fix: clean up stale test references to removed attributes

Remove tests for deleted should_compress_preflight/get_status/last_total_tokens
from test_context_compressor.py. Remove stale _reasoning_deltas_fired references
from test_reasoning_command.py (attribute removed, tests were passing vacuously).

Dockerfile

@@ -13,8 +13,7 @@ COPY . /opt/hermes
 WORKDIR /opt/hermes
 
 # Install Python and Node dependencies in one layer, no cache
-RUN pip install --no-cache-dir uv --break-system-packages && \
-    uv pip install --system --break-system-packages --no-cache -e ".[all]" && \
+RUN pip install --no-cache-dir -e ".[all]" --break-system-packages && \
     npm install --prefer-offline --no-audit && \
     npx playwright install --with-deps chromium --only-shell && \
     cd /opt/hermes/scripts/whatsapp-bridge && \

README.md

@@ -33,10 +33,8 @@ Use any model you want — [Nous Portal](https://portal.nousresearch.com), [Open
 curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
 ```
 
-Works on Linux, macOS, WSL2, and Android via Termux. The installer handles the platform-specific setup for you.
+Works on Linux, macOS, and WSL2. The installer handles everything — Python, Node.js, dependencies, and the `hermes` command. No prerequisites except git.
 
-> **Android / Termux:** The tested manual path is documented in the [Termux guide](https://hermes-agent.nousresearch.com/docs/getting-started/termux). On Termux, Hermes installs a curated `.[termux]` extra because the full `.[all]` extra currently pulls Android-incompatible voice dependencies.
->
 > **Windows:** Native Windows is not supported. Please install [WSL2](https://learn.microsoft.com/en-us/windows/wsl/install) and run the command above.
 
 After installation:

agent/anthropic_adapter.py

@@ -74,11 +74,8 @@ def _get_anthropic_max_output(model: str) -> int:
     model IDs (claude-sonnet-4-5-20250929) and variant suffixes (:1m, :fast)
     resolve correctly.  Longest-prefix match wins to avoid e.g. "claude-3-5"
     matching before "claude-3-5-sonnet".
-
-    Normalizes dots to hyphens so that model names like
-    ``anthropic/claude-opus-4.6`` match the ``claude-opus-4-6`` table key.
     """
-    m = model.lower().replace(".", "-")
+    m = model.lower()
     best_key = ""
     best_val = _ANTHROPIC_DEFAULT_OUTPUT_LIMIT
     for key, val in _ANTHROPIC_OUTPUT_LIMITS.items():
@@ -98,15 +95,6 @@ _COMMON_BETAS = [
     "interleaved-thinking-2025-05-14",
     "fine-grained-tool-streaming-2025-05-14",
 ]
-# MiniMax's Anthropic-compatible endpoints fail tool-use requests when
-# the fine-grained tool streaming beta is present.  Omit it so tool calls
-# fall back to the provider's default response path.
-_TOOL_STREAMING_BETA = "fine-grained-tool-streaming-2025-05-14"
-
-# Fast mode beta — enables the ``speed: "fast"`` request parameter for
-# significantly higher output token throughput on Opus 4.6 (~2.5x).
-# See https://platform.claude.com/docs/en/build-with-claude/fast-mode
-_FAST_MODE_BETA = "fast-mode-2026-02-01"
 
 # Additional beta headers required for OAuth/subscription auth.
 # Matches what Claude Code (and pi-ai / OpenCode) send.
@@ -216,19 +204,6 @@ def _requires_bearer_auth(base_url: str | None) -> bool:
     return normalized.startswith(("https://api.minimax.io/anthropic", "https://api.minimaxi.com/anthropic"))
 
 
-def _common_betas_for_base_url(base_url: str | None) -> list[str]:
-    """Return the beta headers that are safe for the configured endpoint.
-
-    MiniMax's Anthropic-compatible endpoints (Bearer-auth) reject requests
-    that include Anthropic's ``fine-grained-tool-streaming`` beta — every
-    tool-use message triggers a connection error.  Strip that beta for
-    Bearer-auth endpoints while keeping all other betas intact.
-    """
-    if _requires_bearer_auth(base_url):
-        return [b for b in _COMMON_BETAS if b != _TOOL_STREAMING_BETA]
-    return _COMMON_BETAS
-
-
 def build_anthropic_client(api_key: str, base_url: str = None):
     """Create an Anthropic client, auto-detecting setup-tokens vs API keys.
 
@@ -247,7 +222,6 @@ def build_anthropic_client(api_key: str, base_url: str = None):
     }
     if normalized_base_url:
         kwargs["base_url"] = normalized_base_url
-    common_betas = _common_betas_for_base_url(normalized_base_url)
 
     if _requires_bearer_auth(normalized_base_url):
         # Some Anthropic-compatible providers (e.g. MiniMax) expect the API key in
@@ -257,21 +231,21 @@ def build_anthropic_client(api_key: str, base_url: str = None):
         # not use Anthropic's sk-ant-api prefix and would otherwise be misread as
         # Anthropic OAuth/setup tokens.
         kwargs["auth_token"] = api_key
-        if common_betas:
-            kwargs["default_headers"] = {"anthropic-beta": ",".join(common_betas)}
+        if _COMMON_BETAS:
+            kwargs["default_headers"] = {"anthropic-beta": ",".join(_COMMON_BETAS)}
     elif _is_third_party_anthropic_endpoint(base_url):
         # Third-party proxies (Azure AI Foundry, AWS Bedrock, etc.) use their
         # own API keys with x-api-key auth. Skip OAuth detection — their keys
         # don't follow Anthropic's sk-ant-* prefix convention and would be
         # misclassified as OAuth tokens.
         kwargs["api_key"] = api_key
-        if common_betas:
-            kwargs["default_headers"] = {"anthropic-beta": ",".join(common_betas)}
+        if _COMMON_BETAS:
+            kwargs["default_headers"] = {"anthropic-beta": ",".join(_COMMON_BETAS)}
     elif _is_oauth_token(api_key):
         # OAuth access token / setup-token → Bearer auth + Claude Code identity.
         # Anthropic routes OAuth requests based on user-agent and headers;
         # without Claude Code's fingerprint, requests get intermittent 500s.
-        all_betas = common_betas + _OAUTH_ONLY_BETAS
+        all_betas = _COMMON_BETAS + _OAUTH_ONLY_BETAS
         kwargs["auth_token"] = api_key
         kwargs["default_headers"] = {
             "anthropic-beta": ",".join(all_betas),
@@ -281,8 +255,8 @@ def build_anthropic_client(api_key: str, base_url: str = None):
     else:
         # Regular API key → x-api-key header + common betas
         kwargs["api_key"] = api_key
-        if common_betas:
-            kwargs["default_headers"] = {"anthropic-beta": ",".join(common_betas)}
+        if _COMMON_BETAS:
+            kwargs["default_headers"] = {"anthropic-beta": ",".join(_COMMON_BETAS)}
 
     return _anthropic_sdk.Anthropic(**kwargs)
 
@@ -511,35 +485,6 @@ def _prefer_refreshable_claude_code_token(env_token: str, creds: Optional[Dict[s
     return None
 
 
-def get_anthropic_token_source(token: Optional[str] = None) -> str:
-    """Best-effort source classification for an Anthropic credential token."""
-    token = (token or "").strip()
-    if not token:
-        return "none"
-
-    env_token = os.getenv("ANTHROPIC_TOKEN", "").strip()
-    if env_token and env_token == token:
-        return "anthropic_token_env"
-
-    cc_env_token = os.getenv("CLAUDE_CODE_OAUTH_TOKEN", "").strip()
-    if cc_env_token and cc_env_token == token:
-        return "claude_code_oauth_token_env"
-
-    creds = read_claude_code_credentials()
-    if creds and creds.get("accessToken") == token:
-        return str(creds.get("source") or "claude_code_credentials")
-
-    managed_key = read_claude_managed_key()
-    if managed_key and managed_key == token:
-        return "claude_json_primary_api_key"
-
-    api_key = os.getenv("ANTHROPIC_API_KEY", "").strip()
-    if api_key and api_key == token:
-        return "anthropic_api_key_env"
-
-    return "unknown"
-
-
 def resolve_anthropic_token() -> Optional[str]:
     """Resolve an Anthropic token from all available sources.
 
@@ -746,21 +691,6 @@ def run_hermes_oauth_login_pure() -> Optional[Dict[str, Any]]:
     }
 
 
-def _save_hermes_oauth_credentials(access_token: str, refresh_token: str, expires_at_ms: int) -> None:
-    """Save OAuth credentials to ~/.hermes/.anthropic_oauth.json."""
-    data = {
-        "accessToken": access_token,
-        "refreshToken": refresh_token,
-        "expiresAt": expires_at_ms,
-    }
-    try:
-        _HERMES_OAUTH_FILE.parent.mkdir(parents=True, exist_ok=True)
-        _HERMES_OAUTH_FILE.write_text(json.dumps(data, indent=2), encoding="utf-8")
-        _HERMES_OAUTH_FILE.chmod(0o600)
-    except (OSError, IOError) as e:
-        logger.debug("Failed to save Hermes OAuth credentials: %s", e)
-
-
 def read_hermes_oauth_credentials() -> Optional[Dict[str, Any]]:
     """Read Hermes-managed OAuth credentials from ~/.hermes/.anthropic_oauth.json."""
     if _HERMES_OAUTH_FILE.exists():
@@ -809,39 +739,6 @@ def _sanitize_tool_id(tool_id: str) -> str:
     return sanitized or "tool_0"
 
 
-def _convert_openai_image_part_to_anthropic(part: Dict[str, Any]) -> Optional[Dict[str, Any]]:
-    """Convert an OpenAI-style image block to Anthropic's image source format."""
-    image_data = part.get("image_url", {})
-    url = image_data.get("url", "") if isinstance(image_data, dict) else str(image_data)
-    if not isinstance(url, str) or not url.strip():
-        return None
-    url = url.strip()
-
-    if url.startswith("data:"):
-        header, sep, data = url.partition(",")
-        if sep and ";base64" in header:
-            media_type = header[5:].split(";", 1)[0] or "image/png"
-            return {
-                "type": "image",
-                "source": {
-                    "type": "base64",
-                    "media_type": media_type,
-                    "data": data,
-                },
-            }
-
-    if url.startswith(("http://", "https://")):
-        return {
-            "type": "image",
-            "source": {
-                "type": "url",
-                "url": url,
-            },
-        }
-
-    return None
-
-
 def convert_tools_to_anthropic(tools: List[Dict]) -> List[Dict]:
     """Convert OpenAI tool definitions to Anthropic format."""
     if not tools:
@@ -1261,7 +1158,6 @@ def build_anthropic_kwargs(
     preserve_dots: bool = False,
     context_length: Optional[int] = None,
     base_url: str | None = None,
-    fast_mode: bool = False,
 ) -> Dict[str, Any]:
     """Build kwargs for anthropic.messages.create().
 
@@ -1295,10 +1191,6 @@ def build_anthropic_kwargs(
 
     When *base_url* points to a third-party Anthropic-compatible endpoint,
     thinking block signatures are stripped (they are Anthropic-proprietary).
-
-    When *fast_mode* is True, adds ``speed: "fast"`` and the fast-mode beta
-    header for ~2.5x faster output throughput on Opus 4.6.  Currently only
-    supported on native Anthropic endpoints (not third-party compatible ones).
     """
     system, anthropic_messages = convert_messages_to_anthropic(messages, base_url=base_url)
     anthropic_tools = convert_tools_to_anthropic(tools) if tools else []
@@ -1397,20 +1289,6 @@ def build_anthropic_kwargs(
                 kwargs["temperature"] = 1
                 kwargs["max_tokens"] = max(effective_max_tokens, budget + 4096)
 
-    # ── Fast mode (Opus 4.6 only) ────────────────────────────────────
-    # Adds speed:"fast" + the fast-mode beta header for ~2.5x output speed.
-    # Only for native Anthropic endpoints — third-party providers would
-    # reject the unknown beta header and speed parameter.
-    if fast_mode and not _is_third_party_anthropic_endpoint(base_url):
-        kwargs["speed"] = "fast"
-        # Build extra_headers with ALL applicable betas (the per-request
-        # extra_headers override the client-level anthropic-beta header).
-        betas = list(_common_betas_for_base_url(base_url))
-        if is_oauth:
-            betas.extend(_OAUTH_ONLY_BETAS)
-        betas.append(_FAST_MODE_BETA)
-        kwargs["extra_headers"] = {"anthropic-beta": ",".join(betas)}
-
     return kwargs
 
 
@@ -1472,4 +1350,4 @@ def normalize_anthropic_response(
             reasoning_details=reasoning_details or None,
         ),
         finish_reason,
-    )
+    )

agent/auxiliary_client.py

@@ -702,7 +702,7 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
             logger.debug("Auxiliary text client: %s (%s) via pool", pconfig.name, model)
             extra = {}
             if "api.kimi.com" in base_url.lower():
-                extra["default_headers"] = {"User-Agent": "KimiCLI/1.30.0"}
+                extra["default_headers"] = {"User-Agent": "KimiCLI/1.3"}
             elif "api.githubcopilot.com" in base_url.lower():
                 from hermes_cli.models import copilot_default_headers
 
@@ -721,7 +721,7 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
         logger.debug("Auxiliary text client: %s (%s)", pconfig.name, model)
         extra = {}
         if "api.kimi.com" in base_url.lower():
-            extra["default_headers"] = {"User-Agent": "KimiCLI/1.30.0"}
+            extra["default_headers"] = {"User-Agent": "KimiCLI/1.3"}
         elif "api.githubcopilot.com" in base_url.lower():
             from hermes_cli.models import copilot_default_headers
 
@@ -967,40 +967,6 @@ def _try_anthropic() -> Tuple[Optional[Any], Optional[str]]:
     return AnthropicAuxiliaryClient(real_client, model, token, base_url, is_oauth=is_oauth), model
 
 
-def _resolve_forced_provider(forced: str) -> Tuple[Optional[OpenAI], Optional[str]]:
-    """Resolve a specific forced provider.  Returns (None, None) if creds missing."""
-    if forced == "openrouter":
-        client, model = _try_openrouter()
-        if client is None:
-            logger.warning("auxiliary.provider=openrouter but OPENROUTER_API_KEY not set")
-        return client, model
-
-    if forced == "nous":
-        client, model = _try_nous()
-        if client is None:
-            logger.warning("auxiliary.provider=nous but Nous Portal not configured (run: hermes auth)")
-        return client, model
-
-    if forced == "codex":
-        client, model = _try_codex()
-        if client is None:
-            logger.warning("auxiliary.provider=codex but no Codex OAuth token found (run: hermes model)")
-        return client, model
-
-    if forced == "main":
-        # "main" = skip OpenRouter/Nous, use the main chat model's credentials.
-        for try_fn in (_try_custom_endpoint, _try_codex, _resolve_api_key_provider):
-            client, model = try_fn()
-            if client is not None:
-                return client, model
-        logger.warning("auxiliary.provider=main but no main endpoint credentials found")
-        return None, None
-
-    # Unknown provider name — fall through to auto
-    logger.warning("Unknown auxiliary.provider=%r, falling back to auto", forced)
-    return None, None
-
-
 _AUTO_PROVIDER_LABELS = {
     "_try_openrouter": "openrouter",
     "_try_nous": "nous",
@@ -1195,7 +1161,7 @@ def _to_async_client(sync_client, model: str):
 
         async_kwargs["default_headers"] = copilot_default_headers()
     elif "api.kimi.com" in base_lower:
-        async_kwargs["default_headers"] = {"User-Agent": "KimiCLI/1.30.0"}
+        async_kwargs["default_headers"] = {"User-Agent": "KimiCLI/1.3"}
     return AsyncOpenAI(**async_kwargs), model
 
 
@@ -1317,7 +1283,7 @@ def resolve_provider_client(
             final_model = model or _read_main_model() or "gpt-4o-mini"
             extra = {}
             if "api.kimi.com" in custom_base.lower():
-                extra["default_headers"] = {"User-Agent": "KimiCLI/1.30.0"}
+                extra["default_headers"] = {"User-Agent": "KimiCLI/1.3"}
             elif "api.githubcopilot.com" in custom_base.lower():
                 from hermes_cli.models import copilot_default_headers
                 extra["default_headers"] = copilot_default_headers()
@@ -1400,7 +1366,7 @@ def resolve_provider_client(
         # Provider-specific headers
         headers = {}
         if "api.kimi.com" in base_url.lower():
-            headers["User-Agent"] = "KimiCLI/1.30.0"
+            headers["User-Agent"] = "KimiCLI/1.3"
         elif "api.githubcopilot.com" in base_url.lower():
             from hermes_cli.models import copilot_default_headers
 
@@ -1495,22 +1461,6 @@ def _strict_vision_backend_available(provider: str) -> bool:
     return _resolve_strict_vision_backend(provider)[0] is not None
 
 
-def _preferred_main_vision_provider() -> Optional[str]:
-    """Return the selected main provider when it is also a supported vision backend."""
-    try:
-        from hermes_cli.config import load_config
-
-        config = load_config()
-        model_cfg = config.get("model", {})
-        if isinstance(model_cfg, dict):
-            provider = _normalize_vision_provider(model_cfg.get("provider", ""))
-            if provider in _VISION_AUTO_PROVIDER_ORDER:
-                return provider
-    except Exception:
-        pass
-    return None
-
-
 def get_available_vision_backends() -> List[str]:
     """Return the currently available vision backends in auto-selection order.
 
@@ -1624,18 +1574,6 @@ def resolve_vision_provider_client(
     return requested, client, final_model
 
 
-def get_vision_auxiliary_client() -> Tuple[Optional[OpenAI], Optional[str]]:
-    """Return (client, default_model_slug) for vision/multimodal auxiliary tasks."""
-    _, client, final_model = resolve_vision_provider_client(async_mode=False)
-    return client, final_model
-
-
-def get_async_vision_auxiliary_client():
-    """Return (async_client, model_slug) for async vision consumers."""
-    _, client, final_model = resolve_vision_provider_client(async_mode=True)
-    return client, final_model
-
-
 def get_auxiliary_extra_body() -> dict:
     """Return extra_body kwargs for auxiliary API calls.
     

agent/builtin_memory_provider.py

@@ -1,114 +0,0 @@
-"""BuiltinMemoryProvider — wraps MEMORY.md / USER.md as a MemoryProvider.
-
-Always registered as the first provider. Cannot be disabled or removed.
-This is the existing Hermes memory system exposed through the provider
-interface for compatibility with the MemoryManager.
-
-The actual storage logic lives in tools/memory_tool.py (MemoryStore).
-This provider is a thin adapter that delegates to MemoryStore and
-exposes the memory tool schema.
-"""
-
-from __future__ import annotations
-
-import json
-import logging
-from typing import Any, Dict, List
-
-from agent.memory_provider import MemoryProvider
-from tools.registry import tool_error
-
-logger = logging.getLogger(__name__)
-
-
-class BuiltinMemoryProvider(MemoryProvider):
-    """Built-in file-backed memory (MEMORY.md + USER.md).
-
-    Always active, never disabled by other providers. The `memory` tool
-    is handled by run_agent.py's agent-level tool interception (not through
-    the normal registry), so get_tool_schemas() returns an empty list —
-    the memory tool is already wired separately.
-    """
-
-    def __init__(
-        self,
-        memory_store=None,
-        memory_enabled: bool = False,
-        user_profile_enabled: bool = False,
-    ):
-        self._store = memory_store
-        self._memory_enabled = memory_enabled
-        self._user_profile_enabled = user_profile_enabled
-
-    @property
-    def name(self) -> str:
-        return "builtin"
-
-    def is_available(self) -> bool:
-        """Built-in memory is always available."""
-        return True
-
-    def initialize(self, session_id: str, **kwargs) -> None:
-        """Load memory from disk if not already loaded."""
-        if self._store is not None:
-            self._store.load_from_disk()
-
-    def system_prompt_block(self) -> str:
-        """Return MEMORY.md and USER.md content for the system prompt.
-
-        Uses the frozen snapshot captured at load time. This ensures the
-        system prompt stays stable throughout a session (preserving the
-        prompt cache), even though the live entries may change via tool calls.
-        """
-        if not self._store:
-            return ""
-
-        parts = []
-        if self._memory_enabled:
-            mem_block = self._store.format_for_system_prompt("memory")
-            if mem_block:
-                parts.append(mem_block)
-        if self._user_profile_enabled:
-            user_block = self._store.format_for_system_prompt("user")
-            if user_block:
-                parts.append(user_block)
-
-        return "\n\n".join(parts)
-
-    def prefetch(self, query: str, *, session_id: str = "") -> str:
-        """Built-in memory doesn't do query-based recall — it's injected via system_prompt_block."""
-        return ""
-
-    def sync_turn(self, user_content: str, assistant_content: str, *, session_id: str = "") -> None:
-        """Built-in memory doesn't auto-sync turns — writes happen via the memory tool."""
-
-    def get_tool_schemas(self) -> List[Dict[str, Any]]:
-        """Return empty list.
-
-        The `memory` tool is an agent-level intercepted tool, handled
-        specially in run_agent.py before normal tool dispatch. It's not
-        part of the standard tool registry. We don't duplicate it here.
-        """
-        return []
-
-    def handle_tool_call(self, tool_name: str, args: Dict[str, Any], **kwargs) -> str:
-        """Not used — the memory tool is intercepted in run_agent.py."""
-        return tool_error("Built-in memory tool is handled by the agent loop")
-
-    def shutdown(self) -> None:
-        """No cleanup needed — files are saved on every write."""
-
-    # -- Property access for backward compatibility --------------------------
-
-    @property
-    def store(self):
-        """Access the underlying MemoryStore for legacy code paths."""
-        return self._store
-
-    @property
-    def memory_enabled(self) -> bool:
-        return self._memory_enabled
-
-    @property
-    def user_profile_enabled(self) -> bool:
-        return self._user_profile_enabled

agent/context_compressor.py

@@ -114,7 +114,6 @@ class ContextCompressor:
 
         self.last_prompt_tokens = 0
         self.last_completion_tokens = 0
-        self.last_total_tokens = 0
 
         self.summary_model = summary_model_override or ""
 
@@ -126,28 +125,12 @@ class ContextCompressor:
         """Update tracked token usage from API response."""
         self.last_prompt_tokens = usage.get("prompt_tokens", 0)
         self.last_completion_tokens = usage.get("completion_tokens", 0)
-        self.last_total_tokens = usage.get("total_tokens", 0)
 
     def should_compress(self, prompt_tokens: int = None) -> bool:
         """Check if context exceeds the compression threshold."""
         tokens = prompt_tokens if prompt_tokens is not None else self.last_prompt_tokens
         return tokens >= self.threshold_tokens
 
-    def should_compress_preflight(self, messages: List[Dict[str, Any]]) -> bool:
-        """Quick pre-flight check using rough estimate (before API call)."""
-        rough_estimate = estimate_messages_tokens_rough(messages)
-        return rough_estimate >= self.threshold_tokens
-
-    def get_status(self) -> Dict[str, Any]:
-        """Get current compression status for display/logging."""
-        return {
-            "last_prompt_tokens": self.last_prompt_tokens,
-            "threshold_tokens": self.threshold_tokens,
-            "context_length": self.context_length,
-            "usage_percent": min(100, (self.last_prompt_tokens / self.context_length * 100)) if self.context_length else 0,
-            "compression_count": self.compression_count,
-        }
-
     # ------------------------------------------------------------------
     # Tool output pruning (cheap pre-pass, no LLM call)
     # ------------------------------------------------------------------

agent/credential_pool.py

@@ -20,7 +20,6 @@ from hermes_cli.auth import (
     DEFAULT_AGENT_KEY_MIN_TTL_SECONDS,
     KIMI_CODE_BASE_URL,
     PROVIDER_REGISTRY,
-    _auth_store_lock,
     _codex_access_token_is_expiring,
     _decode_jwt_claims,
     _import_codex_cli_tokens,
@@ -28,8 +27,6 @@ from hermes_cli.auth import (
     _load_provider_state,
     _resolve_kimi_base_url,
     _resolve_zai_base_url,
-    _save_auth_store,
-    _save_provider_state,
     read_credential_pool,
     write_credential_pool,
 )
@@ -482,67 +479,6 @@ class CredentialPool:
             logger.debug("Failed to sync from ~/.codex/auth.json: %s", exc)
         return entry
 
-    def _sync_device_code_entry_to_auth_store(self, entry: PooledCredential) -> None:
-        """Write refreshed pool entry tokens back to auth.json providers.
-
-        After a pool-level refresh, the pool entry has fresh tokens but
-        auth.json's ``providers.<id>`` still holds the pre-refresh state.
-        On the next ``load_pool()``, ``_seed_from_singletons()`` reads that
-        stale state and can overwrite the fresh pool entry — potentially
-        re-seeding a consumed single-use refresh token.
-
-        Applies to any OAuth provider whose singleton lives in auth.json
-        (currently Nous and OpenAI Codex).
-        """
-        if entry.source != "device_code":
-            return
-        try:
-            with _auth_store_lock():
-                auth_store = _load_auth_store()
-                if self.provider == "nous":
-                    state = _load_provider_state(auth_store, "nous")
-                    if state is None:
-                        return
-                    state["access_token"] = entry.access_token
-                    if entry.refresh_token:
-                        state["refresh_token"] = entry.refresh_token
-                    if entry.expires_at:
-                        state["expires_at"] = entry.expires_at
-                    if entry.agent_key:
-                        state["agent_key"] = entry.agent_key
-                    if entry.agent_key_expires_at:
-                        state["agent_key_expires_at"] = entry.agent_key_expires_at
-                    for extra_key in ("obtained_at", "expires_in", "agent_key_id",
-                                      "agent_key_expires_in", "agent_key_reused",
-                                      "agent_key_obtained_at"):
-                        val = entry.extra.get(extra_key)
-                        if val is not None:
-                            state[extra_key] = val
-                    if entry.inference_base_url:
-                        state["inference_base_url"] = entry.inference_base_url
-                    _save_provider_state(auth_store, "nous", state)
-
-                elif self.provider == "openai-codex":
-                    state = _load_provider_state(auth_store, "openai-codex")
-                    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
-                    _save_provider_state(auth_store, "openai-codex", state)
-
-                else:
-                    return
-
-                _save_auth_store(auth_store)
-        except Exception as exc:
-            logger.debug("Failed to sync %s pool entry back to auth store: %s", self.provider, exc)
-
     def _refresh_entry(self, entry: PooledCredential, *, force: bool) -> Optional[PooledCredential]:
         if entry.auth_type != AUTH_TYPE_OAUTH or not entry.refresh_token:
             if force:
@@ -577,13 +513,6 @@ class CredentialPool:
                     except Exception as wexc:
                         logger.debug("Failed to write refreshed token to credentials file: %s", wexc)
             elif self.provider == "openai-codex":
-                # Proactively sync from ~/.codex/auth.json before refresh.
-                # The Codex CLI (or another Hermes profile) may have already
-                # consumed our refresh_token.  Syncing first avoids a
-                # "refresh_token_reused" error when the CLI has a newer pair.
-                synced = self._sync_codex_entry_from_cli(entry)
-                if synced is not entry:
-                    entry = synced
                 refreshed = auth_mod.refresh_codex_oauth_pure(
                     entry.access_token,
                     entry.refresh_token,
@@ -669,37 +598,6 @@ 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 openai-codex: the refresh_token may have been consumed by
-            # the Codex CLI between our proactive sync and the refresh call.
-            # Re-sync and retry once.
-            if self.provider == "openai-codex":
-                synced = self._sync_codex_entry_from_cli(entry)
-                if synced.refresh_token != entry.refresh_token:
-                    logger.debug("Retrying Codex refresh with synced token from ~/.codex/auth.json")
-                    try:
-                        refreshed = auth_mod.refresh_codex_oauth_pure(
-                            synced.access_token,
-                            synced.refresh_token,
-                        )
-                        updated = replace(
-                            synced,
-                            access_token=refreshed["access_token"],
-                            refresh_token=refreshed["refresh_token"],
-                            last_refresh=refreshed.get("last_refresh"),
-                            last_status=STATUS_OK,
-                            last_status_at=None,
-                            last_error_code=None,
-                        )
-                        self._replace_entry(synced, updated)
-                        self._persist()
-                        self._sync_device_code_entry_to_auth_store(updated)
-                        return updated
-                    except Exception as retry_exc:
-                        logger.debug("Codex retry refresh also failed: %s", retry_exc)
-                elif not self._entry_needs_refresh(synced):
-                    logger.debug("Codex CLI has valid token, using without refresh")
-                    self._sync_device_code_entry_to_auth_store(synced)
-                    return synced
             self._mark_exhausted(entry, None)
             return None
 
@@ -714,10 +612,6 @@ class CredentialPool:
         )
         self._replace_entry(entry, updated)
         self._persist()
-        # Sync refreshed tokens back to auth.json providers so that
-        # _seed_from_singletons() on the next load_pool() sees fresh state
-        # instead of re-seeding stale/consumed tokens.
-        self._sync_device_code_entry_to_auth_store(updated)
         return updated
 
     def _entry_needs_refresh(self, entry: PooledCredential) -> bool:
@@ -739,17 +633,6 @@ class CredentialPool:
             return False
         return False
 
-    def mark_used(self, entry_id: Optional[str] = None) -> None:
-        """Increment request_count for tracking. Used by least_used strategy."""
-        target_id = entry_id or self._current_id
-        if not target_id:
-            return
-        with self._lock:
-            for idx, entry in enumerate(self._entries):
-                if entry.id == target_id:
-                    self._entries[idx] = replace(entry, request_count=entry.request_count + 1)
-                    return
-
     def select(self) -> Optional[PooledCredential]:
         with self._lock:
             return self._select_unlocked()
@@ -911,11 +794,6 @@ class CredentialPool:
             else:
                 self._active_leases[credential_id] = count - 1
 
-    def active_lease_count(self, credential_id: str) -> int:
-        """Return the number of active leases for a credential."""
-        with self._lock:
-            return self._active_leases.get(credential_id, 0)
-
     def try_refresh_current(self) -> Optional[PooledCredential]:
         with self._lock:
             return self._try_refresh_current_unlocked()

agent/display.py

@@ -67,26 +67,6 @@ def _get_skin():
         return None
 
 
-def get_skin_faces(key: str, default: list) -> list:
-    """Get spinner face list from active skin, falling back to default."""
-    skin = _get_skin()
-    if skin:
-        faces = skin.get_spinner_list(key)
-        if faces:
-            return faces
-    return default
-
-
-def get_skin_verbs() -> list:
-    """Get thinking verbs from active skin."""
-    skin = _get_skin()
-    if skin:
-        verbs = skin.get_spinner_list("thinking_verbs")
-        if verbs:
-            return verbs
-    return KawaiiSpinner.THINKING_VERBS
-
-
 def get_skin_tool_prefix() -> str:
     """Get tool output prefix character from active skin."""
     skin = _get_skin()
@@ -723,46 +703,6 @@ class KawaiiSpinner:
         return False
 
 
-# =========================================================================
-# Kawaii face arrays (used by AIAgent._execute_tool_calls for spinner text)
-# =========================================================================
-
-KAWAII_SEARCH = [
-    "♪(´ε` )", "(｡◕‿◕｡)", "ヾ(＾∇＾)", "(◕ᴗ◕✿)", "( ˘▽˘)っ",
-    "٩(◕‿◕｡)۶", "(✿◠‿◠)", "♪～(´ε｀ )", "(ノ´ヮ`)ノ*:・゚✧", "＼(◎o◎)／",
-]
-KAWAII_READ = [
-    "φ(゜▽゜*)♪", "( ˘▽˘)っ", "(⌐■_■)", "٩(｡•́‿•̀｡)۶", "(◕‿◕✿)",
-    "ヾ(＠⌒ー⌒＠)ノ", "(✧ω✧)", "♪(๑ᴖ◡ᴖ๑)♪", "(≧◡≦)", "( ´ ▽ ` )ノ",
-]
-KAWAII_TERMINAL = [
-    "ヽ(>∀<☆)ノ", "(ノ°∀°)ノ", "٩(^ᴗ^)۶", "ヾ(⌐■_■)ノ♪", "(•̀ᴗ•́)و",
-    "┗(＾0＾)┓", "(｀・ω・´)", "＼(￣▽￣)／", "(ง •̀_•́)ง", "ヽ(´▽`)/",
-]
-KAWAII_BROWSER = [
-    "(ノ°∀°)ノ", "(☞゚ヮ゚)☞", "( ͡° ͜ʖ ͡°)", "┌( ಠ_ಠ)┘", "(⊙_⊙)？",
-    "ヾ(•ω•`)o", "(￣ω￣)", "( ˇωˇ )", "(ᵔᴥᵔ)", "＼(◎o◎)／",
-]
-KAWAII_CREATE = [
-    "✧*。٩(ˊᗜˋ*)و✧", "(ﾉ◕ヮ◕)ﾉ*:・ﾟ✧", "ヽ(>∀<☆)ノ", "٩(♡ε♡)۶", "(◕‿◕)♡",
-    "✿◕ ‿ ◕✿", "(*≧▽≦)", "ヾ(＾-＾)ノ", "(☆▽☆)", "°˖✧◝(⁰▿⁰)◜✧˖°",
-]
-KAWAII_SKILL = [
-    "ヾ(＠⌒ー⌒＠)ノ", "(๑˃ᴗ˂)ﻭ", "٩(◕‿◕｡)۶", "(✿╹◡╹)", "ヽ(・∀・)ノ",
-    "(ノ´ヮ`)ノ*:・ﾟ✧", "♪(๑ᴖ◡ᴖ๑)♪", "(◠‿◠)", "٩(ˊᗜˋ*)و", "(＾▽＾)",
-    "ヾ(＾∇＾)", "(★ω★)/", "٩(｡•́‿•̀｡)۶", "(◕ᴗ◕✿)", "＼(◎o◎)／",
-    "(✧ω✧)", "ヽ(>∀<☆)ノ", "( ˘▽˘)っ", "(≧◡≦) ♡", "ヾ(￣▽￣)",
-]
-KAWAII_THINK = [
-    "(っ°Д°;)っ", "(；′⌒`)", "(・_・ヾ", "( ´_ゝ`)", "(￣ヘ￣)",
-    "(。-`ω´-)", "( ˘︹˘ )", "(¬_¬)", "ヽ(ー_ー )ノ", "(；一_一)",
-]
-KAWAII_GENERIC = [
-    "♪(´ε` )", "(◕‿◕✿)", "ヾ(＾∇＾)", "٩(◕‿◕｡)۶", "(✿◠‿◠)",
-    "(ノ´ヮ`)ノ*:・ﾟ✧", "ヽ(>∀<☆)ノ", "(☆▽☆)", "( ˘▽˘)っ", "(≧◡≦)",
-]
-
-
 # =========================================================================
 # Cute tool message (completion line that replaces the spinner)
 # =========================================================================
@@ -970,22 +910,6 @@ _SKY_BLUE = "\033[38;5;117m"
 _ANSI_RESET = "\033[0m"
 
 
-def honcho_session_url(workspace: str, session_name: str) -> str:
-    """Build a Honcho app URL for a session."""
-    from urllib.parse import quote
-    return (
-        f"https://app.honcho.dev/explore"
-        f"?workspace={quote(workspace, safe='')}"
-        f"&view=sessions"
-        f"&session={quote(session_name, safe='')}"
-    )
-
-
-def _osc8_link(url: str, text: str) -> str:
-    """OSC 8 terminal hyperlink (clickable in iTerm2, Ghostty, WezTerm, etc.)."""
-    return f"\033]8;;{url}\033\\{text}\033]8;;\033\\"
-
-
 # =========================================================================
 # Context pressure display (CLI user-facing warnings)
 # =========================================================================

agent/error_classifier.py

@@ -82,16 +82,6 @@ class ClassifiedError:
     def is_auth(self) -> bool:
         return self.reason in (FailoverReason.auth, FailoverReason.auth_permanent)
 
-    @property
-    def is_transient(self) -> bool:
-        """Error is expected to resolve on retry (with or without backoff)."""
-        return self.reason in (
-            FailoverReason.rate_limit,
-            FailoverReason.overloaded,
-            FailoverReason.server_error,
-            FailoverReason.timeout,
-            FailoverReason.unknown,
-        )
 
 
 # ── Provider-specific patterns ──────────────────────────────────────────
@@ -677,27 +667,6 @@ def _classify_by_message(
             should_compress=True,
         )
 
-    # Usage-limit patterns need the same disambiguation as 402: some providers
-    # surface "usage limit" errors without an HTTP status code.  A transient
-    # signal ("try again", "resets at", …) means it's a periodic quota, not
-    # billing exhaustion.
-    has_usage_limit = any(p in error_msg for p in _USAGE_LIMIT_PATTERNS)
-    if has_usage_limit:
-        has_transient_signal = any(p in error_msg for p in _USAGE_LIMIT_TRANSIENT_SIGNALS)
-        if has_transient_signal:
-            return result_fn(
-                FailoverReason.rate_limit,
-                retryable=True,
-                should_rotate_credential=True,
-                should_fallback=True,
-            )
-        return result_fn(
-            FailoverReason.billing,
-            retryable=False,
-            should_rotate_credential=True,
-            should_fallback=True,
-        )
-
     # Billing patterns
     if any(p in error_msg for p in _BILLING_PATTERNS):
         return result_fn(
@@ -725,14 +694,10 @@ def _classify_by_message(
         )
 
     # Auth patterns
-    # Auth errors should NOT be retried directly — the credential is invalid and
-    # retrying with the same key will always fail.  Set retryable=False so the
-    # caller triggers credential rotation (should_rotate_credential=True) or
-    # provider fallback rather than an immediate retry loop.
     if any(p in error_msg for p in _AUTH_PATTERNS):
         return result_fn(
             FailoverReason.auth,
-            retryable=False,
+            retryable=True,
             should_rotate_credential=True,
         )
 

agent/insights.py

@@ -39,15 +39,6 @@ def _has_known_pricing(model_name: str, provider: str = None, base_url: str = No
     return has_known_pricing(model_name, provider=provider, base_url=base_url)
 
 
-def _get_pricing(model_name: str) -> Dict[str, float]:
-    """Look up pricing for a model. Uses fuzzy matching on model name.
-
-    Returns _DEFAULT_PRICING (zero cost) for unknown/custom models —
-    we can't assume costs for self-hosted endpoints, local inference, etc.
-    """
-    return get_pricing(model_name)
-
-
 def _estimate_cost(
     session_or_model: Dict[str, Any] | str,
     input_tokens: int = 0,

agent/memory_manager.py

@@ -134,11 +134,6 @@ class MemoryManager:
         """All registered providers in order."""
         return list(self._providers)
 
-    @property
-    def provider_names(self) -> List[str]:
-        """Names of all registered providers."""
-        return [p.name for p in self._providers]
-
     def get_provider(self, name: str) -> Optional[MemoryProvider]:
         """Get a provider by name, or None if not registered."""
         for p in self._providers:

agent/models_dev.py

@@ -135,9 +135,6 @@ class ProviderInfo:
     doc: str = ""                   # documentation URL
     model_count: int = 0
 
-    def has_api_url(self) -> bool:
-        return bool(self.api)
-
 
 # ---------------------------------------------------------------------------
 # Provider ID mapping: Hermes ↔ models.dev
@@ -634,43 +631,6 @@ def get_provider_info(provider_id: str) -> Optional[ProviderInfo]:
     return _parse_provider_info(mdev_id, raw)
 
 
-def list_all_providers() -> Dict[str, ProviderInfo]:
-    """Return all providers from models.dev as {provider_id: ProviderInfo}.
-
-    Returns the full catalog — 109+ providers.  For providers that have
-    a Hermes alias, both the models.dev ID and the Hermes ID are included.
-    """
-    data = fetch_models_dev()
-    result: Dict[str, ProviderInfo] = {}
-
-    for pid, pdata in data.items():
-        if isinstance(pdata, dict):
-            info = _parse_provider_info(pid, pdata)
-            result[pid] = info
-
-    return result
-
-
-def get_providers_for_env_var(env_var: str) -> List[str]:
-    """Reverse lookup: find all providers that use a given env var.
-
-    Useful for auto-detection: "user has ANTHROPIC_API_KEY set, which
-    providers does that enable?"
-
-    Returns list of models.dev provider IDs.
-    """
-    data = fetch_models_dev()
-    matches: List[str] = []
-
-    for pid, pdata in data.items():
-        if isinstance(pdata, dict):
-            env = pdata.get("env", [])
-            if isinstance(env, list) and env_var in env:
-                matches.append(pid)
-
-    return matches
-
-
 # ---------------------------------------------------------------------------
 # Model-level queries (rich ModelInfo)
 # ---------------------------------------------------------------------------
@@ -708,74 +668,3 @@ def get_model_info(
     return None
 
 
-def get_model_info_any_provider(model_id: str) -> Optional[ModelInfo]:
-    """Search all providers for a model by ID.
-
-    Useful when you have a full slug like "anthropic/claude-sonnet-4.6" or
-    a bare name and want to find it anywhere.  Checks Hermes-mapped providers
-    first, then falls back to all models.dev providers.
-    """
-    data = fetch_models_dev()
-
-    # Try Hermes-mapped providers first (more likely what the user wants)
-    for hermes_id, mdev_id in PROVIDER_TO_MODELS_DEV.items():
-        pdata = data.get(mdev_id)
-        if not isinstance(pdata, dict):
-            continue
-        models = pdata.get("models", {})
-        if not isinstance(models, dict):
-            continue
-
-        raw = models.get(model_id)
-        if isinstance(raw, dict):
-            return _parse_model_info(model_id, raw, mdev_id)
-
-        # Case-insensitive
-        model_lower = model_id.lower()
-        for mid, mdata in models.items():
-            if mid.lower() == model_lower and isinstance(mdata, dict):
-                return _parse_model_info(mid, mdata, mdev_id)
-
-    # Fall back to ALL providers
-    for pid, pdata in data.items():
-        if pid in _get_reverse_mapping():
-            continue  # already checked
-        if not isinstance(pdata, dict):
-            continue
-        models = pdata.get("models", {})
-        if not isinstance(models, dict):
-            continue
-
-        raw = models.get(model_id)
-        if isinstance(raw, dict):
-            return _parse_model_info(model_id, raw, pid)
-
-    return None
-
-
-def list_provider_model_infos(provider_id: str) -> List[ModelInfo]:
-    """Return all models for a provider as ModelInfo objects.
-
-    Filters out deprecated models by default.
-    """
-    mdev_id = PROVIDER_TO_MODELS_DEV.get(provider_id, provider_id)
-
-    data = fetch_models_dev()
-    pdata = data.get(mdev_id)
-    if not isinstance(pdata, dict):
-        return []
-
-    models = pdata.get("models", {})
-    if not isinstance(models, dict):
-        return []
-
-    result: List[ModelInfo] = []
-    for mid, mdata in models.items():
-        if not isinstance(mdata, dict):
-            continue
-        status = mdata.get("status", "")
-        if status == "deprecated":
-            continue
-        result.append(_parse_model_info(mid, mdata, mdev_id))
-
-    return result

agent/prompt_builder.py

@@ -491,17 +491,6 @@ def _parse_skill_file(skill_file: Path) -> tuple[bool, dict, str]:
         return True, {}, ""
 
 
-def _read_skill_conditions(skill_file: Path) -> dict:
-    """Extract conditional activation fields from SKILL.md frontmatter."""
-    try:
-        raw = skill_file.read_text(encoding="utf-8")[:2000]
-        frontmatter, _ = parse_frontmatter(raw)
-        return extract_skill_conditions(frontmatter)
-    except Exception as e:
-        logger.debug("Failed to read skill conditions from %s: %s", skill_file, e)
-        return {}
-
-
 def _skill_should_show(
     conditions: dict,
     available_tools: "set[str] | None",

agent/usage_pricing.py

@@ -595,30 +595,6 @@ def get_pricing(
     }
 
 
-def estimate_cost_usd(
-    model: str,
-    input_tokens: int,
-    output_tokens: int,
-    *,
-    provider: Optional[str] = None,
-    base_url: Optional[str] = None,
-    api_key: Optional[str] = None,
-) -> float:
-    """Backward-compatible helper for legacy callers.
-
-    This uses non-cached input/output only. New code should call
-    `estimate_usage_cost()` with canonical usage buckets.
-    """
-    result = estimate_usage_cost(
-        model,
-        CanonicalUsage(input_tokens=input_tokens, output_tokens=output_tokens),
-        provider=provider,
-        base_url=base_url,
-        api_key=api_key,
-    )
-    return float(result.amount_usd or _ZERO)
-
-
 def format_duration_compact(seconds: float) -> str:
     if seconds < 60:
         return f"{seconds:.0f}s"

constraints-termux.txt

@@ -1,15 +0,0 @@
-# Termux / Android dependency constraints for Hermes Agent.
-#
-# Usage:
-#   python -m pip install -e '.[termux]' -c constraints-termux.txt
-#
-# These pins keep the tested Android install path stable when upstream packages
-# move faster than Termux-compatible wheels / sdists.
-
-ipython<10
-jedi>=0.18.1,<0.20
-parso>=0.8.4,<0.9
-stack-data>=0.6,<0.7
-pexpect>4.3,<5
-matplotlib-inline>=0.1.7,<0.2
-asttokens>=2.1,<3

gateway/config.py

@@ -901,9 +901,6 @@ def _apply_env_overrides(config: GatewayConfig) -> None:
                 pass
         if api_server_host:
             config.platforms[Platform.API_SERVER].extra["host"] = api_server_host
-        api_server_model_name = os.getenv("API_SERVER_MODEL_NAME", "")
-        if api_server_model_name:
-            config.platforms[Platform.API_SERVER].extra["model_name"] = api_server_model_name
 
     # Webhook platform
     webhook_enabled = os.getenv("WEBHOOK_ENABLED", "").lower() in ("true", "1", "yes")

gateway/delivery.py

@@ -124,53 +124,6 @@ class DeliveryRouter:
         self.adapters = adapters or {}
         self.output_dir = get_hermes_home() / "cron" / "output"
     
-    def resolve_targets(
-        self,
-        deliver: Union[str, List[str]],
-        origin: Optional[SessionSource] = None
-    ) -> List[DeliveryTarget]:
-        """
-        Resolve delivery specification to concrete targets.
-        
-        Args:
-            deliver: Delivery spec - "origin", "telegram", ["local", "discord"], etc.
-            origin: The source where the request originated (for "origin" target)
-        
-        Returns:
-            List of resolved delivery targets
-        """
-        if isinstance(deliver, str):
-            deliver = [deliver]
-        
-        targets = []
-        seen_platforms = set()
-        
-        for target_str in deliver:
-            target = DeliveryTarget.parse(target_str, origin)
-            
-            # Resolve home channel if needed
-            if target.chat_id is None and target.platform != Platform.LOCAL:
-                home = self.config.get_home_channel(target.platform)
-                if home:
-                    target.chat_id = home.chat_id
-                else:
-                    # No home channel configured, skip this platform
-                    continue
-            
-            # Deduplicate
-            key = (target.platform, target.chat_id, target.thread_id)
-            if key not in seen_platforms:
-                seen_platforms.add(key)
-                targets.append(target)
-        
-        # Always include local if configured
-        if self.config.always_log_local:
-            local_key = (Platform.LOCAL, None, None)
-            if local_key not in seen_platforms:
-                targets.append(DeliveryTarget(platform=Platform.LOCAL))
-        
-        return targets
-    
     async def deliver(
         self,
         content: str,
@@ -299,19 +252,5 @@ class DeliveryRouter:
         return await adapter.send(target.chat_id, content, metadata=send_metadata or None)
 
 
-def parse_deliver_spec(
-    deliver: Optional[Union[str, List[str]]],
-    origin: Optional[SessionSource] = None,
-    default: str = "origin"
-) -> Union[str, List[str]]:
-    """
-    Normalize a delivery specification.
