c66c68872782261ba43ee17aa67e83555bbe803e
99 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Teknium
|
924bc67eee |
feat(memory): pluggable memory provider interface with profile isolation, review fixes, and honcho CLI restoration (#4623)
* feat(memory): add pluggable memory provider interface with profile isolation Introduces a pluggable MemoryProvider ABC so external memory backends can integrate with Hermes without modifying core files. Each backend becomes a plugin implementing a standard interface, orchestrated by MemoryManager. Key architecture: - agent/memory_provider.py — ABC with core + optional lifecycle hooks - agent/memory_manager.py — single integration point in the agent loop - agent/builtin_memory_provider.py — wraps existing MEMORY.md/USER.md Profile isolation fixes applied to all 6 shipped plugins: - Cognitive Memory: use get_hermes_home() instead of raw env var - Hindsight Memory: check $HERMES_HOME/hindsight/config.json first, fall back to legacy ~/.hindsight/ for backward compat - Hermes Memory Store: replace hardcoded ~/.hermes paths with get_hermes_home() for config loading and DB path defaults - Mem0 Memory: use get_hermes_home() instead of raw env var - RetainDB Memory: auto-derive profile-scoped project name from hermes_home path (hermes-<profile>), explicit env var overrides - OpenViking Memory: read-only, no local state, isolation via .env MemoryManager.initialize_all() now injects hermes_home into kwargs so every provider can resolve profile-scoped storage without importing get_hermes_home() themselves. Plugin system: adds register_memory_provider() to PluginContext and get_plugin_memory_providers() accessor. Based on PR #3825. 46 tests (37 unit + 5 E2E + 4 plugin registration). * refactor(memory): drop cognitive plugin, rewrite OpenViking as full provider Remove cognitive-memory plugin (#727) — core mechanics are broken: decay runs 24x too fast (hourly not daily), prefetch uses row ID as timestamp, search limited by importance not similarity. Rewrite openviking-memory plugin from a read-only search wrapper into a full bidirectional memory provider using the complete OpenViking session lifecycle API: - sync_turn: records user/assistant messages to OpenViking session (threaded, non-blocking) - on_session_end: commits session to trigger automatic memory extraction into 6 categories (profile, preferences, entities, events, cases, patterns) - prefetch: background semantic search via find() endpoint - on_memory_write: mirrors built-in memory writes to the session - is_available: checks env var only, no network calls (ABC compliance) Tools expanded from 3 to 5: - viking_search: semantic search with mode/scope/limit - viking_read: tiered content (abstract ~100tok / overview ~2k / full) - viking_browse: filesystem-style navigation (list/tree/stat) - viking_remember: explicit memory storage via session - viking_add_resource: ingest URLs/docs into knowledge base Uses direct HTTP via httpx (no openviking SDK dependency needed). Response truncation on viking_read to prevent context flooding. * fix(memory): harden Mem0 plugin — thread safety, non-blocking sync, circuit breaker - Remove redundant mem0_context tool (identical to mem0_search with rerank=true, top_k=5 — wastes a tool slot and confuses the model) - Thread sync_turn so it's non-blocking — Mem0's server-side LLM extraction can take 5-10s, was stalling the agent after every turn - Add threading.Lock around _get_client() for thread-safe lazy init (prefetch and sync threads could race on first client creation) - Add circuit breaker: after 5 consecutive API failures, pause calls for 120s instead of hammering a down server every turn. Auto-resets after cooldown. Logs a warning when tripped. - Track success/failure in prefetch, sync_turn, and all tool calls - Wait for previous sync to finish before starting a new one (prevents unbounded thread accumulation on rapid turns) - Clean up shutdown to join both prefetch and sync threads * fix(memory): enforce single external memory provider limit MemoryManager now rejects a second non-builtin provider with a warning. Built-in memory (MEMORY.md/USER.md) is always accepted. Only ONE external plugin provider is allowed at a time. This prevents tool schema bloat (some providers add 3-5 tools each) and conflicting memory backends. The warning message directs users to configure memory.provider in config.yaml to select which provider to activate. Updated all 47 tests to use builtin + one external pattern instead of multiple externals. Added test_second_external_rejected to verify the enforcement. * feat(memory): add ByteRover memory provider plugin Implements the ByteRover integration (from PR #3499 by hieuntg81) as a MemoryProvider plugin instead of direct run_agent.py modifications. ByteRover provides persistent memory via the brv CLI — a hierarchical knowledge tree with tiered retrieval (fuzzy text then LLM-driven search). Local-first with optional cloud sync. Plugin capabilities: - prefetch: background brv query for relevant context - sync_turn: curate conversation turns (threaded, non-blocking) - on_memory_write: mirror built-in memory writes to brv - on_pre_compress: extract insights before context compression Tools (3): - brv_query: search the knowledge tree - brv_curate: store facts/decisions/patterns - brv_status: check CLI version and context tree state Profile isolation: working directory at $HERMES_HOME/byterover/ (scoped per profile). Binary resolution cached with thread-safe double-checked locking. All write operations threaded to avoid blocking the agent (curate can take 120s with LLM processing). * fix(memory): thread remaining sync_turns, fix holographic, add config key Plugin fixes: - Hindsight: thread sync_turn (was blocking up to 30s via _run_in_thread) - RetainDB: thread sync_turn (was blocking on HTTP POST) - Both: shutdown now joins sync threads alongside prefetch threads Holographic retrieval fixes: - reason(): removed dead intersection_key computation (bundled but never used in scoring). Now reuses pre-computed entity_residuals directly, moved role_content encoding outside the inner loop. - contradict(): added _MAX_CONTRADICT_FACTS=500 scaling guard. Above 500 facts, only checks the most recently updated ones to avoid O(n^2) explosion (~125K comparisons at 500 is acceptable). Config: - Added memory.provider key to DEFAULT_CONFIG ("" = builtin only). No version bump needed (deep_merge handles new keys automatically). * feat(memory): extract Honcho as a MemoryProvider plugin Creates plugins/honcho-memory/ as a thin adapter over the existing honcho_integration/ package. All 4 Honcho tools (profile, search, context, conclude) move from the normal tool registry to the MemoryProvider interface. The plugin delegates all work to HonchoSessionManager — no Honcho logic is reimplemented. It uses the existing config chain: $HERMES_HOME/honcho.json -> ~/.honcho/config.json -> env vars. Lifecycle hooks: - initialize: creates HonchoSessionManager via existing client factory - prefetch: background dialectic query - sync_turn: records messages + flushes to API (threaded) - on_memory_write: mirrors user profile writes as conclusions - on_session_end: flushes all pending messages This is a prerequisite for the MemoryManager wiring in run_agent.py. Once wired, Honcho goes through the same provider interface as all other memory plugins, and the scattered Honcho code in run_agent.py can be consolidated into the single MemoryManager integration point. * feat(memory): wire MemoryManager into run_agent.py Adds 8 integration points for the external memory provider plugin, all purely additive (zero existing code modified): 1. Init (~L1130): Create MemoryManager, find matching plugin provider from memory.provider config, initialize with session context 2. Tool injection (~L1160): Append provider tool schemas to self.tools and self.valid_tool_names after memory_manager init 3. System prompt (~L2705): Add external provider's system_prompt_block alongside existing MEMORY.md/USER.md blocks 4. Tool routing (~L5362): Route provider tool calls through memory_manager.handle_tool_call() before the catchall handler 5. Memory write bridge (~L5353): Notify external provider via on_memory_write() when the built-in memory tool writes 6. Pre-compress (~L5233): Call on_pre_compress() before context compression discards messages 7. Prefetch (~L6421): Inject provider prefetch results into the current-turn user message (same pattern as Honcho turn context) 8. Turn sync + session end (~L8161, ~L8172): sync_all() after each completed turn, queue_prefetch_all() for next turn, on_session_end() + shutdown_all() at conversation end All hooks are wrapped in try/except — a failing provider never breaks the agent. The existing memory system, Honcho integration, and all other code paths are completely untouched. Full suite: 7222 passed, 4 pre-existing failures. * refactor(memory): remove legacy Honcho integration from core Extracts all Honcho-specific code from run_agent.py, model_tools.py, toolsets.py, and gateway/run.py. Honcho is now exclusively available as a memory provider plugin (plugins/honcho-memory/). Removed from run_agent.py (-457 lines): - Honcho init block (session manager creation, activation, config) - 8 Honcho methods: _honcho_should_activate, _strip_honcho_tools, _activate_honcho, _register_honcho_exit_hook, _queue_honcho_prefetch, _honcho_prefetch, _honcho_save_user_observation, _honcho_sync - _inject_honcho_turn_context module-level function - Honcho system prompt block (tool descriptions, CLI commands) - Honcho context injection in api_messages building - Honcho params from __init__ (honcho_session_key, honcho_manager, honcho_config) - HONCHO_TOOL_NAMES constant - All honcho-specific tool dispatch forwarding Removed from other files: - model_tools.py: honcho_tools import, honcho params from handle_function_call - toolsets.py: honcho toolset definition, honcho tools from core tools list - gateway/run.py: honcho params from AIAgent constructor calls Removed tests (-339 lines): - 9 Honcho-specific test methods from test_run_agent.py - TestHonchoAtexitFlush class from test_exit_cleanup_interrupt.py Restored two regex constants (_SURROGATE_RE, _BUDGET_WARNING_RE) that