claude: Add a note in CONTRIBUTING.md stating that routing is now done automatically without command prefix.

.env.example

@@ -40,17 +40,6 @@ OPENROUTER_API_KEY=
 # Any random string; also used as litellm's general_settings.master_key.
 LITELLM_MASTER_KEY=
 
-# --- hermes (autonomous agent with its own native Matrix presence) ---
-# Your own Matrix ID — Hermes only responds to this user, and only when @mentioned
-# in a shared room (e.g. "@hermes <task>" in the control room).
-MATRIX_HUMAN_USER_ID=@william:matrix.apps.williamturner.eu
-# Access token for the @hermes bot account (register it the same way as claude-bot —
-# see README — then log in as it via /_matrix/client/v3/login to get this token).
-HERMES_MATRIX_ACCESS_TOKEN=
-# Any random string — bearer key for Hermes's own OpenAI-compatible API server
-# (internal network only, not published anywhere).
-HERMES_API_SERVER_KEY=
-
 # --- portainer (GitOps redeploy) ---
 PORTAINER_STACK_WEBHOOK_URL=
 

CONTRIBUTING.md

@@ -0,0 +1,8 @@
+# Contributing
+
+## Chat routing
+
+Matrix control room messages no longer need a `!claude` or `!ai` command
+prefix. Every message is routed automatically (via the LiteLLM gateway and
+`agent/src/router.js`'s classifier) to the right handler — no prefix is
+required or recognized anymore.

agent/src/matrixBot.js

@@ -49,10 +49,6 @@ export async function startMatrixBot() {
     if (event.sender === BOT_USER_ID) return;
     const body = event.content?.body;
     if (!body) return;
-    // Messages explicitly addressed to another agent in this room (currently just
-    // @hermes) are that agent's to answer — without this, claude-bot's classifier would
-    // also see and reply to them, since it otherwise treats every message as its own.
-    if (/^@hermes\b/i.test(body.trim())) return;
 
     try {
       const decision = await routeMessage(body, KNOWN_REPOS);

docker-compose.yml

@@ -61,38 +61,6 @@ services:
     # Internal only — no Traefik labels. No reason to expose an LLM gateway holding a
     # master key and OAuth-forwarding config to the public internet.
 
-  hermes:
-    # Pinned to a specific dated release, not :latest — same rationale as litellm above.
-    image: nousresearch/hermes-agent:v2026.8.19
-    container_name: hermes
-    restart: unless-stopped
-    environment:
-      HERMES_UID: "1000"
-      HERMES_GID: "1000"
-      # Internal container address, not the public HTTPS one — same docker network as
-      # matrix-homeserver, no reason to round-trip through Traefik/TLS for this.
-      MATRIX_HOMESERVER: http://matrix-homeserver:8008
-      MATRIX_ACCESS_TOKEN: ${HERMES_MATRIX_ACCESS_TOKEN}
-      # Only you can trigger it; and only with an explicit @hermes mention in shared
-      # rooms (DMs to it would respond unprompted, per Hermes's own default behavior).
-      MATRIX_ALLOWED_USERS: ${MATRIX_HUMAN_USER_ID}
-      MATRIX_REQUIRE_MENTION: "true"
-      OPENROUTER_API_KEY: ${OPENROUTER_API_KEY}
-      # Left disabled: Hermes itself warns that a network-reachable API server combined
-      # with the default unsandboxed ('local') terminal backend gives any caller full
-      # terminal/file access within the container. Matrix is the actual interface in use;
-      # re-enable (API_SERVER_HOST: 0.0.0.0) only alongside terminal.backend: docker if
-      # claude-agent ever needs to call Hermes programmatically.
-      API_SERVER_ENABLED: "false"
-    volumes:
-      - /home/william/hermes-data:/opt/data
-    networks:
-      - web
-    # Without this the image's default command launches the interactive CLI, which
-    # immediately exits ("Input is not a terminal") since a detached container has no
-    # stdin — the container then just sits there having done nothing, every restart.
-    command: ["gateway", "run"]
-
   claude-agent:
     image: ${GITEA_REGISTRY_IMAGE}
     depends_on:

litellm-config.yaml

@@ -11,19 +11,13 @@ model_list:
       model: openrouter/openai/gpt-4o-mini
       api_key: os.environ/OPENROUTER_API_KEY
 
-  # Routes to Anthropic using the CALLER's forwarded Authorization header (the Claude
-  # Pro/Max subscription OAuth token) instead of a LiteLLM-held API key — billed against
-  # the subscription, not per-token. CONFIRMED WORKING, but only for the real `claude`
-  # CLI binary as caller (tested: `claude -p` with ANTHROPIC_BASE_URL pointed here
-  # returned a real completion). An earlier test with plain curl replicating the same
-  # request shape failed — Anthropic apparently requires header/fingerprint details only
-  # the real CLI sends, which LiteLLM faithfully relays but a hand-built request won't
-  # have. Do NOT expect this to work for other callers (Hermes, generic HTTP clients) —
-  # they aren't the real CLI and can't reproduce that fingerprint.
-  - model_name: anthropic-claude
-    litellm_params:
-      model: anthropic/claude-sonnet-5
+  # NOT included: a "claude-subscription" route forwarding the Claude Pro/Max OAuth token
+  # (from `claude setup-token`) through to Anthropic's raw API. Tested and confirmed
+  # non-functional — Anthropic returns a generic rate_limit_error for ANY direct API call
+  # using this token type outside the real Claude Code CLI client (reproduced with plain
+  # curl straight to api.anthropic.com, bypassing LiteLLM entirely, same result). The
+  # subscription token only works through the actual Claude Code CLI, which is what
+  # claude-agent already uses directly for code tasks — it was never routed through here.
 
 general_settings:
-  forward_client_headers_to_llm_api: true
   master_key: os.environ/LITELLM_MASTER_KEY