-    
-    If None or empty, returns the default.
-    """
-    if not deliver:
-        return default
-    return deliver
-
 
 

gateway/platforms/api_server.py

@@ -299,9 +299,6 @@ class APIServerAdapter(BasePlatformAdapter):
         self._cors_origins: tuple[str, ...] = self._parse_cors_origins(
             extra.get("cors_origins", os.getenv("API_SERVER_CORS_ORIGINS", "")),
         )
-        self._model_name: str = self._resolve_model_name(
-            extra.get("model_name", os.getenv("API_SERVER_MODEL_NAME", "")),
-        )
         self._app: Optional["web.Application"] = None
         self._runner: Optional["web.AppRunner"] = None
         self._site: Optional["web.TCPSite"] = None
@@ -327,26 +324,6 @@ class APIServerAdapter(BasePlatformAdapter):
 
         return tuple(str(item).strip() for item in items if str(item).strip())
 
-    @staticmethod
-    def _resolve_model_name(explicit: str) -> str:
-        """Derive the advertised model name for /v1/models.
-
-        Priority:
-        1. Explicit override (config extra or API_SERVER_MODEL_NAME env var)
-        2. Active profile name (so each profile advertises a distinct model)
-        3. Fallback: "hermes-agent"
-        """
-        if explicit and explicit.strip():
-            return explicit.strip()
-        try:
-            from hermes_cli.profiles import get_active_profile_name
-            profile = get_active_profile_name()
-            if profile and profile not in ("default", "custom"):
-                return profile
-        except Exception:
-            pass
-        return "hermes-agent"
-
     def _cors_headers_for_origin(self, origin: str) -> Optional[Dict[str, str]]:
         """Return CORS headers for an allowed browser origin."""
         if not origin or not self._cors_origins:
@@ -491,12 +468,12 @@ class APIServerAdapter(BasePlatformAdapter):
             "object": "list",
             "data": [
                 {
-                    "id": self._model_name,
+                    "id": "hermes-agent",
                     "object": "model",
                     "created": int(time.time()),
                     "owned_by": "hermes",
                     "permission": [],
-                    "root": self._model_name,
+                    "root": "hermes-agent",
                     "parent": None,
                 }
             ],
@@ -569,7 +546,7 @@ class APIServerAdapter(BasePlatformAdapter):
             # history already set from request body above
 
         completion_id = f"chatcmpl-{uuid.uuid4().hex[:29]}"
-        model_name = body.get("model", self._model_name)
+        model_name = body.get("model", "hermes-agent")
         created = int(time.time())
 
         if stream:
@@ -946,7 +923,7 @@ class APIServerAdapter(BasePlatformAdapter):
             "object": "response",
             "status": "completed",
             "created_at": created_at,
-            "model": body.get("model", self._model_name),
+            "model": body.get("model", "hermes-agent"),
             "output": output_items,
             "usage": {
                 "input_tokens": usage.get("input_tokens", 0),
@@ -1676,8 +1653,8 @@ class APIServerAdapter(BasePlatformAdapter):
 
             self._mark_connected()
             logger.info(
-                "[%s] API server listening on http://%s:%d (model: %s)",
-                self.name, self._host, self._port, self._model_name,
+                "[%s] API server listening on http://%s:%d",
+                self.name, self._host, self._port,
             )
             return True
 

gateway/platforms/discord.py

@@ -422,7 +422,6 @@ class DiscordAdapter(BasePlatformAdapter):
 
     # Discord message limits
     MAX_MESSAGE_LENGTH = 2000
-    _SPLIT_THRESHOLD = 1900  # near the 2000-char split point
 
     # Auto-disconnect from voice channel after this many seconds of inactivity
     VOICE_TIMEOUT = 300
@@ -434,11 +433,6 @@ class DiscordAdapter(BasePlatformAdapter):
         self._allowed_user_ids: set = set()  # For button approval authorization
         # Voice channel state (per-guild)
         self._voice_clients: Dict[int, Any] = {}  # guild_id -> VoiceClient
-        # Text batching: merge rapid successive messages (Telegram-style)
-        self._text_batch_delay_seconds = float(os.getenv("HERMES_DISCORD_TEXT_BATCH_DELAY_SECONDS", "0.6"))
-        self._text_batch_split_delay_seconds = float(os.getenv("HERMES_DISCORD_TEXT_BATCH_SPLIT_DELAY_SECONDS", "2.0"))
-        self._pending_text_batches: Dict[str, MessageEvent] = {}
-        self._pending_text_batch_tasks: Dict[str, asyncio.Task] = {}
         self._voice_text_channels: Dict[int, int] = {}  # guild_id -> text_channel_id
         self._voice_timeout_tasks: Dict[int, asyncio.Task] = {}  # guild_id -> timeout task
         # Phase 2: voice listening
@@ -2472,80 +2466,7 @@ class DiscordAdapter(BasePlatformAdapter):
         if thread_id:
             self._track_thread(thread_id)
 
-        # Only batch plain text messages — commands, media, etc. dispatch
-        # immediately since they won't be split by the Discord client.
-        if msg_type == MessageType.TEXT and self._text_batch_delay_seconds > 0:
-            self._enqueue_text_event(event)
-        else:
-            await self.handle_message(event)
-
-    # ------------------------------------------------------------------
-    # Text message aggregation (handles Discord client-side splits)
-    # ------------------------------------------------------------------
-
-    def _text_batch_key(self, event: MessageEvent) -> str:
-        """Session-scoped key for text message batching."""
-        from gateway.session import build_session_key
-        return build_session_key(
-            event.source,
-            group_sessions_per_user=self.config.extra.get("group_sessions_per_user", True),
-            thread_sessions_per_user=self.config.extra.get("thread_sessions_per_user", False),
-        )
-
-    def _enqueue_text_event(self, event: MessageEvent) -> None:
-        """Buffer a text event and reset the flush timer.
-
-        When Discord splits a long user message at 2000 chars, the chunks
-        arrive within a few hundred milliseconds.  This merges them into
-        a single event before dispatching.
-        """
-        key = self._text_batch_key(event)
-        existing = self._pending_text_batches.get(key)
-        chunk_len = len(event.text or "")
-        if existing is None:
-            event._last_chunk_len = chunk_len  # type: ignore[attr-defined]
-            self._pending_text_batches[key] = event
-        else:
-            if event.text:
-                existing.text = f"{existing.text}\n{event.text}" if existing.text else event.text
-            existing._last_chunk_len = chunk_len  # type: ignore[attr-defined]
-            if event.media_urls:
-                existing.media_urls.extend(event.media_urls)
-                existing.media_types.extend(event.media_types)
-
-        prior_task = self._pending_text_batch_tasks.get(key)
-        if prior_task and not prior_task.done():
-            prior_task.cancel()
-        self._pending_text_batch_tasks[key] = asyncio.create_task(
-            self._flush_text_batch(key)
-        )
-
-    async def _flush_text_batch(self, key: str) -> None:
-        """Wait for the quiet period then dispatch the aggregated text.
-
-        Uses a longer delay when the latest chunk is near Discord's 2000-char
-        split point, since a continuation chunk is almost certain.
-        """
-        current_task = asyncio.current_task()
-        try:
-            pending = self._pending_text_batches.get(key)
-            last_len = getattr(pending, "_last_chunk_len", 0) if pending else 0
-            if last_len >= self._SPLIT_THRESHOLD:
-                delay = self._text_batch_split_delay_seconds
-            else:
-                delay = self._text_batch_delay_seconds
-            await asyncio.sleep(delay)
-            event = self._pending_text_batches.pop(key, None)
-            if not event:
-                return
-            logger.info(
-                "[Discord] Flushing text batch %s (%d chars)",
-                key, len(event.text or ""),
-            )
-            await self.handle_message(event)
-        finally:
-            if self._pending_text_batch_tasks.get(key) is current_task:
-                self._pending_text_batch_tasks.pop(key, None)
+        await self.handle_message(event)
 
 
 # ---------------------------------------------------------------------------

gateway/platforms/feishu.py

@@ -264,7 +264,6 @@ class FeishuAdapterSettings:
     bot_name: str
     dedup_cache_size: int
     text_batch_delay_seconds: float
-    text_batch_split_delay_seconds: float
     text_batch_max_messages: int
     text_batch_max_chars: int
     media_batch_delay_seconds: float
@@ -1015,10 +1014,6 @@ class FeishuAdapter(BasePlatformAdapter):
     """Feishu/Lark bot adapter."""
 
     MAX_MESSAGE_LENGTH = 8000
-    # Threshold for detecting Feishu client-side message splits.
-    # When a chunk is near the ~4096-char practical limit, a continuation
-    # is almost certain.
-    _SPLIT_THRESHOLD = 4000
 
     # =========================================================================
     # Lifecycle — init / settings / connect / disconnect
@@ -1110,9 +1105,6 @@ class FeishuAdapter(BasePlatformAdapter):
             text_batch_delay_seconds=float(
                 os.getenv("HERMES_FEISHU_TEXT_BATCH_DELAY_SECONDS", str(_DEFAULT_TEXT_BATCH_DELAY_SECONDS))
             ),
-            text_batch_split_delay_seconds=float(
-                os.getenv("HERMES_FEISHU_TEXT_BATCH_SPLIT_DELAY_SECONDS", "2.0")
-            ),
             text_batch_max_messages=max(
                 1,
                 int(os.getenv("HERMES_FEISHU_TEXT_BATCH_MAX_MESSAGES", str(_DEFAULT_TEXT_BATCH_MAX_MESSAGES))),
@@ -1160,7 +1152,6 @@ class FeishuAdapter(BasePlatformAdapter):
         self._bot_name = settings.bot_name
         self._dedup_cache_size = settings.dedup_cache_size
         self._text_batch_delay_seconds = settings.text_batch_delay_seconds
-        self._text_batch_split_delay_seconds = settings.text_batch_split_delay_seconds
         self._text_batch_max_messages = settings.text_batch_max_messages
         self._text_batch_max_chars = settings.text_batch_max_chars
         self._media_batch_delay_seconds = settings.media_batch_delay_seconds
@@ -2487,10 +2478,8 @@ class FeishuAdapter(BasePlatformAdapter):
     async def _enqueue_text_event(self, event: MessageEvent) -> None:
         """Debounce rapid Feishu text bursts into a single MessageEvent."""
         key = self._text_batch_key(event)
-        chunk_len = len(event.text or "")
         existing = self._pending_text_batches.get(key)
         if existing is None:
-            event._last_chunk_len = chunk_len  # type: ignore[attr-defined]
             self._pending_text_batches[key] = event
             self._pending_text_batch_counts[key] = 1
             self._schedule_text_batch_flush(key)
@@ -2515,7 +2504,6 @@ class FeishuAdapter(BasePlatformAdapter):
             return
 
         existing.text = next_text
-        existing._last_chunk_len = chunk_len  # type: ignore[attr-defined]
         existing.timestamp = event.timestamp
         if event.message_id:
             existing.message_id = event.message_id
@@ -2542,22 +2530,10 @@ class FeishuAdapter(BasePlatformAdapter):
         task_map[key] = asyncio.create_task(flush_fn(key))
 
     async def _flush_text_batch(self, key: str) -> None:
-        """Flush a pending text batch after the quiet period.
-
-        Uses a longer delay when the latest chunk is near Feishu's ~4096-char
-        split point, since a continuation chunk is almost certain.
-        """
+        """Flush a pending text batch after the quiet period."""
         current_task = asyncio.current_task()
         try:
-            # Adaptive delay: if the latest chunk is near the split threshold,
-            # a continuation is almost certain — wait longer.
-            pending = self._pending_text_batches.get(key)
-            last_len = getattr(pending, "_last_chunk_len", 0) if pending else 0
-            if last_len >= self._SPLIT_THRESHOLD:
-                delay = self._text_batch_split_delay_seconds
-            else:
-                delay = self._text_batch_delay_seconds
-            await asyncio.sleep(delay)
+            await asyncio.sleep(self._text_batch_delay_seconds)
             await self._flush_text_batch_now(key)
         finally:
             if self._pending_text_batch_tasks.get(key) is current_task:

gateway/platforms/matrix.py

@@ -120,11 +120,6 @@ def check_matrix_requirements() -> bool:
 class MatrixAdapter(BasePlatformAdapter):
     """Gateway adapter for Matrix (any homeserver)."""
 
-    # Threshold for detecting Matrix client-side message splits.
-    # When a chunk is near the ~4000-char practical limit, a continuation
-    # is almost certain.
-    _SPLIT_THRESHOLD = 3900
-
     def __init__(self, config: PlatformConfig):
         super().__init__(config, Platform.MATRIX)
 
@@ -177,13 +172,6 @@ class MatrixAdapter(BasePlatformAdapter):
             "MATRIX_REACTIONS", "true"
         ).lower() not in ("false", "0", "no")
 
-        # Text batching: merge rapid successive messages (Telegram-style).
-        # Matrix clients split long messages around 4000 chars.
-        self._text_batch_delay_seconds = float(os.getenv("HERMES_MATRIX_TEXT_BATCH_DELAY_SECONDS", "0.6"))
-        self._text_batch_split_delay_seconds = float(os.getenv("HERMES_MATRIX_TEXT_BATCH_SPLIT_DELAY_SECONDS", "2.0"))
-        self._pending_text_batches: Dict[str, MessageEvent] = {}
-        self._pending_text_batch_tasks: Dict[str, asyncio.Task] = {}
-
     def _is_duplicate_event(self, event_id) -> bool:
         """Return True if this event was already processed. Tracks the ID otherwise."""
         if not event_id:
@@ -1100,81 +1088,7 @@ class MatrixAdapter(BasePlatformAdapter):
         # Acknowledge receipt so the room shows as read (fire-and-forget).
         self._background_read_receipt(room.room_id, event.event_id)
 
-        # Only batch plain text messages — commands dispatch immediately.
-        if msg_type == MessageType.TEXT and self._text_batch_delay_seconds > 0:
-            self._enqueue_text_event(msg_event)
-        else:
-            await self.handle_message(msg_event)
-
-    # ------------------------------------------------------------------
-    # Text message aggregation (handles Matrix client-side splits)
-    # ------------------------------------------------------------------
-
-    def _text_batch_key(self, event: MessageEvent) -> str:
-        """Session-scoped key for text message batching."""
-        from gateway.session import build_session_key
-        return build_session_key(
-            event.source,
-            group_sessions_per_user=self.config.extra.get("group_sessions_per_user", True),
-            thread_sessions_per_user=self.config.extra.get("thread_sessions_per_user", False),
-        )
-
-    def _enqueue_text_event(self, event: MessageEvent) -> None:
-        """Buffer a text event and reset the flush timer.
-
-        When a Matrix client splits a long message, the chunks arrive within
-        a few hundred milliseconds.  This merges them into a single event
-        before dispatching.
-        """
-        key = self._text_batch_key(event)
-        existing = self._pending_text_batches.get(key)
-        chunk_len = len(event.text or "")
-        if existing is None:
-            event._last_chunk_len = chunk_len  # type: ignore[attr-defined]
-            self._pending_text_batches[key] = event
-        else:
-            if event.text:
-                existing.text = f"{existing.text}\n{event.text}" if existing.text else event.text
-            existing._last_chunk_len = chunk_len  # type: ignore[attr-defined]
-            # Merge any media that might be attached
-            if event.media_urls:
-                existing.media_urls.extend(event.media_urls)
-                existing.media_types.extend(event.media_types)
-
-        # Cancel any pending flush and restart the timer
-        prior_task = self._pending_text_batch_tasks.get(key)
-        if prior_task and not prior_task.done():
-            prior_task.cancel()
-        self._pending_text_batch_tasks[key] = asyncio.create_task(
-            self._flush_text_batch(key)
-        )
-
-    async def _flush_text_batch(self, key: str) -> None:
-        """Wait for the quiet period then dispatch the aggregated text.
-
-        Uses a longer delay when the latest chunk is near Matrix's ~4000-char
-        split point, since a continuation chunk is almost certain.
-        """
-        current_task = asyncio.current_task()
-        try:
-            pending = self._pending_text_batches.get(key)
-            last_len = getattr(pending, "_last_chunk_len", 0) if pending else 0
-            if last_len >= self._SPLIT_THRESHOLD:
-                delay = self._text_batch_split_delay_seconds
-            else:
-                delay = self._text_batch_delay_seconds
-            await asyncio.sleep(delay)
-            event = self._pending_text_batches.pop(key, None)
-            if not event:
-                return
-            logger.info(
-                "[Matrix] Flushing text batch %s (%d chars)",
-                key, len(event.text or ""),
-            )
-            await self.handle_message(event)
-        finally:
-            if self._pending_text_batch_tasks.get(key) is current_task:
-                self._pending_text_batch_tasks.pop(key, None)
+        await self.handle_message(msg_event)
 
     async def _on_room_message_media(self, room: Any, event: Any) -> None:
         """Handle incoming media messages (images, audio, video, files)."""

gateway/platforms/telegram.py

@@ -121,9 +121,6 @@ class TelegramAdapter(BasePlatformAdapter):
     
     # Telegram message limits
     MAX_MESSAGE_LENGTH = 4096
-    # Threshold for detecting Telegram client-side message splits.
-    # When a chunk is near this limit, a continuation is almost certain.
-    _SPLIT_THRESHOLD = 4000
     MEDIA_GROUP_WAIT_SECONDS = 0.8
     
     def __init__(self, config: PlatformConfig):
@@ -143,7 +140,6 @@ class TelegramAdapter(BasePlatformAdapter):
         # Buffer rapid text messages so Telegram client-side splits of long
         # messages are aggregated into a single MessageEvent.
         self._text_batch_delay_seconds = float(os.getenv("HERMES_TELEGRAM_TEXT_BATCH_DELAY_SECONDS", "0.6"))
-        self._text_batch_split_delay_seconds = float(os.getenv("HERMES_TELEGRAM_TEXT_BATCH_SPLIT_DELAY_SECONDS", "2.0"))
         self._pending_text_batches: Dict[str, MessageEvent] = {}
         self._pending_text_batch_tasks: Dict[str, asyncio.Task] = {}
         self._token_lock_identity: Optional[str] = None
@@ -2164,15 +2160,12 @@ class TelegramAdapter(BasePlatformAdapter):
         """
         key = self._text_batch_key(event)
         existing = self._pending_text_batches.get(key)
-        chunk_len = len(event.text or "")
         if existing is None:
-            event._last_chunk_len = chunk_len  # type: ignore[attr-defined]
             self._pending_text_batches[key] = event
         else:
             # Append text from the follow-up chunk
             if event.text:
                 existing.text = f"{existing.text}\n{event.text}" if existing.text else event.text
-            existing._last_chunk_len = chunk_len  # type: ignore[attr-defined]
             # Merge any media that might be attached
             if event.media_urls:
                 existing.media_urls.extend(event.media_urls)
@@ -2187,22 +2180,10 @@ class TelegramAdapter(BasePlatformAdapter):
         )
 
     async def _flush_text_batch(self, key: str) -> None:
-        """Wait for the quiet period then dispatch the aggregated text.
-
-        Uses a longer delay when the latest chunk is near Telegram's 4096-char
-        split point, since a continuation chunk is almost certain.
-        """
+        """Wait for the quiet period then dispatch the aggregated text."""
         current_task = asyncio.current_task()
         try:
-            # Adaptive delay: if the latest chunk is near Telegram's 4096-char
-            # split point, a continuation is almost certain — wait longer.
-            pending = self._pending_text_batches.get(key)
-            last_len = getattr(pending, "_last_chunk_len", 0) if pending else 0
-            if last_len >= self._SPLIT_THRESHOLD:
-                delay = self._text_batch_split_delay_seconds
-            else:
-                delay = self._text_batch_delay_seconds
-            await asyncio.sleep(delay)
+            await asyncio.sleep(self._text_batch_delay_seconds)
             event = self._pending_text_batches.pop(key, None)
             if not event:
                 return

gateway/platforms/wecom.py

@@ -143,9 +143,6 @@ class WeComAdapter(BasePlatformAdapter):
     """WeCom AI Bot adapter backed by a persistent WebSocket connection."""
 
     MAX_MESSAGE_LENGTH = MAX_MESSAGE_LENGTH
-    # Threshold for detecting WeCom client-side message splits.
-    # When a chunk is near the 4000-char limit, a continuation is almost certain.
-    _SPLIT_THRESHOLD = 3900
 
     def __init__(self, config: PlatformConfig):
         super().__init__(config, Platform.WECOM)
@@ -175,13 +172,6 @@ class WeComAdapter(BasePlatformAdapter):
         self._seen_messages: Dict[str, float] = {}
         self._reply_req_ids: Dict[str, str] = {}
 
-        # Text batching: merge rapid successive messages (Telegram-style).
-        # WeCom clients split long messages around 4000 chars.
-        self._text_batch_delay_seconds = float(os.getenv("HERMES_WECOM_TEXT_BATCH_DELAY_SECONDS", "0.6"))
-        self._text_batch_split_delay_seconds = float(os.getenv("HERMES_WECOM_TEXT_BATCH_SPLIT_DELAY_SECONDS", "2.0"))
-        self._pending_text_batches: Dict[str, MessageEvent] = {}
-        self._pending_text_batch_tasks: Dict[str, asyncio.Task] = {}
-
     # ------------------------------------------------------------------
     # Connection lifecycle
     # ------------------------------------------------------------------
@@ -529,82 +519,7 @@ class WeComAdapter(BasePlatformAdapter):
             timestamp=datetime.now(tz=timezone.utc),
         )
 
-        # Only batch plain text messages — commands, media, etc. dispatch
-        # immediately since they won't be split by the WeCom client.
-        if message_type == MessageType.TEXT and self._text_batch_delay_seconds > 0:
-            self._enqueue_text_event(event)
-        else:
-            await self.handle_message(event)
-
-    # ------------------------------------------------------------------
-    # Text message aggregation (handles WeCom client-side splits)
-    # ------------------------------------------------------------------
-
-    def _text_batch_key(self, event: MessageEvent) -> str:
-        """Session-scoped key for text message batching."""
-        from gateway.session import build_session_key
-        return build_session_key(
-            event.source,
-            group_sessions_per_user=self.config.extra.get("group_sessions_per_user", True),
-            thread_sessions_per_user=self.config.extra.get("thread_sessions_per_user", False),
-        )
-
-    def _enqueue_text_event(self, event: MessageEvent) -> None:
-        """Buffer a text event and reset the flush timer.
-
-        When WeCom splits a long user message at 4000 chars, the chunks
-        arrive within a few hundred milliseconds.  This merges them into
-        a single event before dispatching.
-        """
-        key = self._text_batch_key(event)
-        existing = self._pending_text_batches.get(key)
-        chunk_len = len(event.text or "")
-        if existing is None:
-            event._last_chunk_len = chunk_len  # type: ignore[attr-defined]
-            self._pending_text_batches[key] = event
-        else:
-            if event.text:
-                existing.text = f"{existing.text}\n{event.text}" if existing.text else event.text
-            existing._last_chunk_len = chunk_len  # type: ignore[attr-defined]
-            # Merge any media that might be attached
-            if event.media_urls:
-                existing.media_urls.extend(event.media_urls)
-                existing.media_types.extend(event.media_types)
-
-        # Cancel any pending flush and restart the timer
-        prior_task = self._pending_text_batch_tasks.get(key)
-        if prior_task and not prior_task.done():
-            prior_task.cancel()
-        self._pending_text_batch_tasks[key] = asyncio.create_task(
-            self._flush_text_batch(key)
-        )
-
-    async def _flush_text_batch(self, key: str) -> None:
-        """Wait for the quiet period then dispatch the aggregated text.
-
-        Uses a longer delay when the latest chunk is near WeCom's 4000-char
-        split point, since a continuation chunk is almost certain.
-        """
-        current_task = asyncio.current_task()
-        try:
-            pending = self._pending_text_batches.get(key)
-            last_len = getattr(pending, "_last_chunk_len", 0) if pending else 0
-            if last_len >= self._SPLIT_THRESHOLD:
-                delay = self._text_batch_split_delay_seconds
-            else:
-                delay = self._text_batch_delay_seconds
-            await asyncio.sleep(delay)
-            event = self._pending_text_batches.pop(key, None)
-            if not event:
-                return
-            logger.info(
-                "[WeCom] Flushing text batch %s (%d chars)",
-                key, len(event.text or ""),
-            )
-            await self.handle_message(event)
-        finally:
-            if self._pending_text_batch_tasks.get(key) is current_task:
-                self._pending_text_batch_tasks.pop(key, None)
+        await self.handle_message(event)
 
     @staticmethod
     def _extract_text(body: Dict[str, Any]) -> Tuple[str, Optional[str]]:

gateway/run.py

@@ -514,12 +514,6 @@ class GatewayRunner:
         self._agent_cache: Dict[str, tuple] = {}
         self._agent_cache_lock = _threading.Lock()
 
-        # Track active fallback model/provider when primary is rate-limited.
-        # Set after an agent run where fallback was activated; cleared when
-        # the primary model succeeds again or the user switches via /model.
-        self._effective_model: Optional[str] = None
-        self._effective_provider: Optional[str] = None
-
         # Per-session model overrides from /model command.
         # Key: session_key, Value: dict with model/provider/api_key/base_url/api_mode
         self._session_model_overrides: Dict[str, Dict[str, str]] = {}
@@ -5274,76 +5268,27 @@ class GatewayRunner:
         )
 
     async def _handle_usage_command(self, event: MessageEvent) -> str:
-        """Handle /usage command -- show token usage for the current session.
-
-        Checks both _running_agents (mid-turn) and _agent_cache (between turns)
-        so that rate limits, cost estimates, and detailed token breakdowns are
-        available whenever the user asks, not only while the agent is running.
-        """
+        """Handle /usage command -- show token usage for the session's last agent run."""
         source = event.source
         session_key = self._session_key_for_source(source)
 
-        # Try running agent first (mid-turn), then cached agent (between turns)
         agent = self._running_agents.get(session_key)
-        if not agent or agent is _AGENT_PENDING_SENTINEL:
-            _cache_lock = getattr(self, "_agent_cache_lock", None)
-            _cache = getattr(self, "_agent_cache", None)
-            if _cache_lock and _cache is not None:
-                with _cache_lock:
-                    cached = _cache.get(session_key)
-                    if cached:
-                        agent = cached[0]
-
         if agent and hasattr(agent, "session_total_tokens") and agent.session_api_calls > 0:
             lines = []
 
-            # Rate limits (when available from provider headers)
+            # Rate limits first (when available from provider headers)
             rl_state = agent.get_rate_limit_state()
             if rl_state and rl_state.has_data:
                 from agent.rate_limit_tracker import format_rate_limit_compact
                 lines.append(f"⏱️ **Rate Limits:** {format_rate_limit_compact(rl_state)}")
                 lines.append("")
 
-            # Session token usage — detailed breakdown matching CLI
-            input_tokens = getattr(agent, "session_input_tokens", 0) or 0
-            output_tokens = getattr(agent, "session_output_tokens", 0) or 0
-            cache_read = getattr(agent, "session_cache_read_tokens", 0) or 0
-            cache_write = getattr(agent, "session_cache_write_tokens", 0) or 0
-
+            # Session token usage
             lines.append("📊 **Session Token Usage**")
-            lines.append(f"Model: `{agent.model}`")
-            lines.append(f"Input tokens: {input_tokens:,}")
-            if cache_read:
-                lines.append(f"Cache read tokens: {cache_read:,}")
-            if cache_write:
-                lines.append(f"Cache write tokens: {cache_write:,}")
-            lines.append(f"Output tokens: {output_tokens:,}")
+            lines.append(f"Prompt (input): {agent.session_prompt_tokens:,}")
+            lines.append(f"Completion (output): {agent.session_completion_tokens:,}")
             lines.append(f"Total: {agent.session_total_tokens:,}")
             lines.append(f"API calls: {agent.session_api_calls}")
-
-            # Cost estimation
-            try:
-                from agent.usage_pricing import CanonicalUsage, estimate_usage_cost
-                cost_result = estimate_usage_cost(
-                    agent.model,
-                    CanonicalUsage(
-                        input_tokens=input_tokens,
-                        output_tokens=output_tokens,
-                        cache_read_tokens=cache_read,
-                        cache_write_tokens=cache_write,
-                    ),
-                    provider=getattr(agent, "provider", None),
-                    base_url=getattr(agent, "base_url", None),
-                )
-                if cost_result.amount_usd is not None:
-                    prefix = "~" if cost_result.status == "estimated" else ""
-                    lines.append(f"Cost: {prefix}${float(cost_result.amount_usd):.4f}")
-                elif cost_result.status == "included":
-                    lines.append("Cost: included")
-            except Exception:
-                pass
-
-            # Context window and compressions
             ctx = agent.context_compressor
             if ctx.last_prompt_tokens:
                 pct = min(100, ctx.last_prompt_tokens / ctx.context_length * 100) if ctx.context_length else 0
@@ -5353,7 +5298,7 @@ class GatewayRunner:
 
             return "\n".join(lines)
 
-        # No agent at all -- check session history for a rough count
+        # No running agent -- check session history for a rough count
         session_entry = self.session_store.get_or_create_session(source)
         history = self.session_store.load_transcript(session_entry.session_id)
         if history:
@@ -5364,7 +5309,7 @@ class GatewayRunner:
                 f"📊 **Session Info**\n"
                 f"Messages: {len(msgs)}\n"
                 f"Estimated context: ~{approx:,} tokens\n"
-                f"_(Detailed usage available after the first agent response)_"
+                f"_(Detailed usage available during active conversations)_"
             )
         return "No usage data available for this session."
 
@@ -7329,15 +7274,9 @@ class GatewayRunner:
             if _agent is not None and hasattr(_agent, 'model'):
                 _cfg_model = _resolve_gateway_model()
                 if _agent.model != _cfg_model:
-                    self._effective_model = _agent.model
-                    self._effective_provider = getattr(_agent, 'provider', None)
                     # Fallback activated — evict cached agent so the next
                     # message starts fresh and retries the primary model.
                     self._evict_cached_agent(session_key)
-                else:
-                    # Primary model worked — clear any stale fallback state
-                    self._effective_model = None
-                    self._effective_provider = None
 
             # Check if we were interrupted OR have a queued message (/queue).
             result = result_holder[0]

gateway/session.py

@@ -32,9 +32,6 @@ def _now() -> datetime:
 # PII redaction helpers
 # ---------------------------------------------------------------------------
 
-_PHONE_RE = re.compile(r"^\+?\d[\d\-\s]{6,}$")
-
-
 def _hash_id(value: str) -> str:
     """Deterministic 12-char hex hash of an identifier."""
     return hashlib.sha256(value.encode("utf-8")).hexdigest()[:12]
@@ -58,10 +55,6 @@ def _hash_chat_id(value: str) -> str:
     return _hash_id(value)
 
 
-def _looks_like_phone(value: str) -> bool:
-    """Return True if *value* looks like a phone number (E.164 or similar)."""
-    return bool(_PHONE_RE.match(value.strip()))
-
 from .config import (
     Platform,
     GatewayConfig,
@@ -144,15 +137,6 @@ class SessionSource:
             chat_id_alt=data.get("chat_id_alt"),
         )
     
-    @classmethod
-    def local_cli(cls) -> "SessionSource":
-        """Create a source representing the local CLI."""
-        return cls(
-            platform=Platform.LOCAL,
-            chat_id="cli",
-            chat_name="CLI terminal",
-            chat_type="dm",
-        )
 
 
 @dataclass
@@ -510,8 +494,7 @@ class SessionStore:
     """
     
     def __init__(self, sessions_dir: Path, config: GatewayConfig,
-                 has_active_processes_fn=None,
-                 on_auto_reset=None):
+                 has_active_processes_fn=None):
         self.sessions_dir = sessions_dir
         self.config = config
         self._entries: Dict[str, SessionEntry] = {}

hermes_cli/auth.py

@@ -70,7 +70,6 @@ DEFAULT_CODEX_BASE_URL = "https://chatgpt.com/backend-api/codex"
 DEFAULT_QWEN_BASE_URL = "https://portal.qwen.ai/v1"
 DEFAULT_GITHUB_MODELS_BASE_URL = "https://api.githubcopilot.com"
 DEFAULT_COPILOT_ACP_BASE_URL = "acp://copilot"
-DEFAULT_GEMINI_BASE_URL = "https://generativelanguage.googleapis.com/v1beta/openai"
 CODEX_OAUTH_CLIENT_ID = "app_EMoamEEZ73f0CkXaXp7hrann"
 CODEX_OAUTH_TOKEN_URL = "https://auth.openai.com/oauth/token"
 CODEX_ACCESS_TOKEN_REFRESH_SKEW_SECONDS = 120
@@ -2342,33 +2341,6 @@ def resolve_external_process_provider_credentials(provider_id: str) -> Dict[str,
     }
 
 
-# =============================================================================
-# External credential detection
-# =============================================================================
-
-def detect_external_credentials() -> List[Dict[str, Any]]:
-    """Scan for credentials from other CLI tools that Hermes can reuse.
-
-    Returns a list of dicts, each with:
-      - provider: str   -- Hermes provider id (e.g. "openai-codex")
-      - path: str       -- filesystem path where creds were found
-      - label: str      -- human-friendly description for the setup UI
-    """
-    found: List[Dict[str, Any]] = []
-
-    # Codex CLI: ~/.codex/auth.json (importable, not shared)
-    cli_tokens = _import_codex_cli_tokens()
-    if cli_tokens:
-        codex_path = Path.home() / ".codex" / "auth.json"
-        found.append({
-            "provider": "openai-codex",
-            "path": str(codex_path),
-            "label": f"Codex CLI credentials found ({codex_path}) — run `hermes auth` to create a separate session",
-        })
-
-    return found
-
-
 # =============================================================================
 # CLI Commands — login / logout
 # =============================================================================

hermes_cli/banner.py

@@ -90,12 +90,6 @@ HERMES_CADUCEUS = """[#CD7F32]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⣀⡀⠀⣀⣀
 [#B8860B]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⠳⠈⣡⠞⠁⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
 [#B8860B]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]"""
 
-COMPACT_BANNER = """
-[bold #FFD700]╔══════════════════════════════════════════════════════════════╗[/]
-[bold #FFD700]║[/]  [#FFBF00]⚕ NOUS HERMES[/] [dim #B8860B]- AI Agent Framework[/]              [bold #FFD700]║[/]
-[bold #FFD700]║[/]  [#CD7F32]Messenger of the Digital Gods[/]    [dim #B8860B]Nous Research[/]   [bold #FFD700]║[/]
-[bold #FFD700]╚══════════════════════════════════════════════════════════════╝[/]
-"""
 
 
 # =========================================================================

hermes_cli/checklist.py

@@ -1,140 +0,0 @@
-"""Shared curses-based multi-select checklist for Hermes CLI.
-
-Used by both ``hermes tools`` and ``hermes skills`` to present a
-toggleable list of items.  Falls back to a numbered text UI when
-curses is unavailable (Windows without curses, piped stdin, etc.).
-"""
-
-import sys
-from typing import List, Set
-
-from hermes_cli.colors import Colors, color
-
-
-def curses_checklist(
-    title: str,
-    items: List[str],
-    pre_selected: Set[int],
-) -> Set[int]:
-    """Multi-select checklist.  Returns set of **selected** indices.
-
-    Args:
-        title: Header text shown at the top of the checklist.
-        items: Display labels for each row.
-        pre_selected: Indices that start checked.
-
-    Returns:
-        The indices the user confirmed as checked.  On cancel (ESC/q),
-        returns ``pre_selected`` unchanged.
-    """
-    # Safety: return defaults when stdin is not a terminal.
-    if not sys.stdin.isatty():
-        return set(pre_selected)
-
-    try:
-        import curses
-        selected = set(pre_selected)
-        result = [None]
-
-        def _ui(stdscr):
-            curses.curs_set(0)
-            if curses.has_colors():
-                curses.start_color()
-                curses.use_default_colors()
-                curses.init_pair(1, curses.COLOR_GREEN, -1)
-                curses.init_pair(2, curses.COLOR_YELLOW, -1)
-                curses.init_pair(3, 8, -1)  # dim gray
-            cursor = 0
-            scroll_offset = 0
-
-            while True:
-                stdscr.clear()
-                max_y, max_x = stdscr.getmaxyx()
-
-                # Header
-                try:
-                    hattr = curses.A_BOLD | (curses.color_pair(2) if curses.has_colors() else 0)
-                    stdscr.addnstr(0, 0, title, max_x - 1, hattr)
-                    stdscr.addnstr(
-                        1, 0,
-                        "  ↑↓ navigate  SPACE toggle  ENTER confirm  ESC cancel",
-                        max_x - 1, curses.A_DIM,
-                    )
-                except curses.error:
-                    pass
-
-                # Scrollable item list
-                visible_rows = max_y - 3
-                if cursor < scroll_offset:
-                    scroll_offset = cursor
-                elif cursor >= scroll_offset + visible_rows:
-                    scroll_offset = cursor - visible_rows + 1
-
-                for draw_i, i in enumerate(
-                    range(scroll_offset, min(len(items), scroll_offset + visible_rows))
-                ):
-                    y = draw_i + 3
-                    if y >= max_y - 1:
-                        break
-                    check = "✓" if i in selected else " "
-                    arrow = "→" if i == cursor else " "
-                    line = f" {arrow} [{check}] {items[i]}"
-
-                    attr = curses.A_NORMAL
-                    if i == cursor:
-                        attr = curses.A_BOLD
-                        if curses.has_colors():
-                            attr |= curses.color_pair(1)
-                    try:
-                        stdscr.addnstr(y, 0, line, max_x - 1, attr)
-                    except curses.error:
-                        pass
-
-                stdscr.refresh()
-                key = stdscr.getch()
-
-                if key in (curses.KEY_UP, ord("k")):
-                    cursor = (cursor - 1) % len(items)
-                elif key in (curses.KEY_DOWN, ord("j")):
-                    cursor = (cursor + 1) % len(items)
-                elif key == ord(" "):
-                    selected.symmetric_difference_update({cursor})
-                elif key in (curses.KEY_ENTER, 10, 13):
-                    result[0] = set(selected)
-                    return
-                elif key in (27, ord("q")):
-                    result[0] = set(pre_selected)
-                    return
-
-        curses.wrapper(_ui)
-        return result[0] if result[0] is not None else set(pre_selected)
-
-    except Exception:
-        pass  # fall through to numbered fallback
-
-    # ── Numbered text fallback ────────────────────────────────────────────
-    selected = set(pre_selected)
-    print(color(f"\n  {title}", Colors.YELLOW))
-    print(color("  Toggle by number, Enter to confirm.\n", Colors.DIM))
-
-    while True:
-        for i, label in enumerate(items):
-            check = "✓" if i in selected else " "
-            print(f"    {i + 1:3}. [{check}] {label}")
-        print()
-
-        try:
-            raw = input(color("  Number to toggle, 's' to save, 'q' to cancel: ", Colors.DIM)).strip()
-        except (KeyboardInterrupt, EOFError):
-            return set(pre_selected)
-
-        if raw.lower() == "s" or raw == "":
-            return selected
-        if raw.lower() == "q":
-            return set(pre_selected)
-        try:
-            idx = int(raw) - 1
-            if 0 <= idx < len(items):
-                selected.symmetric_difference_update({idx})
-        except ValueError:
-            print(color("  Invalid input", Colors.DIM))

hermes_cli/commands.py

@@ -100,9 +100,6 @@ COMMAND_REGISTRY: list[CommandDef] = [
     CommandDef("reasoning", "Manage reasoning effort and display", "Configuration",
                args_hint="[level|show|hide]",
                subcommands=("none", "minimal", "low", "medium", "high", "xhigh", "show", "hide", "on", "off")),
-    CommandDef("fast", "Toggle fast mode — OpenAI Priority Processing / Anthropic Fast Mode (Normal/Fast)", "Configuration",
-               cli_only=True, args_hint="[normal|fast|status]",
-               subcommands=("normal", "fast", "status", "on", "off")),
     CommandDef("skin", "Show or change the display skin/theme", "Configuration",
                cli_only=True, args_hint="[name]"),
     CommandDef("voice", "Toggle voice mode", "Configuration",
@@ -138,8 +135,6 @@ COMMAND_REGISTRY: list[CommandDef] = [
                cli_only=True, aliases=("gateway",)),
     CommandDef("paste", "Check clipboard for an image and attach it", "Info",
                cli_only=True),
-    CommandDef("image", "Attach a local image file for your next prompt", "Info",
-               cli_only=True, args_hint="<path>"),
     CommandDef("update", "Update Hermes Agent to the latest version", "Info",
                gateway_only=True),
 
@@ -174,12 +169,6 @@ def resolve_command(name: str) -> CommandDef | None:
     return _COMMAND_LOOKUP.get(name.lower().lstrip("/"))
 
 
-def register_plugin_command(cmd: CommandDef) -> None:
-    """Append a plugin-defined command to the registry and refresh lookups."""
-    COMMAND_REGISTRY.append(cmd)
-    rebuild_lookups()
-
-
 def rebuild_lookups() -> None:
     """Rebuild all derived lookup dicts from the current COMMAND_REGISTRY.
 
@@ -642,18 +631,8 @@ class SlashCommandCompleter(Completer):
     def __init__(
         self,
         skill_commands_provider: Callable[[], Mapping[str, dict[str, Any]]] | None = None,
-        command_filter: Callable[[str], bool] | None = None,
     ) -> None:
         self._skill_commands_provider = skill_commands_provider
-        self._command_filter = command_filter
-
-    def _command_allowed(self, slash_command: str) -> bool:
-        if self._command_filter is None:
-            return True
-        try:
-            return bool(self._command_filter(slash_command))
-        except Exception:
-            return True
 
     def _iter_skill_commands(self) -> Mapping[str, dict[str, Any]]:
         if self._skill_commands_provider is None:
@@ -931,7 +910,7 @@ class SlashCommandCompleter(Completer):
                 return
 
             # Static subcommand completions
-            if " " not in sub_text and base_cmd in SUBCOMMANDS and self._command_allowed(base_cmd):
+            if " " not in sub_text and base_cmd in SUBCOMMANDS:
                 for sub in SUBCOMMANDS[base_cmd]:
                     if sub.startswith(sub_lower) and sub != sub_lower:
                         yield Completion(
@@ -944,8 +923,6 @@ class SlashCommandCompleter(Completer):
         word = text[1:]
 
         for cmd, desc in COMMANDS.items():
-            if not self._command_allowed(cmd):
-                continue
             cmd_name = cmd[1:]
             if cmd_name.startswith(word):
                 yield Completion(
@@ -1004,8 +981,6 @@ class SlashCommandAutoSuggest(AutoSuggest):
             # Still typing the command name: /upd → suggest "ate"
             word = text[1:].lower()
             for cmd in COMMANDS:
-                if self._completer is not None and not self._completer._command_allowed(cmd):
-                    continue
                 cmd_name = cmd[1:]  # strip leading /
                 if cmd_name.startswith(word) and cmd_name != word:
                     return Suggestion(cmd_name[len(word):])
@@ -1016,8 +991,6 @@ class SlashCommandAutoSuggest(AutoSuggest):
         sub_lower = sub_text.lower()
 
         # Static subcommands
-        if self._completer is not None and not self._completer._command_allowed(base_cmd):
-            return None
         if base_cmd in SUBCOMMANDS and SUBCOMMANDS[base_cmd]:
             if " " not in sub_text:
                 for sub in SUBCOMMANDS[base_cmd]:

hermes_cli/config.py

@@ -255,7 +255,6 @@ DEFAULT_CONFIG = {
         # tools or receiving API responses.  Only fires when the agent has
         # been completely idle for this duration.  0 = unlimited.
         "gateway_timeout": 1800,
-        "service_tier": "",
         # Tool-use enforcement: injects system prompt guidance that tells the
         # model to actually call tools instead of describing intended actions.
         # Values: "auto" (default — applies to gpt/codex models), true/false
@@ -1217,14 +1216,6 @@ OPTIONAL_ENV_VARS = {
         "category": "messaging",
         "advanced": True,
     },
-    "API_SERVER_MODEL_NAME": {
-        "description": "Model name advertised on /v1/models. Defaults to the profile name (or 'hermes-agent' for the default profile). Useful for multi-user setups with OpenWebUI.",
-        "prompt": "API server model name",
-        "url": None,
-        "password": False,
-        "category": "messaging",
-        "advanced": True,
-    },
     "WEBHOOK_ENABLED": {
         "description": "Enable the webhook platform adapter for receiving events from GitHub, GitLab, etc.",
         "prompt": "Enable webhooks (true/false)",

hermes_cli/copilot_auth.py

@@ -31,13 +31,6 @@ logger = logging.getLogger(__name__)
 
 # OAuth device code flow constants (same client ID as opencode/Copilot CLI)
 COPILOT_OAUTH_CLIENT_ID = "Ov23li8tweQw6odWQebz"
-COPILOT_DEVICE_CODE_URL = "https://github.com/login/device/code"
-COPILOT_ACCESS_TOKEN_URL = "https://github.com/login/oauth/access_token"
-
-# Copilot API constants
-COPILOT_TOKEN_EXCHANGE_URL = "https://api.github.com/copilot_internal/v2/token"
-COPILOT_API_BASE_URL = "https://api.githubcopilot.com"
-
 # Token type prefixes
 _CLASSIC_PAT_PREFIX = "ghp_"
 _SUPPORTED_PREFIXES = ("gho_", "github_pat_", "ghu_")
@@ -50,11 +43,6 @@ _DEVICE_CODE_POLL_INTERVAL = 5  # seconds
 _DEVICE_CODE_POLL_SAFETY_MARGIN = 3  # seconds
 
 
-def is_classic_pat(token: str) -> bool:
-    """Check if a token is a classic PAT (ghp_*), which Copilot doesn't support."""
-    return token.strip().startswith(_CLASSIC_PAT_PREFIX)
-
-
 def validate_copilot_token(token: str) -> tuple[bool, str]:
     """Validate that a token is usable with the Copilot API.
