "nsDialogs.nsh"
-!include "WinMessages.nsh"
-!include "FileFunc.nsh"
-
-Var HermesDialog
-Var HermesPyStatusLabel
-Var HermesPyCheckbox
-Var HermesNodeStatusLabel
-Var HermesNodeCheckbox
-Var HermesGitBashStatusLabel
-Var HermesGitBashCheckbox
-Var HermesFooterLabel
-Var HermesHasWinget
-Var HermesHasPython
-Var HermesHasNode
-Var HermesHasGitBash
-Var HermesInstallPython
-Var HermesInstallNode
-Var HermesInstallGitBash
-Var HermesLogHandle
-Var HermesLogPath
-
-; ----------------------------------------------------------------------------
-; Installer logging
-; ----------------------------------------------------------------------------
-; We write a structured log to $TEMP\Hermes-Installer.log so users can attach
-; it to bug reports when prereq detection or winget installs misbehave.
-;
-; Why this design:
-;   - The wizard's built-in Details panel only exists at runtime; once the
-;     user clicks Finish (or Cancel) it's gone. The file persists.
-;   - NSIS's built-in `LogSet on` / `LogText` requires the "advanced logging"
-;     build of makensis (NSIS_CONFIG_LOG=1), which electron-builder's bundled
-;     binary doesn't include. So we roll our own with FileWrite.
-;   - Python's winget invocation streams stdout/stderr into the log via
-;     nsExec::ExecToStack. Node.js and Git use ExecShellWait instead because
-;     their installers may elevate; this keeps UAC in front of the wizard.
-;   - Detection probes also log exit codes + captured output, so when a user
-;     reports "the page said Python isn't installed but I have it", we can
-;     see exactly which probes ran and what they returned.
-;   - File is opened (truncate mode) in customInit and explicitly closed at
-;     the end of customInstall. If the installer crashes or the user
-;     cancels before customInstall completes, the file remains on disk —
-;     whatever we wrote up to that point survives. FileWrite per-line is a
-;     normal Windows I/O call that hits the kernel buffer cache; the OS
-;     flushes that buffer when the process exits, so even on hard cancel
-;     the user can attach a partial log.
-;
-; Macros:
-;   ${HermesLog} "free-form text"          — emit a timestamped line
-;   ${HermesLogKV} "key" "value"           — emit a "key = value" line
-;   ${HermesLogBlock} "label" "varname"    — emit a delimited block (no `$`)
-;
-; The macros are no-ops when $HermesLogHandle is empty (e.g. if FileOpen
-; failed because $TEMP was unwritable — rare but defensive).
-; ----------------------------------------------------------------------------
-!macro _HermesLogRaw Line
-  ${If} $HermesLogHandle != ""
-    FileWrite $HermesLogHandle "${Line}$\r$\n"
-  ${EndIf}
-!macroend
-
-!macro _HermesLogTimestamped Msg
-  ; ${__TIMESTAMP__} is the BUILD-time stamp, not runtime. We want runtime,
-  ; so use ${GetTime} from FileFunc.nsh. $R0..$R6 = day, month, year, dow,
-  ; hour, minute, second. Stash callers' $R0–$R6 first.
-  Push $R0
-  Push $R1
-  Push $R2
-  Push $R3
-  Push $R4
-  Push $R5
-  Push $R6
-  ${GetTime} "" "L" $R0 $R1 $R2 $R3 $R4 $R5 $R6
-  ${If} $HermesLogHandle != ""
-    FileWrite $HermesLogHandle "[$R2-$R1-$R0 $R4:$R5:$R6] ${Msg}$\r$\n"
-  ${EndIf}
-  Pop $R6
-  Pop $R5
-  Pop $R4
-  Pop $R3
-  Pop $R2
-  Pop $R1
-  Pop $R0
-!macroend
-!define HermesLog "!insertmacro _HermesLogTimestamped"
-
-!macro _HermesLogKV Key Value
-  ${HermesLog} "${Key} = ${Value}"
-!macroend
-!define HermesLogKV "!insertmacro _HermesLogKV"
-
-; HermesLogBlock — write a multi-line block (typically captured command
-; output) with a "--- begin/end ---" frame so it's clear in the log where
-; the captured payload starts and stops. The `Payload` parameter is the
-; NSIS variable name (without `$`) holding the captured string.
-!macro _HermesLogBlock Label PayloadVar
-  ${HermesLog} "--- begin ${Label} ---"
-  !insertmacro _HermesLogRaw "$${PayloadVar}"
-  ${HermesLog} "--- end ${Label} ---"
-!macroend
-!define HermesLogBlock "!insertmacro _HermesLogBlock"
-
-
-; ----------------------------------------------------------------------------
-; HermesDetectPythonViaRegistry — sets $HermesHasPython="1" if a PEP 514
-; entry exists for any of the supported Python versions. Reads HKLM
-; (system-wide installs) then HKCU (per-user installs). Vendor "PythonCore"
-; covers official python.org distributions; "ContinuumAnalytics" covers
-; Anaconda/Miniconda. We don't enumerate other vendors because they're
-; rare in our user base and we'd rather miss them and let winget add a
-; second Python than misclassify something else as a working Python.
-; ----------------------------------------------------------------------------
-Function HermesDetectPythonViaRegistry
-  Push $1
-  Push $2
-
-  ${HermesLog} "registry: scanning HKLM/HKCU SOFTWARE\Python\PythonCore for 3.11/3.12/3.13"
-
-  ; Set view to 64-bit on x64 systems so we read the right hive — the
-  ; default 32-bit view would miss a 64-bit Python install on 64-bit
-  ; Windows. SetRegView 32 restored at function exit.
-  SetRegView 64
-
-  ; Iterate the supported versions. Each is its own ReadRegStr — NSIS
-  ; doesn't have loops over arrays inside functions easily, and four
-  ; copies is clearer than gymnastics with $R0-$R9.