were accidentally removed during the honcho function extraction. The honcho_integration/ package is kept intact — the plugin delegates to it. tools/honcho_tools.py registry entries are now dead code (import commented out in model_tools.py) but the file is preserved for reference. Full suite: 7207 passed, 4 pre-existing failures. Zero regressions. * refactor(memory): restructure plugins, add CLI, clean gateway, migration notice Plugin restructure: - Move all memory plugins from plugins/<name>-memory/ to plugins/memory/<name>/ (byterover, hindsight, holographic, honcho, mem0, openviking, retaindb) - New plugins/memory/__init__.py discovery module that scans the directory directly, loading providers by name without the general plugin system - run_agent.py uses load_memory_provider() instead of get_plugin_memory_providers() CLI wiring: - hermes memory setup — interactive curses picker + config wizard - hermes memory status — show active provider, config, availability - hermes memory off — disable external provider (built-in only) - hermes honcho — now shows migration notice pointing to hermes memory setup Gateway cleanup: - Remove _get_or_create_gateway_honcho (already removed in prev commit) - Remove _shutdown_gateway_honcho and _shutdown_all_gateway_honcho methods - Remove all calls to shutdown methods (4 call sites) - Remove _honcho_managers/_honcho_configs dict references Dead code removal: - Delete tools/honcho_tools.py (279 lines, import was already commented out) - Delete tests/gateway/test_honcho_lifecycle.py (131 lines, tested removed methods) - Remove if False placeholder from run_agent.py Migration: - Honcho migration notice on startup: detects existing honcho.json or ~/.honcho/config.json, prints guidance to run hermes memory setup. Only fires when memory.provider is not set and not in quiet mode. Full suite: 7203 passed, 4 pre-existing failures. Zero regressions. * feat(memory): standardize plugin config + add per-plugin documentation Config architecture: - Add save_config(values, hermes_home) to MemoryProvider ABC - Honcho: writes to $HERMES_HOME/honcho.json (SDK native) - Mem0: writes to $HERMES_HOME/mem0.json - Hindsight: writes to $HERMES_HOME/hindsight/config.json - Holographic: writes to config.yaml under plugins.hermes-memory-store - OpenViking/RetainDB/ByteRover: env-var only (default no-op) Setup wizard (hermes memory setup): - Now calls provider.save_config() for non-secret config - Secrets still go to .env via env vars - Only memory.provider activation key goes to config.yaml Documentation: - README.md for each of the 7 providers in plugins/memory/<name>/ - Requirements, setup (wizard + manual), config reference, tools table - Consistent format across all providers The contract for new memory plugins: - get_config_schema() declares all fields (REQUIRED) - save_config() writes native config (REQUIRED if not env-var-only) - Secrets use env_var field in schema, written to .env by wizard - README.md in the plugin directory * docs: add memory providers user guide + developer guide New pages: - user-guide/features/memory-providers.md — comprehensive guide covering all 7 shipped providers (Honcho, OpenViking, Mem0, Hindsight, Holographic, RetainDB, ByteRover). Each with setup, config, tools, cost, and unique features. Includes comparison table and profile isolation notes. - developer-guide/memory-provider-plugin.md — how to build a new memory provider plugin. Covers ABC, required methods, config schema, save_config, threading contract, profile isolation, testing. Updated pages: - user-guide/features/memory.md — replaced Honcho section with link to new Memory Providers page - user-guide/features/honcho.md — replaced with migration redirect to the new Memory Providers page - sidebars.ts — added both new pages to navigation * fix(memory): auto-migrate Honcho users to memory provider plugin When honcho.json or ~/.honcho/config.json exists but memory.provider is not set, automatically set memory.provider: honcho in config.yaml and activate the plugin. The plugin reads the same config files, so all data and credentials are preserved. Zero user action needed. Persists the migration to config.yaml so it only fires once. Prints a one-line confirmation in non-quiet mode. * fix(memory): only auto-migrate Honcho when enabled + credentialed Check HonchoClientConfig.enabled AND (api_key OR base_url) before auto-migrating — not just file existence. Prevents false activation for users who disabled Honcho, stopped using it (config lingers), or have ~/.honcho/ from a different tool. * feat(memory): auto-install pip dependencies during hermes memory setup Reads pip_dependencies from plugin.yaml, checks which are missing, installs them via pip before config walkthrough. Also shows install guidance for external_dependencies (e.g. brv CLI for ByteRover). Updated all 7 plugin.yaml files with pip_dependencies: - honcho: honcho-ai - mem0: mem0ai - openviking: httpx - hindsight: hindsight-client - holographic: (none) - retaindb: requests - byterover: (external_dependencies for brv CLI) * fix: remove remaining Honcho crash risks from cli.py and gateway cli.py: removed Honcho session re-mapping block (would crash importing deleted tools/honcho_tools.py), Honcho flush on compress, Honcho session display on startup, Honcho shutdown on exit, honcho_session_key AIAgent param. gateway/run.py: removed honcho_session_key params from helper methods, sync_honcho param, _honcho.shutdown() block. tests: fixed test_cron_session_with_honcho_key_skipped (was passing removed honcho_key param to _flush_memories_for_session). * fix: include plugins/ in pyproject.toml package list Without this, plugins/memory/ wouldn't be included in non-editable installs. Hermes always runs from the repo checkout so this is belt- and-suspenders, but prevents breakage if the install method changes. * fix(memory): correct pip-to-import name mapping for dep checks The heuristic dep.replace('-', '_') fails for packages where the pip name differs from the import name: honcho-ai→honcho, mem0ai→mem0, hindsight-client→hindsight_client. Added explicit mapping table so hermes memory setup doesn't try to reinstall already-installed packages. * chore: remove dead code from old plugin memory registration path - hermes_cli/plugins.py: removed register_memory_provider(), _memory_providers list, get_plugin_memory_providers() — memory providers now use plugins/memory/ discovery, not the general plugin system - hermes_cli/main.py: stripped 74 lines of dead honcho argparse subparsers (setup, status, sessions, map, peer, mode, tokens, identity, migrate) — kept only the migration redirect - agent/memory_provider.py: updated docstring to reflect new registration path - tests: replaced TestPluginMemoryProviderRegistration with TestPluginMemoryDiscovery that tests the actual plugins/memory/ discovery system. Added 3 new tests (discover, load, nonexistent). * chore: delete dead honcho_integration/cli.py and its tests cli.py (794 lines) was the old 'hermes honcho' command handler — nobody calls it since cmd_honcho was replaced with a migration redirect. Deleted tests that imported from removed code: - tests/honcho_integration/test_cli.py (tested _resolve_api_key) - tests/honcho_integration/test_config_isolation.py (tested CLI config paths) - tests/tools/test_honcho_tools.py (tested the deleted tools/honcho_tools.py) Remaining honcho_integration/ files (actively used by the plugin): - client.py (445 lines) — config loading, SDK client creation - session.py (991 lines) — session management, queries, flush * refactor: move honcho_integration/ into the honcho plugin Moves client.py (445 lines) and session.py (991 lines) from the top-level honcho_integration/ package into plugins/memory/honcho/. No Honcho code remains in the main codebase. - plugins/memory/honcho/client.py — config loading, SDK client creation - plugins/memory/honcho/session.py — session management, queries, flush - Updated all imports: run_agent.py (auto-migration), hermes_cli/doctor.py, plugin __init__.py, session.py cross-import, all tests - Removed honcho_integration/ package and pyproject.toml entry - Renamed tests/honcho_integration/ → tests/honcho_plugin/ * docs: update architecture + gateway-internals for memory provider system - architecture.md: replaced honcho_integration/ with plugins/memory/ - gateway-internals.md: replaced Honcho-specific session routing and flush lifecycle docs with generic memory provider interface docs * fix: update stale mock path for resolve_active_host after honcho plugin migration * fix(memory): address review feedback — P0 lifecycle, ABC contract, honcho CLI restore Review feedback from Honcho devs (erosika): P0 — Provider lifecycle: - Remove on_session_end() + shutdown_all() from run_conversation() tail (was killing providers after every turn in multi-turn sessions) - Add shutdown_memory_provider() method on AIAgent for callers - Wire shutdown into CLI atexit, reset_conversation, gateway stop/expiry Bug fixes: - Remove sync_honcho=False kwarg from /btw callsites (TypeError crash) - Fix doctor.py references to dead 'hermes honcho setup' command - Cache prefetch_all() before tool loop (was re-calling every iteration) ABC contract hardening (all backwards-compatible): - Add session_id kwarg to prefetch/sync_turn/queue_prefetch - Make on_pre_compress() return str (provider insights in compression) - Add **kwargs to on_turn_start() for runtime context - Add on_delegation() hook for parent-side subagent observation - Document agent_context/agent_identity/agent_workspace kwargs on initialize() (prevents cron corruption, enables profile scoping) - Fix docstring: single external provider, not multiple Honcho CLI restoration: - Add plugins/memory/honcho/cli.py (from main's honcho_integration/cli.py with imports adapted to plugin path) - Restore full hermes honcho command with all subcommands (status, peer, mode, tokens, identity, enable/disable, sync, peers, --target-profile) - Restore auto-clone on profile creation + sync on hermes update - hermes honcho setup now redirects to hermes memory setup * fix(memory): wire on_delegation, skip_memory for cron/flush, fix ByteRover return type - Wire on_delegation() in delegate_tool.py — parent's memory provider is notified with task+result after each subagent completes - Add skip_memory=True to cron scheduler (prevents cron system prompts from corrupting user representations — closes #4052) - Add skip_memory=True to gateway flush agent (throwaway agent shouldn't activate memory provider) - Fix ByteRover on_pre_compress() return type: None -> str * fix(honcho): port profile isolation fixes from PR #4632 Ports 5 bug fixes found during profile testing (erosika's PR #4632): 1. 