 

hermes_cli/doctor.py

@@ -54,32 +54,6 @@ _PROVIDER_ENV_HINTS = (
 )
 
 
-from hermes_constants import is_termux as _is_termux
-
-
-def _python_install_cmd() -> str:
-    return "python -m pip install" if _is_termux() else "uv pip install"
-
-
-def _system_package_install_cmd(pkg: str) -> str:
-    if _is_termux():
-        return f"pkg install {pkg}"
-    if sys.platform == "darwin":
-        return f"brew install {pkg}"
-    return f"sudo apt install {pkg}"
-
-
-def _termux_browser_setup_steps(node_installed: bool) -> list[str]:
-    steps: list[str] = []
-    step = 1
-    if not node_installed:
-        steps.append(f"{step}) pkg install nodejs")
-        step += 1
-    steps.append(f"{step}) npm install -g agent-browser")
-    steps.append(f"{step + 1}) agent-browser install")
-    return steps
-
-
 def _has_provider_env_config(content: str) -> bool:
     """Return True when ~/.hermes/.env contains provider auth/base URL settings."""
     return any(key in content for key in _PROVIDER_ENV_HINTS)
@@ -226,7 +200,7 @@ def run_doctor(args):
             check_ok(name)
         except ImportError:
             check_fail(name, "(missing)")
-            issues.append(f"Install {name}: {_python_install_cmd()} {module}")
+            issues.append(f"Install {name}: uv pip install {module}")
     
     for module, name in optional_packages:
         try:
@@ -529,7 +503,7 @@ def run_doctor(args):
         check_ok("ripgrep (rg)", "(faster file search)")
     else:
         check_warn("ripgrep (rg) not found", "(file search uses grep fallback)")
-        check_info(f"Install for faster search: {_system_package_install_cmd('ripgrep')}")
+        check_info("Install for faster search: sudo apt install ripgrep")
     
     # Docker (optional)
     terminal_env = os.getenv("TERMINAL_ENV", "local")
@@ -552,10 +526,7 @@ def run_doctor(args):
         if shutil.which("docker"):
             check_ok("docker", "(optional)")
         else:
-            if _is_termux():
-                check_info("Docker backend is not available inside Termux (expected on Android)")
-            else:
-                check_warn("docker not found", "(optional)")
+            check_warn("docker not found", "(optional)")
     
     # SSH (if using ssh backend)
     if terminal_env == "ssh":
@@ -603,23 +574,9 @@ def run_doctor(args):
         if agent_browser_path.exists():
             check_ok("agent-browser (Node.js)", "(browser automation)")
         else:
-            if _is_termux():
-                check_info("agent-browser is not installed (expected in the tested Termux path)")
-                check_info("Install it manually later with: npm install -g agent-browser && agent-browser install")
-                check_info("Termux browser setup:")
-                for step in _termux_browser_setup_steps(node_installed=True):
-                    check_info(step)
-            else:
-                check_warn("agent-browser not installed", "(run: npm install)")
+            check_warn("agent-browser not installed", "(run: npm install)")
     else:
-        if _is_termux():
-            check_info("Node.js not found (browser tools are optional in the tested Termux path)")
-            check_info("Install Node.js on Termux with: pkg install nodejs")
-            check_info("Termux browser setup:")
-            for step in _termux_browser_setup_steps(node_installed=False):
-                check_info(step)
-        else:
-            check_warn("Node.js not found", "(optional, needed for browser tools)")
+        check_warn("Node.js not found", "(optional, needed for browser tools)")
     
     # npm audit for all Node.js packages
     if shutil.which("npm"):
@@ -752,7 +709,7 @@ def run_doctor(args):
                 _url = (_base.rstrip("/") + "/models") if _base else _default_url
                 _headers = {"Authorization": f"Bearer {_key}"}
                 if "api.kimi.com" in _url.lower():
-                    _headers["User-Agent"] = "KimiCLI/1.30.0"
+                    _headers["User-Agent"] = "KimiCLI/1.0"
                 _resp = httpx.get(
                     _url,
                     headers=_headers,
@@ -782,9 +739,8 @@ def run_doctor(args):
                 __import__("tinker_atropos")
                 check_ok("tinker-atropos", "(RL training backend)")
             except ImportError:
-                install_cmd = f"{_python_install_cmd()} -e ./tinker-atropos"
-                check_warn("tinker-atropos found but not installed", f"(run: {install_cmd})")
-                issues.append(f"Install tinker-atropos: {install_cmd}")
+                check_warn("tinker-atropos found but not installed", "(run: uv pip install -e ./tinker-atropos)")
+                issues.append("Install tinker-atropos: uv pip install -e ./tinker-atropos")
         else:
             check_warn("tinker-atropos requires Python 3.11+", f"(current: {py_version.major}.{py_version.minor})")
     else:

hermes_cli/dump.py

@@ -32,11 +32,6 @@ def _get_git_commit(project_root: Path) -> str:
     return "(unknown)"
 
 
-def _key_present(name: str) -> str:
-    """Return 'set' or 'not set' for an env var."""
-    return "set" if os.getenv(name) else "not set"
-
-
 def _redact(value: str) -> str:
     """Redact all but first 4 and last 4 chars."""
     if not value:

hermes_cli/gateway.py

@@ -39,7 +39,7 @@ def _get_service_pids() -> set:
     pids: set = set()
 
     # --- systemd (Linux): user and system scopes ---
-    if supports_systemd_services():
+    if is_linux():
         for scope_args in [["systemctl", "--user"], ["systemctl"]]:
             try:
                 result = subprocess.run(
@@ -225,14 +225,6 @@ def stop_profile_gateway() -> bool:
 def is_linux() -> bool:
     return sys.platform.startswith('linux')
 
-
-from hermes_constants import is_termux
-
-
-def supports_systemd_services() -> bool:
-    return is_linux() and not is_termux()
-
-
 def is_macos() -> bool:
     return sys.platform == 'darwin'
 
@@ -316,8 +308,6 @@ def get_service_name() -> str:
     return f"{_SERVICE_BASE}-{suffix}"
 
 
-SERVICE_NAME = _SERVICE_BASE  # backward-compat for external importers; prefer get_service_name()
-
 
 def get_systemd_unit_path(system: bool = False) -> Path:
     name = get_service_name()
@@ -485,15 +475,13 @@ def install_linux_gateway_from_setup(force: bool = False) -> tuple[str | None, b
 
 
 def get_systemd_linger_status() -> tuple[bool | None, str]:
-    """Return systemd linger status for the current user.
+    """Return whether systemd user lingering is enabled for the current user.
 
     Returns:
         (True, "") when linger is enabled.
         (False, "") when linger is disabled.
         (None, detail) when the status could not be determined.
     """
-    if is_termux():
-        return None, "not supported in Termux"
     if not is_linux():
         return None, "not supported on this platform"
 
@@ -591,17 +579,6 @@ def get_python_path() -> str:
             return str(venv_python)
     return sys.executable
 
-def get_hermes_cli_path() -> str:
-    """Get the path to the hermes CLI."""
-    # Check if installed via pip
-    import shutil
-    hermes_bin = shutil.which("hermes")
-    if hermes_bin:
-        return hermes_bin
-    
-    # Fallback to direct module execution
-    return f"{get_python_path()} -m hermes_cli.main"
-
 
 # =============================================================================
 # Systemd (Linux)
@@ -776,7 +753,7 @@ def _print_linger_enable_warning(username: str, detail: str | None = None) -> No
 
 def _ensure_linger_enabled() -> None:
     """Enable linger when possible so the user gateway survives logout."""
-    if is_termux() or not is_linux():
+    if not is_linux():
         return
 
     import getpass
@@ -1811,7 +1788,7 @@ def _setup_whatsapp():
 
 def _is_service_installed() -> bool:
     """Check if the gateway is installed as a system service."""
-    if supports_systemd_services():
+    if is_linux():
         return get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()
     elif is_macos():
         return get_launchd_plist_path().exists()
@@ -1820,7 +1797,7 @@ def _is_service_installed() -> bool:
 
 def _is_service_running() -> bool:
     """Check if the gateway service is currently running."""
-    if supports_systemd_services():
+    if is_linux():
         user_unit_exists = get_systemd_unit_path(system=False).exists()
         system_unit_exists = get_systemd_unit_path(system=True).exists()
 
@@ -1993,7 +1970,7 @@ def gateway_setup():
     service_installed = _is_service_installed()
     service_running = _is_service_running()
 
-    if supports_systemd_services() and has_conflicting_systemd_units():
+    if is_linux() and has_conflicting_systemd_units():
         print_systemd_scope_conflict_warning()
         print()
 
@@ -2003,7 +1980,7 @@ def gateway_setup():
         print_warning("Gateway service is installed but not running.")
         if prompt_yes_no("  Start it now?", True):
             try:
-                if supports_systemd_services():
+                if is_linux():
                     systemd_start()
                 elif is_macos():
                     launchd_start()
@@ -2054,7 +2031,7 @@ def gateway_setup():
         if service_running:
             if prompt_yes_no("  Restart the gateway to pick up changes?", True):
                 try:
-                    if supports_systemd_services():
+                    if is_linux():
                         systemd_restart()
                     elif is_macos():
                         launchd_restart()
@@ -2066,7 +2043,7 @@ def gateway_setup():
         elif service_installed:
             if prompt_yes_no("  Start the gateway service?", True):
                 try:
-                    if supports_systemd_services():
+                    if is_linux():
                         systemd_start()
                     elif is_macos():
                         launchd_start()
@@ -2074,13 +2051,13 @@ def gateway_setup():
                     print_error(f"  Start failed: {e}")
         else:
             print()
-            if supports_systemd_services() or is_macos():
-                platform_name = "systemd" if supports_systemd_services() else "launchd"
+            if is_linux() or is_macos():
+                platform_name = "systemd" if is_linux() else "launchd"
                 if prompt_yes_no(f"  Install the gateway as a {platform_name} service? (runs in background, starts on boot)", True):
                     try:
                         installed_scope = None
                         did_install = False
-                        if supports_systemd_services():
+                        if is_linux():
                             installed_scope, did_install = install_linux_gateway_from_setup(force=False)
                         else:
                             launchd_install(force=False)
@@ -2088,7 +2065,7 @@ def gateway_setup():
                         print()
                         if did_install and prompt_yes_no("  Start the service now?", True):
                             try:
-                                if supports_systemd_services():
+                                if is_linux():
                                     systemd_start(system=installed_scope == "system")
                                 else:
                                     launchd_start()
@@ -2099,18 +2076,12 @@ def gateway_setup():
                         print_info("  You can try manually: hermes gateway install")
                 else:
                     print_info("  You can install later: hermes gateway install")
-                    if supports_systemd_services():
+                    if is_linux():
                         print_info("  Or as a boot-time service: sudo hermes gateway install --system")
                     print_info("  Or run in foreground:  hermes gateway")
             else:
-                if is_termux():
-                    from hermes_constants import display_hermes_home as _dhh
-                    print_info("  Termux does not use systemd/launchd services.")
-                    print_info("  Run in foreground: hermes gateway")
-                    print_info(f"  Or start it manually in the background (best effort): nohup hermes gateway >{_dhh()}/logs/gateway.log 2>&1 &")
-                else:
-                    print_info("  Service install not supported on this platform.")
-                    print_info("  Run in foreground: hermes gateway")
+                print_info("  Service install not supported on this platform.")
+                print_info("  Run in foreground: hermes gateway")
     else:
         print()
         print_info("No platforms configured. Run 'hermes gateway setup' when ready.")
@@ -2146,11 +2117,7 @@ def gateway_command(args):
         force = getattr(args, 'force', False)
         system = getattr(args, 'system', False)
         run_as_user = getattr(args, 'run_as_user', None)
-        if is_termux():
-            print("Gateway service installation is not supported on Termux.")
-            print("Run manually: hermes gateway")
-            sys.exit(1)
-        if supports_systemd_services():
+        if is_linux():
             systemd_install(force=force, system=system, run_as_user=run_as_user)
         elif is_macos():
             launchd_install(force)
@@ -2164,11 +2131,7 @@ def gateway_command(args):
             managed_error("uninstall gateway service (managed by NixOS)")
             return
         system = getattr(args, 'system', False)
-        if is_termux():
-            print("Gateway service uninstall is not supported on Termux because there is no managed service to remove.")
-            print("Stop manual runs with: hermes gateway stop")
-            sys.exit(1)
-        if supports_systemd_services():
+        if is_linux():
             systemd_uninstall(system=system)
         elif is_macos():
             launchd_uninstall()
@@ -2178,11 +2141,7 @@ def gateway_command(args):
     
     elif subcmd == "start":
         system = getattr(args, 'system', False)
-        if is_termux():
-            print("Gateway service start is not supported on Termux because there is no system service manager.")
-            print("Run manually: hermes gateway")
-            sys.exit(1)
-        if supports_systemd_services():
+        if is_linux():
             systemd_start(system=system)
         elif is_macos():
             launchd_start()
@@ -2197,7 +2156,7 @@ def gateway_command(args):
         if stop_all:
             # --all: kill every gateway process on the machine
             service_available = False
-            if supports_systemd_services() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
+            if is_linux() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
                 try:
                     systemd_stop(system=system)
                     service_available = True
@@ -2218,7 +2177,7 @@ def gateway_command(args):
         else:
             # Default: stop only the current profile's gateway
             service_available = False
-            if supports_systemd_services() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
+            if is_linux() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
                 try:
                     systemd_stop(system=system)
                     service_available = True
@@ -2246,7 +2205,7 @@ def gateway_command(args):
         system = getattr(args, 'system', False)
         service_configured = False
         
-        if supports_systemd_services() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
+        if is_linux() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
             service_configured = True
             try:
                 systemd_restart(system=system)
@@ -2263,7 +2222,7 @@ def gateway_command(args):
         
         if not service_available:
             # systemd/launchd restart failed — check if linger is the issue
-            if supports_systemd_services():
+            if is_linux():
                 linger_ok, _detail = get_systemd_linger_status()
                 if linger_ok is not True:
                     import getpass
@@ -2300,7 +2259,7 @@ def gateway_command(args):
         system = getattr(args, 'system', False)
         
         # Check for service first
-        if supports_systemd_services() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
+        if is_linux() and (get_systemd_unit_path(system=False).exists() or get_systemd_unit_path(system=True).exists()):
             systemd_status(deep, system=system)
         elif is_macos() and get_launchd_plist_path().exists():
             launchd_status(deep)
@@ -2317,13 +2276,9 @@ def gateway_command(args):
                     for line in runtime_lines:
                         print(f"  {line}")
                 print()
-                if is_termux():
-                    print("Termux note:")
-                    print("  Android may stop background jobs when Termux is suspended")
-                else:
-                    print("To install as a service:")
-                    print("  hermes gateway install")
-                    print("  sudo hermes gateway install --system")
+                print("To install as a service:")
+                print("  hermes gateway install")
+                print("  sudo hermes gateway install --system")
             else:
                 print("✗ Gateway is not running")
                 runtime_lines = _runtime_health_lines()
@@ -2335,8 +2290,5 @@ def gateway_command(args):
                 print()
                 print("To start:")
                 print("  hermes gateway          # Run in foreground")
-                if is_termux():
-                    print("  nohup hermes gateway > ~/.hermes/logs/gateway.log 2>&1 &  # Best-effort background start")
-                else:
-                    print("  hermes gateway install  # Install as user service")
-                    print("  sudo hermes gateway install --system  # Install as boot-time system service")
+                print("  hermes gateway install  # Install as user service")
+                print("  sudo hermes gateway install --system  # Install as boot-time system service")

hermes_cli/main.py

@@ -646,7 +646,6 @@ def cmd_chat(args):
         "verbose": args.verbose,
         "quiet": getattr(args, "quiet", False),
         "query": args.query,
-        "image": getattr(args, "image", None),
         "resume": getattr(args, "resume", None),
         "worktree": getattr(args, "worktree", False),
         "checkpoints": getattr(args, "checkpoints", False),
@@ -3022,19 +3021,33 @@ def _restore_stashed_changes(
         print("\nYour stashed changes are preserved — nothing is lost.")
         print(f"  Stash ref: {stash_ref}")
 
-        # Always reset to clean state — leaving conflict markers in source
-        # files makes hermes completely unrunnable (SyntaxError on import).
-        # The user's changes are safe in the stash for manual recovery.
-        subprocess.run(
-            git_cmd + ["reset", "--hard", "HEAD"],
-            cwd=cwd,
-            capture_output=True,
-        )
-        print("Working tree reset to clean state.")
-        print(f"Restore your changes later with: git stash apply {stash_ref}")
-        # Don't sys.exit — the code update itself succeeded, only the stash
-        # restore had conflicts.  Let cmd_update continue with pip install,
-        # skill sync, and gateway restart.
+        # Ask before resetting (if interactive)
+        do_reset = True
+        if prompt_user:
+            print("\nReset working tree to clean state so Hermes can run?")
+            print("  (You can re-apply your changes later with: git stash apply)")
+            print("[Y/n] ", end="", flush=True)
+            response = input().strip().lower()
+            if response not in ("", "y", "yes"):
+                do_reset = False
+
+        if do_reset:
+            subprocess.run(
+                git_cmd + ["reset", "--hard", "HEAD"],
+                cwd=cwd,
+                capture_output=True,
+            )
+            print("Working tree reset to clean state.")
+        else:
+            print("Working tree left as-is (may have conflict markers).")
+            print("Resolve conflicts manually, then run: git stash drop")
+
+        print(f"Restore your changes with: git stash apply {stash_ref}")
+        # In non-interactive mode (gateway /update), don't abort — the code
+        # update itself succeeded, only the stash restore had conflicts.
+        # Aborting would report the entire update as failed.
+        if prompt_user:
+            sys.exit(1)
         return False
 
     stash_selector = _resolve_stash_selector(git_cmd, cwd, stash_ref)
@@ -3750,7 +3763,7 @@ def cmd_update(args):
         # running gateway needs restarting to pick up the new code.
         try:
             from hermes_cli.gateway import (
-                is_macos, supports_systemd_services, _ensure_user_systemd_env,
+                is_macos, is_linux, _ensure_user_systemd_env,
                 find_gateway_pids,
                 _get_service_pids,
             )
@@ -3761,7 +3774,7 @@ def cmd_update(args):
 
             # --- Systemd services (Linux) ---
             # Discover all hermes-gateway* units (default + profiles)
-            if supports_systemd_services():
+            if is_linux():
                 try:
                     _ensure_user_systemd_env()
                 except Exception:
@@ -4278,10 +4291,6 @@ For more help on a command:
         "-q", "--query",
         help="Single query (non-interactive mode)"
     )
-    chat_parser.add_argument(
-        "--image",
-        help="Optional local image path to attach to a single query"
-    )
     chat_parser.add_argument(
         "-m", "--model",
         help="Model to use (e.g., anthropic/claude-sonnet-4)"

hermes_cli/model_normalize.py

@@ -332,31 +332,3 @@ def normalize_model_for_provider(model_input: str, target_provider: str) -> str:
 # Batch / convenience helpers
 # ---------------------------------------------------------------------------
 
-def model_display_name(model_id: str) -> str:
-    """Return a short, human-readable display name for a model id.
-
-    Strips the vendor prefix (if any) for a cleaner display in menus
-    and status bars, while preserving dots for readability.
-
-    Examples::
-
-        >>> model_display_name("anthropic/claude-sonnet-4.6")
-        'claude-sonnet-4.6'
-        >>> model_display_name("claude-sonnet-4-6")
-        'claude-sonnet-4-6'
-    """
-    return _strip_vendor_prefix((model_id or "").strip())
-
-
-def is_aggregator_provider(provider: str) -> bool:
-    """Check if a provider is an aggregator that needs vendor/model format."""
-    return (provider or "").strip().lower() in _AGGREGATOR_PROVIDERS
-
-
-def vendor_for_model(model_name: str) -> str:
-    """Return the vendor slug for a model, or ``""`` if unknown.
-
-    Convenience wrapper around :func:`detect_vendor` that never returns
-    ``None``.
-    """
-    return detect_vendor(model_name) or ""

hermes_cli/model_switch.py

@@ -859,74 +859,3 @@ def list_authenticated_providers(
     return results
 
 
-# ---------------------------------------------------------------------------
-# Fuzzy suggestions
-# ---------------------------------------------------------------------------
-
-def suggest_models(raw_input: str, limit: int = 3) -> List[str]:
-    """Return fuzzy model suggestions for a (possibly misspelled) input."""
-    query = raw_input.strip()
-    if not query:
-        return []
-
-    results = search_models_dev(query, limit=limit)
-    suggestions: list[str] = []
-    for r in results:
-        mid = r.get("model_id", "")
-        if mid:
-            suggestions.append(mid)
-
-    return suggestions[:limit]
-
-
-# ---------------------------------------------------------------------------
-# Custom provider switch
-# ---------------------------------------------------------------------------
-
-def switch_to_custom_provider() -> CustomAutoResult:
-    """Handle bare '/model --provider custom' — resolve endpoint and auto-detect model."""
-    from hermes_cli.runtime_provider import (
-        resolve_runtime_provider,
-        _auto_detect_local_model,
-    )
-
-    try:
-        runtime = resolve_runtime_provider(requested="custom")
-    except Exception as e:
-        return CustomAutoResult(
-            success=False,
-            error_message=f"Could not resolve custom endpoint: {e}",
-        )
-
-    cust_base = runtime.get("base_url", "")
-    cust_key = runtime.get("api_key", "")
-
-    if not cust_base or "openrouter.ai" in cust_base:
-        return CustomAutoResult(
-            success=False,
-            error_message=(
-                "No custom endpoint configured. "
-                "Set model.base_url in config.yaml, or set OPENAI_BASE_URL "
-                "in .env, or run: hermes setup -> Custom OpenAI-compatible endpoint"
-            ),
-        )
-
-    detected_model = _auto_detect_local_model(cust_base)
-    if not detected_model:
-        return CustomAutoResult(
-            success=False,
-            base_url=cust_base,
-            api_key=cust_key,
-            error_message=(
-                f"Custom endpoint at {cust_base} is reachable but no single "
-                f"model was auto-detected. Specify the model explicitly: "
-                f"/model <model-name> --provider custom"
-            ),
-        )
-
-    return CustomAutoResult(
-        success=True,
-        model=detected_model,
-        base_url=cust_base,
-        api_key=cust_key,
-    )

hermes_cli/models.py

@@ -20,10 +20,6 @@ COPILOT_EDITOR_VERSION = "vscode/1.104.1"
 COPILOT_REASONING_EFFORTS_GPT5 = ["minimal", "low", "medium", "high"]
 COPILOT_REASONING_EFFORTS_O_SERIES = ["low", "medium", "high"]
 
-# Backward-compatible aliases for the earlier GitHub Models-backed Copilot work.
-GITHUB_MODELS_BASE_URL = COPILOT_BASE_URL
-GITHUB_MODELS_CATALOG_URL = COPILOT_MODELS_URL
-
 # (model_id, display description shown in menus)
 OPENROUTER_MODELS: list[tuple[str, str]] = [
     ("anthropic/claude-opus-4.6",       "recommended"),
@@ -416,12 +412,6 @@ _FREE_TIER_CACHE_TTL: int = 180  # seconds (3 minutes)
 _free_tier_cache: tuple[bool, float] | None = None  # (result, timestamp)
 
 
-def clear_nous_free_tier_cache() -> None:
-    """Invalidate the cached free-tier result (e.g. after login/logout)."""
-    global _free_tier_cache
-    _free_tier_cache = None
-
-
 def check_nous_free_tier() -> bool:
     """Check if the current Nous Portal user is on a free (unpaid) tier.
 
@@ -535,14 +525,6 @@ def model_ids() -> list[str]:
     return [mid for mid, _ in OPENROUTER_MODELS]
 
 
-def menu_labels() -> list[str]:
-    """Return display labels like 'anthropic/claude-opus-4.6 (recommended)'."""
-    labels = []
-    for mid, desc in OPENROUTER_MODELS:
-        labels.append(f"{mid} ({desc})" if desc else mid)
-    return labels
-
-
 # ---------------------------------------------------------------------------
 # Pricing helpers — fetch live pricing from OpenRouter-compatible /v1/models
 # ---------------------------------------------------------------------------
@@ -575,31 +557,6 @@ def _format_price_per_mtok(per_token_str: str) -> str:
     return f"${per_m:.2f}"
 
 
-def format_pricing_label(pricing: dict[str, str] | None) -> str:
-    """Build a compact pricing label like 'in $3 · out $15 · cache $0.30/Mtok'.
-
-    Returns empty string when pricing is unavailable.
-    """
-    if not pricing:
-        return ""
-    prompt_price = pricing.get("prompt", "")
-    completion_price = pricing.get("completion", "")
-    if not prompt_price and not completion_price:
-        return ""
-    inp = _format_price_per_mtok(prompt_price)
-    out = _format_price_per_mtok(completion_price)
-    if inp == "free" and out == "free":
-        return "free"
-    cache_read = pricing.get("input_cache_read", "")
-    cache_str = _format_price_per_mtok(cache_read) if cache_read else ""
-    if inp == out and not cache_str:
-        return f"{inp}/Mtok"
-    parts = [f"in {inp}", f"out {out}"]
-    if cache_str and cache_str != "?" and cache_str != inp:
-        parts.append(f"cache {cache_str}")
-    return " · ".join(parts) + "/Mtok"
-
-
 def format_model_pricing_table(
     models: list[tuple[str, str]],
     pricing_map: dict[str, dict[str, str]],
@@ -1017,79 +974,6 @@ def provider_label(provider: Optional[str]) -> str:
     return _PROVIDER_LABELS.get(normalized, original or "OpenRouter")
 
 
-# Models that support OpenAI Priority Processing (service_tier="priority").
-# See https://openai.com/api-priority-processing/ for the canonical list.
-# Only the bare model slug is stored (no vendor prefix).
-_PRIORITY_PROCESSING_MODELS: frozenset[str] = frozenset({
-    "gpt-5.4",
-    "gpt-5.4-mini",
-    "gpt-5.2",
-    "gpt-5.1",
-    "gpt-5",
-    "gpt-5-mini",
-    "gpt-4.1",
-    "gpt-4.1-mini",
-    "gpt-4.1-nano",
-    "gpt-4o",
-    "gpt-4o-mini",
-    "o3",
-    "o4-mini",
-})
-
-# Models that support Anthropic Fast Mode (speed="fast").
-# See https://platform.claude.com/docs/en/build-with-claude/fast-mode
-# Currently only Claude Opus 4.6.  Both hyphen and dot variants are stored
-# to handle native Anthropic (claude-opus-4-6) and OpenRouter (claude-opus-4.6).
-_ANTHROPIC_FAST_MODE_MODELS: frozenset[str] = frozenset({
-    "claude-opus-4-6",
-    "claude-opus-4.6",
-})
-
-
-def _strip_vendor_prefix(model_id: str) -> str:
-    """Strip vendor/ prefix from a model ID (e.g. 'anthropic/claude-opus-4-6' -> 'claude-opus-4-6')."""
-    raw = str(model_id or "").strip().lower()
-    if "/" in raw:
-        raw = raw.split("/", 1)[1]
-    return raw
-
-
-def model_supports_fast_mode(model_id: Optional[str]) -> bool:
-    """Return whether Hermes should expose the /fast toggle for this model."""
-    raw = _strip_vendor_prefix(str(model_id or ""))
-    if raw in _PRIORITY_PROCESSING_MODELS:
-        return True
-    # Anthropic fast mode — strip date suffixes (e.g. claude-opus-4-6-20260401)
-    # and OpenRouter variant tags (:fast, :beta) for matching.
-    base = raw.split(":")[0]
-    return base in _ANTHROPIC_FAST_MODE_MODELS
-
-
-def _is_anthropic_fast_model(model_id: Optional[str]) -> bool:
-    """Return True if the model supports Anthropic's fast mode (speed='fast')."""
-    raw = _strip_vendor_prefix(str(model_id or ""))
-    base = raw.split(":")[0]
-    return base in _ANTHROPIC_FAST_MODE_MODELS
-
-
-def resolve_fast_mode_overrides(model_id: Optional[str]) -> dict[str, Any] | None:
-    """Return request_overrides for fast/priority mode, or None if unsupported.
-
-    Returns provider-appropriate overrides:
-    - OpenAI models: ``{"service_tier": "priority"}`` (Priority Processing)
-    - Anthropic models: ``{"speed": "fast"}`` (Anthropic Fast Mode beta)
-
-    The overrides are injected into the API request kwargs by
-    ``_build_api_kwargs`` in run_agent.py — each API path handles its own
-    keys (service_tier for OpenAI/Codex, speed for Anthropic Messages).
-    """
-    if not model_supports_fast_mode(model_id):
-        return None
-    if _is_anthropic_fast_model(model_id):
-        return {"speed": "fast"}
-    return {"service_tier": "priority"}
-
-
 def _resolve_copilot_catalog_api_key() -> str:
     """Best-effort GitHub token for fetching the Copilot model catalog."""
     try:

hermes_cli/providers.py

@@ -148,10 +148,6 @@ class ProviderDef:
     doc: str = ""
     source: str = ""                      # "models.dev", "hermes", "user-config"
 
-    @property
-    def is_user_defined(self) -> bool:
-        return self.source == "user-config"
-
 
 # -- Aliases ------------------------------------------------------------------
 # Maps human-friendly / legacy names to canonical provider IDs.
@@ -262,12 +258,6 @@ def normalize_provider(name: str) -> str:
     return ALIASES.get(key, key)
 
 
-def get_overlay(provider_id: str) -> Optional[HermesOverlay]:
-    """Get Hermes overlay for a provider, if one exists."""
-    canonical = normalize_provider(provider_id)
-    return HERMES_OVERLAYS.get(canonical)
-
-
 def get_provider(name: str) -> Optional[ProviderDef]:
     """Look up a provider by id or alias, merging all data sources.
 
@@ -350,37 +340,6 @@ def get_label(provider_id: str) -> str:
     return canonical
 
 
-# For direct import compat, expose as module-level dict
-# Built on demand by get_label() calls
-LABELS: Dict[str, str] = {
-    # Static entries for backward compat — get_label() is the proper API
-    "openrouter": "OpenRouter",
-    "nous": "Nous Portal",
-    "openai-codex": "OpenAI Codex",
-    "copilot-acp": "GitHub Copilot ACP",
-    "github-copilot": "GitHub Copilot",
-    "anthropic": "Anthropic",
-    "zai": "Z.AI / GLM",
-    "kimi-for-coding": "Kimi / Moonshot",
-    "minimax": "MiniMax",
-    "minimax-cn": "MiniMax (China)",
-    "deepseek": "DeepSeek",
-    "alibaba": "Alibaba Cloud (DashScope)",
-    "vercel": "Vercel AI Gateway",
-    "opencode": "OpenCode Zen",
-    "opencode-go": "OpenCode Go",
-    "kilo": "Kilo Gateway",
-    "huggingface": "Hugging Face",
-    "local": "Local endpoint",
-    "custom": "Custom endpoint",
-    # Legacy Hermes IDs (point to same providers)
-    "ai-gateway": "Vercel AI Gateway",
-    "kilocode": "Kilo Gateway",
-    "copilot": "GitHub Copilot",
-    "kimi-coding": "Kimi / Moonshot",
-    "opencode-zen": "OpenCode Zen",
-}
-
 
 def is_aggregator(provider: str) -> bool:
     """Return True when the provider is a multi-model aggregator."""

hermes_cli/runtime_provider.py

@@ -16,7 +16,6 @@ from hermes_cli.auth import (
     DEFAULT_CODEX_BASE_URL,
     DEFAULT_QWEN_BASE_URL,
     PROVIDER_REGISTRY,
-    _agent_key_is_usable,
     format_auth_error,
     resolve_provider,
     resolve_nous_runtime_credentials,
@@ -645,21 +644,6 @@ def resolve_runtime_provider(
                 getattr(entry, "runtime_api_key", None)
                 or getattr(entry, "access_token", "")
             )
-        # For Nous, the pool entry's runtime_api_key is the agent_key — a
-        # short-lived inference credential (~30 min TTL).  The pool doesn't
-        # refresh it during selection (that would trigger network calls in
-        # non-runtime contexts like `hermes auth list`).  If the key is
-        # expired, clear pool_api_key so we fall through to
-        # resolve_nous_runtime_credentials() which handles refresh + mint.
-        if provider == "nous" and entry is not None and pool_api_key:
-            min_ttl = max(60, int(os.getenv("HERMES_NOUS_MIN_KEY_TTL_SECONDS", "1800")))
-            nous_state = {
-                "agent_key": getattr(entry, "agent_key", None),
-                "agent_key_expires_at": getattr(entry, "agent_key_expires_at", None),
-            }
-            if not _agent_key_is_usable(nous_state, min_ttl):
-                logger.debug("Nous pool entry agent_key expired/missing, falling through to runtime resolution")
-                pool_api_key = ""
         if entry is not None and pool_api_key:
             return _resolve_runtime_from_pool_entry(
                 provider=provider,

hermes_cli/setup.py

@@ -172,147 +172,6 @@ def _setup_copilot_reasoning_selection(
         _set_reasoning_effort(config, "none")
 
 
-def _setup_provider_model_selection(config, provider_id, current_model, prompt_choice, prompt_fn):
-    """Model selection for API-key providers with live /models detection.
-
-    Tries the provider's /models endpoint first.  Falls back to a
-    hardcoded default list with a warning if the endpoint is unreachable.
-    Always offers a 'Custom model' escape hatch.
-    """
-    from hermes_cli.auth import PROVIDER_REGISTRY, resolve_api_key_provider_credentials
-    from hermes_cli.config import get_env_value
-    from hermes_cli.models import (
-        copilot_model_api_mode,
-        fetch_api_models,
-        fetch_github_model_catalog,
-        normalize_copilot_model_id,
-        normalize_opencode_model_id,
-        opencode_model_api_mode,
-    )
-
-    pconfig = PROVIDER_REGISTRY[provider_id]
-    is_copilot_catalog_provider = provider_id in {"copilot", "copilot-acp"}
-
-    # Resolve API key and base URL for the probe
-    if is_copilot_catalog_provider:
-        api_key = ""
-        if provider_id == "copilot":
-            creds = resolve_api_key_provider_credentials(provider_id)
-            api_key = creds.get("api_key", "")
-            base_url = creds.get("base_url", "") or pconfig.inference_base_url
-        else:
-            try:
-                creds = resolve_api_key_provider_credentials("copilot")
-                api_key = creds.get("api_key", "")
-            except Exception:
-                pass
-            base_url = pconfig.inference_base_url
-        catalog = fetch_github_model_catalog(api_key)
-        current_model = normalize_copilot_model_id(
-            current_model,
-            catalog=catalog,
-            api_key=api_key,
-        ) or current_model
-    else:
-        api_key = ""
-        for ev in pconfig.api_key_env_vars:
-            api_key = get_env_value(ev) or os.getenv(ev, "")
-            if api_key:
-                break
-        base_url_env = pconfig.base_url_env_var or ""
-        base_url = (get_env_value(base_url_env) if base_url_env else "") or pconfig.inference_base_url
-        catalog = None
-
-    # Try live /models endpoint
-    if is_copilot_catalog_provider and catalog:
-        live_models = [item.get("id", "") for item in catalog if item.get("id")]
-    else:
-        live_models = fetch_api_models(api_key, base_url)
-
-    if live_models:
-        provider_models = live_models
-        print_info(f"Found {len(live_models)} model(s) from {pconfig.name} API")
-    else:
-        fallback_provider_id = "copilot" if provider_id == "copilot-acp" else provider_id
-        provider_models = _DEFAULT_PROVIDER_MODELS.get(fallback_provider_id, [])
-        if provider_models:
-            print_warning(
-                f"Could not auto-detect models from {pconfig.name} API — showing defaults.\n"
-                f"    Use \"Custom model\" if the model you expect isn't listed."
-            )
-
-    if provider_id in {"opencode-zen", "opencode-go"}:
-        provider_models = [normalize_opencode_model_id(provider_id, mid) for mid in provider_models]
-        current_model = normalize_opencode_model_id(provider_id, current_model)
-        provider_models = list(dict.fromkeys(mid for mid in provider_models if mid))
-
-    model_choices = list(provider_models)
-    model_choices.append("Custom model")
-    model_choices.append(f"Keep current ({current_model})")
-
-    keep_idx = len(model_choices) - 1
-    model_idx = prompt_choice("Select default model:", model_choices, keep_idx)
-
-    selected_model = current_model
-
-    if model_idx < len(provider_models):
-        selected_model = provider_models[model_idx]
-        if is_copilot_catalog_provider:
-            selected_model = normalize_copilot_model_id(
-                selected_model,
-                catalog=catalog,
-                api_key=api_key,
-            ) or selected_model
-        elif provider_id in {"opencode-zen", "opencode-go"}:
-            selected_model = normalize_opencode_model_id(provider_id, selected_model)
-        _set_default_model(config, selected_model)
-    elif model_idx == len(provider_models):
-        custom = prompt_fn("Enter model name")
-        if custom:
-            if is_copilot_catalog_provider:
-                selected_model = normalize_copilot_model_id(
-                    custom,
-                    catalog=catalog,
-                    api_key=api_key,
-                ) or custom
-            elif provider_id in {"opencode-zen", "opencode-go"}:
-                selected_model = normalize_opencode_model_id(provider_id, custom)
-            else:
-                selected_model = custom
-            _set_default_model(config, selected_model)
-    else:
-        # "Keep current" selected — validate it's compatible with the new
-        # provider.  OpenRouter-formatted names (containing "/") won't work
-        # on direct-API providers and would silently break the gateway.
-        if "/" in (current_model or "") and provider_models:
-            print_warning(
-                f"Current model \"{current_model}\" looks like an OpenRouter model "
-                f"and won't work with {pconfig.name}. "
-                f"Switching to {provider_models[0]}."
-            )
-            selected_model = provider_models[0]
-            _set_default_model(config, provider_models[0])
-
-    if provider_id == "copilot" and selected_model:
-        model_cfg = _model_config_dict(config)
-        model_cfg["api_mode"] = copilot_model_api_mode(
-            selected_model,
-            catalog=catalog,
-            api_key=api_key,
-        )
-        config["model"] = model_cfg
-        _setup_copilot_reasoning_selection(
-            config,
-            selected_model,
-            prompt_choice,
-            catalog=catalog,
-            api_key=api_key,
-        )
-    elif provider_id in {"opencode-zen", "opencode-go"} and selected_model:
-        model_cfg = _model_config_dict(config)
-        model_cfg["api_mode"] = opencode_model_api_mode(provider_id, selected_model)
-        config["model"] = model_cfg
-
 
 # Import config helpers
 from hermes_cli.config import (

hermes_cli/status.py

@@ -79,9 +79,6 @@ def _effective_provider_label() -> str:
     return provider_label(effective)
 
 
-from hermes_constants import is_termux as _is_termux
-
-
 def show_status(args):
     """Show status of all Hermes Agent components."""
     show_all = getattr(args, 'all', False)
@@ -328,25 +325,7 @@ def show_status(args):
     print()
     print(color("◆ Gateway Service", Colors.CYAN, Colors.BOLD))
     
-    if _is_termux():
-        try:
-            from hermes_cli.gateway import find_gateway_pids
-            gateway_pids = find_gateway_pids()
-        except Exception:
-            gateway_pids = []
-        is_running = bool(gateway_pids)
-        print(f"  Status:       {check_mark(is_running)} {'running' if is_running else 'stopped'}")
-        print("  Manager:      Termux / manual process")
-        if gateway_pids:
-            rendered = ", ".join(str(pid) for pid in gateway_pids[:3])
-            if len(gateway_pids) > 3:
-                rendered += ", ..."
-            print(f"  PID(s):       {rendered}")
-        else:
-            print("  Start with:   hermes gateway")
-            print("  Note:         Android may stop background jobs when Termux is suspended")
-
-    elif sys.platform.startswith('linux'):
+    if sys.platform.startswith('linux'):
         try:
             from hermes_cli.gateway import get_service_name
             _gw_svc = get_service_name()
@@ -360,7 +339,7 @@ def show_status(args):
                 timeout=5
             )
             is_active = result.stdout.strip() == "active"
-        except (FileNotFoundError, subprocess.TimeoutExpired):
+        except subprocess.TimeoutExpired:
             is_active = False
         print(f"  Status:       {check_mark(is_active)} {'running' if is_active else 'stopped'}")
         print("  Manager:      systemd (user)")

hermes_cli/uninstall.py

@@ -6,8 +6,6 @@ Provides options for:
 - Keep data: Remove code but keep ~/.hermes/ (configs, sessions, logs)
 """
 
-import os
-import platform
 import shutil
 import subprocess
 from pathlib import Path
@@ -124,10 +122,6 @@ def uninstall_gateway_service():
     
     if platform.system() != "Linux":
         return False
-
-    prefix = os.getenv("PREFIX", "")
-    if os.getenv("TERMUX_VERSION") or "com.termux/files/usr" in prefix:
-        return False
     
     try:
         from hermes_cli.gateway import get_service_name

hermes_constants.py

@@ -93,23 +93,9 @@ def parse_reasoning_effort(effort: str) -> dict | None:
     return None
 
 
-def is_termux() -> bool:
-    """Return True when running inside a Termux (Android) environment.
-
-    Checks ``TERMUX_VERSION`` (set by Termux) or the Termux-specific
-    ``PREFIX`` path.  Import-safe — no heavy deps.
-    """
-    prefix = os.getenv("PREFIX", "")
-    return bool(os.getenv("TERMUX_VERSION") or "com.termux/files/usr" in prefix)
-
-
 OPENROUTER_BASE_URL = "https://openrouter.ai/api/v1"
 OPENROUTER_MODELS_URL = f"{OPENROUTER_BASE_URL}/models"
-OPENROUTER_CHAT_URL = f"{OPENROUTER_BASE_URL}/chat/completions"
 
 AI_GATEWAY_BASE_URL = "https://ai-gateway.vercel.sh/v1"
-AI_GATEWAY_MODELS_URL = f"{AI_GATEWAY_BASE_URL}/models"
-AI_GATEWAY_CHAT_URL = f"{AI_GATEWAY_BASE_URL}/chat/completions"
 
 NOUS_API_BASE_URL = "https://inference-api.nousresearch.com/v1"
-NOUS_API_CHAT_URL = f"{NOUS_API_BASE_URL}/chat/completions"

hermes_state.py

@@ -520,72 +520,6 @@ class SessionDB:
             )
         self._execute_write(_do)
 
-    def set_token_counts(
-        self,
-        session_id: str,
-        input_tokens: int = 0,
-        output_tokens: int = 0,
-        model: str = None,
-        cache_read_tokens: int = 0,
-        cache_write_tokens: int = 0,
-        reasoning_tokens: int = 0,
-        estimated_cost_usd: Optional[float] = None,
-        actual_cost_usd: Optional[float] = None,
-        cost_status: Optional[str] = None,
-        cost_source: Optional[str] = None,
-        pricing_version: Optional[str] = None,
-        billing_provider: Optional[str] = None,
-        billing_base_url: Optional[str] = None,
-        billing_mode: Optional[str] = None,
-    ) -> None:
-        """Set token counters to absolute values (not increment).
-
-        Use this when the caller provides cumulative totals from a completed
-        conversation run (e.g. the gateway, where the cached agent's
-        session_prompt_tokens already reflects the running total).
-        """
-        def _do(conn):
-            conn.execute(
-                """UPDATE sessions SET
-                   input_tokens = ?,
-                   output_tokens = ?,
-                   cache_read_tokens = ?,
-                   cache_write_tokens = ?,
-                   reasoning_tokens = ?,
-                   estimated_cost_usd = ?,
-                   actual_cost_usd = CASE
-                       WHEN ? IS NULL THEN actual_cost_usd
-                       ELSE ?
-                   END,
-                   cost_status = COALESCE(?, cost_status),
-                   cost_source = COALESCE(?, cost_source),
-                   pricing_version = COALESCE(?, pricing_version),
-                   billing_provider = COALESCE(billing_provider, ?),
-                   billing_base_url = COALESCE(billing_base_url, ?),
-                   billing_mode = COALESCE(billing_mode, ?),
-                   model = COALESCE(model, ?)
-                   WHERE id = ?""",
-                (
-                    input_tokens,
-                    output_tokens,
-                    cache_read_tokens,
-                    cache_write_tokens,
-                    reasoning_tokens,
-                    estimated_cost_usd,
-                    actual_cost_usd,
-                    actual_cost_usd,
-                    cost_status,
-                    cost_source,
-                    pricing_version,
-                    billing_provider,
-                    billing_base_url,
-                    billing_mode,
-                    model,
-                    session_id,
-                ),
-            )
-        self._execute_write(_do)
-
     def get_session(self, session_id: str) -> Optional[Dict[str, Any]]:
         """Get a session by ID."""
         with self._lock:

hermes_time.py

@@ -89,13 +89,6 @@ def get_timezone() -> Optional[ZoneInfo]:
     return _cached_tz
 
 
-def get_timezone_name() -> str:
-    """Return the IANA name of the configured timezone, or empty string."""
-    if not _cache_resolved:
-        get_timezone()  # populates cache
-    return _cached_tz_name or ""
-
-
 def now() -> datetime:
     """
     Return the current time as a timezone-aware datetime.
@@ -110,9 +103,3 @@ def now() -> datetime:
     return datetime.now().astimezone()
 
 
-def reset_cache() -> None:
-    """Clear the cached timezone. Used by tests and after config changes."""
-    global _cached_tz, _cached_tz_name, _cache_resolved
-    _cached_tz = None
-    _cached_tz_name = None
-    _cache_resolved = False

pyproject.toml

@@ -63,17 +63,6 @@ homeassistant = ["aiohttp>=3.9.0,<4"]
 sms = ["aiohttp>=3.9.0,<4"]
 acp = ["agent-client-protocol>=0.9.0,<1.0"]
 mistral = ["mistralai>=2.3.0,<3"]
-termux = [
-  # Tested Android / Termux path: keeps the core CLI feature-rich while
-  # avoiding extras that currently depend on non-Android wheels (notably
-  # faster-whisper -> ctranslate2 via the voice extra).
-  "hermes-agent[cron]",
-  "hermes-agent[cli]",
-  "hermes-agent[pty]",
-  "hermes-agent[mcp]",
-  "hermes-agent[honcho]",
-  "hermes-agent[acp]",
-]
 dingtalk = ["dingtalk-stream>=0.1.0,<1"]
 feishu = ["lark-oapi>=1.5.3,<2"]
 rl = [

run_agent.py

@@ -500,8 +500,6 @@ class AIAgent:
         status_callback: callable = None,
         max_tokens: int = None,
         reasoning_config: Dict[str, Any] = None,
-        service_tier: str = None,
-        request_overrides: Dict[str, Any] = None,
         prefill_messages: List[Dict[str, Any]] = None,
         platform: str = None,
         user_id: str = None,
@@ -624,10 +622,8 @@ class AIAgent:
         self.tool_progress_callback = tool_progress_callback
         self.tool_start_callback = tool_start_callback
         self.tool_complete_callback = tool_complete_callback
-        self.suppress_status_output = False
         self.thinking_callback = thinking_callback
         self.reasoning_callback = reasoning_callback
-        self._reasoning_deltas_fired = False  # Set by _fire_reasoning_delta, reset per API call
         self.clarify_callback = clarify_callback
         self.step_callback = step_callback
         self.stream_delta_callback = stream_delta_callback
@@ -664,8 +660,6 @@ class AIAgent:
         # Model response configuration
         self.max_tokens = max_tokens  # None = use model default
         self.reasoning_config = reasoning_config  # None = use default (medium for OpenRouter)
-        self.service_tier = service_tier
-        self.request_overrides = dict(request_overrides or {})
         self.prefill_messages = prefill_messages or []  # Prefilled conversation turns
         
         # Anthropic prompt caching: auto-enabled for Claude models via OpenRouter.
@@ -794,7 +788,7 @@ class AIAgent:
                     client_kwargs["default_headers"] = copilot_default_headers()
                 elif "api.kimi.com" in effective_base.lower():
                     client_kwargs["default_headers"] = {
-                        "User-Agent": "KimiCLI/1.30.0",
+                        "User-Agent": "KimiCLI/1.3",
                     }
                 elif "portal.qwen.ai" in effective_base.lower():
                     client_kwargs["default_headers"] = _qwen_portal_headers()
@@ -1304,7 +1298,6 @@ class AIAgent:
         if hasattr(self, "context_compressor") and self.context_compressor:
             self.context_compressor.last_prompt_tokens = 0
             self.context_compressor.last_completion_tokens = 0
-            self.context_compressor.last_total_tokens = 0
             self.context_compressor.compression_count = 0
             self.context_compressor._context_probed = False
             self.context_compressor._context_probe_persistable = False
@@ -1465,14 +1458,7 @@ class AIAgent:
         After the main response has been delivered and the remaining tool
         calls are post-response housekeeping (``_mute_post_response``),
         all non-forced output is suppressed.
-
-        ``suppress_status_output`` is a stricter CLI automation mode used by
-        parseable single-query flows such as ``hermes chat -q``. In that mode,
-        all status/diagnostic prints routed through ``_vprint`` are suppressed
-        so stdout stays machine-readable.
         """
-        if getattr(self, "suppress_status_output", False):
-            return
         if not force and getattr(self, "_mute_post_response", False):
             return
         if not force and self._has_stream_consumers() and not self._executing_tools:
@@ -1498,17 +1484,6 @@ class AIAgent:
         except (AttributeError, ValueError, OSError):
             return False
 
-    def _should_emit_quiet_tool_messages(self) -> bool:
-        """Return True when quiet-mode tool summaries should print directly.
-
-        When the caller provides ``tool_progress_callback`` (for example the CLI
-        TUI or a gateway progress renderer), that callback owns progress display.