-  ReadRegStr $1 HKLM "SOFTWARE\Python\PythonCore\3.11\InstallPath" ""
-  ${If} $1 != ""
-    ${HermesLog} "  hit: HKLM\Python\PythonCore\3.11\InstallPath = $1"
-    StrCpy $HermesHasPython "1"
-    Goto hermes_py_reg_done
-  ${EndIf}
-  ReadRegStr $1 HKLM "SOFTWARE\Python\PythonCore\3.12\InstallPath" ""
-  ${If} $1 != ""
-    ${HermesLog} "  hit: HKLM\Python\PythonCore\3.12\InstallPath = $1"
-    StrCpy $HermesHasPython "1"
-    Goto hermes_py_reg_done
-  ${EndIf}
-  ReadRegStr $1 HKLM "SOFTWARE\Python\PythonCore\3.13\InstallPath" ""
-  ${If} $1 != ""
-    ${HermesLog} "  hit: HKLM\Python\PythonCore\3.13\InstallPath = $1"
-    StrCpy $HermesHasPython "1"
-    Goto hermes_py_reg_done
-  ${EndIf}
-
-  ReadRegStr $1 HKCU "SOFTWARE\Python\PythonCore\3.11\InstallPath" ""
-  ${If} $1 != ""
-    ${HermesLog} "  hit: HKCU\Python\PythonCore\3.11\InstallPath = $1"
-    StrCpy $HermesHasPython "1"
-    Goto hermes_py_reg_done
-  ${EndIf}
-  ReadRegStr $1 HKCU "SOFTWARE\Python\PythonCore\3.12\InstallPath" ""
-  ${If} $1 != ""
-    ${HermesLog} "  hit: HKCU\Python\PythonCore\3.12\InstallPath = $1"
-    StrCpy $HermesHasPython "1"
-    Goto hermes_py_reg_done
-  ${EndIf}
-  ReadRegStr $1 HKCU "SOFTWARE\Python\PythonCore\3.13\InstallPath" ""
-  ${If} $1 != ""
-    ${HermesLog} "  hit: HKCU\Python\PythonCore\3.13\InstallPath = $1"
-    StrCpy $HermesHasPython "1"
-    Goto hermes_py_reg_done
-  ${EndIf}
-
-  ${HermesLog} "  no registry keys matched"
-
-hermes_py_reg_done:
-  SetRegView 32
-  Pop $2
-  Pop $1
-FunctionEnd
-
-; ----------------------------------------------------------------------------
-; HermesDetectPythonViaFilesystem — sets $HermesHasPython="1" if a Python
-; install exists at one of the standard locations. FileExists never runs
-; the binary so this is safe even if the user has the MS Store stub on
-; their PATH. We probe both system-wide (Program Files) and per-user
-; (LocalAppData\Programs) install locations for versions 3.11–3.13.
-; ----------------------------------------------------------------------------
-Function HermesDetectPythonViaFilesystem
-  ${HermesLog} "filesystem: probing standard Python install paths"
-
-  ; System-wide installs (default location for python.org with admin)
-  ${If} ${FileExists} "$PROGRAMFILES64\Python311\python.exe"
-    ${HermesLog} "  hit: $PROGRAMFILES64\Python311\python.exe"
-    StrCpy $HermesHasPython "1"
-    Return
-  ${EndIf}
-  ${If} ${FileExists} "$PROGRAMFILES64\Python312\python.exe"
-    ${HermesLog} "  hit: $PROGRAMFILES64\Python312\python.exe"
-    StrCpy $HermesHasPython "1"
-    Return
-  ${EndIf}
-  ${If} ${FileExists} "$PROGRAMFILES64\Python313\python.exe"
-    ${HermesLog} "  hit: $PROGRAMFILES64\Python313\python.exe"
-    StrCpy $HermesHasPython "1"
-    Return
-  ${EndIf}
-
-  ; Per-user installs (default location for python.org without admin
-  ; or with "Install for me only"). Covers the user-reported case.
-  ${If} ${FileExists} "$LOCALAPPDATA\Programs\Python\Python311\python.exe"
-    ${HermesLog} "  hit: $LOCALAPPDATA\Programs\Python\Python311\python.exe"
-    StrCpy $HermesHasPython "1"
-    Return
-  ${EndIf}
-  ${If} ${FileExists} "$LOCALAPPDATA\Programs\Python\Python312\python.exe"
-    ${HermesLog} "  hit: $LOCALAPPDATA\Programs\Python\Python312\python.exe"
-    StrCpy $HermesHasPython "1"
-    Return
-  ${EndIf}
-  ${If} ${FileExists} "$LOCALAPPDATA\Programs\Python\Python313\python.exe"
-    ${HermesLog} "  hit: $LOCALAPPDATA\Programs\Python\Python313\python.exe"
-    StrCpy $HermesHasPython "1"
-    Return
-  ${EndIf}
-
-  ${HermesLog} "  no filesystem paths matched"
-FunctionEnd
-
-; ----------------------------------------------------------------------------
-; HermesProbe — small wrapper around nsExec::ExecToStack that captures both
-; exit code and stdout/stderr into a single log entry. Used instead of bare
-; nsExec::Exec so we have evidence for "the page said X isn't installed but
-; I have it" bug reports.
-;
-; Caller pushes command string onto the stack before Call.
-; On return:
-;   $0 = exit code (0 = success on Windows)
-;   $1 = captured stdout+stderr (truncated by NSIS to ~64KB)
-; Caller's $0/$1 are clobbered; $9 is preserved.
-; ----------------------------------------------------------------------------
-Function HermesProbe
-  ; Stack on entry (top → bottom): <command>, <caller-return-addr>, ...
-  ; Save $9 so we can use it as a local. Standard NSIS stack-arg idiom:
-  ;   Exch $9   ; $9 = arg, old $9 pushed onto stack
-  ;   ... work ...
-  ;   Pop $9    ; restore old $9 (discards arg)
-  Exch $9
-  nsExec::ExecToStack '$9'
-  Pop $0    ; exit code
-  Pop $1    ; captured output
-  ${HermesLog} "probe: $9"
-  ${HermesLog} "  exit = $0"
-  ${If} $1 != ""
-    ${HermesLogBlock} "probe output" "1"
-  ${EndIf}
-  Pop $9    ; restore caller's $9 (discards the command arg)
-FunctionEnd
-
-; ----------------------------------------------------------------------------
-; HermesDetectPrereqs — populates $HermesHasWinget / $HermesHasPython /
-; $HermesHasNode / $HermesHasGitBash with "0" or "1". Called from the
-; page-create function. Every probe is logged via HermesProbe.