3-tier config resolution — resolve_config_path() now checks $HERMES_HOME/honcho.json → ~/.hermes/honcho.json → ~/.honcho/config.json (non-default profiles couldn't find shared host blocks) 2. Thread host=_host_key() through from_global_config() in cmd_setup, cmd_status, cmd_identity (--target-profile was being ignored) 3. Use bare profile name as aiPeer (not host key with dots) — Honcho's peer ID pattern is ^[a-zA-Z0-9_-]+$, dots are invalid 4. Wrap add_peers() in try/except — was fatal on new AI peers, killed all message uploads for the session 5. Gate Honcho clone behind --clone/--clone-all on profile create (bare create should be blank-slate) Also: sanitize assistant_peer_id via _sanitize_id() * fix(tests): add module cleanup fixture to test_cli_provider_resolution test_cli_provider_resolution._import_cli() wipes tools.*, cli, and run_agent from sys.modules to force fresh imports, but had no cleanup. This poisoned all subsequent tests on the same xdist worker — mocks targeting tools.file_tools, tools.send_message_tool, etc. patched the NEW module object while already-imported functions still referenced the OLD one. Caused ~25 cascade failures: send_message KeyError, process_registry FileNotFoundError, file_read_guards timeouts, read_loop_detection file-not-found, mcp_oauth None port, and provider_parity/codex_execution stale tool lists. Fix: autouse fixture saves all affected modules before each test and restores them after, matching the pattern in test_managed_browserbase_and_modal.py. |
||
|
Teknium
|
acea9ee20b |
fix(tests): fix 11 real test failures + major cascade poisoner (#4570)
Three root causes addressed: 1. AIAgent no longer defaults base_url to OpenRouter (9 tests) Tests that assert OpenRouter-specific behavior (prompt caching, reasoning extra_body, provider preferences) need explicit base_url and model set on the agent. Updated test_run_agent.py and test_provider_parity.py. 2. Credential pool auto-seeding from host env (2 tests) test_auxiliary_client.py tests for Anthropic OAuth and custom endpoint fallback were not mocking _select_pool_entry, so the host's credential pool interfered. Added pool + codex mocks. 3. sys.modules corruption cascade (major - ~250 tests) test_managed_modal_environment.py replaced sys.modules entries (tools, hermes_cli, agent packages) with SimpleNamespace stubs but had NO cleanup fixture. Every subsequent test in the process saw corrupted imports: 'cannot import get_config_path from <unknown module name>' and 'module tools has no attribute environments'. Added _restore_tool_and_agent_modules autouse fixture matching the pattern in test_managed_browserbase_and_modal.py. This was also the root cause of CI failures (104 failed on main). |
||
|
Ben Barclay
|
a2e56d044b | Merge branch 'main' into rewbs/tool-use-charge-to-subscription | ||
|
Teknium
|
fad3f338d1 |
fix: patch _REDACT_ENABLED in test fixture for module-level snapshot
The _REDACT_ENABLED constant is snapshotted at import time, so monkeypatch.delenv() alone doesn't re-enable redaction during tests when HERMES_REDACT_SECRETS=false is set in the host environment. |
||
|
Teknium
|
8d59881a62 |
feat(auth): same-provider credential pools with rotation, custom endpoint support, and interactive CLI (#2647)
* feat(auth): add same-provider credential pools and rotation UX Add same-provider credential pooling so Hermes can rotate across multiple credentials for a single provider, recover from exhausted credentials without jumping providers immediately, and configure that behavior directly in hermes setup. - agent/credential_pool.py: persisted per-provider credential pools - hermes auth add/list/remove/reset CLI commands - 429/402/401 recovery with pool rotation in run_agent.py - Setup wizard integration for pool strategy configuration - Auto-seeding from env vars and existing OAuth state Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com> Salvaged from PR #2647 * fix(tests): prevent pool auto-seeding from host env in credential pool tests Tests for non-pool Anthropic paths and auth remove were failing when host env vars (ANTHROPIC_API_KEY) or file-backed OAuth credentials were present. The pool auto-seeding picked these up, causing unexpected pool entries in tests. - Mock _select_pool_entry in auxiliary_client OAuth flag tests - Clear Anthropic env vars and mock _seed_from_singletons in auth remove test * feat(auth): add thread safety, least_used strategy, and request counting - Add threading.Lock to CredentialPool for gateway thread safety (concurrent requests from multiple gateway sessions could race on pool state mutations without this) - Add 'least_used' rotation strategy that selects the credential with the lowest request_count, distributing load more evenly - Add request_count field to PooledCredential for usage tracking - Add mark_used() method to increment per-credential request counts - Wrap select(), mark_exhausted_and_rotate(), and try_refresh_current() with lock acquisition - Add tests: least_used selection, mark_used counting, concurrent thread safety (4 threads × 20 selects with no corruption) * feat(auth): add interactive mode for bare 'hermes auth' command When 'hermes auth' is called without a subcommand, it now launches an interactive wizard that: 1. Shows full credential pool status across all providers 2. Offers a menu: add, remove, reset cooldowns, set strategy 3. For OAuth-capable providers (anthropic, nous, openai-codex), the add flow explicitly asks 'API key or OAuth login?' — making it clear that both auth types are supported for the same provider 4. Strategy picker shows all 4 options (fill_first, round_robin, least_used, random) with the current selection marked 5. Remove flow shows entries with indices for easy selection The subcommand paths (hermes auth add/list/remove/reset) still work exactly as before for scripted/non-interactive use. * fix(tests): update runtime_provider tests for config.yaml source of truth (#4165) Tests were using OPENAI_BASE_URL env var which is no longer consulted after #4165. Updated to use model config (provider, base_url, api_key) which is the new single source of truth for custom endpoint URLs. * feat(auth): support custom endpoint credential pools keyed by provider name Custom OpenAI-compatible endpoints all share provider='custom', making the provider-keyed pool useless. Now pools for custom endpoints are keyed by 'custom:<normalized_name>' where the name comes from the custom_providers config list (auto-generated from URL hostname). - Pool key format: 'custom:together.ai', 'custom:local-(localhost:8080)' - load_pool('custom:name') seeds from custom_providers api_key AND model.api_key when base_url matches - hermes auth add/list now shows custom endpoints alongside registry providers - _resolve_openrouter_runtime and _resolve_named_custom_runtime check pool before falling back to single config key - 6 new tests covering custom pool keying, seeding, and listing * docs: add Excalidraw diagram of full credential pool flow Comprehensive architecture diagram showing: - Credential sources (env vars, auth.json OAuth, config.yaml, CLI) - Pool storage and auto-seeding - Runtime resolution paths (registry, custom, OpenRouter) - Error recovery (429 retry-then-rotate, 402 immediate, 401 refresh) - CLI management commands and strategy configuration Open at: https://excalidraw.com/#json=2Ycqhqpi6f12E_3ITyiwh,c7u9jSt5BwrmiVzHGbm87g * fix(tests): update setup wizard pool tests for unified select_provider_and_model flow The setup wizard now delegates to select_provider_and_model() instead of using its own prompt_choice-based provider picker. Tests needed: - Mock select_provider_and_model as no-op (provider pre-written to config) - Call _stub_tts BEFORE custom prompt_choice mock (it overwrites it) - Pre-write model.provider to config so the pool step is reached * docs: add comprehensive credential pool documentation - New page: website/docs/user-guide/features/credential-pools.md Full guide covering quick start, CLI commands, rotation strategies, error recovery, custom endpoint pools, auto-discovery, thread safety, architecture, and storage format. - Updated fallback-providers.md to reference credential pools as the first layer of resilience (same-provider rotation before cross-provider) - Added hermes auth to CLI commands reference with usage examples - Added credential_pool_strategies to configuration guide * chore: remove excalidraw diagram from repo (external link only) * refactor: simplify credential pool code — extract helpers, collapse extras, dedup patterns - _load_config_safe(): replace 4 identical try/except/import blocks - _iter_custom_providers(): shared generator for custom provider iteration - PooledCredential.extra dict: collapse 11 round-trip-only fields (token_type, scope, client_id, portal_base_url, obtained_at, expires_in, agent_key_id, agent_key_expires_in, agent_key_reused, agent_key_obtained_at, tls) into a single extra dict with __getattr__ for backward-compatible access - _available_entries(): shared exhaustion-check between select and peek - Dedup anthropic OAuth seeding (hermes_pkce + claude_code identical) - SimpleNamespace replaces class _Args boilerplate in auth_commands - _try_resolve_from_custom_pool(): shared pool-check in runtime_provider Net -17 lines. All 383 targeted tests pass. --------- Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com> |
||
|
Teknium
|
f890a94c12 |
refactor: make config.yaml the single source of truth for endpoint URLs (#4165)
OPENAI_BASE_URL was written to .env AND config.yaml, creating a dual-source
confusion. Users (especially Docker) would see the URL in .env and assume
that's where all config lives, then wonder why LLM_MODEL in .env didn't work.