-        Emitting quiet-mode summary lines here duplicates progress and leaks tool
-        previews into flows that are expected to stay silent, such as
-        ``hermes chat -q``.
-        """
-        return self.quiet_mode and not self.tool_progress_callback
-
     def _emit_status(self, message: str) -> None:
         """Emit a lifecycle status message to both CLI and gateway channels.
 
@@ -3347,7 +3322,7 @@ class AIAgent:
         allowed_keys = {
             "model", "instructions", "input", "tools", "store",
             "reasoning", "include", "max_output_tokens", "temperature",
-            "tool_choice", "parallel_tool_calls", "prompt_cache_key", "service_tier",
+            "tool_choice", "parallel_tool_calls", "prompt_cache_key",
         }
         normalized: Dict[str, Any] = {
             "model": model,
@@ -3365,9 +3340,6 @@ class AIAgent:
         include = api_kwargs.get("include")
         if isinstance(include, list):
             normalized["include"] = include
-        service_tier = api_kwargs.get("service_tier")
-        if isinstance(service_tier, str) and service_tier.strip():
-            normalized["service_tier"] = service_tier.strip()
 
         # Pass through max_output_tokens and temperature
         max_output_tokens = api_kwargs.get("max_output_tokens")
@@ -3875,7 +3847,6 @@ class AIAgent:
         max_stream_retries = 1
         has_tool_calls = False
         first_delta_fired = False
-        self._reasoning_deltas_fired = False
         # Accumulate streamed text so we can recover if get_final_response()
         # returns empty output (e.g. chatgpt.com backend-api sends
         # response.incomplete instead of response.completed).
@@ -4181,7 +4152,7 @@ class AIAgent:
 
             self._client_kwargs["default_headers"] = copilot_default_headers()
         elif "api.kimi.com" in normalized:
-            self._client_kwargs["default_headers"] = {"User-Agent": "KimiCLI/1.30.0"}
+            self._client_kwargs["default_headers"] = {"User-Agent": "KimiCLI/1.3"}
         elif "portal.qwen.ai" in normalized:
             self._client_kwargs["default_headers"] = _qwen_portal_headers()
         else:
@@ -4353,7 +4324,6 @@ class AIAgent:
 
     def _fire_reasoning_delta(self, text: str) -> None:
         """Fire reasoning callback if registered."""
-        self._reasoning_deltas_fired = True
         cb = self.reasoning_callback
         if cb is not None:
             try:
@@ -4433,17 +4403,7 @@ class AIAgent:
             """Stream a chat completions response."""
             import httpx as _httpx
             _base_timeout = float(os.getenv("HERMES_API_TIMEOUT", 1800.0))
-            _stream_read_timeout = float(os.getenv("HERMES_STREAM_READ_TIMEOUT", 120.0))
-            # Local providers (Ollama, llama.cpp, vLLM) can take minutes for
-            # prefill on large contexts before producing the first token.
-            # Auto-increase the httpx read timeout unless the user explicitly
-            # overrode HERMES_STREAM_READ_TIMEOUT.
-            if _stream_read_timeout == 120.0 and self.base_url and is_local_endpoint(self.base_url):
-                _stream_read_timeout = _base_timeout
-                logger.debug(
-                    "Local provider detected (%s) — stream read timeout raised to %.0fs",
-                    self.base_url, _stream_read_timeout,
-                )
+            _stream_read_timeout = float(os.getenv("HERMES_STREAM_READ_TIMEOUT", 60.0))
             stream_kwargs = {
                 **api_kwargs,
                 "stream": True,
@@ -4483,10 +4443,6 @@ class AIAgent:
             role = "assistant"
             reasoning_parts: list = []
             usage_obj = None
-            # Reset per-call reasoning tracking so _build_assistant_message
-            # knows whether reasoning was already displayed during streaming.
-            self._reasoning_deltas_fired = False
-
             _first_chunk_seen = False
             for chunk in stream:
                 last_chunk_time["t"] = time.time()
@@ -4601,31 +4557,20 @@ class AIAgent:
             # Build mock response matching non-streaming shape
             full_content = "".join(content_parts) or None
             mock_tool_calls = None
-            has_truncated_tool_args = False
             if tool_calls_acc:
                 mock_tool_calls = []
                 for idx in sorted(tool_calls_acc):
                     tc = tool_calls_acc[idx]
-                    arguments = tc["function"]["arguments"]
-                    if arguments and arguments.strip():
-                        try:
-                            json.loads(arguments)
-                        except json.JSONDecodeError:
-                            has_truncated_tool_args = True
                     mock_tool_calls.append(SimpleNamespace(
                         id=tc["id"],
                         type=tc["type"],
                         extra_content=tc.get("extra_content"),
                         function=SimpleNamespace(
                             name=tc["function"]["name"],
-                            arguments=arguments,
+                            arguments=tc["function"]["arguments"],
                         ),
                     ))
 
-            effective_finish_reason = finish_reason or "stop"
-            if has_truncated_tool_args:
-                effective_finish_reason = "length"
-
             full_reasoning = "".join(reasoning_parts) or None
             mock_message = SimpleNamespace(
                 role=role,
@@ -4636,7 +4581,7 @@ class AIAgent:
             mock_choice = SimpleNamespace(
                 index=0,
                 message=mock_message,
-                finish_reason=effective_finish_reason,
+                finish_reason=finish_reason or "stop",
             )
             return SimpleNamespace(
                 id="stream-" + str(uuid.uuid4()),
@@ -4654,7 +4599,6 @@ class AIAgent:
             works unchanged.
             """
             has_tool_use = False
-            self._reasoning_deltas_fired = False
 
             # Reset stale-stream timer for this attempt
             last_chunk_time["t"] = time.time()
@@ -5466,7 +5410,6 @@ class AIAgent:
                 preserve_dots=self._anthropic_preserve_dots(),
                 context_length=ctx_len,
                 base_url=getattr(self, "_anthropic_base_url", None),
-                fast_mode=self.request_overrides.get("speed") == "fast",
             )
 
         if self.api_mode == "codex_responses":
@@ -5482,10 +5425,6 @@ class AIAgent:
                 "models.github.ai" in self.base_url.lower()
                 or "api.githubcopilot.com" in self.base_url.lower()
             )
-            is_codex_backend = (
-                self.provider == "openai-codex"
-                or "chatgpt.com/backend-api/codex" in self.base_url.lower()
-            )
 
             # Resolve reasoning effort: config > default (medium)
             reasoning_effort = "medium"
@@ -5523,10 +5462,7 @@ class AIAgent:
             elif not is_github_responses:
                 kwargs["include"] = []
 
-            if self.request_overrides:
-                kwargs.update(self.request_overrides)
-
-            if self.max_tokens is not None and not is_codex_backend:
+            if self.max_tokens is not None:
                 kwargs["max_output_tokens"] = self.max_tokens
 
             return kwargs
@@ -5621,20 +5557,20 @@ class AIAgent:
         if self.max_tokens is not None:
             if not self._is_qwen_portal():
                 api_kwargs.update(self._max_tokens_param(self.max_tokens))
-        elif (self._is_openrouter_url() or "nousresearch" in self._base_url_lower) and "claude" in (self.model or "").lower():
-            # OpenRouter and Nous Portal translate requests to Anthropic's
-            # Messages API, which requires max_tokens as a mandatory field.
-            # When we omit it, the proxy picks a default that can be too
-            # low — the model spends its output budget on thinking and has
-            # almost nothing left for the actual response (especially large
-            # tool calls like write_file).  Sending the model's real output
-            # limit ensures full capacity.
+        elif self._is_openrouter_url() and "claude" in (self.model or "").lower():
+            # OpenRouter translates requests to Anthropic's Messages API,
+            # which requires max_tokens as a mandatory field.  When we omit
+            # it, OpenRouter picks a default that can be too low — the model
+            # spends its output budget on thinking and has almost nothing
+            # left for the actual response (especially large tool calls like
+            # write_file).  Sending the model's real output limit ensures
+            # full capacity.  Other providers handle the default fine.
             try:
                 from agent.anthropic_adapter import _get_anthropic_max_output
                 _model_output_limit = _get_anthropic_max_output(self.model)
                 api_kwargs["max_tokens"] = _model_output_limit
             except Exception:
-                pass  # fail open — let the proxy pick its default
+                pass  # fail open — let OpenRouter pick its default
 
         extra_body = {}
 
@@ -5697,11 +5633,6 @@ class AIAgent:
         if "x.ai" in self._base_url_lower and hasattr(self, "session_id") and self.session_id:
             api_kwargs["extra_headers"] = {"x-grok-conv-id": self.session_id}
 
-        # Priority Processing / generic request overrides (e.g. service_tier).
-        # Applied last so overrides win over any defaults set above.
-        if self.request_overrides:
-            api_kwargs.update(self.request_overrides)
-
         return api_kwargs
 
     def _supports_reasoning_extra_body(self) -> bool:
@@ -6407,7 +6338,7 @@ class AIAgent:
 
         # Start spinner for CLI mode (skip when TUI handles tool progress)
         spinner = None
-        if self._should_emit_quiet_tool_messages() and self._should_start_quiet_spinner():
+        if self.quiet_mode and not self.tool_progress_callback and self._should_start_quiet_spinner():
             face = random.choice(KawaiiSpinner.KAWAII_WAITING)
             spinner = KawaiiSpinner(f"{face} ⚡ running {num_tools} tools concurrently", spinner_type='dots', print_fn=self._print_fn)
             spinner.start()
@@ -6457,7 +6388,7 @@ class AIAgent:
                     logging.debug(f"Tool result ({len(function_result)} chars): {function_result}")
 
             # Print cute message per tool
-            if self._should_emit_quiet_tool_messages():
+            if self.quiet_mode:
                 cute_msg = _get_cute_tool_message_impl(name, args, tool_duration, result=function_result)
                 self._safe_print(f"  {cute_msg}")
             elif not self.quiet_mode:
@@ -6614,7 +6545,7 @@ class AIAgent:
                     store=self._todo_store,
                 )
                 tool_duration = time.time() - tool_start_time
-                if self._should_emit_quiet_tool_messages():
+                if self.quiet_mode:
                     self._vprint(f"  {_get_cute_tool_message_impl('todo', function_args, tool_duration, result=function_result)}")
             elif function_name == "session_search":
                 if not self._session_db:
@@ -6629,7 +6560,7 @@ class AIAgent:
                         current_session_id=self.session_id,
                     )
                 tool_duration = time.time() - tool_start_time
-                if self._should_emit_quiet_tool_messages():
+                if self.quiet_mode:
                     self._vprint(f"  {_get_cute_tool_message_impl('session_search', function_args, tool_duration, result=function_result)}")
             elif function_name == "memory":
                 target = function_args.get("target", "memory")
@@ -6642,7 +6573,7 @@ class AIAgent:
                     store=self._memory_store,
                 )
                 tool_duration = time.time() - tool_start_time
-                if self._should_emit_quiet_tool_messages():
+                if self.quiet_mode:
                     self._vprint(f"  {_get_cute_tool_message_impl('memory', function_args, tool_duration, result=function_result)}")
             elif function_name == "clarify":
                 from tools.clarify_tool import clarify_tool as _clarify_tool
@@ -6652,7 +6583,7 @@ class AIAgent:
                     callback=self.clarify_callback,
                 )
                 tool_duration = time.time() - tool_start_time
-                if self._should_emit_quiet_tool_messages():
+                if self.quiet_mode:
                     self._vprint(f"  {_get_cute_tool_message_impl('clarify', function_args, tool_duration, result=function_result)}")
             elif function_name == "delegate_task":
                 from tools.delegate_tool import delegate_task as _delegate_task
@@ -6663,7 +6594,7 @@ class AIAgent:
                     goal_preview = (function_args.get("goal") or "")[:30]
                     spinner_label = f"🔀 {goal_preview}" if goal_preview else "🔀 delegating"
                 spinner = None
-                if self._should_emit_quiet_tool_messages() and self._should_start_quiet_spinner():
+                if self.quiet_mode and not self.tool_progress_callback and self._should_start_quiet_spinner():
                     face = random.choice(KawaiiSpinner.KAWAII_WAITING)
                     spinner = KawaiiSpinner(f"{face} {spinner_label}", spinner_type='dots', print_fn=self._print_fn)
                     spinner.start()
@@ -6685,13 +6616,13 @@ class AIAgent:
                     cute_msg = _get_cute_tool_message_impl('delegate_task', function_args, tool_duration, result=_delegate_result)
                     if spinner:
                         spinner.stop(cute_msg)
-                    elif self._should_emit_quiet_tool_messages():
+                    elif self.quiet_mode:
                         self._vprint(f"  {cute_msg}")
             elif self._memory_manager and self._memory_manager.has_tool(function_name):
                 # Memory provider tools (hindsight_retain, honcho_search, etc.)
                 # These are not in the tool registry — route through MemoryManager.
                 spinner = None
-                if self._should_emit_quiet_tool_messages() and self._should_start_quiet_spinner():
+                if self.quiet_mode and not self.tool_progress_callback:
                     face = random.choice(KawaiiSpinner.KAWAII_WAITING)
                     emoji = _get_tool_emoji(function_name)
                     preview = _build_tool_preview(function_name, function_args) or function_name
@@ -6709,11 +6640,11 @@ class AIAgent:
                     cute_msg = _get_cute_tool_message_impl(function_name, function_args, tool_duration, result=_mem_result)
                     if spinner:
                         spinner.stop(cute_msg)
-                    elif self._should_emit_quiet_tool_messages():
+                    elif self.quiet_mode:
                         self._vprint(f"  {cute_msg}")
             elif self.quiet_mode:
                 spinner = None
-                if self._should_emit_quiet_tool_messages() and self._should_start_quiet_spinner():
+                if not self.tool_progress_callback:
                     face = random.choice(KawaiiSpinner.KAWAII_WAITING)
                     emoji = _get_tool_emoji(function_name)
                     preview = _build_tool_preview(function_name, function_args) or function_name
@@ -6736,7 +6667,7 @@ class AIAgent:
                     cute_msg = _get_cute_tool_message_impl(function_name, function_args, tool_duration, result=_spinner_result)
                     if spinner:
                         spinner.stop(cute_msg)
-                    elif self._should_emit_quiet_tool_messages():
+                    else:
                         self._vprint(f"  {cute_msg}")
             else:
                 try:
@@ -7360,7 +7291,6 @@ class AIAgent:
         interrupted = False
         codex_ack_continuations = 0
         length_continue_retries = 0
-        truncated_tool_call_retries = 0
         truncated_response_prefix = ""
         compression_attempts = 0
         _turn_exit_reason = "unknown"  # Diagnostic: why the loop ended
@@ -7829,11 +7759,9 @@ class AIAgent:
                         # retries are pointless.  Detect this early and give a
                         # targeted error instead of wasting 3 API calls.
                         _trunc_content = None
-                        _trunc_has_tool_calls = False
                         if self.api_mode == "chat_completions":
                             _trunc_msg = response.choices[0].message if (hasattr(response, "choices") and response.choices) else None
                             _trunc_content = getattr(_trunc_msg, "content", None) if _trunc_msg else None
-                            _trunc_has_tool_calls = bool(getattr(_trunc_msg, "tool_calls", None)) if _trunc_msg else False
                         elif self.api_mode == "anthropic_messages":
                             # Anthropic response.content is a list of blocks
                             _text_parts = []
@@ -7843,11 +7771,9 @@ class AIAgent:
                             _trunc_content = "\n".join(_text_parts) if _text_parts else None
 
                         _thinking_exhausted = (
-                            not _trunc_has_tool_calls and (
-                                (_trunc_content is not None and not self._has_content_after_think_block(_trunc_content))
-                                or _trunc_content is None
-                            )
-                        )
+                            _trunc_content is not None
+                            and not self._has_content_after_think_block(_trunc_content)
+                        ) or _trunc_content is None
 
                         if _thinking_exhausted:
                             _exhaust_error = (
@@ -7923,34 +7849,6 @@ class AIAgent:
                                     "error": "Response remained truncated after 3 continuation attempts",
                                 }
 
-                        if self.api_mode == "chat_completions":
-                            assistant_message = response.choices[0].message
-                            if assistant_message.tool_calls:
-                                if truncated_tool_call_retries < 1:
-                                    truncated_tool_call_retries += 1
-                                    self._vprint(
-                                        f"{self.log_prefix}⚠️  Truncated tool call detected — retrying API call...",
-                                        force=True,
-                                    )
-                                    # Don't append the broken response to messages;
-                                    # just re-run the same API call from the current
-                                    # message state, giving the model another chance.
-                                    continue
-                                self._vprint(
-                                    f"{self.log_prefix}⚠️  Truncated tool call response detected again — refusing to execute incomplete tool arguments.",
-                                    force=True,
-                                )
-                                self._cleanup_task_resources(effective_task_id)
-                                self._persist_session(messages, conversation_history)
-                                return {
-                                    "final_response": None,
-                                    "messages": messages,
-                                    "api_calls": api_call_count,
-                                    "completed": False,
-                                    "partial": True,
-                                    "error": "Response truncated due to output length limit",
-                                }
-
                         # If we have prior messages, roll back to last complete state
                         if len(messages) > 1:
                             self._vprint(f"{self.log_prefix}   ⏪ Rolling back to last complete assistant turn")
@@ -8263,33 +8161,7 @@ class AIAgent:
                         if _err_body_str:
                             self._vprint(f"{self.log_prefix}   📋 Details: {_err_body_str}", force=True)
                     self._vprint(f"{self.log_prefix}   ⏱️  Elapsed: {elapsed_time:.2f}s  Context: {len(api_messages)} msgs, ~{approx_tokens:,} tokens")
-
-                    # Actionable hint for OpenRouter "no tool endpoints" error.
-                    # This fires regardless of whether fallback succeeds — the
-                    # user needs to know WHY their model failed so they can fix
-                    # their provider routing, not just silently fall back.
-                    if (
-                        self._is_openrouter_url()
-                        and "support tool use" in error_msg
-                    ):
-                        self._vprint(
-                            f"{self.log_prefix}   💡 No OpenRouter providers for {_model} support tool calling with your current settings.",
-                            force=True,
-                        )
-                        if self.providers_allowed:
-                            self._vprint(
-                                f"{self.log_prefix}      Your provider_routing.only restriction is filtering out tool-capable providers.",
-                                force=True,
-                            )
-                            self._vprint(
-                                f"{self.log_prefix}      Try removing the restriction or adding providers that support tools for this model.",
-                                force=True,
-                            )
-                        self._vprint(
-                            f"{self.log_prefix}      Check which providers support tools: https://openrouter.ai/models/{_model}",
-                            force=True,
-                        )
-
+                    
                     # Check for interrupt before deciding to retry
                     if self._interrupt_requested:
                         self._vprint(f"{self.log_prefix}⚡ Interrupt detected during error handling, aborting retries.", force=True)
@@ -8345,10 +8217,6 @@ class AIAgent:
                                 approx_tokens=approx_tokens,
                                 task_id=effective_task_id,
                             )
-                            # Compression created a new session — clear history
-                            # so _flush_messages_to_session_db writes compressed
-                            # messages to the new session, not skipping them.
-                            conversation_history = None
                             if len(messages) < original_len or old_ctx > _reduced_ctx:
                                 self._emit_status(
                                     f"🗜️ Context reduced to {_reduced_ctx:,} tokens "
@@ -8406,10 +8274,6 @@ class AIAgent:
                             messages, system_message, approx_tokens=approx_tokens,
                             task_id=effective_task_id,
                         )
-                        # Compression created a new session — clear history
-                        # so _flush_messages_to_session_db writes compressed
-                        # messages to the new session, not skipping them.
-                        conversation_history = None
 
                         if len(messages) < original_len:
                             self._emit_status(f"🗜️ Compressed {original_len} → {len(messages)} messages, retrying...")
@@ -8528,10 +8392,6 @@ class AIAgent:
                             messages, system_message, approx_tokens=approx_tokens,
                             task_id=effective_task_id,
                         )
-                        # Compression created a new session — clear history
-                        # so _flush_messages_to_session_db writes compressed
-                        # messages to the new session, not skipping them.
-                        conversation_history = None
 
                         if len(messages) < original_len or new_ctx and new_ctx < old_ctx:
                             if len(messages) < original_len:
@@ -9139,11 +8999,6 @@ class AIAgent:
 
                     self._execute_tool_calls(assistant_message, messages, effective_task_id, api_call_count)
 
-                    # Reset per-turn retry counters after successful tool
-                    # execution so a single truncation doesn't poison the
-                    # entire conversation.
-                    truncated_tool_call_retries = 0
-
                     # Signal that a paragraph break is needed before the next
                     # streamed text.  We don't emit it immediately because
                     # multiple consecutive tool iterations would stack up
@@ -9330,7 +9185,6 @@ class AIAgent:
                     # Reset retry counter/signature on successful content
                     if hasattr(self, '_empty_content_retries'):
                         self._empty_content_retries = 0
-                    self._last_empty_content_signature = None
                     self._thinking_prefill_retries = 0
 
                     if (
@@ -9402,7 +9256,6 @@ class AIAgent:
                 # If an assistant message with tool_calls was already appended,
                 # the API expects a role="tool" result for every tool_call_id.
                 # Fill in error results for any that weren't answered yet.
-                pending_handled = False
                 for idx in range(len(messages) - 1, -1, -1):
                     msg = messages[idx]
                     if not isinstance(msg, dict):

scripts/install.sh

@@ -2,8 +2,8 @@
 # ============================================================================
 # Hermes Agent Installer
 # ============================================================================
-# Installation script for Linux, macOS, and Android/Termux.
-# Uses uv for desktop/server installs and Python's stdlib venv + pip on Termux.
+# Installation script for Linux and macOS.
+# Uses uv for fast Python provisioning and package management.
 #
 # Usage:
 #   curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
@@ -117,36 +117,6 @@ log_error() {
     echo -e "${RED}✗${NC} $1"
 }
 
-is_termux() {
-    [ -n "${TERMUX_VERSION:-}" ] || [[ "${PREFIX:-}" == *"com.termux/files/usr"* ]]
-}
-
-get_command_link_dir() {
-    if is_termux && [ -n "${PREFIX:-}" ]; then
-        echo "$PREFIX/bin"
-    else
-        echo "$HOME/.local/bin"
-    fi
-}
-
-get_command_link_display_dir() {
-    if is_termux && [ -n "${PREFIX:-}" ]; then
-        echo '$PREFIX/bin'
-    else
-        echo '~/.local/bin'
-    fi
-}
-
-get_hermes_command_path() {
-    local link_dir
-    link_dir="$(get_command_link_dir)"
-    if [ -x "$link_dir/hermes" ]; then
-        echo "$link_dir/hermes"
-    else
-        echo "hermes"
-    fi
-}
-
 # ============================================================================
 # System detection
 # ============================================================================
@@ -154,17 +124,12 @@ get_hermes_command_path() {
 detect_os() {
     case "$(uname -s)" in
         Linux*)
-            if is_termux; then
-                OS="android"
-                DISTRO="termux"
+            OS="linux"
+            if [ -f /etc/os-release ]; then
+                . /etc/os-release
+                DISTRO="$ID"
             else
-                OS="linux"
-                if [ -f /etc/os-release ]; then
-                    . /etc/os-release
-                    DISTRO="$ID"
-                else
-                    DISTRO="unknown"
-                fi
+                DISTRO="unknown"
             fi
             ;;
         Darwin*)
@@ -193,12 +158,6 @@ detect_os() {
 # ============================================================================
 
 install_uv() {
-    if [ "$DISTRO" = "termux" ]; then
-        log_info "Termux detected — using Python's stdlib venv + pip instead of uv"
-        UV_CMD=""
-        return 0
-    fi
-
     log_info "Checking for uv package manager..."
 
     # Check common locations for uv
@@ -250,25 +209,6 @@ install_uv() {
 }
 
 check_python() {
-    if [ "$DISTRO" = "termux" ]; then
-        log_info "Checking Termux Python..."
-        if command -v python >/dev/null 2>&1; then
-            PYTHON_PATH="$(command -v python)"
-            if "$PYTHON_PATH" -c 'import sys; raise SystemExit(0 if sys.version_info >= (3, 11) else 1)' 2>/dev/null; then
-                PYTHON_FOUND_VERSION=$($PYTHON_PATH --version 2>/dev/null)
-                log_success "Python found: $PYTHON_FOUND_VERSION"
-                return 0
-            fi
-        fi
-
-        log_info "Installing Python via pkg..."
-        pkg install -y python >/dev/null
-        PYTHON_PATH="$(command -v python)"
-        PYTHON_FOUND_VERSION=$($PYTHON_PATH --version 2>/dev/null)
-        log_success "Python installed: $PYTHON_FOUND_VERSION"
-        return 0
-    fi
-
     log_info "Checking Python $PYTHON_VERSION..."
 
     # Let uv handle Python — it can download and manage Python versions
@@ -303,17 +243,6 @@ check_git() {
     fi
 
     log_error "Git not found"
-
-    if [ "$DISTRO" = "termux" ]; then
-        log_info "Installing Git via pkg..."
-        pkg install -y git >/dev/null
-        if command -v git >/dev/null 2>&1; then
-            GIT_VERSION=$(git --version | awk '{print $3}')
-            log_success "Git $GIT_VERSION installed"
-            return 0
-        fi
-    fi
-
     log_info "Please install Git:"
 
     case "$OS" in
@@ -333,9 +262,6 @@ check_git() {
                     ;;
             esac
             ;;
-        android)
-            log_info "  pkg install git"
-            ;;
         macos)
             log_info "  xcode-select --install"
             log_info "  Or: brew install git"
@@ -364,29 +290,11 @@ check_node() {
         return 0
     fi
 
-    if [ "$DISTRO" = "termux" ]; then
-        log_info "Node.js not found — installing Node.js via pkg..."
-    else
-        log_info "Node.js not found — installing Node.js $NODE_VERSION LTS..."
-    fi
+    log_info "Node.js not found — installing Node.js $NODE_VERSION LTS..."
     install_node
 }
 
 install_node() {
-    if [ "$DISTRO" = "termux" ]; then
-        log_info "Installing Node.js via pkg..."
-        if pkg install -y nodejs >/dev/null; then
-            local installed_ver
-            installed_ver=$(node --version 2>/dev/null)
-            log_success "Node.js $installed_ver installed via pkg"
-            HAS_NODE=true
-        else
-            log_warn "Failed to install Node.js via pkg"
-            HAS_NODE=false
-        fi
-        return 0
-    fi
-
     local arch=$(uname -m)
     local node_arch
     case "$arch" in
@@ -505,30 +413,6 @@ install_system_packages() {
         need_ffmpeg=true
     fi
 
-    # Termux always needs the Android build toolchain for the tested pip path,
-    # even when ripgrep/ffmpeg are already present.
-    if [ "$DISTRO" = "termux" ]; then
-        local termux_pkgs=(clang rust make pkg-config libffi openssl)
-        if [ "$need_ripgrep" = true ]; then
-            termux_pkgs+=("ripgrep")
-        fi
-        if [ "$need_ffmpeg" = true ]; then
-            termux_pkgs+=("ffmpeg")
-        fi
-
-        log_info "Installing Termux packages: ${termux_pkgs[*]}"
-        if pkg install -y "${termux_pkgs[@]}" >/dev/null; then
-            [ "$need_ripgrep" = true ] && HAS_RIPGREP=true && log_success "ripgrep installed"
-            [ "$need_ffmpeg" = true ]  && HAS_FFMPEG=true  && log_success "ffmpeg installed"
-            log_success "Termux build dependencies installed"
-            return 0
-        fi
-
-        log_warn "Could not auto-install all Termux packages"
-        log_info "Install manually: pkg install ${termux_pkgs[*]}"
-        return 0
-    fi
-
     # Nothing to install — done
     if [ "$need_ripgrep" = false ] && [ "$need_ffmpeg" = false ]; then
         return 0
@@ -666,9 +550,6 @@ show_manual_install_hint() {
                 *)             log_info "  Use your package manager or visit the project homepage" ;;
             esac
             ;;
-        android)
-            log_info "  pkg install $pkg"
-            ;;
         macos) log_info "  brew install $pkg" ;;
     esac
 }
@@ -765,19 +646,6 @@ setup_venv() {
         return 0
     fi
 
-    if [ "$DISTRO" = "termux" ]; then
-        log_info "Creating virtual environment with Termux Python..."
-
-        if [ -d "venv" ]; then
-            log_info "Virtual environment already exists, recreating..."
-            rm -rf venv
-        fi
-
-        "$PYTHON_PATH" -m venv venv
-        log_success "Virtual environment ready ($(./venv/bin/python --version 2>/dev/null))"
-        return 0
-    fi
-
     log_info "Creating virtual environment with Python $PYTHON_VERSION..."
 
     if [ -d "venv" ]; then
@@ -794,46 +662,6 @@ setup_venv() {
 install_deps() {
     log_info "Installing dependencies..."
 
-    if [ "$DISTRO" = "termux" ]; then
-        if [ "$USE_VENV" = true ]; then
-            export VIRTUAL_ENV="$INSTALL_DIR/venv"
-            PIP_PYTHON="$INSTALL_DIR/venv/bin/python"
-        else
-            PIP_PYTHON="$PYTHON_PATH"
-        fi
-
-        if [ -z "${ANDROID_API_LEVEL:-}" ]; then
-            ANDROID_API_LEVEL="$(getprop ro.build.version.sdk 2>/dev/null || true)"
-            if [ -z "$ANDROID_API_LEVEL" ]; then
-                ANDROID_API_LEVEL=24
-            fi
-            export ANDROID_API_LEVEL
-            log_info "Using ANDROID_API_LEVEL=$ANDROID_API_LEVEL for Android wheel builds"
-        fi
-
-        "$PIP_PYTHON" -m pip install --upgrade pip setuptools wheel >/dev/null
-        if ! "$PIP_PYTHON" -m pip install -e '.[termux]' -c constraints-termux.txt; then
-            log_warn "Termux feature install (.[termux]) failed, trying base install..."
-            if ! "$PIP_PYTHON" -m pip install -e '.' -c constraints-termux.txt; then
-                log_error "Package installation failed on Termux."
-                log_info "Ensure these packages are installed: pkg install clang rust make pkg-config libffi openssl"
-                log_info "Then re-run: cd $INSTALL_DIR && python -m pip install -e '.[termux]' -c constraints-termux.txt"
-                exit 1
-            fi
-        fi
-
-        log_success "Main package installed"
-        log_info "Termux note: browser/WhatsApp tooling is not installed by default; see the Termux guide for optional follow-up steps."
-
-        if [ -d "tinker-atropos" ] && [ -f "tinker-atropos/pyproject.toml" ]; then
-            log_info "tinker-atropos submodule found — skipping install (optional, for RL training)"
-            log_info "  To install later: $PIP_PYTHON -m pip install -e \"./tinker-atropos\""
-        fi
-
-        log_success "All dependencies installed"
-        return 0
-    fi
-
     if [ "$USE_VENV" = true ]; then
         # Tell uv to install into our venv (no need to activate)
         export VIRTUAL_ENV="$INSTALL_DIR/venv"
@@ -915,35 +743,19 @@ setup_path() {
     if [ ! -x "$HERMES_BIN" ]; then
         log_warn "hermes entry point not found at $HERMES_BIN"
         log_info "This usually means the pip install didn't complete successfully."
-        if [ "$DISTRO" = "termux" ]; then
-            log_info "Try: cd $INSTALL_DIR && python -m pip install -e '.[termux]' -c constraints-termux.txt"
-        else
-            log_info "Try: cd $INSTALL_DIR && uv pip install -e '.[all]'"
-        fi
+        log_info "Try: cd $INSTALL_DIR && uv pip install -e '.[all]'"
         return 0
     fi
 
-    local command_link_dir
-    local command_link_display_dir
-    command_link_dir="$(get_command_link_dir)"
-    command_link_display_dir="$(get_command_link_display_dir)"
-
-    # Create a user-facing shim for the hermes command.
-    mkdir -p "$command_link_dir"
-    ln -sf "$HERMES_BIN" "$command_link_dir/hermes"
-    log_success "Symlinked hermes → $command_link_display_dir/hermes"
-
-    if [ "$DISTRO" = "termux" ]; then
-        export PATH="$command_link_dir:$PATH"
-        log_info "$command_link_display_dir is the native Termux command path"
-        log_success "hermes command ready"
-        return 0
-    fi
+    # Create symlink in ~/.local/bin (standard user binary location, usually on PATH)
+    mkdir -p "$HOME/.local/bin"
+    ln -sf "$HERMES_BIN" "$HOME/.local/bin/hermes"
+    log_success "Symlinked hermes → ~/.local/bin/hermes"
 
     # Check if ~/.local/bin is on PATH; if not, add it to shell config.
     # Detect the user's actual login shell (not the shell running this script,
     # which is always bash when piped from curl).
-    if ! echo "$PATH" | tr ':' '\n' | grep -q "^$command_link_dir$"; then
+    if ! echo "$PATH" | tr ':' '\n' | grep -q "^$HOME/.local/bin$"; then
         SHELL_CONFIGS=()
         LOGIN_SHELL="$(basename "${SHELL:-/bin/bash}")"
         case "$LOGIN_SHELL" in
@@ -989,7 +801,7 @@ setup_path() {
     fi
 
     # Export for current session so hermes works immediately
-    export PATH="$command_link_dir:$PATH"
+    export PATH="$HOME/.local/bin:$PATH"
 
     log_success "hermes command ready"
 }
@@ -1066,13 +878,6 @@ install_node_deps() {
         return 0
     fi
 
-    if [ "$DISTRO" = "termux" ]; then
-        log_info "Skipping automatic Node/browser dependency setup on Termux"
-        log_info "Browser automation and WhatsApp bridge are not part of the tested Termux install path yet."
-        log_info "If you want to experiment manually later, run: cd $INSTALL_DIR && npm install"
-        return 0
-    fi
-
     if [ -f "$INSTALL_DIR/package.json" ]; then
         log_info "Installing Node.js dependencies (browser tools)..."
         cd "$INSTALL_DIR"
@@ -1187,7 +992,8 @@ maybe_start_gateway() {
             read -p "Pair WhatsApp now? [Y/n] " -n 1 -r
             echo
             if [[ $REPLY =~ ^[Yy]$ ]] || [[ -z $REPLY ]]; then
-                HERMES_CMD="$(get_hermes_command_path)"
+                HERMES_CMD="$HOME/.local/bin/hermes"
+                [ ! -x "$HERMES_CMD" ] && HERMES_CMD="hermes"
                 $HERMES_CMD whatsapp || true
             fi
         else
@@ -1201,17 +1007,16 @@ maybe_start_gateway() {
     fi
 
     echo ""
-    if [ "$DISTRO" = "termux" ]; then
-        read -p "Would you like to start the gateway in the background? [Y/n] " -n 1 -r < /dev/tty
-    else
-        read -p "Would you like to install the gateway as a background service? [Y/n] " -n 1 -r < /dev/tty
-    fi
+    read -p "Would you like to install the gateway as a background service? [Y/n] " -n 1 -r < /dev/tty
     echo
 
     if [[ $REPLY =~ ^[Yy]$ ]] || [[ -z $REPLY ]]; then
-        HERMES_CMD="$(get_hermes_command_path)"
+        HERMES_CMD="$HOME/.local/bin/hermes"
+        if [ ! -x "$HERMES_CMD" ]; then
+            HERMES_CMD="hermes"
+        fi
 
-        if [ "$DISTRO" != "termux" ] && command -v systemctl &> /dev/null; then
+        if command -v systemctl &> /dev/null; then
             log_info "Installing systemd service..."
             if $HERMES_CMD gateway install 2>/dev/null; then
                 log_success "Gateway service installed"
@@ -1224,19 +1029,12 @@ maybe_start_gateway() {
                 log_warn "Systemd install failed. You can start manually: hermes gateway"
             fi
         else
-            if [ "$DISTRO" = "termux" ]; then
-                log_info "Termux detected — starting gateway in best-effort background mode..."
-            else
-                log_info "systemd not available — starting gateway in background..."
-            fi
+            log_info "systemd not available — starting gateway in background..."
             nohup $HERMES_CMD gateway > "$HERMES_HOME/logs/gateway.log" 2>&1 &
             GATEWAY_PID=$!
             log_success "Gateway started (PID $GATEWAY_PID). Logs: ~/.hermes/logs/gateway.log"
             log_info "To stop: kill $GATEWAY_PID"
             log_info "To restart later: hermes gateway"
-            if [ "$DISTRO" = "termux" ]; then
-                log_warn "Android may stop background processes when Termux is suspended or the system reclaims resources."
-            fi
         fi
     else
         log_info "Skipped. Start the gateway later with: hermes gateway"
@@ -1275,33 +1073,24 @@ print_success() {
 
     echo -e "${CYAN}─────────────────────────────────────────────────────────${NC}"
     echo ""
-    if [ "$DISTRO" = "termux" ]; then
-        echo -e "${YELLOW}⚡ 'hermes' was linked into $(get_command_link_display_dir), which is already on PATH in Termux.${NC}"
-        echo ""
+    echo -e "${YELLOW}⚡ Reload your shell to use 'hermes' command:${NC}"
+    echo ""
+    LOGIN_SHELL="$(basename "${SHELL:-/bin/bash}")"
+    if [ "$LOGIN_SHELL" = "zsh" ]; then
+        echo "   source ~/.zshrc"
+    elif [ "$LOGIN_SHELL" = "bash" ]; then
+        echo "   source ~/.bashrc"
     else
-        echo -e "${YELLOW}⚡ Reload your shell to use 'hermes' command:${NC}"
-        echo ""
-        LOGIN_SHELL="$(basename "${SHELL:-/bin/bash}")"
-        if [ "$LOGIN_SHELL" = "zsh" ]; then
-            echo "   source ~/.zshrc"
-        elif [ "$LOGIN_SHELL" = "bash" ]; then
-            echo "   source ~/.bashrc"
-        else
-            echo "   source ~/.bashrc   # or ~/.zshrc"
-        fi
-        echo ""
+        echo "   source ~/.bashrc   # or ~/.zshrc"
     fi
+    echo ""
 
     # Show Node.js warning if auto-install failed
     if [ "$HAS_NODE" = false ]; then
         echo -e "${YELLOW}"
         echo "Note: Node.js could not be installed automatically."
         echo "Browser tools need Node.js. Install manually:"
-        if [ "$DISTRO" = "termux" ]; then
-            echo "  pkg install nodejs"
-        else
-            echo "  https://nodejs.org/en/download/"
-        fi
+        echo "  https://nodejs.org/en/download/"
         echo -e "${NC}"
     fi
 
@@ -1310,11 +1099,7 @@ print_success() {
         echo -e "${YELLOW}"
         echo "Note: ripgrep (rg) was not found. File search will use"
         echo "grep as a fallback. For faster search in large codebases,"
-        if [ "$DISTRO" = "termux" ]; then
-            echo "install ripgrep: pkg install ripgrep"
-        else
-            echo "install ripgrep: sudo apt install ripgrep (or brew install ripgrep)"
-        fi
+        echo "install ripgrep: sudo apt install ripgrep (or brew install ripgrep)"
         echo -e "${NC}"
     fi
 }

setup-hermes.sh

@@ -3,17 +3,17 @@
 # Hermes Agent Setup Script
 # ============================================================================
 # Quick setup for developers who cloned the repo manually.
-# Uses uv for desktop/server setup and Python's stdlib venv + pip on Termux.
+# Uses uv for fast Python provisioning and package management.
 #
 # Usage:
 #   ./setup-hermes.sh
 #
 # This script:
-# 1. Detects desktop/server vs Android/Termux setup path
-# 2. Creates a Python 3.11 virtual environment
-# 3. Installs the appropriate dependency set for the platform
+# 1. Installs uv if not present
+# 2. Creates a virtual environment with Python 3.11 via uv
+# 3. Installs all dependencies (main package + submodules)
 # 4. Creates .env from template (if not exists)
-# 5. Symlinks the 'hermes' CLI command into a user-facing bin dir
+# 5. Symlinks the 'hermes' CLI command into ~/.local/bin
 # 6. Runs the setup wizard (optional)
 # ============================================================================
 
@@ -31,26 +31,6 @@ cd "$SCRIPT_DIR"
 
 PYTHON_VERSION="3.11"
 
-is_termux() {
-    [ -n "${TERMUX_VERSION:-}" ] || [[ "${PREFIX:-}" == *"com.termux/files/usr"* ]]
-}
-
-get_command_link_dir() {
-    if is_termux && [ -n "${PREFIX:-}" ]; then
-        echo "$PREFIX/bin"
-    else
-        echo "$HOME/.local/bin"
-    fi
-}
-
-get_command_link_display_dir() {
-    if is_termux && [ -n "${PREFIX:-}" ]; then
-        echo '$PREFIX/bin'
-    else
-        echo '~/.local/bin'
-    fi
-}
-
 echo ""
 echo -e "${CYAN}⚕ Hermes Agent Setup${NC}"
 echo ""
@@ -62,40 +42,36 @@ echo ""
 echo -e "${CYAN}→${NC} Checking for uv..."
 
 UV_CMD=""
-if is_termux; then
-    echo -e "${CYAN}→${NC} Termux detected — using Python's stdlib venv + pip instead of uv"
+if command -v uv &> /dev/null; then
+    UV_CMD="uv"
+elif [ -x "$HOME/.local/bin/uv" ]; then
+    UV_CMD="$HOME/.local/bin/uv"
+elif [ -x "$HOME/.cargo/bin/uv" ]; then
+    UV_CMD="$HOME/.cargo/bin/uv"
+fi
+
+if [ -n "$UV_CMD" ]; then
+    UV_VERSION=$($UV_CMD --version 2>/dev/null)
+    echo -e "${GREEN}✓${NC} uv found ($UV_VERSION)"
 else
-    if command -v uv &> /dev/null; then
-        UV_CMD="uv"
-    elif [ -x "$HOME/.local/bin/uv" ]; then
-        UV_CMD="$HOME/.local/bin/uv"
-    elif [ -x "$HOME/.cargo/bin/uv" ]; then
-        UV_CMD="$HOME/.cargo/bin/uv"
-    fi
-
-    if [ -n "$UV_CMD" ]; then
-        UV_VERSION=$($UV_CMD --version 2>/dev/null)
-        echo -e "${GREEN}✓${NC} uv found ($UV_VERSION)"
-    else
-        echo -e "${CYAN}→${NC} Installing uv..."
-        if curl -LsSf https://astral.sh/uv/install.sh | sh 2>/dev/null; then
-            if [ -x "$HOME/.local/bin/uv" ]; then
-                UV_CMD="$HOME/.local/bin/uv"
-            elif [ -x "$HOME/.cargo/bin/uv" ]; then
-                UV_CMD="$HOME/.cargo/bin/uv"
-            fi
-
-            if [ -n "$UV_CMD" ]; then
-                UV_VERSION=$($UV_CMD --version 2>/dev/null)
-                echo -e "${GREEN}✓${NC} uv installed ($UV_VERSION)"
-            else
-                echo -e "${RED}✗${NC} uv installed but not found. Add ~/.local/bin to PATH and retry."
-                exit 1
-            fi
+    echo -e "${CYAN}→${NC} Installing uv..."
+    if curl -LsSf https://astral.sh/uv/install.sh | sh 2>/dev/null; then
+        if [ -x "$HOME/.local/bin/uv" ]; then
+            UV_CMD="$HOME/.local/bin/uv"
+        elif [ -x "$HOME/.cargo/bin/uv" ]; then
+            UV_CMD="$HOME/.cargo/bin/uv"
+        fi
+        
+        if [ -n "$UV_CMD" ]; then
+            UV_VERSION=$($UV_CMD --version 2>/dev/null)
+            echo -e "${GREEN}✓${NC} uv installed ($UV_VERSION)"
         else
-            echo -e "${RED}✗${NC} Failed to install uv. Visit https://docs.astral.sh/uv/"
+            echo -e "${RED}✗${NC} uv installed but not found. Add ~/.local/bin to PATH and retry."
             exit 1
         fi
+    else
+        echo -e "${RED}✗${NC} Failed to install uv. Visit https://docs.astral.sh/uv/"
+        exit 1
     fi
 fi
 
@@ -105,34 +81,16 @@ fi
 
 echo -e "${CYAN}→${NC} Checking Python $PYTHON_VERSION..."
 
-if is_termux; then
-    if command -v python >/dev/null 2>&1; then
-        PYTHON_PATH="$(command -v python)"
-        if "$PYTHON_PATH" -c 'import sys; raise SystemExit(0 if sys.version_info >= (3, 11) else 1)' 2>/dev/null; then
-            PYTHON_FOUND_VERSION=$($PYTHON_PATH --version 2>/dev/null)
-            echo -e "${GREEN}✓${NC} $PYTHON_FOUND_VERSION found"
-        else
-            echo -e "${RED}✗${NC} Termux Python must be 3.11+"
-            echo "    Run: pkg install python"
-            exit 1
-        fi
-    else
-        echo -e "${RED}✗${NC} Python not found in Termux"
-        echo "    Run: pkg install python"
-        exit 1
-    fi
+if $UV_CMD python find "$PYTHON_VERSION" &> /dev/null; then
+    PYTHON_PATH=$($UV_CMD python find "$PYTHON_VERSION")
+    PYTHON_FOUND_VERSION=$($PYTHON_PATH --version 2>/dev/null)
+    echo -e "${GREEN}✓${NC} $PYTHON_FOUND_VERSION found"
 else
-    if $UV_CMD python find "$PYTHON_VERSION" &> /dev/null; then
-        PYTHON_PATH=$($UV_CMD python find "$PYTHON_VERSION")
-        PYTHON_FOUND_VERSION=$($PYTHON_PATH --version 2>/dev/null)
-        echo -e "${GREEN}✓${NC} $PYTHON_FOUND_VERSION found"
-    else
-        echo -e "${CYAN}→${NC} Python $PYTHON_VERSION not found, installing via uv..."
-        $UV_CMD python install "$PYTHON_VERSION"
-        PYTHON_PATH=$($UV_CMD python find "$PYTHON_VERSION")
-        PYTHON_FOUND_VERSION=$($PYTHON_PATH --version 2>/dev/null)
-        echo -e "${GREEN}✓${NC} $PYTHON_FOUND_VERSION installed"
-    fi
+    echo -e "${CYAN}→${NC} Python $PYTHON_VERSION not found, installing via uv..."
+    $UV_CMD python install "$PYTHON_VERSION"
+    PYTHON_PATH=$($UV_CMD python find "$PYTHON_VERSION")
+    PYTHON_FOUND_VERSION=$($PYTHON_PATH --version 2>/dev/null)
+    echo -e "${GREEN}✓${NC} $PYTHON_FOUND_VERSION installed"
 fi
 
 # ============================================================================
@@ -146,16 +104,11 @@ if [ -d "venv" ]; then
     rm -rf venv
 fi
 
-if is_termux; then
-    "$PYTHON_PATH" -m venv venv
-    echo -e "${GREEN}✓${NC} venv created with stdlib venv"
-else
-    $UV_CMD venv venv --python "$PYTHON_VERSION"
-    echo -e "${GREEN}✓${NC} venv created (Python $PYTHON_VERSION)"
-fi
+$UV_CMD venv venv --python "$PYTHON_VERSION"
+echo -e "${GREEN}✓${NC} venv created (Python $PYTHON_VERSION)"
 
+# Tell uv to install into this venv (no activation needed for uv)
 export VIRTUAL_ENV="$SCRIPT_DIR/venv"
-SETUP_PYTHON="$SCRIPT_DIR/venv/bin/python"
 
 # ============================================================================
 # Dependencies
@@ -163,34 +116,19 @@ SETUP_PYTHON="$SCRIPT_DIR/venv/bin/python"
 
 echo -e "${CYAN}→${NC} Installing dependencies..."