-; ----------------------------------------------------------------------------
-Function HermesDetectPrereqs
-  ${HermesLog} "=== HermesDetectPrereqs: begin ==="
-
-  ; --- winget ---
-  Push 'cmd.exe /c where winget'
-  Call HermesProbe
-  ${If} $0 == 0
-    StrCpy $HermesHasWinget "1"
-  ${Else}
-    StrCpy $HermesHasWinget "0"
-  ${EndIf}
-  ${HermesLogKV} "HermesHasWinget" "$HermesHasWinget"
-
-  ; --- Python 3.11 / 3.12 / 3.13 ---
-  ; We deliberately accept 3.11–3.13 only and NOT 3.14, because some of
-  ; Hermes' transitive deps (notably pywinpty, which carries Rust crates
-  ; like windows_x86_64_msvc) don't yet publish 3.14 wheels. Without
-  ; wheels, `pip install -e .` falls back to building from sdist, which
-  ; needs a Rust toolchain. Users without one see a confusing "could
-  ; not compile windows_x86_64_msvc build script" error. install.ps1
-  ; sidesteps this by pinning to 3.11 via uv; the desktop installer
-  ; can't easily install uv in the same flow yet, so we just refuse to
-  ; accept 3.14 as "good" and offer 3.11 via winget instead. Revisit
-  ; when 3.14 wheels are widely available across our dep tree.
-  ;
-  ; Detection strategy, in order from most-precise to least-precise.
-  ; Each step uses ONLY operations that don't execute `python.exe`
-  ; directly off PATH — running `python` on Windows can open the
-  ; Microsoft Store if only the "Python stub" is installed, which is
-  ; terrible UX during an installer. We avoid that by:
-  ;   (a) launcher checks (py.exe runs no python until -V),
-  ;   (b) registry reads (PEP 514, no execution at all),
-  ;   (c) filesystem probes via FileExists.
-  StrCpy $HermesHasPython "0"
-
-  ; (1) The py launcher. Ships with python.org installer when
-  ;     "Install launcher for all users" is checked (default for some
-  ;     paths, not for per-user installs without elevation). When
-  ;     present, py -3.X --version returns 0 iff that version exists.
-  Push 'cmd.exe /c py -3.11 --version'
-  Call HermesProbe
-  ${If} $0 == 0
-    StrCpy $HermesHasPython "1"
-  ${Else}
-    Push 'cmd.exe /c py -3.12 --version'
-    Call HermesProbe
-    ${If} $0 == 0
-      StrCpy $HermesHasPython "1"
-    ${Else}
-      Push 'cmd.exe /c py -3.13 --version'
-      Call HermesProbe
-      ${If} $0 == 0
-        StrCpy $HermesHasPython "1"
-      ${EndIf}
-    ${EndIf}
-  ${EndIf}
-  ${HermesLogKV} "after py-launcher probes, HermesHasPython" "$HermesHasPython"
-
-  ; (2) PEP 514 registry probe. Every standards-compliant Python
-  ;     installer registers itself under HKLM or HKCU at
-  ;     SOFTWARE\Python\PythonCore\<version>\InstallPath. The MS Store
-  ;     stub does NOT register here — so we get a clean signal for
-  ;     "real Python is installed" without ever risking the Store
-  ;     popup. Covers the case the user reported: per-user Python.org
-  ;     install without launcher checkbox, plus Anaconda which writes
-  ;     similar keys under a different vendor name.
-  ${If} $HermesHasPython == "0"
-    Call HermesDetectPythonViaRegistry
-    ${HermesLogKV} "after registry probe, HermesHasPython" "$HermesHasPython"
-  ${EndIf}
-
-  ; (3) Filesystem probe of common install locations. Catches edge
-  ;     cases where the installer didn't update the registry (rare
-  ;     but possible with hand-extracted Python or some third-party
-  ;     installers). We only check standard paths — running anything
-  ;     would risk spawning the Store stub.
-  ${If} $HermesHasPython == "0"
-    Call HermesDetectPythonViaFilesystem
-    ${HermesLogKV} "after filesystem probe, HermesHasPython" "$HermesHasPython"
-  ${EndIf}
-
-  ; --- Node.js 20+ ---
-  Push 'cmd.exe /c node -e "process.exit(Number(process.versions.node.split(String.fromCharCode(46))[0]) >= 20 ? 0 : 1)"'
-  Call HermesProbe
-  ${If} $0 == 0
-    StrCpy $HermesHasNode "1"
-  ${ElseIf} ${FileExists} "$LOCALAPPDATA\hermes\node\node.exe"
-    Push '"$LOCALAPPDATA\hermes\node\node.exe" -e "process.exit(Number(process.versions.node.split(String.fromCharCode(46))[0]) >= 20 ? 0 : 1)"'
-    Call HermesProbe
-    ${If} $0 == 0
-      StrCpy $HermesHasNode "1"
-    ${Else}
-      StrCpy $HermesHasNode "0"
-    ${EndIf}
-  ${Else}
-    StrCpy $HermesHasNode "0"
-  ${EndIf}
-  ${HermesLogKV} "HermesHasNode" "$HermesHasNode"
-
-  ; --- Git Bash ---
-  StrCpy $HermesHasGitBash "0"
-  ${If} ${FileExists} "$LOCALAPPDATA\hermes\git\bin\bash.exe"
-    StrCpy $HermesHasGitBash "1"
-  ${ElseIf} ${FileExists} "$LOCALAPPDATA\hermes\git\usr\bin\bash.exe"
-    StrCpy $HermesHasGitBash "1"
-  ${ElseIf} ${FileExists} "$PROGRAMFILES64\Git\bin\bash.exe"
-    StrCpy $HermesHasGitBash "1"
-  ${ElseIf} ${FileExists} "$PROGRAMFILES\Git\bin\bash.exe"
-    StrCpy $HermesHasGitBash "1"
-  ${ElseIf} ${FileExists} "$PROGRAMFILES32\Git\bin\bash.exe"
-    StrCpy $HermesHasGitBash "1"
-  ${ElseIf} ${FileExists} "$LOCALAPPDATA\Programs\Git\bin\bash.exe"
-    StrCpy $HermesHasGitBash "1"
-  ${EndIf}
-  ${HermesLogKV} "HermesHasGitBash" "$HermesHasGitBash"
-
-  ${HermesLog} "=== HermesDetectPrereqs: end ==="
-FunctionEnd
-
-; ----------------------------------------------------------------------------
-; HermesRunWinget — invoke `winget install ...` and capture both exit code
-; and full stdout/stderr to the log. Also replays the captured output to the
-; install Details panel via DetailPrint so the user sees progress (batched
-; at end rather than live — acceptable trade-off; winget installs take 30-90
-; seconds and emit ~10-30 lines).
-;
-; Caller pushes:  <args-after-winget>     (e.g. 'install -e --id Python...')
-;                 <human-name>            (e.g. 'Python 3.11')
-; On return:      $0 = winget exit code, $1 = full captured output
-; ----------------------------------------------------------------------------
-Function HermesRunWinget
-  Exch $9       ; $9 = human-name
-  Exch
-  Exch $8       ; $8 = args
-  Push $2       ; preserve for caller
-
-  ${HermesLog} "winget: invoking for $9"
-  ${HermesLog} "  command: winget $8"
-  DetailPrint "Running: winget $8"
-
-  ; ExecToStack captures up to ~64KB of combined stdout+stderr.