Changes:
- Remove all 27 save_env_value("OPENAI_BASE_URL", ...) calls across main.py,
setup.py, and tools_config.py
- Remove OPENAI_BASE_URL env var reading from runtime_provider.py, cli.py,
models.py, and gateway/run.py
- Remove LLM_MODEL/HERMES_MODEL env var reading from gateway/run.py and
auxiliary_client.py — config.yaml model.default is authoritative
- Vision base URL now saved to config.yaml auxiliary.vision.base_url
(both setup wizard and tools_config paths)
- Tests updated to set config values instead of env vars
Convention enforced: .env is for SECRETS only (API keys). All other
configuration (model names, base URLs, provider selection) lives
exclusively in config.yaml.
|
||
|
Teknium
|
d30ea65c9b |
fix: URL-based auth for third-party Anthropic endpoints + CI test fixes (#4148)
* fix(tests): mock sys.stdin.isatty for cmd_model TTY guard * fix(tests): update camofox snapshot format + trajectory compressor mock path - test_browser_camofox: mock response now uses snapshot format (accessibility tree) - test_trajectory_compressor: mock _get_async_client instead of setting async_client directly * fix: URL-based auth detection for third-party Anthropic endpoints + test fixes Reverts the key-prefix approach from #4093 which broke JWT and managed key OAuth detection. Instead, detects third-party endpoints by URL: if base_url is set and isn't anthropic.com, it's a proxy (Azure AI Foundry, AWS Bedrock, etc.) that uses x-api-key regardless of key format. Auth decision chain is now: 1. _requires_bearer_auth(url) → MiniMax → Bearer 2. _is_third_party_anthropic_endpoint(url) → Azure/Bedrock → x-api-key 3. _is_oauth_token(key) → OAuth on direct Anthropic → Bearer 4. else → x-api-key Also includes test fixes from PR #4051 by @erosika: - Mock sys.stdin.isatty for cmd_model TTY guard - Update camofox snapshot format mock - Fix trajectory compressor async client mock path --------- Co-authored-by: Erosika <eri@plasticlabs.ai> |
||
|
Teknium
|
ffd5d37f9b |
fix: treat non-sk-ant- keys as regular API keys, not OAuth tokens (#4093)
* fix: treat non-sk-ant- prefixed keys (Azure AI Foundry) as regular API keys, not OAuth tokens * fix: treat non-sk-ant- keys as regular API keys, not OAuth tokens _is_oauth_token() returned True for any key not starting with sk-ant-api, misclassifying Azure AI Foundry keys as OAuth tokens and sending Bearer auth instead of x-api-key → 401 rejection. Real Anthropic OAuth tokens all start with sk-ant-oat (confirmed from live .credentials.json). Non-sk-ant- keys are third-party provider keys that should use x-api-key. Test fixtures updated to use realistic sk-ant-oat01- prefixed tokens instead of fake strings. Salvaged from PR #4075 by @HangGlidersRule. --------- Co-authored-by: Clawdbot <clawdbot@openclaw.ai> |
||
|
Robin Fernandes
|
1126284c97 | Merge branch 'main' into rewbs/tool-use-charge-to-subscription | ||
|
Robin Fernandes
|
6e4598ce1e | Merge branch 'main' into rewbs/tool-use-charge-to-subscription | ||
|
Teknium
|
fb634068df |
fix(security): extend secret redaction to ElevenLabs, Tavily and Exa API keys (#3920)
ElevenLabs (sk_), Tavily (tvly-), and Exa (exa_) keys were not covered by _PREFIX_PATTERNS, leaking in plain text via printenv or log output. Salvaged from PR #3790 by @memosr. Tests rewritten with correct assertions (original tests had vacuously true checks). Co-authored-by: memosr <memosr@users.noreply.github.com> |
||
|
Robin Fernandes
|
1cbb1b99cc | Gate tool-gateway behind an env var, so it's not in users' faces until we're ready. Even if users enable it, it'll be blocked server-side for now, until we unlock for non-admin users on tool-gateway. | ||
|
Teknium
|
3cc50532d1 |
fix: auxiliary client uses placeholder key for local servers without auth (#3842)
Local inference servers (Ollama, llama.cpp, vLLM, LM Studio) don't require API keys, but the auxiliary client's _resolve_custom_runtime() rejected endpoints with empty keys — causing the auto-detection chain to skip the user's local server entirely. This broke compression, summarization, and memory flush for users running local models without an OpenRouter/cloud API key. The main CLI already had this fix (PR #2556, 'no-key-required' placeholder), but the auxiliary client's resolution path was missed. Two fixes: - _resolve_custom_runtime(): use 'no-key-required' placeholder instead of returning None when base_url is present but key is empty - resolve_provider_client() custom branch: same placeholder fallback for explicit_base_url without explicit_api_key Updates 2 tests that expected the old (broken) behavior. |
||
|
Teknium
|
ba1b600bce |
fix(tests): align skill/setup and platform mocks with current behavior (#3721)
- Skill invocation: no secret capture callback so SSH remote setup note is emitted - Patch agent.skill_utils.sys for platform checks (skill_matches_platform) - Skip CLAUDE.md priority test on Darwin (case-insensitive FS) Made-with: Cursor Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com> |
||
|
Teknium
|
fcd1645223 |
feat(skills): support external skill directories via config (#3678)
Add skills.external_dirs config option — a list of additional directories to scan for skills alongside ~/.hermes/skills/. External dirs are read-only: skill creation/editing always writes to the local dir. Local skills take precedence when names collide. This lets users share skills across tools/agents without copying them into Hermes's own directory (e.g. ~/.agents/skills, /shared/team-skills). Changes: - agent/skill_utils.py: add get_external_skills_dirs() and get_all_skills_dirs() - agent/prompt_builder.py: scan external dirs in build_skills_system_prompt() - tools/skills_tool.py: _find_all_skills() and skill_view() search external dirs; security check recognizes configured external dirs as trusted - agent/skill_commands.py: /skill slash commands discover external skills - hermes_cli/config.py: add skills.external_dirs to DEFAULT_CONFIG - cli-config.yaml.example: document the option - tests/agent/test_external_skills.py: 11 tests covering discovery, precedence, deduplication, and skill_view for external skills Requested by community member primco. |
||
|
Teknium
|
831e8ba0e5 |
feat: tool-use enforcement + strip budget warnings from history (#3528)
Cherry-pick of feat/gpt-tool-steering with modifications:
1. Tool-use enforcement prompt (refactored from GPT-specific):
- Renamed GPT_TOOL_USE_GUIDANCE -> TOOL_USE_ENFORCEMENT_GUIDANCE
- Added TOOL_USE_ENFORCEMENT_MODELS tuple: ('gpt', 'codex')
- Injection logic now checks against the tuple instead of hardcoding
'gpt' — adding new model families is a one-line change
- Addresses models describing actions instead of making tool calls
2. Budget warning history stripping:
- _strip_budget_warnings_from_history() strips _budget_warning JSON
keys and [BUDGET WARNING: ...] text from tool results at the start
of run_conversation()
- Prevents old budget warnings from poisoning subsequent turns
Based on PR #3479 by teknium1.