 
-if is_termux; then
-    export ANDROID_API_LEVEL="$(getprop ro.build.version.sdk 2>/dev/null || printf '%s' "${ANDROID_API_LEVEL:-}")"
-    echo -e "${CYAN}→${NC} Termux detected — installing the tested Android bundle"
-    "$SETUP_PYTHON" -m pip install --upgrade pip setuptools wheel
-    if [ -f "constraints-termux.txt" ]; then
-        "$SETUP_PYTHON" -m pip install -e ".[termux]" -c constraints-termux.txt || {
-            echo -e "${YELLOW}⚠${NC} Termux bundle install failed, falling back to base install..."
-            "$SETUP_PYTHON" -m pip install -e "." -c constraints-termux.txt
-        }
-    else
-        "$SETUP_PYTHON" -m pip install -e ".[termux]" || "$SETUP_PYTHON" -m pip install -e "."
-    fi
-    echo -e "${GREEN}✓${NC} Dependencies installed"
-else
-    # Prefer uv sync with lockfile (hash-verified installs) when available,
-    # fall back to pip install for compatibility or when lockfile is stale.
-    if [ -f "uv.lock" ]; then
-        echo -e "${CYAN}→${NC} Using uv.lock for hash-verified installation..."
-        UV_PROJECT_ENVIRONMENT="$SCRIPT_DIR/venv" $UV_CMD sync --all-extras --locked 2>/dev/null && \
-            echo -e "${GREEN}✓${NC} Dependencies installed (lockfile verified)" || {
-            echo -e "${YELLOW}⚠${NC} Lockfile install failed (may be outdated), falling back to pip install..."
-            $UV_CMD pip install -e ".[all]" || $UV_CMD pip install -e "."
-            echo -e "${GREEN}✓${NC} Dependencies installed"
-        }
-    else
+# Prefer uv sync with lockfile (hash-verified installs) when available,
+# fall back to pip install for compatibility or when lockfile is stale.
+if [ -f "uv.lock" ]; then
+    echo -e "${CYAN}→${NC} Using uv.lock for hash-verified installation..."
+    UV_PROJECT_ENVIRONMENT="$SCRIPT_DIR/venv" $UV_CMD sync --all-extras --locked 2>/dev/null && \
+        echo -e "${GREEN}✓${NC} Dependencies installed (lockfile verified)" || {
+        echo -e "${YELLOW}⚠${NC} Lockfile install failed (may be outdated), falling back to pip install..."
         $UV_CMD pip install -e ".[all]" || $UV_CMD pip install -e "."
         echo -e "${GREEN}✓${NC} Dependencies installed"
-    fi
+    }
+else
+    $UV_CMD pip install -e ".[all]" || $UV_CMD pip install -e "."
+    echo -e "${GREEN}✓${NC} Dependencies installed"
 fi
 
 # ============================================================================
@@ -200,9 +138,7 @@ fi
 echo -e "${CYAN}→${NC} Installing optional submodules..."
 
 # tinker-atropos (RL training backend)
-if is_termux; then
-    echo -e "${CYAN}→${NC} Skipping tinker-atropos on Termux (not part of the tested Android path)"
-elif [ -d "tinker-atropos" ] && [ -f "tinker-atropos/pyproject.toml" ]; then
+if [ -d "tinker-atropos" ] && [ -f "tinker-atropos/pyproject.toml" ]; then
     $UV_CMD pip install -e "./tinker-atropos" && \
         echo -e "${GREEN}✓${NC} tinker-atropos installed" || \
         echo -e "${YELLOW}⚠${NC} tinker-atropos install failed (RL tools may not work)"
@@ -224,42 +160,34 @@ else
     echo
     if [[ $REPLY =~ ^[Yy]$ ]] || [[ -z $REPLY ]]; then
         INSTALLED=false
-
-        if is_termux; then
-            pkg install -y ripgrep && INSTALLED=true
-        else
-            # Check if sudo is available
-            if command -v sudo &> /dev/null && sudo -n true 2>/dev/null; then
-                if command -v apt &> /dev/null; then
-                    sudo apt install -y ripgrep && INSTALLED=true
-                elif command -v dnf &> /dev/null; then
-                    sudo dnf install -y ripgrep && INSTALLED=true
-                fi
-            fi
-
-            # Try brew (no sudo needed)
-            if [ "$INSTALLED" = false ] && command -v brew &> /dev/null; then
-                brew install ripgrep && INSTALLED=true
-            fi
-
-            # Try cargo (no sudo needed)
-            if [ "$INSTALLED" = false ] && command -v cargo &> /dev/null; then
-                echo -e "${CYAN}→${NC} Trying cargo install (no sudo required)..."
-                cargo install ripgrep && INSTALLED=true
+        
+        # Check if sudo is available
+        if command -v sudo &> /dev/null && sudo -n true 2>/dev/null; then
+            if command -v apt &> /dev/null; then
+                sudo apt install -y ripgrep && INSTALLED=true
+            elif command -v dnf &> /dev/null; then
+                sudo dnf install -y ripgrep && INSTALLED=true
             fi
         fi
-
+        
+        # Try brew (no sudo needed)
+        if [ "$INSTALLED" = false ] && command -v brew &> /dev/null; then
+            brew install ripgrep && INSTALLED=true
+        fi
+        
+        # Try cargo (no sudo needed)
+        if [ "$INSTALLED" = false ] && command -v cargo &> /dev/null; then
+            echo -e "${CYAN}→${NC} Trying cargo install (no sudo required)..."
+            cargo install ripgrep && INSTALLED=true
+        fi
+        
         if [ "$INSTALLED" = true ]; then
             echo -e "${GREEN}✓${NC} ripgrep installed"
         else
             echo -e "${YELLOW}⚠${NC} Auto-install failed. Install options:"
-            if is_termux; then
-                echo "    pkg install ripgrep          # Termux / Android"
-            else
-                echo "    sudo apt install ripgrep     # Debian/Ubuntu"
-                echo "    brew install ripgrep         # macOS"
-                echo "    cargo install ripgrep        # With Rust (no sudo)"
-            fi
+            echo "    sudo apt install ripgrep     # Debian/Ubuntu"
+            echo "    brew install ripgrep         # macOS"
+            echo "    cargo install ripgrep        # With Rust (no sudo)"
             echo "    https://github.com/BurntSushi/ripgrep#installation"
         fi
     fi
@@ -279,56 +207,49 @@ else
 fi
 
 # ============================================================================
-# PATH setup — symlink hermes into a user-facing bin dir
+# PATH setup — symlink hermes into ~/.local/bin
 # ============================================================================
 
 echo -e "${CYAN}→${NC} Setting up hermes command..."
 
 HERMES_BIN="$SCRIPT_DIR/venv/bin/hermes"
-COMMAND_LINK_DIR="$(get_command_link_dir)"
-COMMAND_LINK_DISPLAY_DIR="$(get_command_link_display_dir)"
-mkdir -p "$COMMAND_LINK_DIR"
-ln -sf "$HERMES_BIN" "$COMMAND_LINK_DIR/hermes"
-echo -e "${GREEN}✓${NC} Symlinked hermes → $COMMAND_LINK_DISPLAY_DIR/hermes"
+mkdir -p "$HOME/.local/bin"
+ln -sf "$HERMES_BIN" "$HOME/.local/bin/hermes"
+echo -e "${GREEN}✓${NC} Symlinked hermes → ~/.local/bin/hermes"
 
-if is_termux; then
-    export PATH="$COMMAND_LINK_DIR:$PATH"
-    echo -e "${GREEN}✓${NC} $COMMAND_LINK_DISPLAY_DIR is already on PATH in Termux"
+# Determine the appropriate shell config file
+SHELL_CONFIG=""
+if [[ "$SHELL" == *"zsh"* ]]; then
+    SHELL_CONFIG="$HOME/.zshrc"
+elif [[ "$SHELL" == *"bash"* ]]; then
+    SHELL_CONFIG="$HOME/.bashrc"
+    [ ! -f "$SHELL_CONFIG" ] && SHELL_CONFIG="$HOME/.bash_profile"
 else
-    # Determine the appropriate shell config file
-    SHELL_CONFIG=""
-    if [[ "$SHELL" == *"zsh"* ]]; then
+    # Fallback to checking existing files
+    if [ -f "$HOME/.zshrc" ]; then
         SHELL_CONFIG="$HOME/.zshrc"
-    elif [[ "$SHELL" == *"bash"* ]]; then
+    elif [ -f "$HOME/.bashrc" ]; then
         SHELL_CONFIG="$HOME/.bashrc"
-        [ ! -f "$SHELL_CONFIG" ] && SHELL_CONFIG="$HOME/.bash_profile"
-    else
-        # Fallback to checking existing files
-        if [ -f "$HOME/.zshrc" ]; then
-            SHELL_CONFIG="$HOME/.zshrc"
-        elif [ -f "$HOME/.bashrc" ]; then
-            SHELL_CONFIG="$HOME/.bashrc"
-        elif [ -f "$HOME/.bash_profile" ]; then
-            SHELL_CONFIG="$HOME/.bash_profile"
-        fi
+    elif [ -f "$HOME/.bash_profile" ]; then
+        SHELL_CONFIG="$HOME/.bash_profile"
     fi
+fi
 
-    if [ -n "$SHELL_CONFIG" ]; then
-        # Touch the file just in case it doesn't exist yet but was selected
-        touch "$SHELL_CONFIG" 2>/dev/null || true
-
-        if ! echo "$PATH" | tr ':' '\n' | grep -q "^$HOME/.local/bin$"; then
-            if ! grep -q '\.local/bin' "$SHELL_CONFIG" 2>/dev/null; then
-                echo "" >> "$SHELL_CONFIG"
-                echo "# Hermes Agent — ensure ~/.local/bin is on PATH" >> "$SHELL_CONFIG"
-                echo 'export PATH="$HOME/.local/bin:$PATH"' >> "$SHELL_CONFIG"
-                echo -e "${GREEN}✓${NC} Added ~/.local/bin to PATH in $SHELL_CONFIG"
-            else
-                echo -e "${GREEN}✓${NC} ~/.local/bin already in $SHELL_CONFIG"
-            fi
+if [ -n "$SHELL_CONFIG" ]; then
+    # Touch the file just in case it doesn't exist yet but was selected
+    touch "$SHELL_CONFIG" 2>/dev/null || true
+    
+    if ! echo "$PATH" | tr ':' '\n' | grep -q "^$HOME/.local/bin$"; then
+        if ! grep -q '\.local/bin' "$SHELL_CONFIG" 2>/dev/null; then
+            echo "" >> "$SHELL_CONFIG"
+            echo "# Hermes Agent — ensure ~/.local/bin is on PATH" >> "$SHELL_CONFIG"
+            echo 'export PATH="$HOME/.local/bin:$PATH"' >> "$SHELL_CONFIG"
+            echo -e "${GREEN}✓${NC} Added ~/.local/bin to PATH in $SHELL_CONFIG"
         else
-            echo -e "${GREEN}✓${NC} ~/.local/bin already on PATH"
+            echo -e "${GREEN}✓${NC} ~/.local/bin already in $SHELL_CONFIG"
         fi
+    else
+        echo -e "${GREEN}✓${NC} ~/.local/bin already on PATH"
     fi
 fi
 
@@ -360,31 +281,18 @@ echo -e "${GREEN}✓ Setup complete!${NC}"
 echo ""
 echo "Next steps:"
 echo ""
-if is_termux; then
-    echo "  1. Run the setup wizard to configure API keys:"
-    echo "     hermes setup"
-    echo ""
-    echo "  2. Start chatting:"
-    echo "     hermes"
-    echo ""
-else
-    echo "  1. Reload your shell:"
-    echo "     source $SHELL_CONFIG"
-    echo ""
-    echo "  2. Run the setup wizard to configure API keys:"
-    echo "     hermes setup"
-    echo ""
-    echo "  3. Start chatting:"
-    echo "     hermes"
-    echo ""
-fi
+echo "  1. Reload your shell:"
+echo "     source $SHELL_CONFIG"
+echo ""
+echo "  2. Run the setup wizard to configure API keys:"
+echo "     hermes setup"
+echo ""
+echo "  3. Start chatting:"
+echo "     hermes"
+echo ""
 echo "Other commands:"
 echo "  hermes status        # Check configuration"
-if is_termux; then
-    echo "  hermes gateway       # Run gateway in foreground"
-else
-    echo "  hermes gateway install # Install gateway service (messaging + cron)"
-fi
+echo "  hermes gateway install # Install gateway service (messaging + cron)"
 echo "  hermes cron list     # View scheduled jobs"
 echo "  hermes doctor        # Diagnose issues"
 echo ""

tests/agent/test_anthropic_adapter.py

@@ -17,7 +17,6 @@ from agent.anthropic_adapter import (
     build_anthropic_kwargs,
     convert_messages_to_anthropic,
     convert_tools_to_anthropic,
-    get_anthropic_token_source,
     is_claude_code_token_valid,
     normalize_anthropic_response,
     normalize_model_name,
@@ -81,9 +80,6 @@ class TestBuildAnthropicClient:
             build_anthropic_client("sk-ant-api03-x", base_url="https://custom.api.com")
             kwargs = mock_sdk.Anthropic.call_args[1]
             assert kwargs["base_url"] == "https://custom.api.com"
-            assert kwargs["default_headers"] == {
-                "anthropic-beta": "interleaved-thinking-2025-05-14,fine-grained-tool-streaming-2025-05-14"
-            }
 
     def test_minimax_anthropic_endpoint_uses_bearer_auth_for_regular_api_keys(self):
         with patch("agent.anthropic_adapter._anthropic_sdk") as mock_sdk:
@@ -95,20 +91,7 @@ class TestBuildAnthropicClient:
             assert kwargs["auth_token"] == "minimax-secret-123"
             assert "api_key" not in kwargs
             assert kwargs["default_headers"] == {
-                "anthropic-beta": "interleaved-thinking-2025-05-14"
-            }
-
-    def test_minimax_cn_anthropic_endpoint_omits_tool_streaming_beta(self):
-        with patch("agent.anthropic_adapter._anthropic_sdk") as mock_sdk:
-            build_anthropic_client(
-                "minimax-cn-secret-123",
-                base_url="https://api.minimaxi.com/anthropic",
-            )
-            kwargs = mock_sdk.Anthropic.call_args[1]
-            assert kwargs["auth_token"] == "minimax-cn-secret-123"
-            assert "api_key" not in kwargs
-            assert kwargs["default_headers"] == {
-                "anthropic-beta": "interleaved-thinking-2025-05-14"
+                "anthropic-beta": "interleaved-thinking-2025-05-14,fine-grained-tool-streaming-2025-05-14"
             }
 
 
@@ -181,15 +164,6 @@ class TestResolveAnthropicToken:
         monkeypatch.setattr("agent.anthropic_adapter.Path.home", lambda: tmp_path)
         assert resolve_anthropic_token() == "sk-ant-oat01-mytoken"
 
-    def test_reports_claude_json_primary_key_source(self, monkeypatch, tmp_path):
-        monkeypatch.delenv("ANTHROPIC_API_KEY", raising=False)
-        monkeypatch.delenv("ANTHROPIC_TOKEN", raising=False)
-        monkeypatch.delenv("CLAUDE_CODE_OAUTH_TOKEN", raising=False)
-        (tmp_path / ".claude.json").write_text(json.dumps({"primaryApiKey": "sk-ant-api03-primary"}))
-        monkeypatch.setattr("agent.anthropic_adapter.Path.home", lambda: tmp_path)
-
-        assert get_anthropic_token_source("sk-ant-api03-primary") == "claude_json_primary_api_key"
-
     def test_does_not_resolve_primary_api_key_as_native_anthropic_token(self, monkeypatch, tmp_path):
         monkeypatch.delenv("ANTHROPIC_API_KEY", raising=False)
         monkeypatch.delenv("ANTHROPIC_TOKEN", raising=False)

tests/agent/test_auxiliary_client.py

@@ -9,7 +9,6 @@ import pytest
 
 from agent.auxiliary_client import (
     get_text_auxiliary_client,
-    get_vision_auxiliary_client,
     get_available_vision_backends,
     resolve_vision_provider_client,
     resolve_provider_client,
@@ -20,7 +19,6 @@ from agent.auxiliary_client import (
     _get_provider_chain,
     _is_payment_error,
     _try_payment_fallback,
-    _resolve_forced_provider,
     _resolve_auto,
 )
 
@@ -664,15 +662,6 @@ class TestGetTextAuxiliaryClient:
 class TestVisionClientFallback:
     """Vision client auto mode resolves known-good multimodal backends."""
 
-    def test_vision_returns_none_without_any_credentials(self):
-        with (
-            patch("agent.auxiliary_client._read_nous_auth", return_value=None),
-            patch("agent.auxiliary_client._try_anthropic", return_value=(None, None)),
-        ):
-            client, model = get_vision_auxiliary_client()
-        assert client is None
-        assert model is None
-
     def test_vision_auto_includes_active_provider_when_configured(self, monkeypatch):
         """Active provider appears in available backends when credentials exist."""
         monkeypatch.setenv("ANTHROPIC_API_KEY", "***")
@@ -754,21 +743,6 @@ class TestAuxiliaryPoolAwareness:
         assert call_kwargs["base_url"] == "https://api.githubcopilot.com"
         assert call_kwargs["default_headers"]["Editor-Version"]
 
-    def test_vision_auto_uses_active_provider_as_fallback(self, monkeypatch):
-        """When no OpenRouter/Nous available, vision auto falls back to active provider."""
-        monkeypatch.setenv("ANTHROPIC_API_KEY", "***")
-        with (
-            patch("agent.auxiliary_client._read_nous_auth", return_value=None),
-            patch("agent.auxiliary_client._read_main_provider", return_value="anthropic"),
-            patch("agent.auxiliary_client._read_main_model", return_value="claude-sonnet-4"),
-            patch("agent.anthropic_adapter.build_anthropic_client", return_value=MagicMock()),
-            patch("agent.anthropic_adapter.resolve_anthropic_token", return_value="***"),
-        ):
-            client, model = get_vision_auxiliary_client()
-
-        assert client is not None
-        assert client.__class__.__name__ == "AnthropicAuxiliaryClient"
-
     def test_vision_auto_prefers_active_provider_over_openrouter(self, monkeypatch):
         """Active provider is tried before OpenRouter in vision auto."""
         monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
@@ -800,43 +774,6 @@ class TestAuxiliaryPoolAwareness:
         assert client is not None
         assert provider == "custom:local"
 
-    def test_vision_direct_endpoint_override(self, monkeypatch):
-        monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
-        monkeypatch.setenv("AUXILIARY_VISION_BASE_URL", "http://localhost:4567/v1")
-        monkeypatch.setenv("AUXILIARY_VISION_API_KEY", "vision-key")
-        monkeypatch.setenv("AUXILIARY_VISION_MODEL", "vision-model")
-        with patch("agent.auxiliary_client.OpenAI") as mock_openai:
-            client, model = get_vision_auxiliary_client()
-        assert model == "vision-model"
-        assert mock_openai.call_args.kwargs["base_url"] == "http://localhost:4567/v1"
-        assert mock_openai.call_args.kwargs["api_key"] == "vision-key"
-
-    def test_vision_direct_endpoint_without_key_uses_placeholder(self, monkeypatch):
-        """Vision endpoint without API key should use 'no-key-required' placeholder."""
-        monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
-        monkeypatch.setenv("AUXILIARY_VISION_BASE_URL", "http://localhost:4567/v1")
-        monkeypatch.setenv("AUXILIARY_VISION_MODEL", "vision-model")
-        with patch("agent.auxiliary_client.OpenAI") as mock_openai:
-            client, model = get_vision_auxiliary_client()
-        assert client is not None
-        assert model == "vision-model"
-        assert mock_openai.call_args.kwargs["api_key"] == "no-key-required"
-
-    def test_vision_uses_openrouter_when_available(self, monkeypatch):
-        monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
-        with patch("agent.auxiliary_client.OpenAI") as mock_openai:
-            client, model = get_vision_auxiliary_client()
-        assert model == "google/gemini-3-flash-preview"
-        assert client is not None
-
-    def test_vision_uses_nous_when_available(self, monkeypatch):
-        with patch("agent.auxiliary_client._read_nous_auth") as mock_nous, \
-             patch("agent.auxiliary_client.OpenAI"):
-            mock_nous.return_value = {"access_token": "nous-tok"}
-            client, model = get_vision_auxiliary_client()
-        assert model == "google/gemini-3-flash-preview"
-        assert client is not None
-
     def test_vision_config_google_provider_uses_gemini_credentials(self, monkeypatch):
         config = {
             "auxiliary": {
@@ -862,53 +799,6 @@ class TestAuxiliaryPoolAwareness:
         assert mock_openai.call_args.kwargs["api_key"] == "gemini-key"
         assert mock_openai.call_args.kwargs["base_url"] == "https://generativelanguage.googleapis.com/v1beta/openai"
 
-    def test_vision_forced_main_uses_custom_endpoint(self, monkeypatch):
-        """When explicitly forced to 'main', vision CAN use custom endpoint."""
-        config = {
-            "model": {
-                "provider": "custom",
-                "base_url": "http://localhost:1234/v1",
-                "default": "my-local-model",
-            }
-        }
-        monkeypatch.setenv("AUXILIARY_VISION_PROVIDER", "main")
-        monkeypatch.setenv("OPENAI_API_KEY", "local-key")
-        monkeypatch.setattr("hermes_cli.config.load_config", lambda: config)
-        monkeypatch.setattr("hermes_cli.runtime_provider.load_config", lambda: config)
-        with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
-             patch("agent.auxiliary_client.OpenAI") as mock_openai:
-            client, model = get_vision_auxiliary_client()
-        assert client is not None
-        assert model == "my-local-model"
-
-    def test_vision_forced_main_returns_none_without_creds(self, monkeypatch):
-        """Forced main with no credentials still returns None."""
-        monkeypatch.setenv("AUXILIARY_VISION_PROVIDER", "main")
-        monkeypatch.delenv("OPENAI_BASE_URL", raising=False)
-        monkeypatch.delenv("OPENAI_API_KEY", raising=False)
-        # Clear client cache to avoid stale entries from previous tests
-        from agent.auxiliary_client import _client_cache
-        _client_cache.clear()
-        with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
-             patch("agent.auxiliary_client._read_main_provider", return_value=""), \
-             patch("agent.auxiliary_client._read_main_model", return_value=""), \
-             patch("agent.auxiliary_client._select_pool_entry", return_value=(False, None)), \
-             patch("agent.auxiliary_client._resolve_custom_runtime", return_value=(None, None)), \
-             patch("agent.auxiliary_client._read_codex_access_token", return_value=None), \
-             patch("agent.auxiliary_client._resolve_api_key_provider", return_value=(None, None)):
-            client, model = get_vision_auxiliary_client()
-        assert client is None
-        assert model is None
-
-    def test_vision_forced_codex(self, monkeypatch, codex_auth_dir):
-        """When forced to 'codex', vision uses Codex OAuth."""
-        monkeypatch.setenv("AUXILIARY_VISION_PROVIDER", "codex")
-        with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
-             patch("agent.auxiliary_client.OpenAI"):
-            client, model = get_vision_auxiliary_client()
-        from agent.auxiliary_client import CodexAuxiliaryClient
-        assert isinstance(client, CodexAuxiliaryClient)
-        assert model == "gpt-5.2-codex"
 
 
 class TestGetAuxiliaryProvider:
@@ -948,122 +838,6 @@ class TestGetAuxiliaryProvider:
         assert _get_auxiliary_provider("web_extract") == "main"
 
 
-class TestResolveForcedProvider:
-    """Tests for _resolve_forced_provider with explicit provider selection."""
-
-    def test_forced_openrouter(self, monkeypatch):
-        monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
-        with patch("agent.auxiliary_client.OpenAI") as mock_openai:
-            client, model = _resolve_forced_provider("openrouter")
-        assert model == "google/gemini-3-flash-preview"
-        assert client is not None
-
-    def test_forced_openrouter_no_key(self, monkeypatch):
-        with patch("agent.auxiliary_client._read_nous_auth", return_value=None):
-            client, model = _resolve_forced_provider("openrouter")
-        assert client is None
-        assert model is None
-
-    def test_forced_nous(self, monkeypatch):
-        with patch("agent.auxiliary_client._read_nous_auth") as mock_nous, \
-             patch("agent.auxiliary_client.OpenAI"):
-            mock_nous.return_value = {"access_token": "nous-tok"}
-            client, model = _resolve_forced_provider("nous")
-        assert model == "google/gemini-3-flash-preview"
-        assert client is not None
-
-    def test_forced_nous_not_configured(self, monkeypatch):
-        with patch("agent.auxiliary_client._read_nous_auth", return_value=None):
-            client, model = _resolve_forced_provider("nous")
-        assert client is None
-        assert model is None
-
-    def test_forced_main_uses_custom(self, monkeypatch):
-        config = {
-            "model": {
-                "provider": "custom",
-                "base_url": "http://local:8080/v1",
-                "default": "my-local-model",
-            }
-        }
-        monkeypatch.setenv("OPENAI_API_KEY", "local-key")
-        monkeypatch.setattr("hermes_cli.config.load_config", lambda: config)
-        monkeypatch.setattr("hermes_cli.runtime_provider.load_config", lambda: config)
-        with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
-             patch("agent.auxiliary_client.OpenAI") as mock_openai:
-            client, model = _resolve_forced_provider("main")
-        assert model == "my-local-model"
-
-    def test_forced_main_uses_config_saved_custom_endpoint(self, monkeypatch):
-        config = {
-            "model": {
-                "provider": "custom",
-                "base_url": "http://local:8080/v1",
-                "default": "my-local-model",
-            }
-        }
-        monkeypatch.setenv("OPENAI_API_KEY", "local-key")
-        monkeypatch.setattr("hermes_cli.config.load_config", lambda: config)
-        monkeypatch.setattr("hermes_cli.runtime_provider.load_config", lambda: config)
-        with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
-             patch("agent.auxiliary_client._read_codex_access_token", return_value=None), \
-             patch("agent.auxiliary_client._resolve_api_key_provider", return_value=(None, None)), \
-             patch("agent.auxiliary_client.OpenAI") as mock_openai:
-            client, model = _resolve_forced_provider("main")
-        assert client is not None
-        assert model == "my-local-model"
-        call_kwargs = mock_openai.call_args
-        assert call_kwargs.kwargs["base_url"] == "http://local:8080/v1"
-
-    def test_forced_main_skips_openrouter_nous(self, monkeypatch):
-        """Even if OpenRouter key is set, 'main' skips it."""
-        config = {
-            "model": {
-                "provider": "custom",
-                "base_url": "http://local:8080/v1",
-                "default": "my-local-model",
-            }
-        }
-        monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
-        monkeypatch.setenv("OPENAI_API_KEY", "local-key")
-        monkeypatch.setattr("hermes_cli.config.load_config", lambda: config)
-        monkeypatch.setattr("hermes_cli.runtime_provider.load_config", lambda: config)
-        with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
-             patch("agent.auxiliary_client.OpenAI") as mock_openai:
-            client, model = _resolve_forced_provider("main")
-        # Should use custom endpoint, not OpenRouter
-        assert model == "my-local-model"
-
-    def test_forced_main_falls_to_codex(self, codex_auth_dir, monkeypatch):
-        with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
-             patch("agent.auxiliary_client.OpenAI"):
-            client, model = _resolve_forced_provider("main")
-        from agent.auxiliary_client import CodexAuxiliaryClient
-        assert isinstance(client, CodexAuxiliaryClient)
-        assert model == "gpt-5.2-codex"
-
-    def test_forced_codex(self, codex_auth_dir, monkeypatch):
-        with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
-             patch("agent.auxiliary_client.OpenAI"):
-            client, model = _resolve_forced_provider("codex")
-        from agent.auxiliary_client import CodexAuxiliaryClient
-        assert isinstance(client, CodexAuxiliaryClient)
-        assert model == "gpt-5.2-codex"
-
-    def test_forced_codex_no_token(self, monkeypatch):
-        with patch("agent.auxiliary_client._read_codex_access_token", return_value=None):
-            client, model = _resolve_forced_provider("codex")
-        assert client is None
-        assert model is None
-
-    def test_forced_unknown_returns_none(self, monkeypatch):
-        with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
-             patch("agent.auxiliary_client._read_codex_access_token", return_value=None):
-            client, model = _resolve_forced_provider("invalid-provider")
-        assert client is None
-        assert model is None
-
-
 class TestTaskSpecificOverrides:
     """Integration tests for per-task provider routing via get_text_auxiliary_client(task=...)."""
 

tests/agent/test_context_compressor.py

@@ -38,16 +38,6 @@ class TestShouldCompress:
         assert compressor.should_compress(prompt_tokens=50000) is False
 
 
-class TestShouldCompressPreflight:
-    def test_short_messages(self, compressor):
-        msgs = [{"role": "user", "content": "short"}]
-        assert compressor.should_compress_preflight(msgs) is False
-
-    def test_long_messages(self, compressor):
-        # Each message ~100k chars / 4 = 25k tokens, need >85k threshold
-        msgs = [{"role": "user", "content": "x" * 400000}]
-        assert compressor.should_compress_preflight(msgs) is True
-
 
 class TestUpdateFromResponse:
     def test_updates_fields(self, compressor):
@@ -58,27 +48,12 @@ class TestUpdateFromResponse:
         })
         assert compressor.last_prompt_tokens == 5000
         assert compressor.last_completion_tokens == 1000
-        assert compressor.last_total_tokens == 6000
 
     def test_missing_fields_default_zero(self, compressor):
         compressor.update_from_response({})
         assert compressor.last_prompt_tokens == 0
 
 
-class TestGetStatus:
-    def test_returns_expected_keys(self, compressor):
-        status = compressor.get_status()
-        assert "last_prompt_tokens" in status
-        assert "threshold_tokens" in status
-        assert "context_length" in status
-        assert "usage_percent" in status
-        assert "compression_count" in status
-
-    def test_usage_percent_calculation(self, compressor):
-        compressor.last_prompt_tokens = 50000
-        status = compressor.get_status()
-        assert status["usage_percent"] == 50.0
-
 
 class TestCompress:
     def _make_messages(self, n):

tests/agent/test_error_classifier.py

@@ -480,39 +480,6 @@ class TestClassifyApiError:
         result = classify_api_error(e)
         assert result.reason == FailoverReason.context_overflow
 
-    # ── Message-only usage limit disambiguation (no status code) ──
-
-    def test_message_usage_limit_transient_is_rate_limit(self):
-        """'usage limit' + 'try again' with no status code → rate_limit, not billing."""
-        e = Exception("usage limit exceeded, try again in 5 minutes")
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.rate_limit
-        assert result.retryable is True
-        assert result.should_rotate_credential is True
-        assert result.should_fallback is True
-
-    def test_message_usage_limit_no_retry_signal_is_billing(self):
-        """'usage limit' with no transient signal and no status code → billing."""
-        e = Exception("usage limit reached")
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.billing
-        assert result.retryable is False
-        assert result.should_rotate_credential is True
-
-    def test_message_quota_with_reset_window_is_rate_limit(self):
-        """'quota' + 'resets at' with no status code → rate_limit."""
-        e = Exception("quota exceeded, resets at midnight UTC")
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.rate_limit
-        assert result.retryable is True
-
-    def test_message_limit_exceeded_with_wait_is_rate_limit(self):
-        """'limit exceeded' + 'wait' with no status code → rate_limit."""
-        e = Exception("key limit exceeded, please wait before retrying")
-        result = classify_api_error(e)
-        assert result.reason == FailoverReason.rate_limit
-        assert result.retryable is True
-
     # ── Unknown / fallback ──
 
     def test_generic_exception_is_unknown(self):

tests/agent/test_insights.py

@@ -7,7 +7,6 @@ from pathlib import Path
 from hermes_state import SessionDB
 from agent.insights import (
     InsightsEngine,
-    _get_pricing,
     _estimate_cost,
     _format_duration,
     _bar_chart,
@@ -118,45 +117,6 @@ def populated_db(db):
     return db
 
 
-# =========================================================================
-# Pricing helpers
-# =========================================================================
-
-class TestPricing:
-    def test_provider_prefix_stripped(self):
-        pricing = _get_pricing("anthropic/claude-sonnet-4-20250514")
-        assert pricing["input"] == 3.00
-        assert pricing["output"] == 15.00
-
-    def test_unknown_models_do_not_use_heuristics(self):
-        pricing = _get_pricing("some-new-opus-model")
-        assert pricing == _DEFAULT_PRICING
-        pricing = _get_pricing("anthropic/claude-haiku-future")
-        assert pricing == _DEFAULT_PRICING
-
-    def test_unknown_model_returns_zero_cost(self):
-        """Unknown/custom models should NOT have fabricated costs."""
-        pricing = _get_pricing("totally-unknown-model-xyz")
-        assert pricing == _DEFAULT_PRICING
-        assert pricing["input"] == 0.0
-        assert pricing["output"] == 0.0
-
-    def test_custom_endpoint_model_zero_cost(self):
-        """Self-hosted models should return zero cost."""
-        for model in ["FP16_Hermes_4.5", "Hermes_4.5_1T_epoch2", "my-local-llama"]:
-            pricing = _get_pricing(model)
-            assert pricing["input"] == 0.0, f"{model} should have zero cost"
-            assert pricing["output"] == 0.0, f"{model} should have zero cost"
-
-    def test_none_model(self):
-        pricing = _get_pricing(None)
-        assert pricing == _DEFAULT_PRICING
-
-    def test_empty_model(self):
-        pricing = _get_pricing("")
-        assert pricing == _DEFAULT_PRICING
-
-
 class TestHasKnownPricing:
     def test_known_commercial_model(self):
         assert _has_known_pricing("gpt-4o", provider="openai") is True

tests/agent/test_local_stream_timeout.py

@@ -1,70 +0,0 @@
-"""Tests for local provider stream read timeout auto-detection.
-
-When a local LLM provider is detected (Ollama, llama.cpp, vLLM, etc.),
-the httpx stream read timeout should be automatically increased from the
-default 60s to HERMES_API_TIMEOUT (1800s) to avoid premature connection
-kills during long prefill phases.
-"""
-
-import os
-import pytest
-from unittest.mock import patch
-
-from agent.model_metadata import is_local_endpoint
-
-
-class TestLocalStreamReadTimeout:
-    """Verify stream read timeout auto-detection logic."""
-
-    @pytest.mark.parametrize("base_url", [
-        "http://localhost:11434",
-        "http://127.0.0.1:8080",
-        "http://0.0.0.0:5000",
-        "http://192.168.1.100:8000",
-        "http://10.0.0.5:1234",
-    ])
-    def test_local_endpoint_bumps_read_timeout(self, base_url):
-        """Local endpoint + default timeout -> bumps to base_timeout."""
-        with patch.dict(os.environ, {}, clear=False):
-            os.environ.pop("HERMES_STREAM_READ_TIMEOUT", None)
-            _base_timeout = float(os.getenv("HERMES_API_TIMEOUT", 1800.0))
-            _stream_read_timeout = float(os.getenv("HERMES_STREAM_READ_TIMEOUT", 120.0))
-            if _stream_read_timeout == 120.0 and base_url and is_local_endpoint(base_url):
-                _stream_read_timeout = _base_timeout
-            assert _stream_read_timeout == 1800.0
-
-    def test_user_override_respected_for_local(self):
-        """User sets HERMES_STREAM_READ_TIMEOUT -> keep their value even for local."""
-        with patch.dict(os.environ, {"HERMES_STREAM_READ_TIMEOUT": "300"}, clear=False):
-            _base_timeout = float(os.getenv("HERMES_API_TIMEOUT", 1800.0))
-            _stream_read_timeout = float(os.getenv("HERMES_STREAM_READ_TIMEOUT", 120.0))
-            base_url = "http://localhost:11434"
-            if _stream_read_timeout == 120.0 and base_url and is_local_endpoint(base_url):
-                _stream_read_timeout = _base_timeout
-            assert _stream_read_timeout == 300.0
-
-    @pytest.mark.parametrize("base_url", [
-        "https://api.openai.com",
-        "https://openrouter.ai/api",
-        "https://api.anthropic.com",
-    ])
-    def test_remote_endpoint_keeps_default(self, base_url):
-        """Remote endpoint -> keep 120s default."""
-        with patch.dict(os.environ, {}, clear=False):
-            os.environ.pop("HERMES_STREAM_READ_TIMEOUT", None)
-            _base_timeout = float(os.getenv("HERMES_API_TIMEOUT", 1800.0))
-            _stream_read_timeout = float(os.getenv("HERMES_STREAM_READ_TIMEOUT", 120.0))
-            if _stream_read_timeout == 120.0 and base_url and is_local_endpoint(base_url):
-                _stream_read_timeout = _base_timeout
-            assert _stream_read_timeout == 120.0
-
-    def test_empty_base_url_keeps_default(self):
-        """No base_url set -> keep 120s default."""
-        with patch.dict(os.environ, {}, clear=False):
-            os.environ.pop("HERMES_STREAM_READ_TIMEOUT", None)
-            _base_timeout = float(os.getenv("HERMES_API_TIMEOUT", 1800.0))
-            _stream_read_timeout = float(os.getenv("HERMES_STREAM_READ_TIMEOUT", 120.0))
-            base_url = ""
-            if _stream_read_timeout == 120.0 and base_url and is_local_endpoint(base_url):
-                _stream_read_timeout = _base_timeout
-            assert _stream_read_timeout == 120.0

tests/agent/test_memory_plugin_e2e.py

@@ -1,299 +0,0 @@
-"""End-to-end test: a SQLite-backed memory plugin exercising the full interface.
-
-This proves a real plugin can register as a MemoryProvider and get wired
-into the agent loop via MemoryManager. Uses SQLite + FTS5 (stdlib, no
-external deps, no API keys).
-"""
-
-import json
-import os
-import sqlite3
-import tempfile
-import pytest
-from unittest.mock import patch, MagicMock
-
-from agent.memory_provider import MemoryProvider
-from agent.memory_manager import MemoryManager
-from agent.builtin_memory_provider import BuiltinMemoryProvider
-
-
-# ---------------------------------------------------------------------------
-# SQLite FTS5 memory provider — a real, minimal plugin implementation
-# ---------------------------------------------------------------------------
-
-
-class SQLiteMemoryProvider(MemoryProvider):
-    """Minimal SQLite + FTS5 memory provider for testing.
-
-    Demonstrates the full MemoryProvider interface with a real backend.
-    No external dependencies — just stdlib sqlite3.
-    """
-
-    def __init__(self, db_path: str = ":memory:"):
-        self._db_path = db_path
-        self._conn = None
-
-    @property
-    def name(self) -> str:
-        return "sqlite_memory"
-
-    def is_available(self) -> bool:
-        return True  # SQLite is always available
-
-    def initialize(self, session_id: str, **kwargs) -> None:
-        self._conn = sqlite3.connect(self._db_path)
-        self._conn.execute("PRAGMA journal_mode=WAL")
-        self._conn.execute("""
-            CREATE VIRTUAL TABLE IF NOT EXISTS memories
-            USING fts5(content, context, session_id)
-        """)
-        self._session_id = session_id
-
-    def system_prompt_block(self) -> str:
-        if not self._conn:
-            return ""
-        count = self._conn.execute("SELECT COUNT(*) FROM memories").fetchone()[0]
-        if count == 0:
-            return ""
-        return (
-            f"# SQLite Memory Plugin\n"
-            f"Active. {count} memories stored.\n"
-            f"Use sqlite_recall to search, sqlite_retain to store."
-        )
-
-    def prefetch(self, query: str, *, session_id: str = "") -> str:
-        if not self._conn or not query:
-            return ""
-        # FTS5 search
-        try:
-            rows = self._conn.execute(
-                "SELECT content FROM memories WHERE memories MATCH ? LIMIT 5",
-                (query,)
-            ).fetchall()
-            if not rows:
-                return ""
-            results = [row[0] for row in rows]
-            return "## SQLite Memory\n" + "\n".join(f"- {r}" for r in results)
-        except sqlite3.OperationalError:
-            return ""
-
-    def sync_turn(self, user_content: str, assistant_content: str, *, session_id: str = "") -> None:
-        if not self._conn:
-            return
-        combined = f"User: {user_content}\nAssistant: {assistant_content}"
-        self._conn.execute(
-            "INSERT INTO memories (content, context, session_id) VALUES (?, ?, ?)",
-            (combined, "conversation", self._session_id),
-        )
-        self._conn.commit()
-
-    def get_tool_schemas(self):
-        return [
-            {
-                "name": "sqlite_retain",
-                "description": "Store a fact to SQLite memory.",
-                "parameters": {
-                    "type": "object",
-                    "properties": {
-                        "content": {"type": "string", "description": "What to remember"},
-                        "context": {"type": "string", "description": "Category/context"},
-                    },
-                    "required": ["content"],
-                },
-            },
-            {
-                "name": "sqlite_recall",
-                "description": "Search SQLite memory.",
-                "parameters": {
-                    "type": "object",
-                    "properties": {
-                        "query": {"type": "string", "description": "Search query"},
-                    },
-                    "required": ["query"],
-                },
-            },
-        ]
-
-    def handle_tool_call(self, tool_name: str, args: dict, **kwargs) -> str:
-        if tool_name == "sqlite_retain":
-            content = args.get("content", "")
-            context = args.get("context", "explicit")
-            if not content:
-                return json.dumps({"error": "content is required"})
-            self._conn.execute(
-                "INSERT INTO memories (content, context, session_id) VALUES (?, ?, ?)",
-                (content, context, self._session_id),
-            )
-            self._conn.commit()
-            return json.dumps({"result": "Stored."})
-
-        elif tool_name == "sqlite_recall":
-            query = args.get("query", "")
-            if not query:
-                return json.dumps({"error": "query is required"})
-            try:
-                rows = self._conn.execute(
-                    "SELECT content, context FROM memories WHERE memories MATCH ? LIMIT 10",
-                    (query,)
-                ).fetchall()
-                results = [{"content": r[0], "context": r[1]} for r in rows]
-                return json.dumps({"results": results})
-            except sqlite3.OperationalError:
-                return json.dumps({"results": []})
-
-        return json.dumps({"error": f"Unknown tool: {tool_name}"})
-
-    def on_memory_write(self, action, target, content):
-        """Mirror built-in memory writes to SQLite."""
-        if action == "add" and self._conn:
-            self._conn.execute(
-                "INSERT INTO memories (content, context, session_id) VALUES (?, ?, ?)",
-                (content, f"builtin_{target}", self._session_id),
-            )
-            self._conn.commit()
-
-    def shutdown(self):
-        if self._conn:
-            self._conn.close()
-            self._conn = None
-
-
-# ---------------------------------------------------------------------------
-# End-to-end tests
-# ---------------------------------------------------------------------------
-
-
-class TestSQLiteMemoryPlugin:
-    """Full lifecycle test with the SQLite provider."""
-
-    def test_full_lifecycle(self):
-        """Exercise init → store → recall → sync → prefetch → shutdown."""
-        mgr = MemoryManager()
-        builtin = BuiltinMemoryProvider()
-        sqlite_mem = SQLiteMemoryProvider()
-
-        mgr.add_provider(builtin)
-        mgr.add_provider(sqlite_mem)
-
-        # Initialize
-        mgr.initialize_all(session_id="test-session-1", platform="cli")
-        assert sqlite_mem._conn is not None
-
-        # System prompt — empty at first
-        prompt = mgr.build_system_prompt()
-        assert "SQLite Memory Plugin" not in prompt
-
-        # Store via tool call
-        result = json.loads(mgr.handle_tool_call(
-            "sqlite_retain", {"content": "User prefers dark mode", "context": "preference"}
-        ))
-        assert result["result"] == "Stored."
-
-        # System prompt now shows count
-        prompt = mgr.build_system_prompt()
-        assert "1 memories stored" in prompt
-
-        # Recall via tool call
-        result = json.loads(mgr.handle_tool_call(
-            "sqlite_recall", {"query": "dark mode"}
-        ))
-        assert len(result["results"]) == 1
-        assert "dark mode" in result["results"][0]["content"]
-
-        # Sync a turn (auto-stores conversation)
-        mgr.sync_all("What's my theme?", "You prefer dark mode.")
-        count = sqlite_mem._conn.execute("SELECT COUNT(*) FROM memories").fetchone()[0]
-        assert count == 2  # 1 explicit + 1 synced
-
-        # Prefetch for next turn
-        prefetched = mgr.prefetch_all("dark mode")
-        assert "dark mode" in prefetched
-
-        # Memory bridge — mirroring builtin writes
-        mgr.on_memory_write("add", "user", "Timezone: US Pacific")
-        count = sqlite_mem._conn.execute("SELECT COUNT(*) FROM memories").fetchone()[0]
-        assert count == 3
-
-        # Shutdown
-        mgr.shutdown_all()
-        assert sqlite_mem._conn is None
-
-    def test_tool_routing_with_builtin(self):
-        """Verify builtin + plugin tools coexist without conflict."""
-        mgr = MemoryManager()
-        builtin = BuiltinMemoryProvider()
-        sqlite_mem = SQLiteMemoryProvider()
-        mgr.add_provider(builtin)
-        mgr.add_provider(sqlite_mem)
-        mgr.initialize_all(session_id="test-2")
-
-        # Builtin has no tools
-        assert len(builtin.get_tool_schemas()) == 0
-        # SQLite has 2 tools
-        schemas = mgr.get_all_tool_schemas()
-        names = {s["name"] for s in schemas}
-        assert names == {"sqlite_retain", "sqlite_recall"}
-
-        # Routing works
-        assert mgr.has_tool("sqlite_retain")
-        assert mgr.has_tool("sqlite_recall")
-        assert not mgr.has_tool("memory")  # builtin doesn't register this
-
-    def test_second_external_plugin_rejected(self):
-        """Only one external memory provider is allowed at a time."""
-        mgr = MemoryManager()
-        p1 = SQLiteMemoryProvider()
-        p2 = SQLiteMemoryProvider()
-        # Hack name for p2
-        p2._name_override = "sqlite_memory_2"
-        original_name = p2.__class__.name
-        type(p2).name = property(lambda self: getattr(self, '_name_override', 'sqlite_memory'))
-
-        mgr.add_provider(p1)
-        mgr.add_provider(p2)  # should be rejected
-
-        # Only p1 was accepted
-        assert len(mgr.providers) == 1
-        assert mgr.provider_names == ["sqlite_memory"]
-
-        # Restore class
-        type(p2).name = original_name
-        mgr.shutdown_all()
-
-    def test_provider_failure_isolation(self):
-        """Failing external provider doesn't break builtin."""
-        from agent.builtin_memory_provider import BuiltinMemoryProvider
-
-        mgr = MemoryManager()
-        builtin = BuiltinMemoryProvider()  # name="builtin", always accepted
-        ext = SQLiteMemoryProvider()
-
-        mgr.add_provider(builtin)
-        mgr.add_provider(ext)
-        mgr.initialize_all(session_id="test-4")
-
-        # Break external provider's connection
-        ext._conn.close()
-        ext._conn = None
-
-        # Sync — external fails silently, builtin (no-op sync) succeeds
-        mgr.sync_all("user", "assistant")  # should not raise
-
-        mgr.shutdown_all()
-
-    def test_plugin_registration_flow(self):
-        """Simulate the full plugin load → agent init path."""