-  ; The 'cmd.exe /c' wrapper ensures we use the user's PATH-resolved winget
-  ; and that I/O redirection works portably.
-  nsExec::ExecToStack 'cmd.exe /c winget $8'
-  Pop $0    ; exit code
-  Pop $1    ; captured output
-
-  ${HermesLog} "  exit code = $0"
-  ${If} $1 != ""
-    ${HermesLogBlock} "winget output ($9)" "1"
-    ; Echo captured output to Details panel so user sees what winget did.
-    ; DetailPrint takes one line; the captured blob may contain $\r$\n. We
-    ; pass it whole — DetailPrint handles embedded newlines reasonably.
-    DetailPrint "$1"
-  ${EndIf}
-
-  Pop $2
-  Pop $8
-  Pop $9
-FunctionEnd
-
-; ----------------------------------------------------------------------------
-; HermesPrereqPageCreate — builds the prereq page UI. If all items are
-; already installed we Abort, which causes NSIS to skip directly to the next
-; page in the sequence (InstFiles).
-; ----------------------------------------------------------------------------
-Function HermesPrereqPageCreate
-  Call HermesDetectPrereqs
-
-  ${If} $HermesHasPython == "1"
-  ${AndIf} $HermesHasNode == "1"
-  ${AndIf} $HermesHasGitBash == "1"
-    ${HermesLog} "page: all prereqs detected, auto-skipping prereq page"
-    Abort
-  ${EndIf}
-
-  ${HermesLog} "page: rendering prereq page (winget=$HermesHasWinget python=$HermesHasPython node=$HermesHasNode git_bash=$HermesHasGitBash)"
-
-  ; Set the wizard's standard header (top blue/gradient bar). 1037 is the
-  ; title control, 1038 is the subtitle. Without this, the header still
-  ; reads "Choose Install Location" left over from the Directory page.
-  GetDlgItem $0 $HWNDPARENT 1037
-  SendMessage $0 ${WM_SETTEXT} 0 "STR:System Requirements"
-  GetDlgItem $0 $HWNDPARENT 1038
-  SendMessage $0 ${WM_SETTEXT} 0 "STR:Install baseline runtime dependencies before the GUI finishes Hermes setup."
-
-  nsDialogs::Create 1018
-  Pop $HermesDialog
-  ${If} $HermesDialog == error
-    Abort
-  ${EndIf}
-
-  StrCpy $HermesInstallPython "0"
-  StrCpy $HermesInstallNode "0"
-  StrCpy $HermesInstallGitBash "0"
-
-  ; Page body intro. The wizard's header (set above) shows the title
-  ; "System Requirements" and subtitle, so we don't repeat them here.
-  ${If} $HermesHasWinget == "1"
-    ${NSD_CreateLabel} 0u 0u 100% 16u "Detected items are listed below. Missing items can be installed automatically via winget."
-  ${Else}
-    ${NSD_CreateLabel} 0u 0u 100% 16u "Detected items are listed below. Continue setup, then install missing items manually."
-  ${EndIf}
-  Pop $0
-
-  ; --- Python panel ---
-  ${NSD_CreateGroupBox} 0u 18u 100% 30u "Python 3.11-3.13"
-  Pop $0
-  ${If} $HermesHasPython == "1"
-    ${NSD_CreateLabel} 8u 28u 95% 10u "Detected on your system."
-    Pop $HermesPyStatusLabel
-  ${Else}
-    ${If} $HermesHasWinget == "1"
-      ${NSD_CreateLabel} 8u 27u 95% 9u "Not detected."
-      Pop $HermesPyStatusLabel
-      ${NSD_CreateCheckbox} 8u 37u 95% 9u "Install Python 3.11"
-      Pop $HermesPyCheckbox
-      ${NSD_Check} $HermesPyCheckbox
-    ${Else}
-      ${NSD_CreateLabel} 8u 27u 95% 14u "Not detected. Install manually from https://www.python.org/downloads/, then relaunch Hermes."
-      Pop $HermesPyStatusLabel
-    ${EndIf}
-  ${EndIf}
-
-  ; --- Node.js panel ---
-  ${NSD_CreateGroupBox} 0u 50u 100% 30u "Node.js 20+ LTS"
-  Pop $0
-  ${If} $HermesHasNode == "1"
-    ${NSD_CreateLabel} 8u 60u 95% 10u "Detected on your system."
-    Pop $HermesNodeStatusLabel
-  ${Else}
-    ${If} $HermesHasWinget == "1"
-      ${NSD_CreateLabel} 8u 59u 95% 9u "Not detected. Used by Hermes browser tools and Node-backed capabilities."
-      Pop $HermesNodeStatusLabel
-      ${NSD_CreateCheckbox} 8u 69u 95% 9u "Install Node.js LTS"
-      Pop $HermesNodeCheckbox
-      ${NSD_Check} $HermesNodeCheckbox
-    ${Else}
-      ${NSD_CreateLabel} 8u 59u 95% 14u "Not detected. Install manually from https://nodejs.org/en/download/, then relaunch Hermes."
-      Pop $HermesNodeStatusLabel
-    ${EndIf}
-  ${EndIf}
-
-  ; --- Git panel ---
-  ${NSD_CreateGroupBox} 0u 82u 100% 30u "Git for Windows"
-  Pop $0
-  ${If} $HermesHasGitBash == "1"
-    ${NSD_CreateLabel} 8u 92u 95% 10u "Detected on your system."
-    Pop $HermesGitBashStatusLabel
-  ${Else}
-    ${If} $HermesHasWinget == "1"
-      ${NSD_CreateLabel} 8u 91u 95% 9u "Not detected. Provides Git Bash for Hermes terminal commands."
-      Pop $HermesGitBashStatusLabel
-      ${NSD_CreateCheckbox} 8u 101u 95% 9u "Install Git for Windows"
-      Pop $HermesGitBashCheckbox
-      ${NSD_Check} $HermesGitBashCheckbox
-    ${Else}
-      ${NSD_CreateLabel} 8u 91u 95% 14u "Not detected. Install manually from https://git-scm.com/download/win for terminal commands."
-      Pop $HermesGitBashStatusLabel
-    ${EndIf}
-  ${EndIf}
-
-  ${If} $HermesHasPython == "1"
-  ${AndIf} $HermesHasNode == "1"
-  ${AndIf} $HermesHasGitBash == "1"
-    ${NSD_CreateLabel} 0u 116u 100% 18u "After launch, Hermes will finish installing the bundled agent files and Python dependencies in the GUI."