|
||
|
Teknium
|
5127567d5d |
perf(ttft): cache skills prompt with shared skill_utils module (salvage #3366) (#3421)
Two-layer caching for build_skills_system_prompt(): 1. In-process LRU (OrderedDict, max 8) — same-process: 546ms → <1ms 2. Disk snapshot (.skills_prompt_snapshot.json) — cold start: 297ms → 103ms Key improvements over original PR #3366: - Extract shared logic into agent/skill_utils.py (parse_frontmatter, skill_matches_platform, get_disabled_skill_names, extract_skill_conditions, extract_skill_description, iter_skill_index_files) - tools/skills_tool.py delegates to shared module — zero code duplication - Proper LRU eviction via OrderedDict.move_to_end + popitem(last=False) - Cache invalidation on all skill mutation paths: - skill_manage tool (in-conversation writes) - hermes skills install (CLI hub) - hermes skills uninstall (CLI hub) - Automatic via mtime/size manifest on cold start prompt_builder.py no longer imports tools.skills_tool (avoids pulling in the entire tool registry chain at prompt build time). 6301 tests pass, 0 failures. Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com> |
||
|
Teknium
|
5a1e2a307a |
perf(ttft): salvage easy-win startup optimizations from #3346 (#3395)
* perf(ttft): dedupe shared tool availability checks * perf(ttft): short-circuit vision auto-resolution * perf(ttft): make Claude Code version detection lazy * perf(ttft): reuse loaded toolsets for skills prompt --------- Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com> |
||
|
Robin Fernandes
|
e95965d76a | Merge branch 'main' into rewbs/tool-use-charge-to-subscription | ||
|
Robin Fernandes
|
95dc9aaa75 |
feat: add managed tool gateway and Nous subscription support
- add managed modal and gateway-backed tool integrations\n- improve CLI setup, auth, and configuration for subscriber flows\n- expand tests and docs for managed tool support |
||
|
Teknium
|
a8e02c7d49 |
fix: align Nous Portal model slugs with OpenRouter naming (#3253)
Nous Portal now passes through OpenRouter model names and routes from there. Update the static fallback model list and auxiliary client default to use OpenRouter-format slugs (provider/model) instead of bare names. - _PROVIDER_MODELS['nous']: full OpenRouter catalog - _NOUS_MODEL: google/gemini-3-flash-preview (was gemini-3-flash) - Updated 4 test assertions for the new default model name |
||
|
Teknium
|
0426bb745f |
fix: reset default SOUL.md to baseline identity text (#3159)
The default SOUL.md seeded for new users should match DEFAULT_AGENT_IDENTITY — a short, neutral identity paragraph. The elaborate voice spec (avoid lists, dialogue examples, symbol conventions) was never intended as the default for all users. Users who want a custom persona write their own SOUL.md. |
||
|
Teknium
|
7258311710 |
fix: stop recursive AGENTS.md walk, load top-level only (#3110)
The recursive os.walk for AGENTS.md in subdirectories was undesired. Only load AGENTS.md from the working directory root, matching the behavior of CLAUDE.md and .cursorrules. |
||
|
Teknium
|
910ec7eb38 |
chore: remove unused Hermes-native PKCE OAuth flow (#3107)
Remove run_hermes_oauth_login(), refresh_hermes_oauth_token(),
read_hermes_oauth_credentials(), _save_hermes_oauth_credentials(),
_generate_pkce(), and associated constants/credential file path.
This code was added in
|
||
|
Teknium
|
37cabc47d3 |
test(skills): add regression tests for null metadata frontmatter
Covers the case where a SKILL.md has `metadata:` (null) or
`metadata.hermes:` (null), which caused an AttributeError
before the fix in
|
||
|
Teknium
|
7ca22ea11b |
fix(compression): restore sane defaults and cap summary at 12K tokens
- threshold: 0.80 → 0.50 (compress at 50%, not 80%) - target_ratio: 0.40 → 0.20, now relative to threshold not total context (20% of 50% = 10% of context as tail budget) - summary ceiling: 32K → 12K (Gemini can't output more than ~12K) - Updated DEFAULT_CONFIG, config display, example config, and tests |
||
|
Teknium
|
9231a335d4 |
fix(compression): replace dead summary_target_tokens with ratio-based scaling (#2554)
The summary_target_tokens parameter was accepted in the constructor,
stored on the instance, and never used — the summary budget was always
computed from hardcoded module constants (_SUMMARY_RATIO=0.20,
_MAX_SUMMARY_TOKENS=8000). This caused two compounding problems:
1. The config value was silently ignored, giving users no control
over post-compression size.
2. Fixed budgets (20K tail, 8K summary cap) didn't scale with
context window size. Switching from a 1M-context model to a
200K model would trigger compression that nuked 350K tokens
of conversation history down to ~30K.
Changes:
- Replace summary_target_tokens with summary_target_ratio (default 0.40)
which sets the post-compression target as a fraction of context_length.
Tail token budget and summary cap now scale proportionally:
MiniMax 200K → ~80K post-compression
GPT-5 1M → ~400K post-compression
- Change threshold_percent default: 0.50 → 0.80 (don't fire until
80% of context is consumed)
- Change protect_last_n default: 4 → 20 (preserve ~10 full turns)
- Summary token cap scales to 5% of context (was fixed 8K), capped
at 32K ceiling
- Read target_ratio and protect_last_n from config.yaml compression
section (both are now configurable)
- Remove hardcoded summary_target_tokens=500 from run_agent.py
- Add 5 new tests for ratio scaling, clamping, and new defaults
|
||
|
Teknium
|
be3eb62047 |
fix(tests): resolve all consistently failing tests
- test_plugins.py: remove tests for unimplemented plugin command API (get_plugin_command_handler, register_command never existed) - test_redact.py: add autouse fixture to clear HERMES_REDACT_SECRETS env var leaked by cli.py import in other tests - test_signal.py: same HERMES_REDACT_SECRETS fix for phone redaction - test_mattermost.py: add @bot_user_id to test messages after the mention-only filter was added in #2443 - test_context_token_tracking.py: mock resolve_provider_client for openai-codex provider that requires real OAuth credentials Full suite: 5893 passed, 0 failed. |
||
|
0xbyt4
|
dbc25a386e |
fix: auxiliary client skips expired Codex JWT and propagates Anthropic OAuth flag
Two bugs in the auxiliary provider auto-detection chain: 1. Expired Codex JWT blocks the auto chain: _read_codex_access_token() returned any stored token without checking expiry, preventing fallback to working providers. Now decodes JWT exp claim and returns None for expired tokens. 2. Auxiliary Anthropic client missing OAuth identity transforms: _AnthropicCompletionsAdapter always called build_anthropic_kwargs with is_oauth=False, causing 400 errors for OAuth tokens. Now detects OAuth tokens via _is_oauth_token() and propagates the flag through the adapter chain. Cherry-picked from PR #2378 by 0xbyt4. Fixed test_api_key_no_oauth_flag to mock resolve_anthropic_token directly (env var alone was insufficient). |
||
|
Teknium
|
1d28b4699b |
fix(redact): safely handle non-string inputs (salvage #2369)
fix(redact): safely handle non-string inputs (salvage #2369) |
||
|
aydnOktay
|
40c9a13476 |
fix(redact): safely handle non-string inputs
redact_sensitive_text() now returns early for None and coerces other non-string values to str before applying regex-based redaction, preventing TypeErrors in logging/tool-output paths. Cherry-picked from PR #2369 by aydnOktay. |
||
|
teyrebaz33
|
bd49bce278 |
fix(prompt-caching): skip top-level cache_control on role:tool for OpenRouter
On the native Anthropic Messages API path, convert_messages_to_anthropic() moves top-level cache_control on role:tool messages inside the tool_result block. On OpenRouter (chat_completions), no such conversion happens — the unexpected top-level field causes a silent hang on the second tool call. Add native_anthropic parameter to _apply_cache_marker() and apply_anthropic_cache_control(). When False (OpenRouter), role:tool messages are skipped entirely. When True (native Anthropic), existing behaviour is preserved. Fixes #2362 |
||
|
Teknium
|
2da79b13df |
feat: priority-based context file selection + CLAUDE.md support (#2301)
Previously, all project context files (AGENTS.md, .cursorrules, .hermes.md) were loaded and concatenated into the system prompt. This bloated the prompt with potentially redundant or conflicting instructions. Now only ONE project context type is loaded, using priority order: 1. .hermes.md / HERMES.md (walk to git root) 2. AGENTS.md / agents.md (recursive directory walk) 3. CLAUDE.md / claude.md (cwd only, NEW) 4. .cursorrules / .cursor/rules/*.mdc (cwd only) SOUL.md from HERMES_HOME remains independent and always loads. Also adds CLAUDE.md as a recognized context file format, matching the convention popularized by Claude Code. Refactored the monolithic function into four focused helpers: _load_hermes_md, _load_agents_md, _load_claude_md, _load_cursorrules. Tests: replaced 1 coexistence test with 10 new tests covering priority ordering, CLAUDE.md loading, case sensitivity, injection blocking. |
||
|
Teknium
|
88643a1ba9 |
feat: overhaul context length detection with models.dev and provider-aware resolution (#2158)