-        # Simulate what AIAgent.__init__ does via plugins/memory/ discovery
-        provider = SQLiteMemoryProvider()
-
-        mem_mgr = MemoryManager()
-        mem_mgr.add_provider(BuiltinMemoryProvider())
-        if provider.is_available():
-            mem_mgr.add_provider(provider)
-        mem_mgr.initialize_all(session_id="agent-session")
-
-        assert len(mem_mgr.providers) == 2
-        assert mem_mgr.provider_names == ["builtin", "sqlite_memory"]
-        assert provider._conn is not None  # initialized = connection established
-
-        mem_mgr.shutdown_all()

tests/agent/test_memory_provider.py

@@ -6,8 +6,6 @@ from unittest.mock import MagicMock, patch
 
 from agent.memory_provider import MemoryProvider
 from agent.memory_manager import MemoryManager
-from agent.builtin_memory_provider import BuiltinMemoryProvider
-
 
 # ---------------------------------------------------------------------------
 # Concrete test provider
@@ -118,7 +116,7 @@ class TestMemoryManager:
     def test_empty_manager(self):
         mgr = MemoryManager()
         assert mgr.providers == []
-        assert mgr.provider_names == []
+        assert [p.name for p in mgr.providers] == []
         assert mgr.get_all_tool_schemas() == []
         assert mgr.build_system_prompt() == ""
         assert mgr.prefetch_all("test") == ""
@@ -128,7 +126,7 @@ class TestMemoryManager:
         p = FakeMemoryProvider("test1")
         mgr.add_provider(p)
         assert len(mgr.providers) == 1
-        assert mgr.provider_names == ["test1"]
+        assert [p.name for p in mgr.providers] == ["test1"]
 
     def test_get_provider_by_name(self):
         mgr = MemoryManager()
@@ -143,7 +141,7 @@ class TestMemoryManager:
         p2 = FakeMemoryProvider("external")
         mgr.add_provider(p1)
         mgr.add_provider(p2)
-        assert mgr.provider_names == ["builtin", "external"]
+        assert [p.name for p in mgr.providers] == ["builtin", "external"]
 
     def test_second_external_rejected(self):
         """Only one non-builtin provider is allowed."""
@@ -154,7 +152,7 @@ class TestMemoryManager:
         mgr.add_provider(builtin)
         mgr.add_provider(ext1)
         mgr.add_provider(ext2)  # should be rejected
-        assert mgr.provider_names == ["builtin", "mem0"]
+        assert [p.name for p in mgr.providers] == ["builtin", "mem0"]
         assert len(mgr.providers) == 2
 
     def test_system_prompt_merges_blocks(self):
@@ -321,17 +319,6 @@ class TestMemoryManager:
         mgr.on_pre_compress([{"role": "user", "content": "old"}])
         assert p.pre_compress_called
 
-    def test_on_memory_write_skips_builtin(self):
-        """on_memory_write should skip the builtin provider."""
-        mgr = MemoryManager()
-        builtin = BuiltinMemoryProvider()
-        external = FakeMemoryProvider("external")
-        mgr.add_provider(builtin)
-        mgr.add_provider(external)
-
-        mgr.on_memory_write("add", "memory", "test fact")
-        assert external.memory_writes == [("add", "memory", "test fact")]
-
     def test_shutdown_all_reverse_order(self):
         mgr = MemoryManager()
         order = []
@@ -385,146 +372,6 @@ class TestMemoryManager:
         assert result == "works fine"
 
 
-# ---------------------------------------------------------------------------
-# BuiltinMemoryProvider tests
-# ---------------------------------------------------------------------------
-
-
-class TestBuiltinMemoryProvider:
-    def test_name(self):
-        p = BuiltinMemoryProvider()
-        assert p.name == "builtin"
-
-    def test_always_available(self):
-        p = BuiltinMemoryProvider()
-        assert p.is_available()
-
-    def test_no_tools(self):
-        """Builtin provider exposes no tools (memory tool is agent-level)."""
-        p = BuiltinMemoryProvider()
-        assert p.get_tool_schemas() == []
-
-    def test_system_prompt_with_store(self):
-        store = MagicMock()
-        store.format_for_system_prompt.side_effect = lambda t: f"BLOCK_{t}" if t == "memory" else f"BLOCK_{t}"
-
-        p = BuiltinMemoryProvider(
-            memory_store=store,
-            memory_enabled=True,
-            user_profile_enabled=True,
-        )
-        block = p.system_prompt_block()
-        assert "BLOCK_memory" in block
-        assert "BLOCK_user" in block
-
-    def test_system_prompt_memory_disabled(self):
-        store = MagicMock()
-        store.format_for_system_prompt.return_value = "content"
-
-        p = BuiltinMemoryProvider(
-            memory_store=store,
-            memory_enabled=False,
-            user_profile_enabled=False,
-        )
-        assert p.system_prompt_block() == ""
-
-    def test_system_prompt_no_store(self):
-        p = BuiltinMemoryProvider(memory_store=None, memory_enabled=True)
-        assert p.system_prompt_block() == ""
-
-    def test_prefetch_returns_empty(self):
-        p = BuiltinMemoryProvider()
-        assert p.prefetch("anything") == ""
-
-    def test_store_property(self):
-        store = MagicMock()
-        p = BuiltinMemoryProvider(memory_store=store)
-        assert p.store is store
-
-    def test_initialize_loads_from_disk(self):
-        store = MagicMock()
-        p = BuiltinMemoryProvider(memory_store=store)
-        p.initialize(session_id="test")
-        store.load_from_disk.assert_called_once()
-
-
-# ---------------------------------------------------------------------------
-# Plugin registration tests
-# ---------------------------------------------------------------------------
-
-
-class TestSingleProviderGating:
-    """Only the configured provider should activate."""
-
-    def test_no_provider_configured_means_builtin_only(self):
-        """When memory.provider is empty, no plugin providers activate."""
-        mgr = MemoryManager()
-        builtin = BuiltinMemoryProvider()
-        mgr.add_provider(builtin)
-
-        # Simulate what run_agent.py does when provider="" 
-        configured = ""
-        available_plugins = [
-            FakeMemoryProvider("holographic"),
-            FakeMemoryProvider("mem0"),
-        ]
-        # With empty config, no plugins should be added
-        if configured:
-            for p in available_plugins:
-                if p.name == configured and p.is_available():
-                    mgr.add_provider(p)
-
-        assert mgr.provider_names == ["builtin"]
-
-    def test_configured_provider_activates(self):
-        """Only the named provider should be added."""
-        mgr = MemoryManager()
-        builtin = BuiltinMemoryProvider()
-        mgr.add_provider(builtin)
-
-        configured = "holographic"
-        p1 = FakeMemoryProvider("holographic")
-        p2 = FakeMemoryProvider("mem0")
-        p3 = FakeMemoryProvider("hindsight")
-
-        for p in [p1, p2, p3]:
-            if p.name == configured and p.is_available():
-                mgr.add_provider(p)
-
-        assert mgr.provider_names == ["builtin", "holographic"]
-        assert p1.initialized is False  # not initialized by the gating logic itself
-
-    def test_unavailable_provider_skipped(self):
-        """If the configured provider is unavailable, it should be skipped."""
-        mgr = MemoryManager()
-        builtin = BuiltinMemoryProvider()
-        mgr.add_provider(builtin)
-
-        configured = "holographic"
-        p1 = FakeMemoryProvider("holographic", available=False)
-
-        for p in [p1]:
-            if p.name == configured and p.is_available():
-                mgr.add_provider(p)
-
-        assert mgr.provider_names == ["builtin"]
-
-    def test_nonexistent_provider_results_in_builtin_only(self):
-        """If the configured name doesn't match any plugin, only builtin remains."""
-        mgr = MemoryManager()
-        builtin = BuiltinMemoryProvider()
-        mgr.add_provider(builtin)
-
-        configured = "nonexistent"
-        plugins = [FakeMemoryProvider("holographic"), FakeMemoryProvider("mem0")]
-
-        for p in plugins:
-            if p.name == configured and p.is_available():
-                mgr.add_provider(p)
-
-        assert mgr.provider_names == ["builtin"]
-
-
 class TestPluginMemoryDiscovery:
     """Memory providers are discovered from plugins/memory/ directory."""
 

tests/agent/test_minimax_provider.py

@@ -1,6 +1,4 @@
-"""Tests for MiniMax provider hardening — context lengths, thinking guard, catalog, beta headers."""
-
-from unittest.mock import patch
+"""Tests for MiniMax provider hardening — context lengths, thinking guard, catalog."""
 
 
 class TestMinimaxContextLengths:
@@ -105,100 +103,3 @@ class TestMinimaxModelCatalog:
             models = _PROVIDER_MODELS[provider]
             assert "MiniMax-M2.7-highspeed" not in models
             assert "MiniMax-M2.5-highspeed" not in models
-
-
-class TestMinimaxBetaHeaders:
-    """MiniMax Anthropic-compat endpoints reject fine-grained-tool-streaming beta.
-
-    Verify that build_anthropic_client omits the tool-streaming beta for MiniMax
-    (both global and China domains) while keeping it for native Anthropic and
-    other third-party endpoints.  Covers the fix for #6510 / #6555.
-    """
-
-    _TOOL_BETA = "fine-grained-tool-streaming-2025-05-14"
-    _THINKING_BETA = "interleaved-thinking-2025-05-14"
-
-    # -- helper ----------------------------------------------------------
-
-    def _build_and_get_betas(self, api_key, base_url=None):
-        """Build client, return the anthropic-beta header string."""
-        from agent.anthropic_adapter import build_anthropic_client
-        with patch("agent.anthropic_adapter._anthropic_sdk") as mock_sdk:
-            build_anthropic_client(api_key, base_url=base_url)
-            kwargs = mock_sdk.Anthropic.call_args[1]
-            headers = kwargs.get("default_headers", {})
-            return headers.get("anthropic-beta", "")
-
-    # -- MiniMax global --------------------------------------------------
-
-    def test_minimax_global_omits_tool_streaming(self):
-        betas = self._build_and_get_betas(
-            "mm-key-123", base_url="https://api.minimax.io/anthropic"
-        )
-        assert self._TOOL_BETA not in betas
-        assert self._THINKING_BETA in betas
-
-    def test_minimax_global_trailing_slash(self):
-        betas = self._build_and_get_betas(
-            "mm-key-123", base_url="https://api.minimax.io/anthropic/"
-        )
-        assert self._TOOL_BETA not in betas
-
-    # -- MiniMax China ---------------------------------------------------
-
-    def test_minimax_cn_omits_tool_streaming(self):
-        betas = self._build_and_get_betas(
-            "mm-cn-key-456", base_url="https://api.minimaxi.com/anthropic"
-        )
-        assert self._TOOL_BETA not in betas
-        assert self._THINKING_BETA in betas
-
-    def test_minimax_cn_trailing_slash(self):
-        betas = self._build_and_get_betas(
-            "mm-cn-key-456", base_url="https://api.minimaxi.com/anthropic/"
-        )
-        assert self._TOOL_BETA not in betas
-
-    # -- Non-MiniMax keeps full betas ------------------------------------
-
-    def test_native_anthropic_keeps_tool_streaming(self):
-        betas = self._build_and_get_betas("sk-ant-api03-real-key-here")
-        assert self._TOOL_BETA in betas
-        assert self._THINKING_BETA in betas
-
-    def test_third_party_proxy_keeps_tool_streaming(self):
-        betas = self._build_and_get_betas(
-            "custom-key", base_url="https://my-proxy.example.com/anthropic"
-        )
-        assert self._TOOL_BETA in betas
-
-    def test_custom_base_url_keeps_tool_streaming(self):
-        betas = self._build_and_get_betas(
-            "custom-key", base_url="https://custom.api.com"
-        )
-        assert self._TOOL_BETA in betas
-
-    # -- _common_betas_for_base_url unit tests ---------------------------
-
-    def test_common_betas_none_url(self):
-        from agent.anthropic_adapter import _common_betas_for_base_url, _COMMON_BETAS
-        assert _common_betas_for_base_url(None) == _COMMON_BETAS
-
-    def test_common_betas_empty_url(self):
-        from agent.anthropic_adapter import _common_betas_for_base_url, _COMMON_BETAS
-        assert _common_betas_for_base_url("") == _COMMON_BETAS
-
-    def test_common_betas_minimax_url(self):
-        from agent.anthropic_adapter import _common_betas_for_base_url, _TOOL_STREAMING_BETA
-        betas = _common_betas_for_base_url("https://api.minimax.io/anthropic")
-        assert _TOOL_STREAMING_BETA not in betas
-        assert len(betas) > 0  # still has other betas
-
-    def test_common_betas_minimax_cn_url(self):
-        from agent.anthropic_adapter import _common_betas_for_base_url, _TOOL_STREAMING_BETA
-        betas = _common_betas_for_base_url("https://api.minimaxi.com/anthropic")
-        assert _TOOL_STREAMING_BETA not in betas
-
-    def test_common_betas_regular_url(self):
-        from agent.anthropic_adapter import _common_betas_for_base_url, _COMMON_BETAS
-        assert _common_betas_for_base_url("https://api.anthropic.com") == _COMMON_BETAS

tests/agent/test_prompt_builder.py

@@ -11,7 +11,6 @@ from agent.prompt_builder import (
     _scan_context_content,
     _truncate_content,
     _parse_skill_file,
-    _read_skill_conditions,
     _skill_should_show,
     _find_hermes_md,
     _find_git_root,
@@ -775,61 +774,6 @@ class TestPromptBuilderConstants:
 # Conditional skill activation
 # =========================================================================
 
-class TestReadSkillConditions:
-    def test_no_conditions_returns_empty_lists(self, tmp_path):
-        skill_file = tmp_path / "SKILL.md"
-        skill_file.write_text("---\nname: test\ndescription: A skill\n---\n")
-        conditions = _read_skill_conditions(skill_file)
-        assert conditions["fallback_for_toolsets"] == []
-        assert conditions["requires_toolsets"] == []
-        assert conditions["fallback_for_tools"] == []
-        assert conditions["requires_tools"] == []
-
-    def test_reads_fallback_for_toolsets(self, tmp_path):
-        skill_file = tmp_path / "SKILL.md"
-        skill_file.write_text(
-            "---\nname: ddg\ndescription: DuckDuckGo\nmetadata:\n  hermes:\n    fallback_for_toolsets: [web]\n---\n"
-        )
-        conditions = _read_skill_conditions(skill_file)
-        assert conditions["fallback_for_toolsets"] == ["web"]
-
-    def test_reads_requires_toolsets(self, tmp_path):
-        skill_file = tmp_path / "SKILL.md"
-        skill_file.write_text(
-            "---\nname: openhue\ndescription: Hue lights\nmetadata:\n  hermes:\n    requires_toolsets: [terminal]\n---\n"
-        )
-        conditions = _read_skill_conditions(skill_file)
-        assert conditions["requires_toolsets"] == ["terminal"]
-
-    def test_reads_multiple_conditions(self, tmp_path):
-        skill_file = tmp_path / "SKILL.md"
-        skill_file.write_text(
-            "---\nname: test\ndescription: Test\nmetadata:\n  hermes:\n    fallback_for_toolsets: [browser]\n    requires_tools: [terminal]\n---\n"
-        )
-        conditions = _read_skill_conditions(skill_file)
-        assert conditions["fallback_for_toolsets"] == ["browser"]
-        assert conditions["requires_tools"] == ["terminal"]
-
-    def test_missing_file_returns_empty(self, tmp_path):
-        conditions = _read_skill_conditions(tmp_path / "missing.md")
-        assert conditions == {}
-
-    def test_logs_condition_read_failures_and_returns_empty(self, tmp_path, monkeypatch, caplog):
-        skill_file = tmp_path / "SKILL.md"
-        skill_file.write_text("---\nname: broken\n---\n")
-
-        def boom(*args, **kwargs):
-            raise OSError("read exploded")
-
-        monkeypatch.setattr(type(skill_file), "read_text", boom)
-        with caplog.at_level(logging.DEBUG, logger="agent.prompt_builder"):
-            conditions = _read_skill_conditions(skill_file)
-
-        assert conditions == {}
-        assert "Failed to read skill conditions" in caplog.text
-        assert str(skill_file) in caplog.text
-
-
 class TestSkillShouldShow:
     def test_no_filter_info_always_shows(self):
         assert _skill_should_show({}, None, None) is True

tests/cli/test_cli_file_drop.py

@@ -147,20 +147,6 @@ class TestEscapedSpaces:
         assert result["path"] == tmp_image_with_spaces
         assert result["remainder"] == "what is this?"
 
-    def test_tilde_prefixed_path(self, tmp_path, monkeypatch):
-        home = tmp_path / "home"
-        img = home / "storage" / "shared" / "Pictures" / "cat.png"
-        img.parent.mkdir(parents=True, exist_ok=True)
-        img.write_bytes(b"\x89PNG\r\n\x1a\n")
-        monkeypatch.setenv("HOME", str(home))
-
-        result = _detect_file_drop("~/storage/shared/Pictures/cat.png what is this?")
-
-        assert result is not None
-        assert result["path"] == img
-        assert result["is_image"] is True
-        assert result["remainder"] == "what is this?"
-
 
 # ---------------------------------------------------------------------------
 # Tests: edge cases

tests/cli/test_cli_image_command.py

@@ -1,109 +0,0 @@
-from pathlib import Path
-from unittest.mock import patch
-
-from cli import (
-    HermesCLI,
-    _collect_query_images,
-    _format_image_attachment_badges,
-    _termux_example_image_path,
-)
-
-
-def _make_cli():
-    cli_obj = HermesCLI.__new__(HermesCLI)
-    cli_obj._attached_images = []
-    return cli_obj
-
-
-def _make_image(path: Path) -> Path:
-    path.parent.mkdir(parents=True, exist_ok=True)
-    path.write_bytes(b"\x89PNG\r\n\x1a\n")
-    return path
-
-
-class TestImageCommand:
-    def test_handle_image_command_attaches_local_image(self, tmp_path):
-        img = _make_image(tmp_path / "photo.png")
-        cli_obj = _make_cli()
-
-        with patch("cli._cprint"):
-            cli_obj._handle_image_command(f"/image {img}")
-
-        assert cli_obj._attached_images == [img]
-
-    def test_handle_image_command_supports_quoted_path_with_spaces(self, tmp_path):
-        img = _make_image(tmp_path / "my photo.png")
-        cli_obj = _make_cli()
-
-        with patch("cli._cprint"):
-            cli_obj._handle_image_command(f'/image "{img}"')
-
-        assert cli_obj._attached_images == [img]
-
-    def test_handle_image_command_rejects_non_image_file(self, tmp_path):
-        file_path = tmp_path / "notes.txt"
-        file_path.write_text("hello\n", encoding="utf-8")
-        cli_obj = _make_cli()
-
-        with patch("cli._cprint") as mock_print:
-            cli_obj._handle_image_command(f"/image {file_path}")
-
-        assert cli_obj._attached_images == []
-        rendered = " ".join(str(arg) for call in mock_print.call_args_list for arg in call.args)
-        assert "Not a supported image file" in rendered
-
-
-class TestCollectQueryImages:
-    def test_collect_query_images_accepts_explicit_image_arg(self, tmp_path):
-        img = _make_image(tmp_path / "diagram.png")
-
-        message, images = _collect_query_images("describe this", str(img))
-
-        assert message == "describe this"
-        assert images == [img]
-
-    def test_collect_query_images_extracts_leading_path(self, tmp_path):
-        img = _make_image(tmp_path / "camera.png")
-
-        message, images = _collect_query_images(f"{img} what do you see?")
-
-        assert message == "what do you see?"
-        assert images == [img]
-
-    def test_collect_query_images_supports_tilde_paths(self, tmp_path, monkeypatch):
-        home = tmp_path / "home"
-        img = _make_image(home / "storage" / "shared" / "Pictures" / "cat.png")
-        monkeypatch.setenv("HOME", str(home))
-
-        message, images = _collect_query_images("describe this", "~/storage/shared/Pictures/cat.png")
-
-        assert message == "describe this"
-        assert images == [img]
-
-
-class TestTermuxImageHints:
-    def test_termux_example_image_path_prefers_real_shared_storage_root(self, monkeypatch):
-        existing = {"/sdcard", "/storage/emulated/0"}
-        monkeypatch.setattr("cli.os.path.isdir", lambda path: path in existing)
-
-        hint = _termux_example_image_path()
-
-        assert hint == "/sdcard/Pictures/cat.png"
-
-
-class TestImageBadgeFormatting:
-    def test_compact_badges_use_filename_on_narrow_terminals(self, tmp_path):
-        img = _make_image(tmp_path / "Screenshot 2026-04-09 at 11.22.33 AM.png")
-
-        badges = _format_image_attachment_badges([img], image_counter=1, width=40)
-
-        assert badges.startswith("[📎 ")
-        assert "Image #1" not in badges
-
-    def test_compact_badges_summarize_multiple_images(self, tmp_path):
-        img1 = _make_image(tmp_path / "one.png")
-        img2 = _make_image(tmp_path / "two.png")
-
-        badges = _format_image_attachment_badges([img1, img2], image_counter=2, width=45)
-
-        assert badges == "[📎 2 images attached]"

tests/cli/test_cli_skin_integration.py

@@ -49,25 +49,6 @@ class TestCliSkinPromptIntegration:
         set_active_skin("ares")
         assert cli._get_tui_prompt_fragments() == [("class:sudo-prompt", "🔑 ❯ ")]
 
-    def test_narrow_terminals_compact_voice_prompt_fragments(self):
-        cli = _make_cli_stub()
-        cli._voice_mode = True
-
-        with patch.object(HermesCLI, "_get_tui_terminal_width", return_value=50):
-            assert cli._get_tui_prompt_fragments() == [("class:voice-prompt", "🎤 ")]
-
-    def test_narrow_terminals_compact_voice_recording_prompt_fragments(self):
-        cli = _make_cli_stub()
-        cli._voice_recording = True
-        cli._voice_recorder = SimpleNamespace(current_rms=3000)
-
-        with patch.object(HermesCLI, "_get_tui_terminal_width", return_value=50):
-            frags = cli._get_tui_prompt_fragments()
-
-        assert frags[0][0] == "class:voice-recording"
-        assert frags[0][1].startswith("●")
-        assert "❯" not in frags[0][1]
-
     def test_icon_only_skin_symbol_still_visible_in_special_states(self):
         cli = _make_cli_stub()
         cli._secret_state = {"response_queue": object()}

tests/cli/test_cli_status_bar.py

@@ -206,59 +206,6 @@ class TestCLIStatusBar:
         assert "⚕" in text
         assert "claude-sonnet-4-20250514" in text
 
-    def test_minimal_tui_chrome_threshold(self):
-        cli_obj = _make_cli()
-
-        assert cli_obj._use_minimal_tui_chrome(width=63) is True
-        assert cli_obj._use_minimal_tui_chrome(width=64) is False
-
-    def test_bottom_input_rule_hides_on_narrow_terminals(self):
-        cli_obj = _make_cli()
-
-        assert cli_obj._tui_input_rule_height("top", width=50) == 1
-        assert cli_obj._tui_input_rule_height("bottom", width=50) == 0
-        assert cli_obj._tui_input_rule_height("bottom", width=90) == 1
-
-    def test_agent_spacer_reclaimed_on_narrow_terminals(self):
-        cli_obj = _make_cli()
-        cli_obj._agent_running = True
-
-        assert cli_obj._agent_spacer_height(width=50) == 0
-        assert cli_obj._agent_spacer_height(width=90) == 1
-        cli_obj._agent_running = False
-        assert cli_obj._agent_spacer_height(width=90) == 0
-
-    def test_spinner_line_hidden_on_narrow_terminals(self):
-        cli_obj = _make_cli()
-        cli_obj._spinner_text = "thinking"
-
-        assert cli_obj._spinner_widget_height(width=50) == 0
-        assert cli_obj._spinner_widget_height(width=90) == 1
-        cli_obj._spinner_text = ""
-        assert cli_obj._spinner_widget_height(width=90) == 0
-
-    def test_voice_status_bar_compacts_on_narrow_terminals(self):
-        cli_obj = _make_cli()
-        cli_obj._voice_mode = True
-        cli_obj._voice_recording = False
-        cli_obj._voice_processing = False
-        cli_obj._voice_tts = True
-        cli_obj._voice_continuous = True
-
-        fragments = cli_obj._get_voice_status_fragments(width=50)
-
-        assert fragments == [("class:voice-status", " 🎤 Ctrl+B ")]
-
-    def test_voice_recording_status_bar_compacts_on_narrow_terminals(self):
-        cli_obj = _make_cli()
-        cli_obj._voice_mode = True
-        cli_obj._voice_recording = True
-        cli_obj._voice_processing = False
-
-        fragments = cli_obj._get_voice_status_fragments(width=50)
-
-        assert fragments == [("class:voice-status-recording", " ● REC ")]
-
 
 class TestCLIUsageReport:
     def test_show_usage_includes_estimated_cost(self, capsys):

tests/cli/test_fast_command.py

@@ -1,413 +0,0 @@
-"""Tests for the /fast CLI command and service-tier config handling."""
-
-import unittest
-from types import SimpleNamespace
-from unittest.mock import MagicMock, patch
-
-
-def _import_cli():
-    import hermes_cli.config as config_mod
-
-    if not hasattr(config_mod, "save_env_value_secure"):
-        config_mod.save_env_value_secure = lambda key, value: {
-            "success": True,
-            "stored_as": key,
-            "validated": False,
-        }
-
-    import cli as cli_mod
-
-    return cli_mod
-
-
-class TestParseServiceTierConfig(unittest.TestCase):
-    def _parse(self, raw):
-        cli_mod = _import_cli()
-        return cli_mod._parse_service_tier_config(raw)
-
-    def test_fast_maps_to_priority(self):
-        self.assertEqual(self._parse("fast"), "priority")
-        self.assertEqual(self._parse("priority"), "priority")
-
-    def test_normal_disables_service_tier(self):
-        self.assertIsNone(self._parse("normal"))
-        self.assertIsNone(self._parse("off"))
-        self.assertIsNone(self._parse(""))
-
-
-class TestHandleFastCommand(unittest.TestCase):
-    def _make_cli(self, service_tier=None):
-        return SimpleNamespace(
-            service_tier=service_tier,
-            provider="openai-codex",
-            requested_provider="openai-codex",
-            model="gpt-5.4",
-            _fast_command_available=lambda: True,
-            agent=MagicMock(),
-        )
-
-    def test_no_args_shows_status(self):
-        cli_mod = _import_cli()
-        stub = self._make_cli(service_tier=None)
-        with (
-            patch.object(cli_mod, "_cprint") as mock_cprint,
-            patch.object(cli_mod, "save_config_value") as mock_save,
-        ):
-            cli_mod.HermesCLI._handle_fast_command(stub, "/fast")
-
-        # Bare /fast shows status, does not change config
-        mock_save.assert_not_called()
-        # Should have printed the status line
-        printed = " ".join(str(c) for c in mock_cprint.call_args_list)
-        self.assertIn("normal", printed)
-
-    def test_no_args_shows_fast_when_enabled(self):
-        cli_mod = _import_cli()
-        stub = self._make_cli(service_tier="priority")
-        with (
-            patch.object(cli_mod, "_cprint") as mock_cprint,
-            patch.object(cli_mod, "save_config_value") as mock_save,
-        ):
-            cli_mod.HermesCLI._handle_fast_command(stub, "/fast")
-
-        mock_save.assert_not_called()
-        printed = " ".join(str(c) for c in mock_cprint.call_args_list)
-        self.assertIn("fast", printed)
-
-    def test_normal_argument_clears_service_tier(self):
-        cli_mod = _import_cli()
-        stub = self._make_cli(service_tier="priority")
-        with (
-            patch.object(cli_mod, "_cprint"),
-            patch.object(cli_mod, "save_config_value", return_value=True) as mock_save,
-        ):
-            cli_mod.HermesCLI._handle_fast_command(stub, "/fast normal")
-
-        mock_save.assert_called_once_with("agent.service_tier", "normal")
-        self.assertIsNone(stub.service_tier)
-        self.assertIsNone(stub.agent)
-
-    def test_unsupported_model_does_not_expose_fast(self):
-        cli_mod = _import_cli()
-        stub = SimpleNamespace(
-            service_tier=None,
-            provider="openai-codex",
-            requested_provider="openai-codex",
-            model="gpt-5.3-codex",
-            _fast_command_available=lambda: False,
-            agent=MagicMock(),
-        )
-
-        with (
-            patch.object(cli_mod, "_cprint") as mock_cprint,
-            patch.object(cli_mod, "save_config_value") as mock_save,
-        ):
-            cli_mod.HermesCLI._handle_fast_command(stub, "/fast")
-
-        mock_save.assert_not_called()
-        self.assertTrue(mock_cprint.called)
-
-
-class TestPriorityProcessingModels(unittest.TestCase):
-    """Verify the expanded Priority Processing model registry."""
-
-    def test_all_documented_models_supported(self):
-        from hermes_cli.models import model_supports_fast_mode
-
-        # All models from OpenAI's Priority Processing pricing table
-        supported = [
-            "gpt-5.4", "gpt-5.4-mini", "gpt-5.2",
-            "gpt-5.1", "gpt-5", "gpt-5-mini",
-            "gpt-4.1", "gpt-4.1-mini", "gpt-4.1-nano",
-            "gpt-4o", "gpt-4o-mini",
-            "o3", "o4-mini",
-        ]
-        for model in supported:
-            assert model_supports_fast_mode(model), f"{model} should support fast mode"
-
-    def test_vendor_prefix_stripped(self):
-        from hermes_cli.models import model_supports_fast_mode
-
-        assert model_supports_fast_mode("openai/gpt-5.4") is True
-        assert model_supports_fast_mode("openai/gpt-4.1") is True
-        assert model_supports_fast_mode("openai/o3") is True
-
-    def test_non_priority_models_rejected(self):
-        from hermes_cli.models import model_supports_fast_mode
-
-        assert model_supports_fast_mode("gpt-5.3-codex") is False
-        assert model_supports_fast_mode("claude-sonnet-4") is False
-        assert model_supports_fast_mode("") is False
-        assert model_supports_fast_mode(None) is False
-
-    def test_resolve_overrides_returns_service_tier(self):
-        from hermes_cli.models import resolve_fast_mode_overrides
-
-        result = resolve_fast_mode_overrides("gpt-5.4")
-        assert result == {"service_tier": "priority"}
-
-        result = resolve_fast_mode_overrides("gpt-4.1")
-        assert result == {"service_tier": "priority"}
-
-    def test_resolve_overrides_none_for_unsupported(self):
-        from hermes_cli.models import resolve_fast_mode_overrides
-
-        assert resolve_fast_mode_overrides("gpt-5.3-codex") is None
-        assert resolve_fast_mode_overrides("claude-sonnet-4") is None
-
-
-class TestFastModeRouting(unittest.TestCase):
-    def test_fast_command_exposed_for_model_even_when_provider_is_auto(self):
-        cli_mod = _import_cli()
-        stub = SimpleNamespace(provider="auto", requested_provider="auto", model="gpt-5.4", agent=None)
-
-        assert cli_mod.HermesCLI._fast_command_available(stub) is True
-
-    def test_fast_command_exposed_for_non_codex_models(self):
-        cli_mod = _import_cli()
-        stub = SimpleNamespace(provider="openai", requested_provider="openai", model="gpt-4.1", agent=None)
-        assert cli_mod.HermesCLI._fast_command_available(stub) is True
-
-        stub = SimpleNamespace(provider="openrouter", requested_provider="openrouter", model="o3", agent=None)
-        assert cli_mod.HermesCLI._fast_command_available(stub) is True
-
-    def test_turn_route_injects_overrides_without_provider_switch(self):
-        """Fast mode should add request_overrides but NOT change the provider/runtime."""
-        cli_mod = _import_cli()
-        stub = SimpleNamespace(
-            model="gpt-5.4",
-            api_key="primary-key",
-            base_url="https://openrouter.ai/api/v1",
-            provider="openrouter",
-            api_mode="chat_completions",
-            acp_command=None,
-            acp_args=[],
-            _credential_pool=None,
-            _smart_model_routing={},
-            service_tier="priority",
-        )
-
-        original_runtime = {
-            "api_key": "***",
-            "base_url": "https://openrouter.ai/api/v1",
-            "provider": "openrouter",
-            "api_mode": "chat_completions",
-            "command": None,
-            "args": [],
-            "credential_pool": None,
-        }
-
-        with patch("agent.smart_model_routing.resolve_turn_route", return_value={
-            "model": "gpt-5.4",
-            "runtime": dict(original_runtime),
-            "label": None,
-            "signature": ("gpt-5.4", "openrouter", "https://openrouter.ai/api/v1", "chat_completions", None, ()),
-        }):
-            route = cli_mod.HermesCLI._resolve_turn_agent_config(stub, "hi")
-
-        # Provider should NOT have changed
-        assert route["runtime"]["provider"] == "openrouter"
-        assert route["runtime"]["api_mode"] == "chat_completions"
-        # But request_overrides should be set
-        assert route["request_overrides"] == {"service_tier": "priority"}
-
-    def test_turn_route_keeps_primary_runtime_when_model_has_no_fast_backend(self):
-        cli_mod = _import_cli()
-        stub = SimpleNamespace(
-            model="gpt-5.3-codex",
-            api_key="primary-key",
-            base_url="https://openrouter.ai/api/v1",
-            provider="openrouter",
-            api_mode="chat_completions",
-            acp_command=None,
-            acp_args=[],
-            _credential_pool=None,
-            _smart_model_routing={},
-            service_tier="priority",
-        )
-
-        primary_route = {
-            "model": "gpt-5.3-codex",
-            "runtime": {
-                "api_key": "***",
-                "base_url": "https://openrouter.ai/api/v1",
-                "provider": "openrouter",
-                "api_mode": "chat_completions",
-                "command": None,
-                "args": [],
-                "credential_pool": None,
-            },
-            "label": None,
-            "signature": ("gpt-5.3-codex", "openrouter", "https://openrouter.ai/api/v1", "chat_completions", None, ()),
-        }
-        with patch("agent.smart_model_routing.resolve_turn_route", return_value=primary_route):
-            route = cli_mod.HermesCLI._resolve_turn_agent_config(stub, "hi")
-
-        assert route["runtime"]["provider"] == "openrouter"
-        assert route.get("request_overrides") is None
-
-
-class TestAnthropicFastMode(unittest.TestCase):
-    """Verify Anthropic Fast Mode model support and override resolution."""
-
-    def test_anthropic_opus_supported(self):
-        from hermes_cli.models import model_supports_fast_mode
-
-        # Native Anthropic format (hyphens)
-        assert model_supports_fast_mode("claude-opus-4-6") is True
-        # OpenRouter format (dots)
-        assert model_supports_fast_mode("claude-opus-4.6") is True
-        # With vendor prefix
-        assert model_supports_fast_mode("anthropic/claude-opus-4-6") is True
-        assert model_supports_fast_mode("anthropic/claude-opus-4.6") is True
-
-    def test_anthropic_non_opus_rejected(self):
-        from hermes_cli.models import model_supports_fast_mode
-
-        assert model_supports_fast_mode("claude-sonnet-4-6") is False
-        assert model_supports_fast_mode("claude-sonnet-4.6") is False
-        assert model_supports_fast_mode("claude-haiku-4-5") is False
-        assert model_supports_fast_mode("anthropic/claude-sonnet-4.6") is False
-
-    def test_anthropic_variant_tags_stripped(self):
-        from hermes_cli.models import model_supports_fast_mode
-
-        # OpenRouter variant tags after colon should be stripped
-        assert model_supports_fast_mode("claude-opus-4.6:fast") is True
-        assert model_supports_fast_mode("claude-opus-4.6:beta") is True
-
-    def test_resolve_overrides_returns_speed_for_anthropic(self):
-        from hermes_cli.models import resolve_fast_mode_overrides
-
-        result = resolve_fast_mode_overrides("claude-opus-4-6")
-        assert result == {"speed": "fast"}
-
-        result = resolve_fast_mode_overrides("anthropic/claude-opus-4.6")
-        assert result == {"speed": "fast"}
-
-    def test_resolve_overrides_returns_service_tier_for_openai(self):
-        """OpenAI models should still get service_tier, not speed."""
-        from hermes_cli.models import resolve_fast_mode_overrides
-
-        result = resolve_fast_mode_overrides("gpt-5.4")
-        assert result == {"service_tier": "priority"}
-
-    def test_is_anthropic_fast_model(self):
-        from hermes_cli.models import _is_anthropic_fast_model
-
-        assert _is_anthropic_fast_model("claude-opus-4-6") is True
-        assert _is_anthropic_fast_model("claude-opus-4.6") is True
-        assert _is_anthropic_fast_model("anthropic/claude-opus-4-6") is True
-        assert _is_anthropic_fast_model("gpt-5.4") is False
-        assert _is_anthropic_fast_model("claude-sonnet-4-6") is False
-
-    def test_fast_command_exposed_for_anthropic_model(self):
-        cli_mod = _import_cli()
-        stub = SimpleNamespace(
-            provider="anthropic", requested_provider="anthropic",
-            model="claude-opus-4-6", agent=None,
-        )
-        assert cli_mod.HermesCLI._fast_command_available(stub) is True
-
-    def test_fast_command_hidden_for_anthropic_sonnet(self):
-        cli_mod = _import_cli()
-        stub = SimpleNamespace(
-            provider="anthropic", requested_provider="anthropic",
-            model="claude-sonnet-4-6", agent=None,
-        )
-        assert cli_mod.HermesCLI._fast_command_available(stub) is False
-
-    def test_turn_route_injects_speed_for_anthropic(self):
-        """Anthropic models should get speed:'fast' override, not service_tier."""
-        cli_mod = _import_cli()
-        stub = SimpleNamespace(
-            model="claude-opus-4-6",
-            api_key="sk-ant-test",
-            base_url="https://api.anthropic.com",
-            provider="anthropic",
-            api_mode="anthropic_messages",
-            acp_command=None,
-            acp_args=[],
-            _credential_pool=None,
-            _smart_model_routing={},
-            service_tier="priority",
-        )
-
-        original_runtime = {
-            "api_key": "***",
-            "base_url": "https://api.anthropic.com",
-            "provider": "anthropic",
-            "api_mode": "anthropic_messages",
-            "command": None,
-            "args": [],
-            "credential_pool": None,
-        }
-
-        with patch("agent.smart_model_routing.resolve_turn_route", return_value={
-            "model": "claude-opus-4-6",
-            "runtime": dict(original_runtime),
-            "label": None,
-            "signature": ("claude-opus-4-6", "anthropic", "https://api.anthropic.com", "anthropic_messages", None, ()),
-        }):
-            route = cli_mod.HermesCLI._resolve_turn_agent_config(stub, "hi")
-
-        assert route["runtime"]["provider"] == "anthropic"
-        assert route["request_overrides"] == {"speed": "fast"}
-
-
-class TestAnthropicFastModeAdapter(unittest.TestCase):
-    """Verify build_anthropic_kwargs handles fast_mode parameter."""
-
-    def test_fast_mode_adds_speed_and_beta(self):
-        from agent.anthropic_adapter import build_anthropic_kwargs, _FAST_MODE_BETA
-
-        kwargs = build_anthropic_kwargs(
-            model="claude-opus-4-6",
-            messages=[{"role": "user", "content": [{"type": "text", "text": "hi"}]}],
-            tools=None,
-            max_tokens=None,
-            reasoning_config=None,
-            fast_mode=True,
-        )
-        assert kwargs.get("speed") == "fast"
-        assert "extra_headers" in kwargs
-        assert _FAST_MODE_BETA in kwargs["extra_headers"].get("anthropic-beta", "")
-
-    def test_fast_mode_off_no_speed(self):
-        from agent.anthropic_adapter import build_anthropic_kwargs
-
-        kwargs = build_anthropic_kwargs(
-            model="claude-opus-4-6",
-            messages=[{"role": "user", "content": [{"type": "text", "text": "hi"}]}],
-            tools=None,
-            max_tokens=None,
-            reasoning_config=None,
-            fast_mode=False,
-        )
-        assert "speed" not in kwargs
-        assert "extra_headers" not in kwargs
-
-    def test_fast_mode_skipped_for_third_party_endpoint(self):
-        from agent.anthropic_adapter import build_anthropic_kwargs
-
-        kwargs = build_anthropic_kwargs(
-            model="claude-opus-4-6",
-            messages=[{"role": "user", "content": [{"type": "text", "text": "hi"}]}],
-            tools=None,
-            max_tokens=None,
-            reasoning_config=None,
-            fast_mode=True,
-            base_url="https://api.minimax.io/anthropic/v1",
-        )
-        # Third-party endpoints should NOT get speed or fast-mode beta
-        assert "speed" not in kwargs
-        assert "extra_headers" not in kwargs
-
-
-class TestConfigDefault(unittest.TestCase):
-    def test_default_config_has_service_tier(self):
-        from hermes_cli.config import DEFAULT_CONFIG
-
-        agent = DEFAULT_CONFIG.get("agent", {})
-        self.assertIn("service_tier", agent)
-        self.assertEqual(agent["service_tier"], "")

tests/cli/test_reasoning_command.py

@@ -619,17 +619,14 @@ class TestReasoningDeltasFiredFlag(unittest.TestCase):
         agent = AIAgent.__new__(AIAgent)
         agent.reasoning_callback = None
         agent.stream_delta_callback = None
-        agent._reasoning_deltas_fired = False
         agent.verbose_logging = False
         return agent
 
-    def test_fire_reasoning_delta_sets_flag(self):
+    def test_fire_reasoning_delta_calls_callback(self):
         agent = self._make_agent()
         captured = []
         agent.reasoning_callback = lambda t: captured.append(t)
-        self.assertFalse(agent._reasoning_deltas_fired)
         agent._fire_reasoning_delta("thinking...")
-        self.assertTrue(agent._reasoning_deltas_fired)
         self.assertEqual(captured, ["thinking..."])
 
     def test_build_assistant_message_skips_callback_when_already_streamed(self):
@@ -640,8 +637,7 @@ class TestReasoningDeltasFiredFlag(unittest.TestCase):
         agent.reasoning_callback = lambda t: captured.append(t)
         agent.stream_delta_callback = lambda t: None  # streaming is active
 
-        # Simulate streaming having fired reasoning
-        agent._reasoning_deltas_fired = True
+        # Simulate streaming having already fired reasoning
 
         msg = SimpleNamespace(
             content="I'll merge that.",
@@ -665,9 +661,8 @@ class TestReasoningDeltasFiredFlag(unittest.TestCase):
         agent.reasoning_callback = lambda t: captured.append(t)
         agent.stream_delta_callback = lambda t: None  # streaming active
 
-        # Even though _reasoning_deltas_fired is False (reasoning came through
-        # content tags, not reasoning_content deltas), callback should not fire
-        agent._reasoning_deltas_fired = False
+        # Reasoning came through content tags, not reasoning_content deltas.
+        # Callback should not fire since streaming is active.
 
         msg = SimpleNamespace(
             content="I'll merge that.",
@@ -689,7 +684,6 @@ class TestReasoningDeltasFiredFlag(unittest.TestCase):
         agent.reasoning_callback = lambda t: captured.append(t)
         # No streaming
         agent.stream_delta_callback = None
-        agent._reasoning_deltas_fired = False
 
         msg = SimpleNamespace(
             content="I'll merge that.",

tests/cli/test_stream_delta_think_tag.py

@@ -1,138 +0,0 @@
-"""Tests for _stream_delta's handling of <think> tags in prose vs real reasoning blocks."""
-import sys
-import os
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", ".."))
-
-import pytest
-
-
-def _make_cli_stub():
-    """Create a minimal HermesCLI-like object with stream state."""
-    from cli import HermesCLI
-
-    cli = HermesCLI.__new__(HermesCLI)
-    cli.show_reasoning = False
-    cli._stream_buf = ""
-    cli._stream_started = False
-    cli._stream_box_opened = False
-    cli._stream_prefilt = ""
-    cli._in_reasoning_block = False
-    cli._reasoning_stream_started = False
-    cli._reasoning_box_opened = False
-    cli._reasoning_buf = ""
-    cli._reasoning_preview_buf = ""
-    cli._deferred_content = ""
-    cli._stream_text_ansi = ""
-    cli._stream_needs_break = False
-    cli._emitted = []
-
-    # Mock _emit_stream_text to capture output
-    def mock_emit(text):
-        cli._emitted.append(text)
-    cli._emit_stream_text = mock_emit
-
-    # Mock _stream_reasoning_delta
-    cli._reasoning_emitted = []
-    def mock_reasoning(text):
-        cli._reasoning_emitted.append(text)
-    cli._stream_reasoning_delta = mock_reasoning
-
-    return cli
-
-
-class TestThinkTagInProse:
-    """<think> mentioned in prose should NOT trigger reasoning suppression."""
-
-    def test_think_tag_mid_sentence(self):
-        """'(/think not producing <think> tags)' should pass through."""
-        cli = _make_cli_stub()
-        tokens = [
-            "  1. Fix reasoning mode in eval ",
-            "(/think not producing ",
-            "<think>",
-            " tags — ~2% gap)",
-            "\n  2. Launch production",
-        ]
-        for t in tokens:
-            cli._stream_delta(t)
-        assert not cli._in_reasoning_block, "<think> in prose should not enter reasoning block"
-        full = "".join(cli._emitted)
-        assert "<think>" in full, "The literal <think> tag should be in the emitted text"
-        assert "Launch production" in full
-
-    def test_think_tag_after_text_on_same_line(self):
-        """'some text <think>' should NOT trigger reasoning."""
-        cli = _make_cli_stub()
-        cli._stream_delta("Here is the <think> tag explanation")
-        assert not cli._in_reasoning_block
-        full = "".join(cli._emitted)
-        assert "<think>" in full
-
-    def test_think_tag_in_backticks(self):
-        """'`<think>`' should NOT trigger reasoning."""
-        cli = _make_cli_stub()
-        cli._stream_delta("Use the `<think>` tag for reasoning")
-        assert not cli._in_reasoning_block
-
-
-class TestRealReasoningBlock:
-    """Real <think> tags at block boundaries should still be caught."""
-
-    def test_think_at_start_of_stream(self):
-        """'<think>reasoning</think>answer' should suppress reasoning."""
-        cli = _make_cli_stub()
-        cli._stream_delta("<think>")
-        assert cli._in_reasoning_block
-        cli._stream_delta("I need to analyze this")
-        cli._stream_delta("</think>")
-        assert not cli._in_reasoning_block
-        cli._stream_delta("Here is my answer")
-        full = "".join(cli._emitted)
-        assert "Here is my answer" in full
-        assert "I need to analyze" not in full  # reasoning was suppressed
-
-    def test_think_after_newline(self):
-        """'text\\n<think>' should trigger reasoning block."""
-        cli = _make_cli_stub()
-        cli._stream_delta("Some preamble\n<think>")
-        assert cli._in_reasoning_block
-        full = "".join(cli._emitted)
-        assert "Some preamble" in full
-
-    def test_think_after_newline_with_whitespace(self):
-        """'text\\n  <think>' should trigger reasoning block."""
-        cli = _make_cli_stub()
-        cli._stream_delta("Some preamble\n  <think>")
-        assert cli._in_reasoning_block
-
-    def test_think_with_only_whitespace_before(self):
-        """'   <think>' (whitespace only prefix) should trigger."""
-        cli = _make_cli_stub()
-        cli._stream_delta("   <think>")
-        assert cli._in_reasoning_block
-
-
-class TestFlushRecovery:
-    """_flush_stream should recover content from false-positive reasoning blocks."""
-
-    def test_flush_recovers_buffered_content(self):
-        """If somehow in reasoning block at flush, content is recovered."""
-        cli = _make_cli_stub()
-        # Manually set up a false-positive state
-        cli._in_reasoning_block = True
-        cli._stream_prefilt = " tags — ~2% gap)\n  2. Launch production"
-        cli._stream_box_opened = True
-
-        # Mock _close_reasoning_box and box closing
-        cli._close_reasoning_box = lambda: None
-
-        # Call flush
-        from unittest.mock import patch
-        import shutil
-        with patch.object(shutil, "get_terminal_size", return_value=os.terminal_size((80, 24))):
-            with patch("cli._cprint"):
-                cli._flush_stream()
-
-        assert not cli._in_reasoning_block
-        full = "".join(cli._emitted)
-        assert "Launch production" in full

tests/gateway/test_api_server.py

@@ -294,40 +294,6 @@ class TestModelsEndpoint:
             assert data["data"][0]["id"] == "hermes-agent"
             assert data["data"][0]["owned_by"] == "hermes"
 
-    @pytest.mark.asyncio
-    async def test_models_returns_profile_name(self):
-        """When running under a named profile, /v1/models advertises the profile name."""