-    Pop $HermesFooterLabel
-  ${ElseIf} $HermesHasWinget == "0"
-    ${NSD_CreateLabel} 0u 116u 100% 18u "Continue setup, then install missing dependencies manually and relaunch Hermes."
-    Pop $HermesFooterLabel
-  ${ElseIf} $HermesHasWinget == "1"
-    ${If} $HermesHasNode == "0"
-    ${OrIf} $HermesHasGitBash == "0"
-      ${NSD_CreateLabel} 0u 116u 100% 18u "Note: Node.js or Git for Windows may request administrator approval. Check your taskbar if hidden."
-      Pop $HermesFooterLabel
-    ${Else}
-      ${NSD_CreateLabel} 0u 116u 100% 18u "Selected missing items will install before launch; Hermes finishes setup in the GUI."
-      Pop $HermesFooterLabel
-    ${EndIf}
-  ${Else}
-    ${NSD_CreateLabel} 0u 116u 100% 18u "Selected missing items will install before launch; Hermes finishes setup in the GUI."
-    Pop $HermesFooterLabel
-  ${EndIf}
-
-  nsDialogs::Show
-FunctionEnd
-
-; ----------------------------------------------------------------------------
-; HermesPrereqPageLeave — read checkbox states when the user clicks Next.
-; Variables stay at "0" if a checkbox doesn't exist (because the
-; corresponding prereq is already installed or winget isn't available).
-; ----------------------------------------------------------------------------
-Function HermesPrereqPageLeave
-  ${If} $HermesHasPython == "0"
-  ${AndIf} $HermesHasWinget == "1"
-    ${NSD_GetState} $HermesPyCheckbox $HermesInstallPython
-  ${EndIf}
-  ${If} $HermesHasNode == "0"
-  ${AndIf} $HermesHasWinget == "1"
-    ${NSD_GetState} $HermesNodeCheckbox $HermesInstallNode
-  ${EndIf}
-  ${If} $HermesHasGitBash == "0"
-  ${AndIf} $HermesHasWinget == "1"
-    ${NSD_GetState} $HermesGitBashCheckbox $HermesInstallGitBash
-  ${EndIf}
-  ${HermesLog} "page: user choices — install_python=$HermesInstallPython install_node=$HermesInstallNode install_git_bash=$HermesInstallGitBash"
-FunctionEnd
-
-; ----------------------------------------------------------------------------
-; Page declaration — inserted between the Directory page and InstFiles via
-; the customPageAfterChangeDir hook (defined in
-; node_modules/app-builder-lib/templates/nsis/assistedInstaller.nsh, included
-; whenever build.nsis.oneClick=false).
-;
-; Note: NSIS's optimizer emits "warning 6010: install function ... not
-; referenced" for these functions because Page custom directives don't count
-; as references in the optimizer's reference-tracking pass. We set
-; build.nsis.warningsAsErrors=false in package.json so this warning doesn't
-; fail the build. The functions ARE actually called by NSIS at page-display
-; time — the optimizer just can't see it statically.
-; ----------------------------------------------------------------------------
-!macro customPageAfterChangeDir
-  Page custom HermesPrereqPageCreate HermesPrereqPageLeave
-!macroend
-
-; ----------------------------------------------------------------------------
-; customInit — runs at installer startup, before any page. We use it to open
-; the installer log file. The log path is $TEMP\Hermes-Installer.log; we
-; truncate (mode "w") on each install so users don't get an ever-growing
-; file. Users hitting bugs are asked to attach this file.
-;
-; If FileOpen fails (e.g. $TEMP unwritable, AV blocking) we just leave
-; $HermesLogHandle empty — every log macro is a no-op when the handle is
-; empty, so the installer still works, we just lose the diagnostic.
-; ----------------------------------------------------------------------------
-!macro customInit
-  StrCpy $HermesLogPath "$TEMP\Hermes-Installer.log"
-  ClearErrors
-  FileOpen $HermesLogHandle "$HermesLogPath" w
-  ${If} ${Errors}
-    StrCpy $HermesLogHandle ""
-    ; Don't MessageBox — installers shouldn't bother the user about logging
-    ; failures. We still install successfully; we just won't have a log.
-  ${Else}
-    ; UTF-8 BOM so Notepad / editors don't garble any non-ASCII in winget
-    ; output (which uses ✓ characters and other glyphs in some locales).
-    FileWriteByte $HermesLogHandle "239"
-    FileWriteByte $HermesLogHandle "187"
-    FileWriteByte $HermesLogHandle "191"
-    ${HermesLog} "================================================================"
-    ${HermesLog} "Hermes Desktop installer log"
-    ${HermesLog} "================================================================"
-    ${HermesLogKV} "log path" "$HermesLogPath"
-    ${HermesLogKV} "installer name" "$EXEFILE"
-    ${HermesLogKV} "installer dir" "$EXEDIR"
-    ${HermesLogKV} "install target dir" "$INSTDIR"
-    ${HermesLogKV} "TEMP" "$TEMP"
-    ${HermesLogKV} "WINDIR" "$WINDIR"
-    ${HermesLogKV} "PROGRAMFILES64" "$PROGRAMFILES64"
-    ${HermesLogKV} "LOCALAPPDATA" "$LOCALAPPDATA"
-    ${HermesLog} "================================================================"
-  ${EndIf}
-!macroend
-
-; ----------------------------------------------------------------------------
-; customInstall — runs the actual winget commands for whatever prereqs the
-; user checked on the page. Output streams to the install progress log AND
-; to $HermesLogPath via HermesRunWinget.
-; ----------------------------------------------------------------------------
-!macro customInstall
-  ${HermesLog} "=== customInstall: begin ==="
-
-  ; Tell the user where the log lives so they can attach it if anything
-  ; goes wrong. Shown in the install Details panel.
-  ${If} $HermesLogHandle != ""
-    DetailPrint "Installer log: $HermesLogPath"
-  ${EndIf}
-
-  ; Skip on silent installs (managed deploys handle prereqs out-of-band).
-  IfSilent 0 hermes_prereq_not_silent
-  ${HermesLog} "silent install (/S) — skipping prereq winget block"
-  Goto hermes_prereq_install_done
-hermes_prereq_not_silent:
-
-  ${If} $HermesInstallPython == "1"
-    ; Python with --scope user installs to %LOCALAPPDATA%\Programs\Python\
-    ; — no UAC, no foreground chain to preserve. HermesRunWinget captures
-    ; both the Details-panel output AND a copy to the installer log.