Replace the fragile hardcoded context length system with a multi-source resolution chain that correctly identifies context windows per provider. Key changes: - New agent/models_dev.py: Fetches and caches the models.dev registry (3800+ models across 100+ providers with per-provider context windows). In-memory cache (1hr TTL) + disk cache for cold starts. - Rewritten get_model_context_length() resolution chain: 0. Config override (model.context_length) 1. Custom providers per-model context_length 2. Persistent disk cache 3. Endpoint /models (local servers) 4. Anthropic /v1/models API (max_input_tokens, API-key only) 5. OpenRouter live API (existing, unchanged) 6. Nous suffix-match via OpenRouter (dot/dash normalization) 7. models.dev registry lookup (provider-aware) 8. Thin hardcoded defaults (broad family patterns) 9. 128K fallback (was 2M) - Provider-aware context: same model now correctly resolves to different context windows per provider (e.g. claude-opus-4.6: 1M on Anthropic, 128K on GitHub Copilot). Provider name flows through ContextCompressor. - DEFAULT_CONTEXT_LENGTHS shrunk from 80+ entries to ~16 broad patterns. models.dev replaces the per-model hardcoding. - CONTEXT_PROBE_TIERS changed from [2M, 1M, 512K, 200K, 128K, 64K, 32K] to [128K, 64K, 32K, 16K, 8K]. Unknown models no longer start at 2M. - hermes model: prompts for context_length when configuring custom endpoints. Supports shorthand (32k, 128K). Saved to custom_providers per-model config. - custom_providers schema extended with optional models dict for per-model context_length (backward compatible). - Nous Portal: suffix-matches bare IDs (claude-opus-4-6) against OpenRouter's prefixed IDs (anthropic/claude-opus-4.6) with dot/dash normalization. Handles all 15 current Nous models. - Anthropic direct: queries /v1/models for max_input_tokens. Only works with regular API keys (sk-ant-api*), not OAuth tokens. Falls through to models.dev for OAuth users. Tests: 5574 passed (18 new tests for models_dev + updated probe tiers) Docs: Updated configuration.md context length section, AGENTS.md Co-authored-by: Test <test@test.com> |
||
|
Teknium
|
3ec6c71e43 |
fix: update claude 4.6 context length from 200K to 1M (#2155)
* fix: preserve Ollama model:tag colons in context length detection The colon-split logic in get_model_context_length() and _query_local_context_length() assumed any colon meant provider:model format (e.g. "local:my-model"). But Ollama uses model:tag format (e.g. "qwen3.5:27b"), so the split turned "qwen3.5:27b" into just "27b" — which matches nothing, causing a fallback to the 2M token probe tier. Now only recognised provider prefixes (local, openrouter, anthropic, etc.) are stripped. Ollama model:tag names pass through intact. * fix: update claude-opus-4-6 and claude-sonnet-4-6 context length from 200K to 1M Both models support 1,000,000 token context windows. The hardcoded defaults were set before Anthropic expanded the context for the 4.6 generation. Verified via models.dev and OpenRouter API data. --------- Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com> Co-authored-by: Test <test@test.com> |
||
|
Teknium
|
471ea81a7d |
fix: preserve Ollama model:tag colons in context length detection (#2149)
The colon-split logic in get_model_context_length() and _query_local_context_length() assumed any colon meant provider:model format (e.g. "local:my-model"). But Ollama uses model:tag format (e.g. "qwen3.5:27b"), so the split turned "qwen3.5:27b" into just "27b" — which matches nothing, causing a fallback to the 2M token probe tier. Now only recognised provider prefixes (local, openrouter, anthropic, etc.) are stripped. Ollama model:tag names pass through intact. Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com> |
||
|
Teknium
|
d76fa7fc37 |
fix: detect context length for custom model endpoints via fuzzy matching + config override (#2051)
* fix: detect context length for custom model endpoints via fuzzy matching + config override Custom model endpoints (non-OpenRouter, non-known-provider) were silently falling back to 2M tokens when the model name didn't exactly match what the endpoint's /v1/models reported. This happened because: 1. Endpoint metadata lookup used exact match only — model name mismatches (e.g. 'qwen3.5:9b' vs 'Qwen3.5-9B-Q4_K_M.gguf') caused a miss 2. Single-model servers (common for local inference) required exact name match even though only one model was loaded 3. No user escape hatch to manually set context length Changes: - Add fuzzy matching for endpoint model metadata: single-model servers use the only available model regardless of name; multi-model servers try substring matching in both directions - Add model.context_length config override (highest priority) so users can explicitly set their model's context length in config.yaml - Log an informative message when falling back to 2M probe, telling users about the config override option - Thread config_context_length through ContextCompressor and AIAgent init Tests: 6 new tests covering fuzzy match, single-model fallback, config override (including zero/None edge cases). * fix: auto-detect local model name and context length for local servers Cherry-picked from PR #2043 by sudoingX. - Auto-detect model name from local server's /v1/models when only one model is loaded (no manual model name config needed) - Add n_ctx_train and n_ctx to context length detection keys for llama.cpp - Query llama.cpp /props endpoint for actual allocated context (not just training context from GGUF metadata) - Strip .gguf suffix from display in banner and status bar - _auto_detect_local_model() in runtime_provider.py for CLI init Co-authored-by: sudo <sudoingx@users.noreply.github.com> * fix: revert accidental summary_target_tokens change + add docs for context_length config - Revert summary_target_tokens from 2500 back to 500 (accidental change during patching) - Add 'Context Length Detection' section to Custom & Self-Hosted docs explaining model.context_length config override --------- Co-authored-by: Test <test@test.com> Co-authored-by: sudo <sudoingx@users.noreply.github.com> |
||
|
Test
|
e7844e9c8d | Merge origin/main, resolve conflicts (self._base_url_lower) | ||
|
Teknium
|
b70dd51cfa |
fix: disabled skills respected across banner, system prompt, slash commands, and skill_view (#1897)
* fix: banner skill count now respects disabled skills and platform filtering The banner's get_available_skills() was doing a raw rglob scan of ~/.hermes/skills/ without checking: - Whether skills are disabled (skills.disabled config) - Whether skills match the current platform (platforms: frontmatter) This caused the banner to show inflated skill counts (e.g. '100 skills' when many are disabled) and list macOS-only skills on Linux. Fix: delegate to _find_all_skills() from tools/skills_tool which already handles both platform gating and disabled-skill filtering. * fix: system prompt and slash commands now respect disabled skills Two more places where disabled skills were still surfaced: 1. build_skills_system_prompt() in prompt_builder.py — disabled skills appeared in the <available_skills> system prompt section, causing the agent to suggest/load them despite being disabled. 2. scan_skill_commands() in skill_commands.py — disabled skills still registered as /skill-name slash commands in CLI help and could be invoked. Both now load _get_disabled_skill_names() and filter accordingly. * fix: skill_view blocks disabled skills skill_view() checked platform compatibility but not disabled state, so the agent could still load and read disabled skills directly. Now returns a clear error when a disabled skill is requested, telling the user to enable it via hermes skills or inspect the files manually. --------- Co-authored-by: Test <test@test.com> |
||
|
Teknium
|
a2440f72f6 |
feat: use endpoint metadata for custom model context and pricing (#1906)
* perf: cache base_url.lower() via property, consolidate triple load_config(), hoist set constant run_agent.py: - Add base_url property that auto-caches _base_url_lower on every assignment, eliminating 12+ redundant .lower() calls per API cycle across __init__, _build_api_kwargs, _supports_reasoning_extra_body, and the main conversation loop - Consolidate three separate load_config() disk reads in __init__ (memory, skills, compression) into a single call, reusing the result dict for all three config sections model_tools.py: - Hoist _READ_SEARCH_TOOLS set to module level (was rebuilt inside handle_function_call on every tool invocation) * Use endpoint metadata for custom model context and pricing --------- Co-authored-by: kshitij <82637225+kshitijk4poor@users.noreply.github.com> |
||
|
max
|
0c392e7a87 |
feat: integrate GitHub Copilot providers across Hermes
Add first-class GitHub Copilot and Copilot ACP provider support across model selection, runtime provider resolution, CLI sessions, delegated subagents, cron jobs, and the Telegram gateway. This also normalizes Copilot model catalogs and API modes, introduces a Copilot ACP OpenAI-compatible shim, and fixes service-mode auth by resolving Homebrew-installed gh binaries under launchd. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> |
||
|
Teknium
|
548cedb869 |
fix(context_compressor): prevent consecutive same-role messages after compression (#1743)