-        with patch("gateway.platforms.api_server.APIServerAdapter._resolve_model_name", return_value="lucas"):
-            adapter = _make_adapter()
-        app = _create_app(adapter)
-        async with TestClient(TestServer(app)) as cli:
-            resp = await cli.get("/v1/models")
-            assert resp.status == 200
-            data = await resp.json()
-            assert data["data"][0]["id"] == "lucas"
-            assert data["data"][0]["root"] == "lucas"
-
-    @pytest.mark.asyncio
-    async def test_models_returns_explicit_model_name(self):
-        """Explicit model_name in config overrides profile name."""
-        extra = {"model_name": "my-custom-agent"}
-        config = PlatformConfig(enabled=True, extra=extra)
-        adapter = APIServerAdapter(config)
-        assert adapter._model_name == "my-custom-agent"
-
-    def test_resolve_model_name_explicit(self):
-        assert APIServerAdapter._resolve_model_name("my-bot") == "my-bot"
-
-    def test_resolve_model_name_default_profile(self):
-        """Default profile falls back to 'hermes-agent'."""
-        with patch("hermes_cli.profiles.get_active_profile_name", return_value="default"):
-            assert APIServerAdapter._resolve_model_name("") == "hermes-agent"
-
-    def test_resolve_model_name_named_profile(self):
-        """Named profile uses the profile name as model name."""
-        with patch("hermes_cli.profiles.get_active_profile_name", return_value="lucas"):
-            assert APIServerAdapter._resolve_model_name("") == "lucas"
-
     @pytest.mark.asyncio
     async def test_models_requires_auth(self, auth_adapter):
         app = _create_app(auth_adapter)

tests/gateway/test_approve_deny_commands.py

@@ -141,7 +141,7 @@ class TestBlockingGatewayApproval:
     def test_resolve_single_pops_oldest_fifo(self):
         """resolve_gateway_approval without resolve_all resolves oldest first."""
         from tools.approval import (
-            resolve_gateway_approval, pending_approval_count,
+            resolve_gateway_approval,
             _ApprovalEntry, _gateway_queues,
         )
         session_key = "test-fifo"
@@ -154,7 +154,7 @@ class TestBlockingGatewayApproval:
         assert e1.event.is_set()
         assert e1.result == "once"
         assert not e2.event.is_set()
-        assert pending_approval_count(session_key) == 1
+        assert len(_gateway_queues[session_key]) == 1
 
     def test_unregister_signals_all_entries(self):
         """unregister_gateway_notify signals all waiting entries to prevent hangs."""
@@ -173,35 +173,6 @@ class TestBlockingGatewayApproval:
         assert e1.event.is_set()
         assert e2.event.is_set()
 
-    def test_clear_session_signals_all_entries(self):
-        """clear_session should unblock all waiting approval threads."""
-        from tools.approval import (
-            register_gateway_notify, clear_session,
-            _ApprovalEntry, _gateway_queues,
-        )
-        session_key = "test-clear"
-        register_gateway_notify(session_key, lambda d: None)
-
-        e1 = _ApprovalEntry({"command": "cmd1"})
-        e2 = _ApprovalEntry({"command": "cmd2"})
-        _gateway_queues[session_key] = [e1, e2]
-
-        clear_session(session_key)
-        assert e1.event.is_set()
-        assert e2.event.is_set()
-
-    def test_pending_approval_count(self):
-        from tools.approval import (
-            pending_approval_count, _ApprovalEntry, _gateway_queues,
-        )
-        session_key = "test-count"
-        assert pending_approval_count(session_key) == 0
-        _gateway_queues[session_key] = [
-            _ApprovalEntry({"command": "a"}),
-            _ApprovalEntry({"command": "b"}),
-        ]
-        assert pending_approval_count(session_key) == 2
-
 
 # ------------------------------------------------------------------
 # /approve command
@@ -506,7 +477,7 @@ class TestBlockingApprovalE2E:
         from tools.approval import (
             register_gateway_notify, unregister_gateway_notify,
             resolve_gateway_approval, check_all_command_guards,
-            pending_approval_count,
+            _gateway_queues,
         )
 
         session_key = "e2e-parallel"
@@ -545,7 +516,7 @@ class TestBlockingApprovalE2E:
             time.sleep(0.05)
 
         assert len(notified) == 3
-        assert pending_approval_count(session_key) == 3
+        assert len(_gateway_queues.get(session_key, [])) == 3
 
         # Approve all at once
         count = resolve_gateway_approval(session_key, "session", resolve_all=True)

tests/gateway/test_delivery.py

@@ -1,7 +1,7 @@
 """Tests for the delivery routing module."""
 
 from gateway.config import Platform, GatewayConfig, PlatformConfig, HomeChannel
-from gateway.delivery import DeliveryRouter, DeliveryTarget, parse_deliver_spec
+from gateway.delivery import DeliveryRouter, DeliveryTarget
 from gateway.session import SessionSource
 
 
@@ -41,28 +41,6 @@ class TestParseTargetPlatformChat:
         assert target.platform == Platform.LOCAL
 
 
-class TestParseDeliverSpec:
-    def test_none_returns_default(self):
-        result = parse_deliver_spec(None)
-        assert result == "origin"
-
-    def test_empty_string_returns_default(self):
-        result = parse_deliver_spec("")
-        assert result == "origin"
-
-    def test_custom_default(self):
-        result = parse_deliver_spec(None, default="local")
-        assert result == "local"
-
-    def test_passthrough_string(self):
-        result = parse_deliver_spec("telegram")
-        assert result == "telegram"
-
-    def test_passthrough_list(self):
-        result = parse_deliver_spec(["local", "telegram"])
-        assert result == ["local", "telegram"]
-
-
 class TestTargetToStringRoundtrip:
     def test_origin_roundtrip(self):
         origin = SessionSource(platform=Platform.TELEGRAM, chat_id="111", thread_id="42")

tests/gateway/test_discord_channel_controls.py

@@ -81,7 +81,6 @@ def adapter(monkeypatch):
     config = PlatformConfig(enabled=True, token="fake-token")
     adapter = DiscordAdapter(config)
     adapter._client = SimpleNamespace(user=SimpleNamespace(id=999))
-    adapter._text_batch_delay_seconds = 0  # disable batching for tests
     adapter.handle_message = AsyncMock()
     return adapter
 

tests/gateway/test_discord_free_response.py

@@ -91,7 +91,6 @@ def adapter(monkeypatch):
     config = PlatformConfig(enabled=True, token="fake-token")
     adapter = DiscordAdapter(config)
     adapter._client = SimpleNamespace(user=SimpleNamespace(id=999))
-    adapter._text_batch_delay_seconds = 0  # disable batching for tests
     adapter.handle_message = AsyncMock()
     return adapter
 

tests/gateway/test_discord_slash_commands.py

@@ -62,7 +62,6 @@ def adapter():
         fetch_channel=AsyncMock(),
         user=SimpleNamespace(id=99999, name="HermesBot"),
     )
-    adapter._text_batch_delay_seconds = 0  # disable batching for tests
     return adapter
 
 

tests/gateway/test_matrix_mention.py

@@ -44,7 +44,6 @@ def _make_adapter(tmp_path=None):
         },
     )
     adapter = MatrixAdapter(config)
-    adapter._text_batch_delay_seconds = 0  # disable batching for tests
     adapter.handle_message = AsyncMock()
     adapter._startup_ts = time.time() - 10  # avoid startup grace filter
     return adapter

tests/gateway/test_pii_redaction.py

@@ -7,7 +7,6 @@ from gateway.session import (
     _hash_id,
     _hash_sender_id,
     _hash_chat_id,
-    _looks_like_phone,
 )
 from gateway.config import Platform, HomeChannel
 
@@ -39,14 +38,6 @@ class TestHashHelpers:
         assert len(result) == 12
         assert "12345" not in result
 
-    def test_looks_like_phone(self):
-        assert _looks_like_phone("+15551234567")
-        assert _looks_like_phone("15551234567")
-        assert _looks_like_phone("+1-555-123-4567")
-        assert not _looks_like_phone("alice")
-        assert not _looks_like_phone("user-123")
-        assert not _looks_like_phone("")
-
 
 # ---------------------------------------------------------------------------
 # Integration: build_session_context_prompt

tests/gateway/test_text_batching.py

@@ -1,448 +0,0 @@
-"""Tests for text message batching across all gateway adapters.
-
-When a user sends a long message, the messaging client splits it at the
-platform's character limit.  Each adapter should buffer rapid successive
-text messages from the same session and aggregate them before dispatching.
-
-Covers: Discord, Matrix, WeCom, and the adaptive delay logic for
-Telegram and Feishu.
-"""
-
-import asyncio
-import os
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import pytest
-
-from gateway.config import Platform, PlatformConfig
-from gateway.platforms.base import MessageEvent, MessageType, SessionSource
-
-
-# =====================================================================
-# Helpers
-# =====================================================================
-
-def _make_event(
-    text: str,
-    platform: Platform,
-    chat_id: str = "12345",
-    msg_type: MessageType = MessageType.TEXT,
-) -> MessageEvent:
-    return MessageEvent(
-        text=text,
-        message_type=msg_type,
-        source=SessionSource(platform=platform, chat_id=chat_id, chat_type="dm"),
-    )
-
-
-# =====================================================================
-# Discord text batching
-# =====================================================================
-
-def _make_discord_adapter():
-    """Create a minimal DiscordAdapter for testing text batching."""
-    from gateway.platforms.discord import DiscordAdapter
-
-    config = PlatformConfig(enabled=True, token="test-token")
-    adapter = object.__new__(DiscordAdapter)
-    adapter._platform = Platform.DISCORD
-    adapter.config = config
-    adapter._pending_text_batches = {}
-    adapter._pending_text_batch_tasks = {}
-    adapter._text_batch_delay_seconds = 0.1  # fast for tests
-    adapter._text_batch_split_delay_seconds = 0.3  # fast for tests
-    adapter._active_sessions = {}
-    adapter._pending_messages = {}
-    adapter._message_handler = AsyncMock()
-    adapter.handle_message = AsyncMock()
-    return adapter
-
-
-class TestDiscordTextBatching:
-    @pytest.mark.asyncio
-    async def test_single_message_dispatched_after_delay(self):
-        adapter = _make_discord_adapter()
-        event = _make_event("hello world", Platform.DISCORD)
-
-        adapter._enqueue_text_event(event)
-
-        # Not dispatched yet
-        adapter.handle_message.assert_not_called()
-
-        # Wait for flush
-        await asyncio.sleep(0.2)
-
-        adapter.handle_message.assert_called_once()
-        dispatched = adapter.handle_message.call_args[0][0]
-        assert dispatched.text == "hello world"
-
-    @pytest.mark.asyncio
-    async def test_split_messages_aggregated(self):
-        """Two rapid messages from the same chat should be merged."""
-        adapter = _make_discord_adapter()
-
-        adapter._enqueue_text_event(_make_event("Part one of a long", Platform.DISCORD))
-        await asyncio.sleep(0.02)
-        adapter._enqueue_text_event(_make_event("message that was split.", Platform.DISCORD))
-
-        adapter.handle_message.assert_not_called()
-
-        await asyncio.sleep(0.2)
-
-        adapter.handle_message.assert_called_once()
-        text = adapter.handle_message.call_args[0][0].text
-        assert "Part one" in text
-        assert "split" in text
-
-    @pytest.mark.asyncio
-    async def test_three_way_split_aggregated(self):
-        adapter = _make_discord_adapter()
-
-        adapter._enqueue_text_event(_make_event("chunk 1", Platform.DISCORD))
-        await asyncio.sleep(0.02)
-        adapter._enqueue_text_event(_make_event("chunk 2", Platform.DISCORD))
-        await asyncio.sleep(0.02)
-        adapter._enqueue_text_event(_make_event("chunk 3", Platform.DISCORD))
-
-        await asyncio.sleep(0.2)
-
-        adapter.handle_message.assert_called_once()
-        text = adapter.handle_message.call_args[0][0].text
-        assert "chunk 1" in text
-        assert "chunk 2" in text
-        assert "chunk 3" in text
-
-    @pytest.mark.asyncio
-    async def test_different_chats_not_merged(self):
-        adapter = _make_discord_adapter()
-
-        adapter._enqueue_text_event(_make_event("from A", Platform.DISCORD, chat_id="111"))
-        adapter._enqueue_text_event(_make_event("from B", Platform.DISCORD, chat_id="222"))
-
-        await asyncio.sleep(0.2)
-
-        assert adapter.handle_message.call_count == 2
-
-    @pytest.mark.asyncio
-    async def test_batch_cleans_up_after_flush(self):
-        adapter = _make_discord_adapter()
-
-        adapter._enqueue_text_event(_make_event("test", Platform.DISCORD))
-        await asyncio.sleep(0.2)
-
-        assert len(adapter._pending_text_batches) == 0
-
-    @pytest.mark.asyncio
-    async def test_adaptive_delay_for_near_limit_chunk(self):
-        """Chunks near the 2000-char limit should trigger longer delay."""
-        adapter = _make_discord_adapter()
-        # Simulate a chunk near Discord's 2000-char split point
-        long_text = "x" * 1950
-        adapter._enqueue_text_event(_make_event(long_text, Platform.DISCORD))
-
-        # After the short delay (0.1s), should NOT have flushed yet (split delay is 0.3s)
-        await asyncio.sleep(0.15)
-        adapter.handle_message.assert_not_called()
-
-        # After the split delay, should be flushed
-        await asyncio.sleep(0.25)
-        adapter.handle_message.assert_called_once()
-
-
-# =====================================================================
-# Matrix text batching
-# =====================================================================
-
-def _make_matrix_adapter():
-    """Create a minimal MatrixAdapter for testing text batching."""
-    from gateway.platforms.matrix import MatrixAdapter
-
-    config = PlatformConfig(enabled=True, token="test-token")
-    adapter = object.__new__(MatrixAdapter)
-    adapter._platform = Platform.MATRIX
-    adapter.config = config
-    adapter._pending_text_batches = {}
-    adapter._pending_text_batch_tasks = {}
-    adapter._text_batch_delay_seconds = 0.1
-    adapter._text_batch_split_delay_seconds = 0.3
-    adapter._active_sessions = {}
-    adapter._pending_messages = {}
-    adapter._message_handler = AsyncMock()
-    adapter.handle_message = AsyncMock()
-    return adapter
-
-
-class TestMatrixTextBatching:
-    @pytest.mark.asyncio
-    async def test_single_message_dispatched_after_delay(self):
-        adapter = _make_matrix_adapter()
-        event = _make_event("hello world", Platform.MATRIX)
-
-        adapter._enqueue_text_event(event)
-
-        adapter.handle_message.assert_not_called()
-        await asyncio.sleep(0.2)
-
-        adapter.handle_message.assert_called_once()
-        assert adapter.handle_message.call_args[0][0].text == "hello world"
-
-    @pytest.mark.asyncio
-    async def test_split_messages_aggregated(self):
-        adapter = _make_matrix_adapter()
-
-        adapter._enqueue_text_event(_make_event("first part", Platform.MATRIX))
-        await asyncio.sleep(0.02)
-        adapter._enqueue_text_event(_make_event("second part", Platform.MATRIX))
-
-        adapter.handle_message.assert_not_called()
-        await asyncio.sleep(0.2)
-
-        adapter.handle_message.assert_called_once()
-        text = adapter.handle_message.call_args[0][0].text
-        assert "first part" in text
-        assert "second part" in text
-
-    @pytest.mark.asyncio
-    async def test_different_rooms_not_merged(self):
-        adapter = _make_matrix_adapter()
-
-        adapter._enqueue_text_event(_make_event("room A", Platform.MATRIX, chat_id="!aaa:matrix.org"))
-        adapter._enqueue_text_event(_make_event("room B", Platform.MATRIX, chat_id="!bbb:matrix.org"))
-
-        await asyncio.sleep(0.2)
-
-        assert adapter.handle_message.call_count == 2
-
-    @pytest.mark.asyncio
-    async def test_adaptive_delay_for_near_limit_chunk(self):
-        """Chunks near the 4000-char limit should trigger longer delay."""
-        adapter = _make_matrix_adapter()
-        long_text = "x" * 3950
-        adapter._enqueue_text_event(_make_event(long_text, Platform.MATRIX))
-
-        await asyncio.sleep(0.15)
-        adapter.handle_message.assert_not_called()
-
-        await asyncio.sleep(0.25)
-        adapter.handle_message.assert_called_once()
-
-    @pytest.mark.asyncio
-    async def test_batch_cleans_up_after_flush(self):
-        adapter = _make_matrix_adapter()
-        adapter._enqueue_text_event(_make_event("test", Platform.MATRIX))
-        await asyncio.sleep(0.2)
-        assert len(adapter._pending_text_batches) == 0
-
-
-# =====================================================================
-# WeCom text batching
-# =====================================================================
-
-def _make_wecom_adapter():
-    """Create a minimal WeComAdapter for testing text batching."""
-    from gateway.platforms.wecom import WeComAdapter
-
-    config = PlatformConfig(enabled=True, token="test-token")
-    adapter = object.__new__(WeComAdapter)
-    adapter._platform = Platform.WECOM
-    adapter.config = config
-    adapter._pending_text_batches = {}
-    adapter._pending_text_batch_tasks = {}
-    adapter._text_batch_delay_seconds = 0.1
-    adapter._text_batch_split_delay_seconds = 0.3
-    adapter._active_sessions = {}
-    adapter._pending_messages = {}
-    adapter._message_handler = AsyncMock()
-    adapter.handle_message = AsyncMock()
-    return adapter
-
-
-class TestWeComTextBatching:
-    @pytest.mark.asyncio
-    async def test_single_message_dispatched_after_delay(self):
-        adapter = _make_wecom_adapter()
-        event = _make_event("hello world", Platform.WECOM)
-
-        adapter._enqueue_text_event(event)
-
-        adapter.handle_message.assert_not_called()
-        await asyncio.sleep(0.2)
-
-        adapter.handle_message.assert_called_once()
-        assert adapter.handle_message.call_args[0][0].text == "hello world"
-
-    @pytest.mark.asyncio
-    async def test_split_messages_aggregated(self):
-        adapter = _make_wecom_adapter()
-
-        adapter._enqueue_text_event(_make_event("first part", Platform.WECOM))
-        await asyncio.sleep(0.02)
-        adapter._enqueue_text_event(_make_event("second part", Platform.WECOM))
-
-        adapter.handle_message.assert_not_called()
-        await asyncio.sleep(0.2)
-
-        adapter.handle_message.assert_called_once()
-        text = adapter.handle_message.call_args[0][0].text
-        assert "first part" in text
-        assert "second part" in text
-
-    @pytest.mark.asyncio
-    async def test_different_chats_not_merged(self):
-        adapter = _make_wecom_adapter()
-
-        adapter._enqueue_text_event(_make_event("chat A", Platform.WECOM, chat_id="chat_a"))
-        adapter._enqueue_text_event(_make_event("chat B", Platform.WECOM, chat_id="chat_b"))
-
-        await asyncio.sleep(0.2)
-
-        assert adapter.handle_message.call_count == 2
-
-    @pytest.mark.asyncio
-    async def test_adaptive_delay_for_near_limit_chunk(self):
-        """Chunks near the 4000-char limit should trigger longer delay."""
-        adapter = _make_wecom_adapter()
-        long_text = "x" * 3950
-        adapter._enqueue_text_event(_make_event(long_text, Platform.WECOM))
-
-        await asyncio.sleep(0.15)
-        adapter.handle_message.assert_not_called()
-
-        await asyncio.sleep(0.25)
-        adapter.handle_message.assert_called_once()
-
-    @pytest.mark.asyncio
-    async def test_batch_cleans_up_after_flush(self):
-        adapter = _make_wecom_adapter()
-        adapter._enqueue_text_event(_make_event("test", Platform.WECOM))
-        await asyncio.sleep(0.2)
-        assert len(adapter._pending_text_batches) == 0
-
-
-# =====================================================================
-# Telegram adaptive delay (PR #6891)
-# =====================================================================
-
-def _make_telegram_adapter():
-    """Create a minimal TelegramAdapter for testing adaptive delay."""
-    from gateway.platforms.telegram import TelegramAdapter
-
-    config = PlatformConfig(enabled=True, token="test-token")
-    adapter = object.__new__(TelegramAdapter)
-    adapter._platform = Platform.TELEGRAM
-    adapter.config = config
-    adapter._pending_text_batches = {}
-    adapter._pending_text_batch_tasks = {}
-    adapter._text_batch_delay_seconds = 0.1
-    adapter._text_batch_split_delay_seconds = 0.3
-    adapter._active_sessions = {}
-    adapter._pending_messages = {}
-    adapter._message_handler = AsyncMock()
-    adapter.handle_message = AsyncMock()
-    return adapter
-
-
-class TestTelegramAdaptiveDelay:
-    @pytest.mark.asyncio
-    async def test_short_chunk_uses_normal_delay(self):
-        adapter = _make_telegram_adapter()
-        adapter._enqueue_text_event(_make_event("short msg", Platform.TELEGRAM))
-
-        # Should flush after the normal 0.1s delay
-        await asyncio.sleep(0.15)
-        adapter.handle_message.assert_called_once()
-
-    @pytest.mark.asyncio
-    async def test_near_limit_chunk_uses_split_delay(self):
-        """A chunk near the 4096-char limit should trigger longer delay."""
-        adapter = _make_telegram_adapter()
-        long_text = "x" * 4050  # near the 4096 limit
-        adapter._enqueue_text_event(_make_event(long_text, Platform.TELEGRAM))
-
-        # After the short delay, should NOT have flushed yet
-        await asyncio.sleep(0.15)
-        adapter.handle_message.assert_not_called()
-
-        # After the split delay, should be flushed
-        await asyncio.sleep(0.25)
-        adapter.handle_message.assert_called_once()
-
-    @pytest.mark.asyncio
-    async def test_split_continuation_merged(self):
-        """Two near-limit chunks should both be merged."""
-        adapter = _make_telegram_adapter()
-
-        adapter._enqueue_text_event(_make_event("x" * 4050, Platform.TELEGRAM))
-        await asyncio.sleep(0.05)
-        adapter._enqueue_text_event(_make_event("continuation text", Platform.TELEGRAM))
-
-        # Short chunk arrived → should use normal delay now
-        await asyncio.sleep(0.15)
-        adapter.handle_message.assert_called_once()
-        text = adapter.handle_message.call_args[0][0].text
-        assert "continuation text" in text
-
-
-# =====================================================================
-# Feishu adaptive delay
-# =====================================================================
-
-def _make_feishu_adapter():
-    """Create a minimal FeishuAdapter for testing adaptive delay."""
-    from gateway.platforms.feishu import FeishuAdapter, FeishuBatchState
-
-    config = PlatformConfig(enabled=True, token="test-token")
-    adapter = object.__new__(FeishuAdapter)
-    adapter._platform = Platform.FEISHU
-    adapter.config = config
-    batch_state = FeishuBatchState()
-    adapter._pending_text_batches = batch_state.events
-    adapter._pending_text_batch_tasks = batch_state.tasks
-    adapter._pending_text_batch_counts = batch_state.counts
-    adapter._text_batch_delay_seconds = 0.1
-    adapter._text_batch_split_delay_seconds = 0.3
-    adapter._text_batch_max_messages = 20
-    adapter._text_batch_max_chars = 50000
-    adapter._active_sessions = {}
-    adapter._pending_messages = {}
-    adapter._message_handler = AsyncMock()
-    adapter._handle_message_with_guards = AsyncMock()
-    return adapter
-
-
-class TestFeishuAdaptiveDelay:
-    @pytest.mark.asyncio
-    async def test_short_chunk_uses_normal_delay(self):
-        adapter = _make_feishu_adapter()
-        event = _make_event("short msg", Platform.FEISHU)
-        await adapter._enqueue_text_event(event)
-
-        await asyncio.sleep(0.15)
-        adapter._handle_message_with_guards.assert_called_once()
-
-    @pytest.mark.asyncio
-    async def test_near_limit_chunk_uses_split_delay(self):
-        """A chunk near the 4096-char limit should trigger longer delay."""
-        adapter = _make_feishu_adapter()
-        long_text = "x" * 4050
-        event = _make_event(long_text, Platform.FEISHU)
-        await adapter._enqueue_text_event(event)
-
-        await asyncio.sleep(0.15)
-        adapter._handle_message_with_guards.assert_not_called()
-
-        await asyncio.sleep(0.25)
-        adapter._handle_message_with_guards.assert_called_once()
-
-    @pytest.mark.asyncio
-    async def test_split_continuation_merged(self):
-        adapter = _make_feishu_adapter()
-
-        await adapter._enqueue_text_event(_make_event("x" * 4050, Platform.FEISHU))
-        await asyncio.sleep(0.05)
-        await adapter._enqueue_text_event(_make_event("continuation text", Platform.FEISHU))
-
-        await asyncio.sleep(0.15)
-        adapter._handle_message_with_guards.assert_called_once()
-        text = adapter._handle_message_with_guards.call_args[0][0].text
-        assert "continuation text" in text

tests/gateway/test_usage_command.py

@@ -1,177 +0,0 @@
-"""Tests for gateway /usage command — agent cache lookup and output fields."""
-
-import asyncio
-import threading
-from unittest.mock import MagicMock, patch
-
-import pytest
-
-
-def _make_mock_agent(**overrides):
-    """Create a mock AIAgent with realistic session counters."""
-    agent = MagicMock()
-    defaults = {
-        "model": "anthropic/claude-sonnet-4.6",
-        "provider": "openrouter",
-        "base_url": None,
-        "session_total_tokens": 50_000,
-        "session_api_calls": 5,
-        "session_prompt_tokens": 40_000,
-        "session_completion_tokens": 10_000,
-        "session_input_tokens": 35_000,
-        "session_output_tokens": 10_000,
-        "session_cache_read_tokens": 5_000,
-        "session_cache_write_tokens": 2_000,
-    }
-    defaults.update(overrides)
-    for k, v in defaults.items():
-        setattr(agent, k, v)
-
-    # Rate limit state
-    rl = MagicMock()
-    rl.has_data = True
-    agent.get_rate_limit_state.return_value = rl
-
-    # Context compressor
-    ctx = MagicMock()
-    ctx.last_prompt_tokens = 30_000
-    ctx.context_length = 200_000
-    ctx.compression_count = 1
-    agent.context_compressor = ctx
-
-    return agent
-
-
-def _make_runner(session_key, agent=None, cached_agent=None):
-    """Build a bare GatewayRunner with just the fields _handle_usage_command needs."""
-    from gateway.run import GatewayRunner, _AGENT_PENDING_SENTINEL
-
-    runner = object.__new__(GatewayRunner)
-    runner._running_agents = {}
-    runner._running_agents_ts = {}
-    runner._agent_cache = {}
-    runner._agent_cache_lock = threading.Lock()
-    runner.session_store = MagicMock()
-
-    if agent is not None:
-        runner._running_agents[session_key] = agent
-
-    if cached_agent is not None:
-        runner._agent_cache[session_key] = (cached_agent, "sig")
-
-    # Wire helper
-    runner._session_key_for_source = MagicMock(return_value=session_key)
-
-    return runner
-
-
-SK = "agent:main:telegram:private:12345"
-
-
-class TestUsageCachedAgent:
-    """The main fix: /usage should find agents in _agent_cache between turns."""
-
-    @pytest.mark.asyncio
-    async def test_cached_agent_shows_detailed_usage(self):
-        agent = _make_mock_agent()
-        runner = _make_runner(SK, cached_agent=agent)
-        event = MagicMock()
-
-        with patch("agent.rate_limit_tracker.format_rate_limit_compact", return_value="RPM: 50/60"), \
-             patch("agent.usage_pricing.estimate_usage_cost") as mock_cost:
-            mock_cost.return_value = MagicMock(amount_usd=0.1234, status="estimated")
-            result = await runner._handle_usage_command(event)
-
-        assert "claude-sonnet-4.6" in result
-        assert "35,000" in result  # input tokens
-        assert "10,000" in result  # output tokens
-        assert "5,000" in result   # cache read
-        assert "2,000" in result   # cache write
-        assert "50,000" in result  # total
-        assert "$0.1234" in result
-        assert "30,000" in result  # context
-        assert "Compressions: 1" in result
-
-    @pytest.mark.asyncio
-    async def test_running_agent_preferred_over_cache(self):
-        """When agent is in both dicts, the running one wins."""
-        running = _make_mock_agent(session_api_calls=10, session_total_tokens=80_000)
-        cached = _make_mock_agent(session_api_calls=5, session_total_tokens=50_000)
-        runner = _make_runner(SK, agent=running, cached_agent=cached)
-        event = MagicMock()
-
-        with patch("agent.rate_limit_tracker.format_rate_limit_compact", return_value="RPM: 50/60"), \
-             patch("agent.usage_pricing.estimate_usage_cost") as mock_cost:
-            mock_cost.return_value = MagicMock(amount_usd=None, status="unknown")
-            result = await runner._handle_usage_command(event)
-
-        assert "80,000" in result   # running agent's total
-        assert "API calls: 10" in result
-
-    @pytest.mark.asyncio
-    async def test_sentinel_skipped_uses_cache(self):
-        """PENDING sentinel in _running_agents should fall through to cache."""
-        from gateway.run import _AGENT_PENDING_SENTINEL
-
-        cached = _make_mock_agent()
-        runner = _make_runner(SK, cached_agent=cached)
-        runner._running_agents[SK] = _AGENT_PENDING_SENTINEL
-        event = MagicMock()
-
-        with patch("agent.rate_limit_tracker.format_rate_limit_compact", return_value="RPM: 50/60"), \
-             patch("agent.usage_pricing.estimate_usage_cost") as mock_cost:
-            mock_cost.return_value = MagicMock(amount_usd=None, status="unknown")
-            result = await runner._handle_usage_command(event)
-
-        assert "claude-sonnet-4.6" in result
-        assert "Session Token Usage" in result
-
-    @pytest.mark.asyncio
-    async def test_no_agent_anywhere_falls_to_history(self):
-        """No running or cached agent → rough estimate from transcript."""
-        runner = _make_runner(SK)
-        event = MagicMock()
-
-        session_entry = MagicMock()
-        session_entry.session_id = "sess123"
-        runner.session_store.get_or_create_session.return_value = session_entry
-        runner.session_store.load_transcript.return_value = [
-            {"role": "user", "content": "hello"},
-            {"role": "assistant", "content": "hi there"},
-        ]
-
-        with patch("agent.model_metadata.estimate_messages_tokens_rough", return_value=500):
-            result = await runner._handle_usage_command(event)
-
-        assert "Session Info" in result
-        assert "Messages: 2" in result
-        assert "~500" in result
-
-    @pytest.mark.asyncio
-    async def test_cache_read_write_hidden_when_zero(self):
-        """Cache token lines should be omitted when zero."""
-        agent = _make_mock_agent(session_cache_read_tokens=0, session_cache_write_tokens=0)
-        runner = _make_runner(SK, cached_agent=agent)
-        event = MagicMock()
-
-        with patch("agent.rate_limit_tracker.format_rate_limit_compact", return_value="RPM: 50/60"), \
-             patch("agent.usage_pricing.estimate_usage_cost") as mock_cost:
-            mock_cost.return_value = MagicMock(amount_usd=None, status="unknown")
-            result = await runner._handle_usage_command(event)
-
-        assert "Cache read" not in result
-        assert "Cache write" not in result
-
-    @pytest.mark.asyncio
-    async def test_cost_included_status(self):
-        """Subscription-included providers show 'included' instead of dollar amount."""
-        agent = _make_mock_agent(provider="openai-codex")
-        runner = _make_runner(SK, cached_agent=agent)
-        event = MagicMock()
-
-        with patch("agent.rate_limit_tracker.format_rate_limit_compact", return_value="RPM: 50/60"), \
-             patch("agent.usage_pricing.estimate_usage_cost") as mock_cost:
-            mock_cost.return_value = MagicMock(amount_usd=None, status="included")
-            result = await runner._handle_usage_command(event)
-
-        assert "Cost: included" in result

tests/gateway/test_wecom.py

@@ -508,7 +508,6 @@ class TestInboundMessages:
         from gateway.platforms.wecom import WeComAdapter
 
         adapter = WeComAdapter(PlatformConfig(enabled=True))
-        adapter._text_batch_delay_seconds = 0  # disable batching for tests
         adapter.handle_message = AsyncMock()
         adapter._extract_media = AsyncMock(return_value=(["/tmp/test.png"], ["image/png"]))
 
@@ -540,7 +539,6 @@ class TestInboundMessages:
         from gateway.platforms.wecom import WeComAdapter
 
         adapter = WeComAdapter(PlatformConfig(enabled=True))
-        adapter._text_batch_delay_seconds = 0  # disable batching for tests
         adapter.handle_message = AsyncMock()
         adapter._extract_media = AsyncMock(return_value=([], []))
 

tests/hermes_cli/test_chat_skills_flag.py

@@ -49,30 +49,6 @@ def test_chat_subcommand_accepts_skills_flag(monkeypatch):
     }
 
 
-def test_chat_subcommand_accepts_image_flag(monkeypatch):
-    import hermes_cli.main as main_mod
-
-    captured = {}
-
-    def fake_cmd_chat(args):
-        captured["query"] = args.query
-        captured["image"] = args.image
-
-    monkeypatch.setattr(main_mod, "cmd_chat", fake_cmd_chat)
-    monkeypatch.setattr(
-        sys,
-        "argv",
-        ["hermes", "chat", "-q", "hello", "--image", "~/storage/shared/Pictures/cat.png"],
-    )
-
-    main_mod.main()
-
-    assert captured == {
-        "query": "hello",
-        "image": "~/storage/shared/Pictures/cat.png",
-    }
-
-
 def test_continue_worktree_and_skills_flags_work_together(monkeypatch):
     import hermes_cli.main as main_mod
 

tests/hermes_cli/test_commands.py

@@ -446,13 +446,6 @@ class TestSubcommands:
         assert "show" in subs
         assert "hide" in subs
 
-    def test_fast_has_subcommands(self):
-        assert "/fast" in SUBCOMMANDS
-        subs = SUBCOMMANDS["/fast"]
-        assert "fast" in subs
-        assert "normal" in subs
-        assert "status" in subs
-
     def test_voice_has_subcommands(self):
         assert "/voice" in SUBCOMMANDS
         assert "on" in SUBCOMMANDS["/voice"]
@@ -481,20 +474,6 @@ class TestSubcommandCompletion:
         assert "high" in texts
         assert "show" in texts
 
-    def test_fast_subcommand_completion_after_space(self):
-        completions = _completions(SlashCommandCompleter(), "/fast ")
-        texts = {c.text for c in completions}
-        assert "fast" in texts
-        assert "normal" in texts
-
-    def test_fast_command_filtered_out_when_unavailable(self):
-        completions = _completions(
-            SlashCommandCompleter(command_filter=lambda cmd: cmd != "/fast"),
-            "/fa",
-        )
-        texts = {c.text for c in completions}
-        assert "fast" not in texts
-
     def test_subcommand_prefix_filters(self):
         """Typing '/reasoning sh' should only show 'show'."""
         completions = _completions(SlashCommandCompleter(), "/reasoning sh")
@@ -548,13 +527,6 @@ class TestGhostText:
         """/reasoning sh → 'ow'"""
         assert _suggestion("/reasoning sh") == "ow"
 
-    def test_fast_subcommand_suggestion(self):
-        assert _suggestion("/fast f") == "ast"
-
-    def test_fast_subcommand_suggestion_hidden_when_filtered(self):
-        completer = SlashCommandCompleter(command_filter=lambda cmd: cmd != "/fast")
-        assert _suggestion("/fa", completer=completer) is None
-
     def test_no_suggestion_for_non_slash(self):
         assert _suggestion("hello") is None
 

tests/hermes_cli/test_copilot_auth.py

@@ -35,12 +35,6 @@ class TestTokenValidation:
         valid, msg = validate_copilot_token("")
         assert valid is False
 
-    def test_is_classic_pat(self):
-        from hermes_cli.copilot_auth import is_classic_pat
-        assert is_classic_pat("ghp_abc123") is True
-        assert is_classic_pat("gho_abc123") is False
-        assert is_classic_pat("github_pat_abc") is False
-        assert is_classic_pat("") is False
 
 
 class TestResolveToken:

tests/hermes_cli/test_doctor.py

@@ -14,23 +14,6 @@ from hermes_cli import doctor as doctor_mod
 from hermes_cli.doctor import _has_provider_env_config
 
 
-class TestDoctorPlatformHints:
-    def test_termux_package_hint(self, monkeypatch):
-        monkeypatch.setenv("TERMUX_VERSION", "0.118.3")
-        monkeypatch.setenv("PREFIX", "/data/data/com.termux/files/usr")
-        assert doctor._is_termux() is True
-        assert doctor._python_install_cmd() == "python -m pip install"
-        assert doctor._system_package_install_cmd("ripgrep") == "pkg install ripgrep"
-
-    def test_non_termux_package_hint_defaults_to_apt(self, monkeypatch):
-        monkeypatch.delenv("TERMUX_VERSION", raising=False)
-        monkeypatch.setenv("PREFIX", "/usr")
-        monkeypatch.setattr(sys, "platform", "linux")
-        assert doctor._is_termux() is False
-        assert doctor._python_install_cmd() == "uv pip install"
-        assert doctor._system_package_install_cmd("ripgrep") == "sudo apt install ripgrep"
-
-
 class TestProviderEnvDetection:
     def test_detects_openai_api_key(self):
         content = "OPENAI_BASE_URL=http://localhost:1234/v1\nOPENAI_API_KEY=***"
@@ -223,72 +206,3 @@ class TestDoctorMemoryProviderSection:
         out = self._run_doctor_and_capture(monkeypatch, tmp_path, provider="mem0")
         assert "Memory Provider" in out
         assert "Built-in memory active" not in out
-
-
-def test_run_doctor_termux_treats_docker_and_browser_warnings_as_expected(monkeypatch, tmp_path):
-    helper = TestDoctorMemoryProviderSection()
-    monkeypatch.setenv("TERMUX_VERSION", "0.118.3")
-    monkeypatch.setenv("PREFIX", "/data/data/com.termux/files/usr")
-
-    real_which = doctor_mod.shutil.which
-
-    def fake_which(cmd):
-        if cmd in {"docker", "node", "npm"}:
-            return None
-        return real_which(cmd)
-
-    monkeypatch.setattr(doctor_mod.shutil, "which", fake_which)
-
-    out = helper._run_doctor_and_capture(monkeypatch, tmp_path, provider="")
-
-    assert "Docker backend is not available inside Termux" in out
-    assert "Node.js not found (browser tools are optional in the tested Termux path)" in out
-    assert "Install Node.js on Termux with: pkg install nodejs" in out
-    assert "Termux browser setup:" in out
-    assert "1) pkg install nodejs" in out
-    assert "2) npm install -g agent-browser" in out
-    assert "3) agent-browser install" in out
-    assert "docker not found (optional)" not in out
-
-
-def test_run_doctor_termux_does_not_mark_browser_available_without_agent_browser(monkeypatch, tmp_path):
-    home = tmp_path / ".hermes"
-    home.mkdir(parents=True, exist_ok=True)
-    (home / "config.yaml").write_text("memory: {}\n", encoding="utf-8")
-    project = tmp_path / "project"
-    project.mkdir(exist_ok=True)
-
-    monkeypatch.setenv("TERMUX_VERSION", "0.118.3")
-    monkeypatch.setenv("PREFIX", "/data/data/com.termux/files/usr")
-    monkeypatch.setattr(doctor_mod, "HERMES_HOME", home)
-    monkeypatch.setattr(doctor_mod, "PROJECT_ROOT", project)
-    monkeypatch.setattr(doctor_mod, "_DHH", str(home))
-    monkeypatch.setattr(doctor_mod.shutil, "which", lambda cmd: "/data/data/com.termux/files/usr/bin/node" if cmd in {"node", "npm"} else None)
-
-    fake_model_tools = types.SimpleNamespace(
-        check_tool_availability=lambda *a, **kw: (["terminal"], [{"name": "browser", "env_vars": [], "tools": ["browser_navigate"]}]),
-        TOOLSET_REQUIREMENTS={
-            "terminal": {"name": "terminal"},
-            "browser": {"name": "browser"},
-        },
-    )
-    monkeypatch.setitem(sys.modules, "model_tools", fake_model_tools)
-
-    try:
-        from hermes_cli import auth as _auth_mod
-        monkeypatch.setattr(_auth_mod, "get_nous_auth_status", lambda: {})
-        monkeypatch.setattr(_auth_mod, "get_codex_auth_status", lambda: {})
-    except Exception:
-        pass
-
-    import io, contextlib
-    buf = io.StringIO()
-    with contextlib.redirect_stdout(buf):
-        doctor_mod.run_doctor(Namespace(fix=False))
-    out = buf.getvalue()
-
-    assert "✓ browser" not in out
-    assert "browser" in out
-    assert "system dependency not met" in out
-    assert "agent-browser is not installed (expected in the tested Termux path)" in out
-    assert "npm install -g agent-browser && agent-browser install" in out

tests/hermes_cli/test_external_credential_detection.py

@@ -1,50 +0,0 @@
-"""Tests for detect_external_credentials() -- Phase 2 credential sync."""
-
-import json
-from pathlib import Path
-from unittest.mock import patch
-
-import pytest
-
-from hermes_cli.auth import detect_external_credentials
-
-
-class TestDetectCodexCLI:
-    def test_detects_valid_codex_auth(self, tmp_path, monkeypatch):
-        codex_dir = tmp_path / ".codex"
-        codex_dir.mkdir()
-        auth = codex_dir / "auth.json"
-        auth.write_text(json.dumps({
-            "tokens": {"access_token": "tok-123", "refresh_token": "ref-456"}
-        }))
-        monkeypatch.setenv("CODEX_HOME", str(codex_dir))
-        result = detect_external_credentials()
-        codex_hits = [c for c in result if c["provider"] == "openai-codex"]
-        assert len(codex_hits) == 1
-        assert "Codex CLI" in codex_hits[0]["label"]
-
-    def test_skips_codex_without_access_token(self, tmp_path, monkeypatch):
-        codex_dir = tmp_path / ".codex"
-        codex_dir.mkdir()
-        (codex_dir / "auth.json").write_text(json.dumps({"tokens": {}}))
-        monkeypatch.setenv("CODEX_HOME", str(codex_dir))
-        result = detect_external_credentials()
-        assert not any(c["provider"] == "openai-codex" for c in result)
-
-    def test_skips_missing_codex_dir(self, tmp_path, monkeypatch):
-        monkeypatch.setenv("CODEX_HOME", str(tmp_path / "nonexistent"))
-        result = detect_external_credentials()
-        assert not any(c["provider"] == "openai-codex" for c in result)
-
-    def test_skips_malformed_codex_auth(self, tmp_path, monkeypatch):
-        codex_dir = tmp_path / ".codex"
-        codex_dir.mkdir()
-        (codex_dir / "auth.json").write_text("{bad json")
-        monkeypatch.setenv("CODEX_HOME", str(codex_dir))
-        result = detect_external_credentials()
-        assert not any(c["provider"] == "openai-codex" for c in result)
-
-    def test_returns_empty_when_nothing_found(self, tmp_path, monkeypatch):
-        monkeypatch.setenv("CODEX_HOME", str(tmp_path / "nonexistent"))
-        result = detect_external_credentials()
-        assert result == []

tests/hermes_cli/test_gateway.py

@@ -10,7 +10,6 @@ import hermes_cli.gateway as gateway
 class TestSystemdLingerStatus:
     def test_reports_enabled(self, monkeypatch):
         monkeypatch.setattr(gateway, "is_linux", lambda: True)
-        monkeypatch.setattr(gateway, "is_termux", lambda: False)
         monkeypatch.setenv("USER", "alice")
         monkeypatch.setattr(
             gateway.subprocess,
@@ -23,7 +22,6 @@ class TestSystemdLingerStatus:
 
     def test_reports_disabled(self, monkeypatch):
         monkeypatch.setattr(gateway, "is_linux", lambda: True)
-        monkeypatch.setattr(gateway, "is_termux", lambda: False)
         monkeypatch.setenv("USER", "alice")
         monkeypatch.setattr(
             gateway.subprocess,
@@ -34,11 +32,6 @@ class TestSystemdLingerStatus:
 
         assert gateway.get_systemd_linger_status() == (False, "")
 
-    def test_reports_termux_as_not_supported(self, monkeypatch):
-        monkeypatch.setattr(gateway, "is_termux", lambda: True)
-
-        assert gateway.get_systemd_linger_status() == (None, "not supported in Termux")
-
 
 def test_systemd_status_warns_when_linger_disabled(monkeypatch, tmp_path, capsys):
     unit_path = tmp_path / "hermes-gateway.service"

tests/hermes_cli/test_gateway_linger.py

@@ -8,7 +8,6 @@ import hermes_cli.gateway as gateway
 class TestEnsureLingerEnabled:
     def test_linger_already_enabled_via_file(self, monkeypatch, capsys):
         monkeypatch.setattr(gateway, "is_linux", lambda: True)
-        monkeypatch.setattr(gateway, "is_termux", lambda: False)
         monkeypatch.setattr("getpass.getuser", lambda: "testuser")
         monkeypatch.setattr(gateway, "Path", lambda _path: SimpleNamespace(exists=lambda: True))
 
@@ -23,7 +22,6 @@ class TestEnsureLingerEnabled:
 
     def test_status_enabled_skips_enable(self, monkeypatch, capsys):
         monkeypatch.setattr(gateway, "is_linux", lambda: True)
-        monkeypatch.setattr(gateway, "is_termux", lambda: False)
         monkeypatch.setattr("getpass.getuser", lambda: "testuser")
         monkeypatch.setattr(gateway, "Path", lambda _path: SimpleNamespace(exists=lambda: False))
         monkeypatch.setattr(gateway, "get_systemd_linger_status", lambda: (True, ""))
@@ -39,7 +37,6 @@ class TestEnsureLingerEnabled:
 
     def test_loginctl_success_enables_linger(self, monkeypatch, capsys):
         monkeypatch.setattr(gateway, "is_linux", lambda: True)
-        monkeypatch.setattr(gateway, "is_termux", lambda: False)
         monkeypatch.setattr("getpass.getuser", lambda: "testuser")
         monkeypatch.setattr(gateway, "Path", lambda _path: SimpleNamespace(exists=lambda: False))
         monkeypatch.setattr(gateway, "get_systemd_linger_status", lambda: (False, ""))
@@ -62,7 +59,6 @@ class TestEnsureLingerEnabled:
 
     def test_missing_loginctl_shows_manual_guidance(self, monkeypatch, capsys):
         monkeypatch.setattr(gateway, "is_linux", lambda: True)
-        monkeypatch.setattr(gateway, "is_termux", lambda: False)
         monkeypatch.setattr("getpass.getuser", lambda: "testuser")
         monkeypatch.setattr(gateway, "Path", lambda _path: SimpleNamespace(exists=lambda: False))
         monkeypatch.setattr(gateway, "get_systemd_linger_status", lambda: (None, "loginctl not found"))
@@ -80,7 +76,6 @@ class TestEnsureLingerEnabled:
 
     def test_loginctl_failure_shows_manual_guidance(self, monkeypatch, capsys):
         monkeypatch.setattr(gateway, "is_linux", lambda: True)
-        monkeypatch.setattr(gateway, "is_termux", lambda: False)
         monkeypatch.setattr("getpass.getuser", lambda: "testuser")
         monkeypatch.setattr(gateway, "Path", lambda _path: SimpleNamespace(exists=lambda: False))
         monkeypatch.setattr(gateway, "get_systemd_linger_status", lambda: (False, ""))

tests/hermes_cli/test_gateway_service.py

@@ -109,8 +109,7 @@ class TestGatewayStopCleanup:
         unit_path = tmp_path / "hermes-gateway.service"
         unit_path.write_text("unit\n", encoding="utf-8")
 
-        monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: True)
-        monkeypatch.setattr(gateway_cli, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway_cli, "is_linux", lambda: True)
         monkeypatch.setattr(gateway_cli, "is_macos", lambda: False)
         monkeypatch.setattr(gateway_cli, "get_systemd_unit_path", lambda system=False: unit_path)
 
@@ -135,8 +134,7 @@ class TestGatewayStopCleanup:
         unit_path = tmp_path / "hermes-gateway.service"
         unit_path.write_text("unit\n", encoding="utf-8")
 
-        monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: True)
-        monkeypatch.setattr(gateway_cli, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway_cli, "is_linux", lambda: True)
         monkeypatch.setattr(gateway_cli, "is_macos", lambda: False)
         monkeypatch.setattr(gateway_cli, "get_systemd_unit_path", lambda system=False: unit_path)
 
@@ -258,8 +256,7 @@ class TestGatewayServiceDetection:
         user_unit = SimpleNamespace(exists=lambda: True)
         system_unit = SimpleNamespace(exists=lambda: True)
 
-        monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: True)
-        monkeypatch.setattr(gateway_cli, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway_cli, "is_linux", lambda: True)
         monkeypatch.setattr(gateway_cli, "is_macos", lambda: False)
         monkeypatch.setattr(
             gateway_cli,
@@ -281,8 +278,7 @@ class TestGatewayServiceDetection:
 
 class TestGatewaySystemServiceRouting:
     def test_gateway_install_passes_system_flags(self, monkeypatch):
-        monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: True)
-        monkeypatch.setattr(gateway_cli, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway_cli, "is_linux", lambda: True)
         monkeypatch.setattr(gateway_cli, "is_macos", lambda: False)
 
         calls = []
@@ -298,30 +294,11 @@ class TestGatewaySystemServiceRouting:
 
         assert calls == [(True, True, "alice")]
 
-    def test_gateway_install_reports_termux_manual_mode(self, monkeypatch, capsys):
-        monkeypatch.setattr(gateway_cli, "is_termux", lambda: True)
-        monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: False)
-        monkeypatch.setattr(gateway_cli, "is_macos", lambda: False)
-
-        try:
-            gateway_cli.gateway_command(
-                SimpleNamespace(gateway_command="install", force=False, system=False, run_as_user=None)
-            )
-        except SystemExit as exc:
-            assert exc.code == 1
-        else:
-            raise AssertionError("Expected gateway_command to exit on unsupported Termux service install")
-
-        out = capsys.readouterr().out
-        assert "not supported on Termux" in out
-        assert "Run manually: hermes gateway" in out
-
     def test_gateway_status_prefers_system_service_when_only_system_unit_exists(self, monkeypatch):
         user_unit = SimpleNamespace(exists=lambda: False)
         system_unit = SimpleNamespace(exists=lambda: True)
 
-        monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: True)
-        monkeypatch.setattr(gateway_cli, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway_cli, "is_linux", lambda: True)
         monkeypatch.setattr(gateway_cli, "is_macos", lambda: False)
         monkeypatch.setattr(
             gateway_cli,
@@ -336,20 +313,6 @@ class TestGatewaySystemServiceRouting:
 
         assert calls == [(False, False)]
 
-    def test_gateway_status_on_termux_shows_manual_guidance(self, monkeypatch, capsys):
-        monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: False)
-        monkeypatch.setattr(gateway_cli, "is_termux", lambda: True)
-        monkeypatch.setattr(gateway_cli, "is_macos", lambda: False)
-        monkeypatch.setattr(gateway_cli, "find_gateway_pids", lambda exclude_pids=None: [])
-        monkeypatch.setattr(gateway_cli, "_runtime_health_lines", lambda: [])
-
-        gateway_cli.gateway_command(SimpleNamespace(gateway_command="status", deep=False, system=False))
-
-        out = capsys.readouterr().out
-        assert "Gateway is not running" in out
-        assert "nohup hermes gateway" in out
-        assert "install as user service" not in out
-
     def test_gateway_restart_does_not_fallback_to_foreground_when_launchd_restart_fails(self, tmp_path, monkeypatch):
         plist_path = tmp_path / "ai.hermes.gateway.plist"
         plist_path.write_text("plist\n", encoding="utf-8")
@@ -550,22 +513,12 @@ class TestGeneratedUnitUsesDetectedVenv:
 class TestGeneratedUnitIncludesLocalBin:
     """~/.local/bin must be in PATH so uvx/pipx tools are discoverable."""