-    DetailPrint "Installing Python 3.11 via winget (silent per-user install, no admin prompt)..."
-    Push 'install -e --id Python.Python.3.11 --scope user --silent --disable-interactivity --accept-package-agreements --accept-source-agreements'
-    Push 'Python 3.11'
-    Call HermesRunWinget
-    ${If} $0 != 0
-      DetailPrint "Python install via winget exited with code $0."
-      ${HermesLog} "Python install FAILED (exit $0). User notified via MessageBox."
-      MessageBox MB_OK|MB_ICONEXCLAMATION|MB_TOPMOST "Python install via winget did not complete successfully (exit code $0).$\r$\n$\r$\nSee log: $HermesLogPath$\r$\n$\r$\nAfter this installer finishes, install Python 3.11, 3.12, or 3.13 manually from https://www.python.org/downloads/, then relaunch Hermes. Hermes will not run until Python is installed."
-    ${Else}
-      DetailPrint "Python 3.11 installed successfully."
-      ${HermesLog} "Python install succeeded"
-    ${EndIf}
-  ${EndIf}
-
-  ${If} $HermesInstallNode == "1"
-    DetailPrint "Installing Node.js LTS via winget..."
-    ${HermesLog} "Node.js: starting ExecShellWait — UAC may appear; no stdout capture possible"
-    ${HermesLog} "  command: winget install -e --id OpenJS.NodeJS.LTS --silent --disable-interactivity --accept-package-agreements --accept-source-agreements"
-    ExecShellWait "open" "winget" "install -e --id OpenJS.NodeJS.LTS --silent --disable-interactivity --accept-package-agreements --accept-source-agreements" SW_SHOWNORMAL
-    ${HermesLog} "Node.js: ExecShellWait returned"
-
-    StrCpy $0 "0"
-    ${If} ${FileExists} "$PROGRAMFILES64\nodejs\node.exe"
-      Push '"$PROGRAMFILES64\nodejs\node.exe" -e "process.exit(Number(process.versions.node.split(String.fromCharCode(46))[0]) >= 20 ? 0 : 1)"'
-      Call HermesProbe
-      ${If} $0 == 0
-        StrCpy $0 "1"
-      ${Else}
-        StrCpy $0 "0"
-      ${EndIf}
-    ${EndIf}
-    ${If} $0 == "0"
-    ${AndIf} ${FileExists} "$PROGRAMFILES\nodejs\node.exe"
-      Push '"$PROGRAMFILES\nodejs\node.exe" -e "process.exit(Number(process.versions.node.split(String.fromCharCode(46))[0]) >= 20 ? 0 : 1)"'
-      Call HermesProbe
-      ${If} $0 == 0
-        StrCpy $0 "1"
-      ${Else}
-        StrCpy $0 "0"
-      ${EndIf}
-    ${EndIf}
-    ${If} $0 == "0"
-    ${AndIf} ${FileExists} "$PROGRAMFILES32\nodejs\node.exe"
-      Push '"$PROGRAMFILES32\nodejs\node.exe" -e "process.exit(Number(process.versions.node.split(String.fromCharCode(46))[0]) >= 20 ? 0 : 1)"'
-      Call HermesProbe
-      ${If} $0 == 0
-        StrCpy $0 "1"
-      ${Else}
-        StrCpy $0 "0"
-      ${EndIf}
-    ${EndIf}
-    ${If} $0 == "0"
-    ${AndIf} ${FileExists} "$LOCALAPPDATA\Programs\nodejs\node.exe"
-      Push '"$LOCALAPPDATA\Programs\nodejs\node.exe" -e "process.exit(Number(process.versions.node.split(String.fromCharCode(46))[0]) >= 20 ? 0 : 1)"'
-      Call HermesProbe
-      ${If} $0 == 0
-        StrCpy $0 "1"
-      ${Else}
-        StrCpy $0 "0"
-      ${EndIf}
-    ${EndIf}
-
-    ${If} $0 == "1"
-      DetailPrint "Node.js installed successfully."
-      ${HermesLog} "Node.js install succeeded (version probe positive)"
-    ${Else}
-      DetailPrint "Node.js 20+ could not be validated after install."
-      ${HermesLog} "Node.js install failed, needs a restart, or installed an unsupported version (version probe negative)."
-      MessageBox MB_OK|MB_ICONEXCLAMATION|MB_TOPMOST "Node.js 20+ could not be validated after winget.$\r$\n$\r$\nA restart may be required. See log: $HermesLogPath$\r$\n$\r$\nInstall Node.js 20+ manually from https://nodejs.org/en/download/ if Hermes browser tools or Node-backed capabilities fail."
-    ${EndIf}
-  ${EndIf}
-
-  ${If} $HermesInstallGitBash == "1"
-    DetailPrint "Installing Git for Windows via winget..."
-    ${HermesLog} "Git: starting ExecShellWait — UAC may appear; no stdout capture possible"
-    ${HermesLog} "  command: winget install -e --id Git.Git --silent --disable-interactivity --accept-package-agreements --accept-source-agreements"
-    ExecShellWait "open" "winget" "install -e --id Git.Git --silent --disable-interactivity --accept-package-agreements --accept-source-agreements" SW_SHOWNORMAL
-    ${HermesLog} "Git: ExecShellWait returned"
-
-    StrCpy $0 "0"
-    ${If} ${FileExists} "$PROGRAMFILES64\Git\bin\bash.exe"
-      StrCpy $0 "1"
-    ${ElseIf} ${FileExists} "$PROGRAMFILES\Git\bin\bash.exe"
-      StrCpy $0 "1"
-    ${ElseIf} ${FileExists} "$PROGRAMFILES32\Git\bin\bash.exe"
-      StrCpy $0 "1"
-    ${ElseIf} ${FileExists} "$LOCALAPPDATA\Programs\Git\bin\bash.exe"
-      StrCpy $0 "1"
-    ${EndIf}
-
-    ${If} $0 == "1"
-      DetailPrint "Git for Windows installed successfully."
-      ${HermesLog} "Git install succeeded (filesystem probe positive)"
-    ${Else}
-      DetailPrint "Git for Windows install did not complete (bash.exe not found at standard install locations)."
-      ${HermesLog} "Git install failed or needs a restart (filesystem probe negative)."
-      MessageBox MB_OK|MB_ICONEXCLAMATION|MB_TOPMOST "Git for Windows install via winget did not complete successfully.$\r$\n$\r$\nSee log: $HermesLogPath$\r$\n$\r$\nInstall Git for Windows manually from https://git-scm.com/download/win if Hermes terminal commands fail."