compress() checks both the head and tail neighbors when choosing the summary message role. When only the tail collides, the role is flipped. When BOTH roles would create consecutive same-role messages (e.g. head=assistant, tail=user), the summary is merged into the first tail message instead of inserting a standalone message that breaks role alternation and causes API 400 errors. The previous code handled head-side collision but left the tail-side uncovered — long conversations would crash mid-reply with no useful error, forcing the user to /reset and lose session history. Based on PR #1186 by @alireza78a, with improved double-collision handling (merge into tail instead of unconditional 'user' fallback). Co-authored-by: alireza78a <alireza78.crypto@gmail.com> |
||
|
Teknium
|
d1d17f4f0a |
feat(compression): add summary_base_url + move compression config to YAML-only
- Add summary_base_url config option to compression block for custom OpenAI-compatible endpoints (e.g. zai, DeepSeek, Ollama) - Remove compression env var bridges from cli.py and gateway/run.py (CONTEXT_COMPRESSION_* env vars no longer set from config) - Switch run_agent.py to read compression config directly from config.yaml instead of env vars - Fix backwards-compat block in _resolve_task_provider_model to also fire when auxiliary.compression.provider is 'auto' (DEFAULT_CONFIG sets this, which was silently preventing the compression section's summary_* keys from being read) - Add test for summary_base_url config-to-client flow - Update docs to show compression as config.yaml-only Closes #1591 Based on PR #1702 by @uzaylisak |
||
|
teknium1
|
0897e4350e | merge: resolve conflicts with origin/main | ||
|
ch3ronsa
|
695eb04243 |
feat(agent): .hermes.md per-repository project config discovery
Adds .hermes.md / HERMES.md discovery for per-project agent configuration. When the agent starts, it walks from cwd to the git root looking for .hermes.md (preferred) or HERMES.md, strips any YAML frontmatter, and injects the markdown body into the system prompt as project context. - Nearest-first discovery (subdirectory configs shadow parent) - Stops at git root boundary (no leaking into parent repos) - YAML frontmatter stripped (structured config deferred to Phase 2) - Same injection scanning and 20K truncation as other context files - 22 comprehensive tests Original implementation by ch3ronsa. Cherry-picked and adapted for current main. Closes #681 (Phase 1) |
||
|
teknium1
|
e5fc916814 |
feat: auto-generate session titles after first exchange
After the first user→assistant exchange, Hermes now generates a short descriptive session title via the auxiliary LLM (compression task config). Title generation runs in a background thread so it never delays the user-facing response. Key behaviors: - Fires only on the first 1-2 exchanges (checks user message count) - Skips if a title already exists (user-set titles are never overwritten) - Uses call_llm with compression task config (cheapest/fastest model) - Truncates long messages to keep the title generation request small - Cleans up LLM output: strips quotes, 'Title:' prefixes, enforces 80 char max - Works in both CLI and gateway (Telegram/Discord/etc.) Also updates /title (no args) to show the session ID alongside the title in both CLI and gateway. Implements #1426 |
||
|
crazywriter1
|
7049dba778 |
fix(docker): remove container on cleanup when container_persistent=false
When container_persistent=false, the inner mini-swe-agent cleanup only runs 'docker stop' in the background, leaving containers in Exited state. Now cleanup() also runs 'docker rm -f' to fully remove the container. Also fixes pre-existing test failures in model_metadata (gpt-4.1 1M context), setup tests (TTS provider step), and adds MockInnerDocker.cleanup(). Original fix by crazywriter1. Cherry-picked and adapted for current main. Fixes #1679 |
||
|
Teknium
|
6405d389aa |
test: align Hermes setup and full-suite expectations (#1710)
Salvaged from PR #1708 by @kartikkabadi. Cherry-picked with authorship preserved. Fixes pre-existing test failures from setup TTS prompt flow changes and environment-sensitive assumptions. Co-authored-by: Kartik <user2@RentKars-MacBook-Air.local> |
||
|
Teknium
|
d417ba2a48 |
feat: add route-aware pricing estimates (#1695)
Salvaged from PR #1563 by @kshitijk4poor. Cherry-picked with authorship preserved. - Route-aware pricing architecture replacing static MODEL_PRICING + heuristics - Canonical usage normalization (Anthropic/OpenAI/Codex API shapes) - Cache-aware billing (separate cache_read/cache_write rates) - Cost status tracking (estimated/included/unknown/actual) - OpenRouter live pricing via models API - Schema migration v4→v5 with billing metadata columns - Removed speculative forward-looking entries - Removed cost display from CLI status bar - Threaded OpenRouter metadata pre-warm Co-authored-by: kshitij <82637225+kshitijk4poor@users.noreply.github.com> |
||
|
Teknium
|
5e5c92663d |
fix: hermes update causes dual gateways on macOS (launchd) (#1567)
* feat: add optional smart model routing Add a conservative cheap-vs-strong routing option that can send very short/simple turns to a cheaper model across providers while keeping the primary model for complex work. Wire it through CLI, gateway, and cron, and document the config.yaml workflow. * fix(gateway): remove recursive ExecStop from systemd units, extend TimeoutStopSec to 60s * fix(gateway): avoid recursive ExecStop in user systemd unit * fix: extend ExecStop removal and TimeoutStopSec=60 to system unit The cherry-picked PR #1448 fix only covered the user systemd unit. The system unit had the same TimeoutStopSec=15 and could benefit from the same 60s timeout for clean shutdown. Also adds a regression test for the system unit. --------- Co-authored-by: Ninja <ninja@local> * feat(skills): add blender-mcp optional skill for 3D modeling Control a running Blender instance from Hermes via socket connection to the blender-mcp addon (port 9876). Supports creating 3D objects, materials, animations, and running arbitrary bpy code. Placed in optional-skills/ since it requires Blender 4.3+ desktop with a third-party addon manually started each session. * feat(acp): support slash commands in ACP adapter (#1532) Adds /help, /model, /tools, /context, /reset, /compact, /version to the ACP adapter (VS Code, Zed, JetBrains). Commands are handled directly in the server without instantiating the TUI — each command queries agent/session state and returns plain text. Unrecognized /commands fall through to the LLM as normal messages. /model uses detect_provider_for_model() for auto-detection when switching models, matching the CLI and gateway behavior. Fixes #1402 * fix(logging): improve error logging in session search tool (#1533) * fix(gateway): restart on retryable startup failures (#1517) * feat(email): add skip_attachments option via config.yaml * feat(email): add skip_attachments option via config.yaml Adds a config.yaml-driven option to skip email attachments in the gateway email adapter. Useful for malware protection and bandwidth savings. Configure in config.yaml: platforms: email: skip_attachments: true Based on PR #1521 by @an420eth, changed from env var to config.yaml (via PlatformConfig.extra) to match the project's config-first pattern. * docs: document skip_attachments option for email adapter * fix(telegram): retry on transient TLS failures during connect and send Add exponential-backoff retry (3 attempts) around initialize() to handle transient TLS resets during gateway startup. Also catches TimedOut and OSError in addition to NetworkError. Add exponential-backoff retry (3 attempts) around send_message() for NetworkError during message delivery, wrapping the existing Markdown fallback logic. Both imports are guarded with try/except ImportError for test environments where telegram is mocked. Based on PR #1527 by cmd8. Closes #1526. * feat: permissive block_anchor thresholds and unicode normalization (#1539) Salvaged from PR #1528 by an420eth. Closes #517. Improves _strategy_block_anchor in fuzzy_match.py: - Add unicode normalization (smart quotes, em/en-dashes, ellipsis, non-breaking spaces → ASCII) so LLM-produced unicode artifacts don't break anchor line matching - Lower thresholds: 0.10 for unique matches (was 0.70), 0.30 for multiple candidates — if first/last lines match exactly, the block is almost certainly correct - Use original (non-normalized) content for offset calculation to preserve correct character positions Tested: 3 new scenarios fixed (em-dash anchors, non-breaking space anchors, very-low-similarity unique matches), zero regressions on all 9 existing fuzzy match tests. Co-authored-by: an420eth <an420eth@users.noreply.github.com> * feat(cli): add file path autocomplete in the input prompt (#1545) When typing a path-like token (./ ../ ~/ / or containing /), the CLI now shows filesystem completions in the dropdown menu. Directories show a trailing slash and 'dir' label; files show their size. Completions are case-insensitive and capped at 30 entries. Triggered by tokens like: edit ./src/ma → shows ./src/main.py, ./src/manifest.json, ... check ~/doc → shows ~/docs/, ~/documents/, ... read /etc/hos → shows /etc/hosts, /etc/hostname, ... open tools/reg → shows