 
-    def test_user_unit_includes_local_bin_in_path(self, monkeypatch):
-        home = Path.home()
-        monkeypatch.setattr(
-            gateway_cli,
-            "_build_user_local_paths",
-            lambda home_path, existing: [str(home / ".local" / "bin")],
-        )
+    def test_user_unit_includes_local_bin_in_path(self):
         unit = gateway_cli.generate_systemd_unit(system=False)
+        home = str(Path.home())
         assert f"{home}/.local/bin" in unit
 
-    def test_system_unit_includes_local_bin_in_path(self, monkeypatch):
-        monkeypatch.setattr(
-            gateway_cli,
-            "_build_user_local_paths",
-            lambda home_path, existing: [str(home_path / ".local" / "bin")],
-        )
+    def test_system_unit_includes_local_bin_in_path(self):
         unit = gateway_cli.generate_systemd_unit(system=True)
         # System unit uses the resolved home dir from _system_service_identity
         assert "/.local/bin" in unit

tests/hermes_cli/test_models.py

@@ -3,15 +3,13 @@
 from unittest.mock import patch, MagicMock
 
 from hermes_cli.models import (
-    OPENROUTER_MODELS, menu_labels, model_ids, detect_provider_for_model,
+    OPENROUTER_MODELS, model_ids, detect_provider_for_model,
     filter_nous_free_models, _NOUS_ALLOWED_FREE_MODELS,
     is_nous_free_tier, partition_nous_models_by_tier,
-    check_nous_free_tier, clear_nous_free_tier_cache,
-    _FREE_TIER_CACHE_TTL,
+    check_nous_free_tier, _FREE_TIER_CACHE_TTL,
 )
 import hermes_cli.models as _models_mod
 
-
 class TestModelIds:
     def test_returns_non_empty_list(self):
         ids = model_ids()
@@ -33,25 +31,6 @@ class TestModelIds:
         assert len(ids) == len(set(ids)), "Duplicate model IDs found"
 
 
-class TestMenuLabels:
-    def test_same_length_as_model_ids(self):
-        assert len(menu_labels()) == len(model_ids())
-
-    def test_first_label_marked_recommended(self):
-        labels = menu_labels()
-        assert "recommended" in labels[0].lower()
-
-    def test_each_label_contains_its_model_id(self):
-        for label, mid in zip(menu_labels(), model_ids()):
-            assert mid in label, f"Label '{label}' doesn't contain model ID '{mid}'"
-
-    def test_non_recommended_labels_have_no_tag(self):
-        """Only the first model should have (recommended)."""
-        labels = menu_labels()
-        for label in labels[1:]:
-            assert "recommended" not in label.lower(), f"Unexpected 'recommended' in '{label}'"
-
-
 class TestOpenRouterModels:
     def test_structure_is_list_of_tuples(self):
         for entry in OPENROUTER_MODELS:
@@ -302,12 +281,10 @@ class TestCheckNousFreeTierCache:
     """Tests for the TTL cache on check_nous_free_tier()."""
 
     def setup_method(self):
-        """Reset cache before each test."""
-        clear_nous_free_tier_cache()
+        _models_mod._free_tier_cache = None
 
     def teardown_method(self):
-        """Reset cache after each test."""
-        clear_nous_free_tier_cache()
+        _models_mod._free_tier_cache = None
 
     @patch("hermes_cli.models.fetch_nous_account_tier")
     @patch("hermes_cli.models.is_nous_free_tier", return_value=True)
@@ -321,7 +298,6 @@ class TestCheckNousFreeTierCache:
 
         assert result1 is True
         assert result2 is True
-        # fetch_nous_account_tier should only be called once (cached on second call)
         assert mock_fetch.call_count == 1
 
     @patch("hermes_cli.models.fetch_nous_account_tier")
@@ -334,7 +310,6 @@ class TestCheckNousFreeTierCache:
             result1 = check_nous_free_tier()
             assert mock_fetch.call_count == 1
 
-            # Simulate TTL expiry by backdating the cache timestamp
             cached_result, cached_at = _models_mod._free_tier_cache
             _models_mod._free_tier_cache = (cached_result, cached_at - _FREE_TIER_CACHE_TTL - 1)
 
@@ -344,15 +319,6 @@ class TestCheckNousFreeTierCache:
         assert result1 is False
         assert result2 is False
 
-    def test_clear_cache_forces_refresh(self):
-        """clear_nous_free_tier_cache() invalidates the cached result."""
-        # Manually seed the cache
-        import time
-        _models_mod._free_tier_cache = (True, time.monotonic())
-
-        clear_nous_free_tier_cache()
-        assert _models_mod._free_tier_cache is None
-
     def test_cache_ttl_is_short(self):
         """TTL should be short enough to catch upgrades quickly (<=5 min)."""
         assert _FREE_TIER_CACHE_TTL <= 300

tests/hermes_cli/test_setup_hermes_script.py

@@ -1,21 +0,0 @@
-from pathlib import Path
-import subprocess
-
-
-REPO_ROOT = Path(__file__).resolve().parents[2]
-SETUP_SCRIPT = REPO_ROOT / "setup-hermes.sh"
-
-
-def test_setup_hermes_script_is_valid_shell():
-    result = subprocess.run(["bash", "-n", str(SETUP_SCRIPT)], capture_output=True, text=True)
-    assert result.returncode == 0, result.stderr
-
-
-def test_setup_hermes_script_has_termux_path():
-    content = SETUP_SCRIPT.read_text(encoding="utf-8")
-
-    assert "is_termux()" in content
-    assert ".[termux]" in content
-    assert "constraints-termux.txt" in content
-    assert "$PREFIX/bin" in content
-    assert "Skipping tinker-atropos on Termux" in content

tests/hermes_cli/test_setup_model_provider.py

@@ -305,7 +305,6 @@ def test_setup_copilot_acp_skips_same_provider_pool_step(tmp_path, monkeypatch):
     monkeypatch.setattr("hermes_cli.setup.prompt_yes_no", fake_prompt_yes_no)
     monkeypatch.setattr("hermes_cli.setup.prompt", lambda *args, **kwargs: "")
     monkeypatch.setattr("hermes_cli.auth.get_active_provider", lambda: None)
-    monkeypatch.setattr("hermes_cli.auth.detect_external_credentials", lambda: [])
     monkeypatch.setattr("agent.auxiliary_client.get_available_vision_backends", lambda: [])
 
     setup_model_provider(config)

tests/hermes_cli/test_setup_model_selection.py

@@ -1,155 +0,0 @@
-"""Tests for _setup_provider_model_selection and the zai/kimi/minimax branch.
-
-Regression test for the is_coding_plan NameError that crashed setup when
-selecting zai, kimi-coding, minimax, or minimax-cn providers.
-"""
-import pytest
-from unittest.mock import patch, MagicMock
-
-
-@pytest.fixture
-def mock_provider_registry():
-    """Minimal PROVIDER_REGISTRY entries for tested providers."""
-    class FakePConfig:
-        def __init__(self, name, env_vars, base_url_env, inference_url):
-            self.name = name
-            self.api_key_env_vars = env_vars
-            self.base_url_env_var = base_url_env
-            self.inference_base_url = inference_url
-
-    return {
-        "zai": FakePConfig("ZAI", ["ZAI_API_KEY"], "ZAI_BASE_URL", "https://api.zai.example"),
-        "kimi-coding": FakePConfig("Kimi Coding", ["KIMI_API_KEY"], "KIMI_BASE_URL", "https://api.kimi.example"),
-        "minimax": FakePConfig("MiniMax", ["MINIMAX_API_KEY"], "MINIMAX_BASE_URL", "https://api.minimax.example"),
-        "minimax-cn": FakePConfig("MiniMax CN", ["MINIMAX_API_KEY"], "MINIMAX_CN_BASE_URL", "https://api.minimax-cn.example"),
-        "opencode-zen": FakePConfig("OpenCode Zen", ["OPENCODE_ZEN_API_KEY"], "OPENCODE_ZEN_BASE_URL", "https://opencode.ai/zen/v1"),
-        "opencode-go": FakePConfig("OpenCode Go", ["OPENCODE_GO_API_KEY"], "OPENCODE_GO_BASE_URL", "https://opencode.ai/zen/go/v1"),
-    }
-
-
-class TestSetupProviderModelSelection:
-    """Verify _setup_provider_model_selection works for all providers
-    that previously hit the is_coding_plan NameError."""
-
-    @pytest.mark.parametrize("provider_id,expected_defaults", [
-        ("zai", ["glm-5", "glm-4.7", "glm-4.5", "glm-4.5-flash"]),
-        ("kimi-coding", ["kimi-k2.5", "kimi-k2-thinking", "kimi-k2-turbo-preview"]),
-        ("minimax", ["MiniMax-M1", "MiniMax-M1-40k", "MiniMax-M1-80k", "MiniMax-M1-128k", "MiniMax-M1-256k", "MiniMax-M2.5", "MiniMax-M2.7"]),
-        ("minimax-cn", ["MiniMax-M1", "MiniMax-M1-40k", "MiniMax-M1-80k", "MiniMax-M1-128k", "MiniMax-M1-256k", "MiniMax-M2.5", "MiniMax-M2.7"]),
-        ("opencode-zen", ["gpt-5.4", "gpt-5.3-codex", "claude-sonnet-4-6", "gemini-3-flash"]),
-        ("opencode-go", ["glm-5", "kimi-k2.5", "minimax-m2.5", "minimax-m2.7"]),
-    ])
-    @patch("hermes_cli.models.fetch_api_models", return_value=[])
-    @patch("hermes_cli.config.get_env_value", return_value="fake-key")
-    def test_falls_back_to_default_models_without_crashing(
-        self, mock_env, mock_fetch, provider_id, expected_defaults, mock_provider_registry
-    ):
-        """Previously this code path raised NameError: 'is_coding_plan'.
-        Now it delegates to _setup_provider_model_selection which uses
-        _DEFAULT_PROVIDER_MODELS -- no crash, correct model list."""
-        from hermes_cli.setup import _setup_provider_model_selection
-
-        captured_choices = {}
-
-        def fake_prompt_choice(label, choices, default):
-            captured_choices["choices"] = choices
-            # Select "Keep current" (last item)
-            return len(choices) - 1
-
-        with patch("hermes_cli.auth.PROVIDER_REGISTRY", mock_provider_registry):
-            _setup_provider_model_selection(
-                config={"model": {}},
-                provider_id=provider_id,
-                current_model="some-model",
-                prompt_choice=fake_prompt_choice,
-                prompt_fn=lambda _: None,
-            )
-
-        # The offered model list should start with the default models
-        offered = captured_choices["choices"]
-        for model in expected_defaults:
-            assert model in offered, f"{model} not in choices for {provider_id}"
-
-    @patch("hermes_cli.models.fetch_api_models")
-    @patch("hermes_cli.config.get_env_value", return_value="fake-key")
-    def test_live_models_used_when_available(
-        self, mock_env, mock_fetch, mock_provider_registry
-    ):
-        """When fetch_api_models returns results, those are used instead of defaults."""
-        from hermes_cli.setup import _setup_provider_model_selection
-
-        live = ["live-model-1", "live-model-2"]
-        mock_fetch.return_value = live
-
-        captured_choices = {}
-
-        def fake_prompt_choice(label, choices, default):
-            captured_choices["choices"] = choices
-            return len(choices) - 1
-
-        with patch("hermes_cli.auth.PROVIDER_REGISTRY", mock_provider_registry):
-            _setup_provider_model_selection(
-                config={"model": {}},
-                provider_id="zai",
-                current_model="some-model",
-                prompt_choice=fake_prompt_choice,
-                prompt_fn=lambda _: None,
-            )
-
-        offered = captured_choices["choices"]
-        assert "live-model-1" in offered
-        assert "live-model-2" in offered
-
-    @patch("hermes_cli.models.fetch_api_models", return_value=[])
-    @patch("hermes_cli.config.get_env_value", return_value="fake-key")
-    def test_custom_model_selection(
-        self, mock_env, mock_fetch, mock_provider_registry
-    ):
-        """Selecting 'Custom model' lets user type a model name."""
-        from hermes_cli.setup import _setup_provider_model_selection, _DEFAULT_PROVIDER_MODELS
-
-        defaults = _DEFAULT_PROVIDER_MODELS["zai"]
-        custom_model_idx = len(defaults)  # "Custom model" is right after defaults
-
-        config = {"model": {}}
-
-        def fake_prompt_choice(label, choices, default):
-            return custom_model_idx
-
-        with patch("hermes_cli.auth.PROVIDER_REGISTRY", mock_provider_registry):
-            _setup_provider_model_selection(
-                config=config,
-                provider_id="zai",
-                current_model="some-model",
-                prompt_choice=fake_prompt_choice,
-                prompt_fn=lambda _: "my-custom-model",
-            )
-
-        assert config["model"]["default"] == "my-custom-model"
-
-    @patch("hermes_cli.models.fetch_api_models", return_value=["opencode-go/kimi-k2.5", "opencode-go/minimax-m2.7"])
-    @patch("hermes_cli.config.get_env_value", return_value="fake-key")
-    def test_opencode_live_models_are_normalized_for_selection(
-        self, mock_env, mock_fetch, mock_provider_registry
-    ):
-        from hermes_cli.setup import _setup_provider_model_selection
-
-        captured_choices = {}
-
-        def fake_prompt_choice(label, choices, default):
-            captured_choices["choices"] = choices
-            return len(choices) - 1
-
-        with patch("hermes_cli.auth.PROVIDER_REGISTRY", mock_provider_registry):
-            _setup_provider_model_selection(
-                config={"model": {}},
-                provider_id="opencode-go",
-                current_model="opencode-go/kimi-k2.5",
-                prompt_choice=fake_prompt_choice,
-                prompt_fn=lambda _: None,
-            )
-
-        offered = captured_choices["choices"]
-        assert "kimi-k2.5" in offered
-        assert "minimax-m2.7" in offered
-        assert all("opencode-go/" not in choice for choice in offered)

tests/hermes_cli/test_skin_engine.py

@@ -196,31 +196,6 @@ class TestDisplayIntegration:
         set_active_skin("ares")
         assert get_skin_tool_prefix() == "╎"
 
-    def test_get_skin_faces_default(self):
-        from agent.display import get_skin_faces, KawaiiSpinner
-        faces = get_skin_faces("waiting_faces", KawaiiSpinner.KAWAII_WAITING)
-        # Default skin has no custom faces, so should return the default list
-        assert faces == KawaiiSpinner.KAWAII_WAITING
-
-    def test_get_skin_faces_ares(self):
-        from hermes_cli.skin_engine import set_active_skin
-        from agent.display import get_skin_faces, KawaiiSpinner
-        set_active_skin("ares")
-        faces = get_skin_faces("waiting_faces", KawaiiSpinner.KAWAII_WAITING)
-        assert "(⚔)" in faces
-
-    def test_get_skin_verbs_default(self):
-        from agent.display import get_skin_verbs, KawaiiSpinner
-        verbs = get_skin_verbs()
-        assert verbs == KawaiiSpinner.THINKING_VERBS
-
-    def test_get_skin_verbs_ares(self):
-        from hermes_cli.skin_engine import set_active_skin
-        from agent.display import get_skin_verbs
-        set_active_skin("ares")
-        verbs = get_skin_verbs()
-        assert "forging" in verbs
-
     def test_tool_message_uses_skin_prefix(self):
         from hermes_cli.skin_engine import set_active_skin
         from agent.display import get_cute_tool_message

tests/hermes_cli/test_status.py

@@ -12,33 +12,3 @@ def test_show_status_includes_tavily_key(monkeypatch, capsys, tmp_path):
     output = capsys.readouterr().out
     assert "Tavily" in output
     assert "tvly...cdef" in output
-
-
-def test_show_status_termux_gateway_section_skips_systemctl(monkeypatch, capsys, tmp_path):
-    from hermes_cli import status as status_mod
-    import hermes_cli.auth as auth_mod
-    import hermes_cli.gateway as gateway_mod
-
-    monkeypatch.setenv("TERMUX_VERSION", "0.118.3")
-    monkeypatch.setenv("PREFIX", "/data/data/com.termux/files/usr")
-    monkeypatch.setattr(status_mod, "get_env_path", lambda: tmp_path / ".env", raising=False)
-    monkeypatch.setattr(status_mod, "get_hermes_home", lambda: tmp_path, raising=False)
-    monkeypatch.setattr(status_mod, "load_config", lambda: {"model": "gpt-5.4"}, raising=False)
-    monkeypatch.setattr(status_mod, "resolve_requested_provider", lambda requested=None: "openai-codex", raising=False)
-    monkeypatch.setattr(status_mod, "resolve_provider", lambda requested=None, **kwargs: "openai-codex", raising=False)
-    monkeypatch.setattr(status_mod, "provider_label", lambda provider: "OpenAI Codex", raising=False)
-    monkeypatch.setattr(auth_mod, "get_nous_auth_status", lambda: {}, raising=False)
-    monkeypatch.setattr(auth_mod, "get_codex_auth_status", lambda: {}, raising=False)
-    monkeypatch.setattr(gateway_mod, "find_gateway_pids", lambda exclude_pids=None: [], raising=False)
-
-    def _unexpected_systemctl(*args, **kwargs):
-        raise AssertionError("systemctl should not be called in the Termux status view")
-
-    monkeypatch.setattr(status_mod.subprocess, "run", _unexpected_systemctl)
-
-    status_mod.show_status(SimpleNamespace(all=False, deep=False))
-
-    output = capsys.readouterr().out
-    assert "Manager:      Termux / manual process" in output
-    assert "Start with:   hermes gateway" in output
-    assert "systemd (user)" not in output

tests/hermes_cli/test_update_autostash.py

@@ -213,12 +213,8 @@ def test_restore_stashed_changes_keeps_going_when_drop_fails(monkeypatch, tmp_pa
     assert "git stash drop stash@{0}" in out
 
 
-def test_restore_stashed_changes_always_resets_on_conflict(monkeypatch, tmp_path, capsys):
-    """Conflicts always auto-reset (no prompt) and return False, even interactively.
-
-    Leaving conflict markers in source files makes hermes unrunnable (SyntaxError).
-    The stash is preserved for manual recovery; cmd_update continues normally.
-    """
+def test_restore_stashed_changes_prompts_before_reset_on_conflict(monkeypatch, tmp_path, capsys):
+    """When conflicts occur interactively, user is prompted before reset."""
     calls = []
 
     def fake_run(cmd, **kwargs):
@@ -234,19 +230,45 @@ def test_restore_stashed_changes_always_resets_on_conflict(monkeypatch, tmp_path
     monkeypatch.setattr(hermes_main.subprocess, "run", fake_run)
     monkeypatch.setattr("builtins.input", lambda: "y")
 
-    result = hermes_main._restore_stashed_changes(["git"], tmp_path, "abc123", prompt_user=True)
+    with pytest.raises(SystemExit, match="1"):
+        hermes_main._restore_stashed_changes(["git"], tmp_path, "abc123", prompt_user=True)
 
-    assert result is False
     out = capsys.readouterr().out
     assert "Conflicted files:" in out
     assert "hermes_cli/main.py" in out
     assert "stashed changes are preserved" in out
+    assert "Reset working tree to clean state" in out
     assert "Working tree reset to clean state" in out
-    assert "git stash apply abc123" in out
     reset_calls = [c for c, _ in calls if c[1:3] == ["reset", "--hard"]]
     assert len(reset_calls) == 1
 
 
+def test_restore_stashed_changes_user_declines_reset(monkeypatch, tmp_path, capsys):
+    """When user declines reset, working tree is left as-is."""
+    calls = []
+
+    def fake_run(cmd, **kwargs):
+        calls.append((cmd, kwargs))
+        if cmd[1:3] == ["stash", "apply"]:
+            return SimpleNamespace(stdout="", stderr="conflict\n", returncode=1)
+        if cmd[1:3] == ["diff", "--name-only"]:
+            return SimpleNamespace(stdout="cli.py\n", stderr="", returncode=0)
+        raise AssertionError(f"unexpected command: {cmd}")
+
+    monkeypatch.setattr(hermes_main.subprocess, "run", fake_run)
+    # First input: "y" to restore, second input: "n" to decline reset
+    inputs = iter(["y", "n"])
+    monkeypatch.setattr("builtins.input", lambda: next(inputs))
+
+    with pytest.raises(SystemExit, match="1"):
+        hermes_main._restore_stashed_changes(["git"], tmp_path, "abc123", prompt_user=True)
+
+    out = capsys.readouterr().out
+    assert "left as-is" in out
+    reset_calls = [c for c, _ in calls if c[1:3] == ["reset", "--hard"]]
+    assert len(reset_calls) == 0
+
+
 def test_restore_stashed_changes_auto_resets_non_interactive(monkeypatch, tmp_path, capsys):
     """Non-interactive mode auto-resets without prompting and returns False
     instead of sys.exit(1) so the update can continue (gateway /update path)."""

tests/hermes_cli/test_update_gateway_restart.py

@@ -368,8 +368,9 @@ class TestCmdUpdateLaunchdRestart:
         monkeypatch.setattr(
             gateway_cli, "is_macos", lambda: False,
         )
-        monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: True)
-        monkeypatch.setattr(gateway_cli, "is_termux", lambda: False)
+        monkeypatch.setattr(
+            gateway_cli, "is_linux", lambda: True,
+        )
 
         mock_run.side_effect = _make_run_side_effect(
             commit_count="3",
@@ -428,8 +429,7 @@ class TestCmdUpdateSystemService:
     ):
         """When user systemd is inactive but a system service exists, restart via system scope."""
         monkeypatch.setattr(gateway_cli, "is_macos", lambda: False)
-        monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: True)
-        monkeypatch.setattr(gateway_cli, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway_cli, "is_linux", lambda: True)
 
         mock_run.side_effect = _make_run_side_effect(
             commit_count="3",
@@ -458,8 +458,7 @@ class TestCmdUpdateSystemService:
     ):
         """When system service restart fails, show the failure message."""
         monkeypatch.setattr(gateway_cli, "is_macos", lambda: False)
-        monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: True)
-        monkeypatch.setattr(gateway_cli, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway_cli, "is_linux", lambda: True)
 
         mock_run.side_effect = _make_run_side_effect(
             commit_count="3",
@@ -481,8 +480,7 @@ class TestCmdUpdateSystemService:
     ):
         """When both user and system services are active, both are restarted."""
         monkeypatch.setattr(gateway_cli, "is_macos", lambda: False)
-        monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: True)
-        monkeypatch.setattr(gateway_cli, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway_cli, "is_linux", lambda: True)
 
         mock_run.side_effect = _make_run_side_effect(
             commit_count="3",
@@ -565,8 +563,7 @@ class TestServicePidExclusion:
     ):
         """After systemd restart, the sweep must exclude the service PID."""
         monkeypatch.setattr(gateway_cli, "is_macos", lambda: False)
-        monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: True)
-        monkeypatch.setattr(gateway_cli, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway_cli, "is_linux", lambda: True)
 
         SERVICE_PID = 55000
 
@@ -645,8 +642,7 @@ class TestGetServicePids:
     """Unit tests for _get_service_pids()."""
 
     def test_returns_systemd_main_pid(self, monkeypatch):
-        monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: True)
-        monkeypatch.setattr(gateway_cli, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway_cli, "is_linux", lambda: True)
         monkeypatch.setattr(gateway_cli, "is_macos", lambda: False)
 
         def fake_run(cmd, **kwargs):
@@ -695,8 +691,7 @@ class TestGetServicePids:
 
     def test_excludes_zero_pid(self, monkeypatch):
         """systemd returns MainPID=0 for stopped services; skip those."""
-        monkeypatch.setattr(gateway_cli, "supports_systemd_services", lambda: True)
-        monkeypatch.setattr(gateway_cli, "is_termux", lambda: False)
+        monkeypatch.setattr(gateway_cli, "is_linux", lambda: True)
         monkeypatch.setattr(gateway_cli, "is_macos", lambda: False)
 
         def fake_run(cmd, **kwargs):

tests/run_agent/test_413_compression.py

@@ -172,87 +172,6 @@ class TestHTTP413Compression:
         mock_compress.assert_called_once()
         assert result["completed"] is True
 
-    def test_413_clears_conversation_history_on_persist(self, agent):
-        """After 413-triggered compression, _persist_session must receive None history.
-
-        Bug: _compress_context() creates a new session and resets _last_flushed_db_idx=0,
-        but if conversation_history still holds the original (pre-compression) list,
-        _flush_messages_to_session_db computes flush_from = max(len(history), 0) which
-        exceeds len(compressed_messages), so messages[flush_from:] is empty and nothing
-        is written to the new session → "Session found but has no messages" on resume.
-        """
-        err_413 = _make_413_error()
-        ok_resp = _mock_response(content="OK", finish_reason="stop")
-        agent.client.chat.completions.create.side_effect = [err_413, ok_resp]
-
-        big_history = [
-            {"role": "user" if i % 2 == 0 else "assistant", "content": f"msg {i}"}
-            for i in range(200)
-        ]
-
-        persist_calls = []
-
-        with (
-            patch.object(agent, "_compress_context") as mock_compress,
-            patch.object(
-                agent, "_persist_session",
-                side_effect=lambda msgs, hist: persist_calls.append(hist),
-            ),
-            patch.object(agent, "_save_trajectory"),
-            patch.object(agent, "_cleanup_task_resources"),
-        ):
-            mock_compress.return_value = (
-                [{"role": "user", "content": "summary"}],
-                "compressed prompt",
-            )
-            agent.run_conversation("hello", conversation_history=big_history)
-
-        assert len(persist_calls) >= 1, "Expected at least one _persist_session call"
-        for hist in persist_calls:
-            assert hist is None, (
-                f"conversation_history should be None after mid-loop compression, "
-                f"got list with {len(hist)} items"
-            )
-
-    def test_context_overflow_clears_conversation_history_on_persist(self, agent):
-        """After context-overflow compression, _persist_session must receive None history."""
-        err_400 = Exception(
-            "Error code: 400 - This endpoint's maximum context length is 128000 tokens. "
-            "However, you requested about 270460 tokens."
-        )
-        err_400.status_code = 400
-        ok_resp = _mock_response(content="OK", finish_reason="stop")
-        agent.client.chat.completions.create.side_effect = [err_400, ok_resp]
-
-        big_history = [
-            {"role": "user" if i % 2 == 0 else "assistant", "content": f"msg {i}"}
-            for i in range(200)
-        ]
-
-        persist_calls = []
-
-        with (
-            patch.object(agent, "_compress_context") as mock_compress,
-            patch.object(
-                agent, "_persist_session",
-                side_effect=lambda msgs, hist: persist_calls.append(hist),
-            ),
-            patch.object(agent, "_save_trajectory"),
-            patch.object(agent, "_cleanup_task_resources"),
-        ):
-            mock_compress.return_value = (
-                [{"role": "user", "content": "summary"}],
-                "compressed prompt",
-            )
-            agent.run_conversation("hello", conversation_history=big_history)
-
-        assert len(persist_calls) >= 1
-        for hist in persist_calls:
-            assert hist is None, (
-                f"conversation_history should be None after context-overflow compression, "
-                f"got list with {len(hist)} items"
-            )
-
     def test_400_context_length_triggers_compression(self, agent):
         """A 400 with 'maximum context length' should trigger compression, not abort as generic 4xx.
 

tests/run_agent/test_provider_parity.py

@@ -225,26 +225,6 @@ class TestDeveloperRoleSwap:
         assert kwargs["messages"][0]["role"] == "developer"
 
 
-class TestBuildApiKwargsChatCompletionsServiceTier:
-    """service_tier via request_overrides works on the chat_completions path."""
-
-    def test_includes_service_tier_via_request_overrides(self, monkeypatch):
-        agent = _make_agent(monkeypatch, "openrouter")
-        agent.model = "gpt-4.1"
-        agent.request_overrides = {"service_tier": "priority"}
-        messages = [{"role": "user", "content": "hi"}]
-        kwargs = agent._build_api_kwargs(messages)
-        assert kwargs["service_tier"] == "priority"
-
-    def test_no_service_tier_when_overrides_empty(self, monkeypatch):
-        agent = _make_agent(monkeypatch, "openrouter")
-        agent.model = "gpt-4.1"
-        agent.request_overrides = {}
-        messages = [{"role": "user", "content": "hi"}]
-        kwargs = agent._build_api_kwargs(messages)
-        assert "service_tier" not in kwargs
-
-
 class TestBuildApiKwargsAIGateway:
     def test_uses_chat_completions_format(self, monkeypatch):
         agent = _make_agent(monkeypatch, "ai-gateway", base_url="https://ai-gateway.vercel.sh/v1")
@@ -376,25 +356,6 @@ class TestBuildApiKwargsCodex:
         assert "reasoning" in kwargs
         assert kwargs["reasoning"]["effort"] == "medium"
 
-    def test_includes_service_tier_via_request_overrides(self, monkeypatch):
-        agent = _make_agent(monkeypatch, "openai-codex", api_mode="codex_responses",
-                            base_url="https://chatgpt.com/backend-api/codex")
-        agent.model = "gpt-5.4"
-        agent.service_tier = "priority"
-        agent.request_overrides = {"service_tier": "priority"}
-        messages = [{"role": "user", "content": "hi"}]
-        kwargs = agent._build_api_kwargs(messages)
-        assert kwargs["service_tier"] == "priority"
-
-    def test_omits_max_output_tokens_for_codex_backend(self, monkeypatch):
-        agent = _make_agent(monkeypatch, "openai-codex", api_mode="codex_responses",
-                            base_url="https://chatgpt.com/backend-api/codex")
-        agent.model = "gpt-5.4"
-        agent.max_tokens = 20
-        messages = [{"role": "user", "content": "hi"}]
-        kwargs = agent._build_api_kwargs(messages)
-        assert "max_output_tokens" not in kwargs
-
     def test_includes_encrypted_content_in_include(self, monkeypatch):
         agent = _make_agent(monkeypatch, "openai-codex", api_mode="codex_responses",
                             base_url="https://chatgpt.com/backend-api/codex")

tests/run_agent/test_run_agent.py

@@ -5,7 +5,6 @@ pieces. The OpenAI client and tool loading are mocked so no network calls
 are made.
 """
 
-import io
 import json
 import logging
 import re
@@ -1062,77 +1061,6 @@ class TestExecuteToolCalls:
         assert len(messages[0]["content"]) < 150_000
         assert ("Truncated" in messages[0]["content"] or "<persisted-output>" in messages[0]["content"])
 
-    def test_quiet_tool_output_suppressed_when_progress_callback_present(self, agent):
-        tc = _mock_tool_call(name="web_search", arguments='{"q":"test"}', call_id="c1")
-        mock_msg = _mock_assistant_msg(content="", tool_calls=[tc])
-        messages = []
-        agent.tool_progress_callback = lambda *args, **kwargs: None
-
-        with patch("run_agent.handle_function_call", return_value="search result"), \
-             patch.object(agent, "_safe_print") as mock_print:
-            agent._execute_tool_calls(mock_msg, messages, "task-1")
-
-        mock_print.assert_not_called()
-        assert len(messages) == 1
-        assert messages[0]["role"] == "tool"
-
-    def test_quiet_tool_output_prints_without_progress_callback(self, agent):
-        tc = _mock_tool_call(name="web_search", arguments='{"q":"test"}', call_id="c1")
-        mock_msg = _mock_assistant_msg(content="", tool_calls=[tc])
-        messages = []
-        agent.tool_progress_callback = None
-
-        with patch("run_agent.handle_function_call", return_value="search result"), \
-             patch.object(agent, "_safe_print") as mock_print:
-            agent._execute_tool_calls(mock_msg, messages, "task-1")
-
-        mock_print.assert_called_once()
-        assert "search" in str(mock_print.call_args.args[0]).lower()
-        assert len(messages) == 1
-        assert messages[0]["role"] == "tool"
-
-    def test_vprint_suppressed_in_parseable_quiet_mode(self, agent):
-        agent.suppress_status_output = True
-
-        with patch.object(agent, "_safe_print") as mock_print:
-            agent._vprint("status line", force=True)
-            agent._vprint("normal line")
-
-        mock_print.assert_not_called()
-
-    def test_run_conversation_suppresses_retry_noise_in_parseable_quiet_mode(self, agent):
-        class _RateLimitError(Exception):
-            status_code = 429
-
-            def __str__(self):
-                return "Error code: 429 - Rate limit exceeded."
-
-        responses = [_RateLimitError(), _mock_response(content="Recovered")]
-
-        def _fake_api_call(api_kwargs):
-            result = responses.pop(0)
-            if isinstance(result, Exception):
-                raise result
-            return result
-
-        agent.suppress_status_output = True
-        agent._interruptible_api_call = _fake_api_call
-        agent._persist_session = lambda *args, **kwargs: None
-        agent._save_trajectory = lambda *args, **kwargs: None
-        agent._save_session_log = lambda *args, **kwargs: None
-
-        captured = io.StringIO()
-        agent._print_fn = lambda *args, **kw: print(*args, file=captured, **kw)
-
-        with patch("run_agent.time.sleep", return_value=None):
-            result = agent.run_conversation("hello")
-
-        assert result["completed"] is True
-        assert result["final_response"] == "Recovered"
-        output = captured.getvalue()
-        assert "API call failed" not in output
-        assert "Rate limit reached" not in output
-
 
 class TestConcurrentToolExecution:
     """Tests for _execute_tool_calls_concurrent and dispatch logic."""
@@ -1949,68 +1877,6 @@ class TestRunConversation:
         assert result["final_response"] is not None
         assert "Thinking Budget Exhausted" in result["final_response"]
 
-    def test_length_with_tool_calls_returns_partial_without_executing_tools(self, agent):
-        self._setup_agent(agent)
-        bad_tc = _mock_tool_call(
-            name="write_file",
-            arguments='{"path":"report.md","content":"partial',
-            call_id="c1",
-        )
-        resp = _mock_response(content="", finish_reason="length", tool_calls=[bad_tc])
-        agent.client.chat.completions.create.return_value = resp
-
-        with (
-            patch("run_agent.handle_function_call") as mock_handle_function_call,
-            patch.object(agent, "_persist_session"),
-            patch.object(agent, "_save_trajectory"),
-            patch.object(agent, "_cleanup_task_resources"),
-        ):
-            result = agent.run_conversation("write the report")
-
-        assert result["completed"] is False
-        assert result["partial"] is True
-        assert "truncated due to output length limit" in result["error"]
-        mock_handle_function_call.assert_not_called()
-
-    def test_truncated_tool_call_retries_once_before_refusing(self, agent):
-        """When tool call args are truncated, the agent retries the API call
-        once. If the retry succeeds (valid JSON args), tool execution proceeds."""
-        self._setup_agent(agent)
-        agent.valid_tool_names.add("write_file")
-        bad_tc = _mock_tool_call(
-            name="write_file",
-            arguments='{"path":"report.md","content":"partial',
-            call_id="c1",
-        )
-        truncated_resp = _mock_response(
-            content="", finish_reason="length", tool_calls=[bad_tc],
-        )
-        good_tc = _mock_tool_call(
-            name="write_file",
-            arguments='{"path":"report.md","content":"full content"}',
-            call_id="c2",
-        )
-        good_resp = _mock_response(
-            content="", finish_reason="stop", tool_calls=[good_tc],
-        )
-        with (
-            patch("run_agent.handle_function_call", return_value='{"success":true}') as mock_hfc,
-            patch.object(agent, "_persist_session"),
-            patch.object(agent, "_save_trajectory"),
-            patch.object(agent, "_cleanup_task_resources"),
-        ):
-            # First call: truncated → retry. Second: valid → execute tool.
-            # Third: final text response.
-            final_resp = _mock_response(content="Done!", finish_reason="stop")
-            agent.client.chat.completions.create.side_effect = [
-                truncated_resp, good_resp, final_resp,
-            ]
-            result = agent.run_conversation("write the report")
-
-        # Tool was executed on the retry (good_resp)
-        mock_hfc.assert_called_once()
-        assert result["final_response"] == "Done!"
-
 
 class TestRetryExhaustion:
     """Regression: retry_count > max_retries was dead code (off-by-one).
@@ -3144,20 +3010,6 @@ class TestStreamingApiCall:
         assert tc[0].function.name == "search"
         assert tc[1].function.name == "read"
 
-    def test_truncated_tool_call_args_upgrade_finish_reason_to_length(self, agent):
-        chunks = [
-            _make_chunk(tool_calls=[_make_tc_delta(0, "call_1", "write_file", '{"path":"x.txt","content":"hel')]),
-        ]
-        agent.client.chat.completions.create.return_value = iter(chunks)
-
-        resp = agent._interruptible_streaming_api_call({"messages": []})
-
-        tc = resp.choices[0].message.tool_calls
-        assert len(tc) == 1
-        assert tc[0].function.name == "write_file"
-        assert tc[0].function.arguments == '{"path":"x.txt","content":"hel'
-        assert resp.choices[0].finish_reason == "length"
-
     def test_ollama_reused_index_separate_tool_calls(self, agent):
         """Ollama sends every tool call at index 0 with different ids.
 

tests/run_agent/test_run_agent_codex_responses.py

@@ -648,15 +648,6 @@ def test_preflight_codex_api_kwargs_allows_reasoning_and_temperature(monkeypatch
     assert result["max_output_tokens"] == 4096
 
 
-def test_preflight_codex_api_kwargs_allows_service_tier(monkeypatch):
-    agent = _build_agent(monkeypatch)
-    kwargs = _codex_request_kwargs()
-    kwargs["service_tier"] = "priority"
-
-    result = agent._preflight_codex_api_kwargs(kwargs)
-    assert result["service_tier"] == "priority"
-
-
 def test_run_conversation_codex_replay_payload_keeps_call_id(monkeypatch):
     agent = _build_agent(monkeypatch)
     responses = [_codex_tool_call_response(), _codex_message_response("done")]

tests/test_timezone.py

@@ -20,6 +20,13 @@ from zoneinfo import ZoneInfo
 import hermes_time
 
 
+def _reset_hermes_time_cache():
+    """Reset the hermes_time module cache (replacement for removed reset_cache)."""
+    hermes_time._cached_tz = None
+    hermes_time._cached_tz_name = None
+    hermes_time._cache_resolved = False
+
+
 # =========================================================================
 # hermes_time.now() — core helper
 # =========================================================================
@@ -28,10 +35,10 @@ class TestHermesTimeNow:
     """Test the timezone-aware now() helper."""
 
     def setup_method(self):
-        hermes_time.reset_cache()
+        _reset_hermes_time_cache()
 
     def teardown_method(self):
-        hermes_time.reset_cache()
+        _reset_hermes_time_cache()
         os.environ.pop("HERMES_TIMEZONE", None)
 
     def test_valid_timezone_applies(self):
@@ -86,24 +93,24 @@ class TestHermesTimeNow:
     def test_cache_invalidation(self):
         """Changing env var + reset_cache picks up new timezone."""
         os.environ["HERMES_TIMEZONE"] = "UTC"
-        hermes_time.reset_cache()
+        _reset_hermes_time_cache()
         r1 = hermes_time.now()
         assert r1.utcoffset() == timedelta(0)
 
         os.environ["HERMES_TIMEZONE"] = "Asia/Kolkata"
-        hermes_time.reset_cache()
+        _reset_hermes_time_cache()
         r2 = hermes_time.now()
         assert r2.utcoffset() == timedelta(hours=5, minutes=30)
 
 
 class TestGetTimezone:
-    """Test get_timezone() and get_timezone_name()."""
+    """Test get_timezone()."""
 
     def setup_method(self):
-        hermes_time.reset_cache()
+        _reset_hermes_time_cache()
 
     def teardown_method(self):
-        hermes_time.reset_cache()
+        _reset_hermes_time_cache()
         os.environ.pop("HERMES_TIMEZONE", None)
 
     def test_returns_zoneinfo_for_valid(self):
@@ -122,9 +129,6 @@ class TestGetTimezone:
         tz = hermes_time.get_timezone()
         assert tz is None
 
-    def test_get_timezone_name(self):
-        os.environ["HERMES_TIMEZONE"] = "Asia/Tokyo"
-        assert hermes_time.get_timezone_name() == "Asia/Tokyo"
 
 
 # =========================================================================
@@ -205,10 +209,10 @@ class TestCronTimezone:
     """Verify cron paths use timezone-aware now()."""
 
     def setup_method(self):
-        hermes_time.reset_cache()
+        _reset_hermes_time_cache()
 
     def teardown_method(self):
-        hermes_time.reset_cache()
+        _reset_hermes_time_cache()
         os.environ.pop("HERMES_TIMEZONE", None)
 
     def test_parse_schedule_duration_uses_tz_aware_now(self):
@@ -237,7 +241,7 @@ class TestCronTimezone:
         monkeypatch.setattr(jobs_module, "OUTPUT_DIR", tmp_path / "cron" / "output")
 
         os.environ["HERMES_TIMEZONE"] = "Asia/Kolkata"
-        hermes_time.reset_cache()
+        _reset_hermes_time_cache()
 
         # Create a job with a NAIVE past timestamp (simulating pre-tz data)
         from cron.jobs import create_job, load_jobs, save_jobs, get_due_jobs
@@ -262,7 +266,7 @@ class TestCronTimezone:
         from cron.jobs import _ensure_aware
 
         os.environ["HERMES_TIMEZONE"] = "Asia/Kolkata"
-        hermes_time.reset_cache()
+        _reset_hermes_time_cache()
 
         # Create a naive datetime — will be interpreted as system-local time
         naive_dt = datetime(2026, 3, 11, 12, 0, 0)
@@ -286,7 +290,7 @@ class TestCronTimezone:
         from cron.jobs import _ensure_aware
 
         os.environ["HERMES_TIMEZONE"] = "Asia/Kolkata"
-        hermes_time.reset_cache()
+        _reset_hermes_time_cache()
 
         # Create an aware datetime in UTC
         utc_dt = datetime(2026, 3, 11, 15, 0, 0, tzinfo=timezone.utc)
@@ -312,7 +316,7 @@ class TestCronTimezone:
         monkeypatch.setattr(jobs_module, "OUTPUT_DIR", tmp_path / "cron" / "output")
 
         os.environ["HERMES_TIMEZONE"] = "UTC"
-        hermes_time.reset_cache()
+        _reset_hermes_time_cache()
 
         from cron.jobs import create_job, load_jobs, save_jobs, get_due_jobs
 
@@ -343,7 +347,7 @@ class TestCronTimezone:
         # of the naive timestamp exceeds _hermes_now's wall time — this would
         # have caused a false "not due" with the old replace(tzinfo=...) approach.
         os.environ["HERMES_TIMEZONE"] = "Pacific/Midway"  # UTC-11
-        hermes_time.reset_cache()
+        _reset_hermes_time_cache()
 
         from cron.jobs import create_job, load_jobs, save_jobs, get_due_jobs
         create_job(prompt="Cross-tz job", schedule="every 1h")
@@ -367,7 +371,7 @@ class TestCronTimezone:
         monkeypatch.setattr(jobs_module, "OUTPUT_DIR", tmp_path / "cron" / "output")
 
         os.environ["HERMES_TIMEZONE"] = "US/Eastern"
-        hermes_time.reset_cache()
+        _reset_hermes_time_cache()
 
         from cron.jobs import create_job
         job = create_job(prompt="TZ test", schedule="every 2h")