-    ${EndIf}
-  ${EndIf}
-
-  hermes_prereq_install_done:
-  ${HermesLog} "=== customInstall: end ==="
-  ; Flush by closing the log handle. NSIS doesn't expose fflush; FileClose
-  ; both flushes and releases the handle. Subsequent macros become no-ops
-  ; because we null out the handle. This is fine — there are no more log
-  ; sites after customInstall in the install path.
-  ${If} $HermesLogHandle != ""
-    FileClose $HermesLogHandle
-    StrCpy $HermesLogHandle ""
-  ${EndIf}
-!macroend

apps/desktop/package.json

@@ -1,201 +0,0 @@
-{
-  "name": "hermes",
-  "productName": "Hermes",
-  "private": true,
-  "version": "0.0.0",
-  "description": "Native desktop shell for Hermes Agent.",
-  "author": "Nous Research",
-  "type": "module",
-  "main": "electron/main.cjs",
-  "scripts": {
-    "dev": "concurrently -k \"npm:dev:renderer\" \"npm:dev:electron\"",
-    "dev:fake-boot": "cross-env HERMES_DESKTOP_BOOT_FAKE=1 HERMES_DESKTOP_BOOT_FAKE_STEP_MS=650 npm run dev",
-    "dev:renderer": "node scripts/assert-root-install.cjs && vite --host 127.0.0.1 --port 5174",
-    "dev:electron": "wait-on http://127.0.0.1:5174 && cross-env XCURSOR_SIZE=24 HERMES_DESKTOP_DEV_SERVER=http://127.0.0.1:5174 electron .",
-    "profile:main": "wait-on http://127.0.0.1:5174 && cross-env XCURSOR_SIZE=24 HERMES_DESKTOP_DEV_SERVER=http://127.0.0.1:5174 electron --inspect=9229 .",
-    "profile:main:cpu": "wait-on http://127.0.0.1:5174 && cross-env XCURSOR_SIZE=24 NODE_OPTIONS=--cpu-prof HERMES_DESKTOP_DEV_SERVER=http://127.0.0.1:5174 electron .",
-    "start": "npm run build && electron .",
-    "build": "node scripts/assert-root-install.cjs && tsc -b && vite build",
-    "stage:hermes": "node scripts/stage-hermes-payload.mjs",
-    "builder": "cross-env NODE_OPTIONS=--max-old-space-size=16384 electron-builder",
-    "pack": "npm run build && npm run stage:hermes && npm run builder -- --dir",
-    "dist": "npm run build && npm run stage:hermes && npm run builder",
-    "dist:mac": "npm run build && npm run stage:hermes && npm run builder -- --mac",
-    "dist:mac:dmg": "npm run build && npm run stage:hermes && npm run builder -- --mac dmg",
-    "dist:mac:zip": "npm run build && npm run stage:hermes && npm run builder -- --mac zip",
-    "dist:win": "npm run build && npm run stage:hermes && npm run builder -- --win",
-    "dist:win:msi": "npm run build && npm run stage:hermes && npm run builder -- --win msi",
-    "dist:win:nsis": "npm run build && npm run stage:hermes && npm run builder -- --win nsis",
-    "test:desktop": "node scripts/test-desktop.mjs",
-    "test:desktop:all": "node scripts/test-desktop.mjs all",
-    "test:desktop:dmg": "node scripts/test-desktop.mjs dmg",
-    "test:desktop:existing": "node scripts/test-desktop.mjs existing",
-    "test:desktop:fresh": "node scripts/test-desktop.mjs fresh",
-    "test:desktop:platforms": "node --test electron/bootstrap-platform.test.cjs electron/hardening.test.cjs",
-    "type-check": "tsc -b",
-    "lint": "eslint src/ electron/",
-    "lint:fix": "eslint src/ electron/ --fix",
-    "fmt": "prettier --write 'src/**/*.{ts,tsx}' 'electron/**/*.{js,cjs}' 'vite.config.ts'",
-    "fix": "npm run lint:fix && npm run fmt",
-    "test:ui": "vitest run --environment jsdom",
-    "preview": "node scripts/assert-root-install.cjs && vite preview --host 127.0.0.1 --port 4174"
-  },
-  "dependencies": {
-    "@assistant-ui/react": "^0.12.28",
-    "@assistant-ui/react-streamdown": "^0.1.11",
-    "@audiowave/react": "^0.6.2",
-    "@chenglou/pretext": "^0.0.6",
-    "@hermes/shared": "file:../shared",
-    "@nanostores/react": "^1.1.0",
-    "@nous-research/ui": "^0.13.0",
-    "@radix-ui/react-slot": "^1.2.4",
-    "@streamdown/code": "^1.1.1",
-    "@tabler/icons-react": "^3.41.1",
-    "@tailwindcss/typography": "^0.5.19",
-    "@tailwindcss/vite": "^4.2.4",
-    "@tanstack/react-query": "^5.100.6",
-    "class-variance-authority": "^0.7.1",
-    "clsx": "^2.1.1",
-    "cmdk": "^1.1.1",
-    "hast-util-from-html-isomorphic": "^2.0.0",
-    "hast-util-to-text": "^4.0.2",
-    "ignore": "^7.0.5",
-    "katex": "^0.16.45",
-    "leva": "^0.10.1",
-    "lucide-react": "^0.577.0",
-    "motion": "^12.38.0",
-    "nanostores": "^1.3.0",
-    "radix-ui": "^1.4.3",
-    "react": "^19.2.5",
-    "react-arborist": "^3.5.0",
-    "react-dom": "^19.2.5",
-    "react-router-dom": "^7.14.2",
-    "react-shiki": "^0.9.3",
-    "remark-math": "^6.0.0",
-    "shiki": "^4.0.2",
-    "streamdown": "^2.5.0",
-    "tailwind-merge": "^3.5.0",
-    "tailwindcss": "^4.2.4",
-    "tw-shimmer": "^0.4.11",
-    "unicode-animations": "^1.0.3",
-    "unified": "^11.0.5",
-    "unist-util-visit-parents": "^6.0.2",
-    "use-stick-to-bottom": "^1.1.4",
-    "vfile": "^6.0.3",
-    "web-haptics": "^0.0.6"
-  },
-  "devDependencies": {
-    "@eslint/js": "^9.39.4",
-    "@testing-library/react": "^16.3.2",
-    "@types/hast": "^3.0.4",
-    "@types/node": "^24.12.2",
-    "@types/react": "^19.2.14",
-    "@types/react-dom": "^19.2.3",
-    "@typescript-eslint/eslint-plugin": "^8.59.1",
-    "@typescript-eslint/parser": "^8.59.1",
-    "@vitejs/plugin-react": "^6.0.1",
-    "concurrently": "^9.2.1",
-    "cross-env": "^10.1.0",