tools/registry.py Slash command autocomplete (/help, /model, etc.) is unaffected — it still triggers when the input starts with /. Inspired by OpenCode PR #145 (file path completion menu). Implementation: - hermes_cli/commands.py: _extract_path_word() detects path-like tokens, _path_completions() yields filesystem Completions with size labels, get_completions() routes to paths vs slash commands - tests/hermes_cli/test_path_completion.py: 26 tests covering path extraction, prefix filtering, directory markers, home expansion, case-insensitivity, integration with slash commands * feat(privacy): redact PII from LLM context when privacy.redact_pii is enabled Add privacy.redact_pii config option (boolean, default false). When enabled, the gateway redacts personally identifiable information from the system prompt before sending it to the LLM provider: - Phone numbers (user IDs on WhatsApp/Signal) → hashed to user_<sha256> - User IDs → hashed to user_<sha256> - Chat IDs → numeric portion hashed, platform prefix preserved - Home channel IDs → hashed - Names/usernames → NOT affected (user-chosen, publicly visible) Hashes are deterministic (same user → same hash) so the model can still distinguish users in group chats. Routing and delivery use the original values internally — redaction only affects LLM context. Inspired by OpenClaw PR #47959. * fix(privacy): skip PII redaction on Discord/Slack (mentions need real IDs) Discord uses <@user_id> for mentions and Slack uses <@U12345> — the LLM needs the real ID to tag users. Redaction now only applies to WhatsApp, Signal, and Telegram where IDs are pure routing metadata. Add 4 platform-specific tests covering Discord, WhatsApp, Signal, Slack. * feat: smart approvals + /stop command (inspired by OpenAI Codex) * feat: smart approvals — LLM-based risk assessment for dangerous commands Adds a 'smart' approval mode that uses the auxiliary LLM to assess whether a flagged command is genuinely dangerous or a false positive, auto-approving low-risk commands without prompting the user. Inspired by OpenAI Codex's Smart Approvals guardian subagent (openai/codex#13860). Config (config.yaml): approvals: mode: manual # manual (default), smart, off Modes: - manual — current behavior, always prompt the user - smart — aux LLM evaluates risk: APPROVE (auto-allow), DENY (block), or ESCALATE (fall through to manual prompt) - off — skip all approval prompts (equivalent to --yolo) When smart mode auto-approves, the pattern gets session-level approval so subsequent uses of the same pattern don't trigger another LLM call. When it denies, the command is blocked without user prompt. When uncertain, it escalates to the normal manual approval flow. The LLM prompt is carefully scoped: it sees only the command text and the flagged reason, assesses actual risk vs false positive, and returns a single-word verdict. * feat: make smart approval model configurable via config.yaml Adds auxiliary.approval section to config.yaml with the same provider/model/base_url/api_key pattern as other aux tasks (vision, web_extract, compression, etc.). Config: auxiliary: approval: provider: auto model: '' # fast/cheap model recommended base_url: '' api_key: '' Bridged to env vars in both CLI and gateway paths so the aux client picks them up automatically. * feat: add /stop command to kill all background processes Adds a /stop slash command that kills all running background processes at once. Currently users have to process(list) then process(kill) for each one individually. Inspired by OpenAI Codex's separation of interrupt (Ctrl+C stops current turn) from /stop (cleans up background processes). See openai/codex#14602. Ctrl+C continues to only interrupt the active agent turn — background dev servers, watchers, etc. are preserved. /stop is the explicit way to clean them all up. * feat: first-class plugin architecture + hide status bar cost by default (#1544) The persistent status bar now shows context %, token counts, and duration but NOT $ cost by default. Cost display is opt-in via: display: show_cost: true in config.yaml, or: hermes config set display.show_cost true The /usage command still shows full cost breakdown since the user explicitly asked for it — this only affects the always-visible bar. Status bar without cost: ⚕ claude-sonnet-4 │ 12K/200K │ 6% │ 15m Status bar with show_cost: true: ⚕ claude-sonnet-4 │ 12K/200K │ 6% │ $0.06 │ 15m * feat: improve memory prioritization + aggressive skill updates (inspired by OpenAI Codex) * feat: improve memory prioritization — user preferences over procedural knowledge Inspired by OpenAI Codex's memory prompt improvements (openai/codex#14493) which focus memory writes on user preferences and recurring patterns rather than procedural task details. Key insight: 'Optimize for reducing future user steering — the most valuable memory prevents the user from having to repeat themselves.' Changes: - MEMORY_GUIDANCE (prompt_builder.py): added prioritization hierarchy and the core principle about reducing user steering - MEMORY_SCHEMA (memory_tool.py): reordered WHEN TO SAVE list to put corrections first, added explicit PRIORITY guidance - Memory nudge (run_agent.py): now asks specifically about preferences, corrections, and workflow patterns instead of generic 'anything' - Memory flush (run_agent.py): now instructs to prioritize user preferences and corrections over task-specific details * feat: more aggressive skill creation and update prompting Press harder on skill updates — the agent should proactively patch skills when it encounters issues during use, not wait to be asked. Changes: - SKILLS_GUIDANCE: 'consider saving' → 'save'; added explicit instruction to patch skills immediately when found outdated/wrong - Skills header: added instruction to update loaded skills before finishing if they had missing steps or wrong commands - Skill nudge: more assertive ('save the approach' not 'consider saving'), now also prompts for updating existing skills used in the task - Skill nudge interval: lowered default from 15 to 10 iterations - skill_manage schema: added 'patch it immediately' to update triggers * feat: first-class plugin architecture (#1555) Plugin system for extending Hermes with custom tools, hooks, and integrations — no source code changes required. Core system (hermes_cli/plugins.py): - Plugin discovery from ~/.hermes/plugins/, .hermes/plugins/, and pip entry_points (hermes_agent.plugins group) - PluginContext with register_tool() and register_hook() - 6 lifecycle hooks: pre/post tool_call, pre/post llm_call, on_session_start/end - Namespace package handling for relative imports in plugins - Graceful error isolation — broken plugins never crash the agent Integration (model_tools.py): - Plugin discovery runs after built-in + MCP tools - Plugin tools bypass toolset filter via get_plugin_tool_names() - Pre/post tool call hooks fire in handle_function_call() CLI: - /plugins command shows loaded plugins, tool counts, status - Added to COMMANDS dict for autocomplete Docs: - Getting started guide (build-a-hermes-plugin.md) — full tutorial building a calculator plugin step by step - Reference page (features/plugins.md) — quick overview + tables - Covers: file structure, schemas, handlers, hooks, data files, bundled skills, env var gating, pip distribution, common mistakes Tests: 16 tests covering discovery, loading, hooks, tool visibility. * fix: hermes update causes dual gateways on macOS (launchd) Three bugs worked together to create the dual-gateway problem: 1. cmd_update only checked systemd for gateway restart, completely ignoring launchd on macOS. After killing the PID it would print 'Restart it with: hermes gateway run' even when launchd was about to auto-respawn the process. 2. launchd's KeepAlive.SuccessfulExit=false respawns the gateway after SIGTERM (non-zero exit), so the user's manual restart created a second instance. 3. The launchd plist lacked --replace (systemd had it), so the respawned gateway didn't kill stale instances on startup. Fixes: - Add --replace to launchd ProgramArguments (matches systemd) - Add launchd detection to cmd_update's auto-restart logic - Print 'auto-restart via launchd' instead of manual restart hint * fix: add launchd plist auto-refresh + explicit restart in cmd_update Two integration issues with the initial fix: 1. Existing macOS users with old plist (no --replace) would never get the fix until manual uninstall/reinstall. Added refresh_launchd_plist_if_needed() — mirrors the existing refresh_systemd_unit_if_needed(). Called from launchd_start(), launchd_restart(), and cmd_update. 2. cmd_update relied on KeepAlive respawn after SIGTERM rather than explicit launchctl stop/start. This caused races: launchd would respawn the old process before the PID file was cleaned up. Now does explicit stop+start (matching how systemd gets an explicit systemctl restart), with plist refresh first so the new --replace flag is picked up. --------- Co-authored-by: Ninja <ninja@local> Co-authored-by: alireza78a <alireza78a@users.noreply.github.com> Co-authored-by: Oktay Aydin <113846926+aydnOktay@users.noreply.github.com> Co-authored-by: JP Lew <polydegen@protonmail.com> Co-authored-by: an420eth <an420eth@users.noreply.github.com> |