-    "electron": "^40.9.3",
-    "electron-builder": "^26.8.1",
-    "eslint": "^9.39.4",
-    "eslint-plugin-perfectionist": "^5.9.0",
-    "eslint-plugin-react": "^7.37.5",
-    "eslint-plugin-react-compiler": "^19.1.0-rc.2",
-    "eslint-plugin-react-hooks": "^7.1.1",
-    "eslint-plugin-unused-imports": "^4.4.1",
-    "globals": "^16.5.0",
-    "jsdom": "^29.1.1",
-    "prettier": "^3.8.3",
-    "typescript": "^6.0.3",
-    "vite": "^8.0.10",
-    "vitest": "^4.1.5",
-    "wait-on": "^9.0.5"
-  },
-  "build": {
-    "electronVersion": "40.9.3",
-    "appId": "com.nousresearch.hermes",
-    "productName": "Hermes",
-    "executableName": "Hermes",
-    "artifactName": "Hermes-${version}-${os}-${arch}.${ext}",
-    "icon": "assets/icon",
-    "directories": {
-      "output": "release"
-    },
-    "files": [
-      "dist/**",
-      "assets/**",
-      "electron/**",
-      "public/**",
-      "package.json"
-    ],
-    "beforeBuild": "scripts/before-build.cjs",
-    "extraResources": [
-      {
-        "from": "build/hermes-agent",
-        "to": "hermes-agent"
-      }
-    ],
-    "asar": true,
-    "afterSign": "scripts/notarize.cjs",
-    "asarUnpack": [
-      "**/*.node"
-    ],
-    "mac": {
-      "category": "public.app-category.developer-tools",
-      "entitlements": "electron/entitlements.mac.plist",
-      "entitlementsInherit": "electron/entitlements.mac.inherit.plist",
-      "extendInfo": {
-        "CFBundleDisplayName": "Hermes",
-        "CFBundleExecutable": "Hermes",
-        "CFBundleName": "Hermes",
-        "NSAudioCaptureUsageDescription": "Hermes uses audio capture for voice conversations.",
-        "NSMicrophoneUsageDescription": "Hermes uses the microphone for voice input and voice conversations."
-      },
-      "gatekeeperAssess": false,
-      "hardenedRuntime": true,
-      "target": [
-        "dmg",
-        "zip"
-      ]
-    },
-    "dmg": {
-      "title": "Install Hermes",
-      "backgroundColor": "#f5f5f7",
-      "iconSize": 96,
-      "window": {
-        "width": 560,
-        "height": 360
-      },
-      "contents": [
-        {
-          "x": 160,
-          "y": 170,
-          "type": "file"
-        },
-        {
-          "x": 400,
-          "y": 170,
-          "type": "link",
-          "path": "/Applications"
-        }
-      ]
-    },
-    "win": {
-      "legalTrademarks": "Hermes",
-      "target": [
-        "nsis",
-        "msi"
-      ]
-    },
-    "nsis": {
-      "oneClick": false,
-      "allowToChangeInstallationDirectory": true,
-      "perMachine": false,
-      "shortcutName": "Hermes",
-      "uninstallDisplayName": "Hermes",
-      "include": "installer/prereq-check.nsh",
-      "warningsAsErrors": false
-    }
-  }
-}

apps/desktop/preview-demo.html

@@ -1,65 +0,0 @@
-<!doctype html>
-<html lang="en">
-<head>
-<meta charset="utf-8" />
-<meta name="viewport" content="width=device-width,initial-scale=1" />
-<title>Preview Demo</title>
-<style>
-  :root { color-scheme: dark; }
-  html, body { height: 100%; margin: 0; }
-  body {
-    font-family: ui-sans-serif, system-ui, -apple-system, "SF Pro Text", sans-serif;
-    background: radial-gradient(1200px 600px at 20% 10%, #4a1a33 0%, #2a1020 40%, #120810 100%);
-    color: #ffe4f1;
-    display: grid;
-    place-items: center;
-    padding: 2rem;
-  }
-  .card {
-    max-width: 520px;
-    padding: 2rem 2.25rem;
-    border: 1px solid rgba(255,182,214,0.18);
-    border-radius: 14px;
-    background: rgba(28,14,22,0.6);
-    backdrop-filter: blur(6px);
-    box-shadow: 0 10px 40px rgba(0,0,0,0.4);
-  }
-  h1 {
-    margin: 0 0 0.5rem;
-    font-size: 1.5rem;
-    letter-spacing: 0.01em;
-  }
-  p { margin: 0.35rem 0; opacity: 0.85; line-height: 1.5; }
-  .dot {
-    display: inline-block; width: 10px; height: 10px; border-radius: 50%;
-    background: #ff6fb5; margin-right: 0.5rem;
-    box-shadow: 0 0 12px #ff6fb5;
-    animation: pulse 1.6s ease-in-out infinite;
-  }
-  @keyframes pulse {
-    0%,100% { transform: scale(1); opacity: 1; }
-    50%     { transform: scale(1.4); opacity: 0.6; }
-  }
-  code {
-    background: rgba(255,182,214,0.10);
-    padding: 0.1rem 0.35rem;
-    border-radius: 4px;
-    font-size: 0.9em;
-  }
-  .time { font-variant-numeric: tabular-nums; opacity: 0.7; font-size: 0.85rem; margin-top: 1rem; }
-</style>
-</head>
-<body>
-  <div class="card">
-    <h1><span class="dot"></span>preview-demo.html</h1>
-    <p>Tiny standalone HTML artifact — no server, no build step.</p>
-    <p>Open directly in a browser via <code>file://</code>.</p>
-    <p class="time" id="t"></p>
-  </div>
-  <script>
-    const el = document.getElementById('t');
-    const tick = () => { el.textContent = new Date().toLocaleString(); };
-    tick(); setInterval(tick, 1000);
-  </script>
-</body>
-</html>

apps/desktop/scripts/assert-root-install.cjs

@@ -1,13 +0,0 @@
-"use strict"
-
-const fs = require("fs")
-const path = require("path")
-
-const root = path.resolve(__dirname, "..", "..", "..")
-
-try {
-  fs.accessSync(path.join(root, "node_modules", "vite", "package.json"))
-} catch {
-  console.error(`Run from repo root: cd ${root} && npm ci`)
-  process.exit(1)
-}