Merge branch 'main' into docs/branch-protection-notes

.env.example

@@ -25,20 +25,10 @@ CLAUDE_CODE_OAUTH_TOKEN=
 MATRIX_HOMESERVER_URL=https://matrix.apps.williamturner.eu
 MATRIX_BOT_TOKEN=
 MATRIX_CONTROL_ROOM_ID=
-# The bot's own Matrix ID (@username:server), e.g. @claude-bot:matrix.apps.williamturner.eu
-# — set explicitly rather than fetched via the API (that call 404s against Continuwuity).
-# Required: without it the bot can't tell its own messages apart from real ones and would
-# reply to itself in a loop, so it refuses to start.
-MATRIX_BOT_USER_ID=
-# Comma-separated "owner/repo" list the chat router is allowed to open code-change PRs
-# against. A plain chat message mentioning a repo NOT in this list is treated as chat,
-# never as a code task — the router only matches confidently against known repos.
-KNOWN_REPOS=william/gitops-automation
 
-# --- litellm (local LLM gateway — see litellm-config.yaml) ---
+# --- openrouter (the "!ai" chat command — other models, not the coding agent) ---
 OPENROUTER_API_KEY=
-# Any random string; also used as litellm's general_settings.master_key.
+OPENROUTER_DEFAULT_MODEL=openai/gpt-4o-mini
-LITELLM_MASTER_KEY=
 
 # --- portainer (GitOps redeploy) ---
 PORTAINER_STACK_WEBHOOK_URL=

.gitea/workflows/build.yml

@@ -31,10 +31,3 @@ jobs:
           IMAGE="${{ vars.REGISTRY_HOST }}/${{ gitea.repository }}/claude-agent:latest"
           docker build -t "$IMAGE" ./agent
           docker push "$IMAGE"
-
-      - name: Trigger Portainer redeploy
-        # Deliberately NOT a separate Gitea repo webhook firing in parallel on the same
-        # push — that raced with this build and could redeploy before the new image was
-        # actually pushed, silently keeping the old code running. Chaining it here as the
-        # last step guarantees the image exists before Portainer goes to pull it.
-        run: curl -f -X POST "${{ secrets.PORTAINER_WEBHOOK_URL }}"

agent/src/litellm.js

@@ -1,37 +0,0 @@
-const LITELLM_BASE_URL = process.env.LITELLM_BASE_URL || "http://litellm:4000";
-const LITELLM_MASTER_KEY = process.env.LITELLM_MASTER_KEY;
-
-// OpenAI-compatible chat completion, for OpenRouter-backed models routed through the
-// local LiteLLM gateway (e.g. "auto" — OpenRouter's own prompt-aware auto-router).
-export async function chatCompletion(model, prompt) {
-  if (!LITELLM_MASTER_KEY) {
-    throw new Error("LITELLM_MASTER_KEY is not set");
-  }
-
-  const res = await fetch(`${LITELLM_BASE_URL}/v1/chat/completions`, {
-    method: "POST",
-    headers: {
-      Authorization: `Bearer ${LITELLM_MASTER_KEY}`,
-      "Content-Type": "application/json",
-    },
-    body: JSON.stringify({
-      model,
-      messages: [{ role: "user", content: prompt }],
-      // Some models default max_tokens to their full context window (e.g. 65536), which
-      // can exceed available credit balance before a single token is generated. This is a
-      // quick chat reply, not a long-form task — cap it.
-      max_tokens: 1024,
-    }),
-  });
-
-  if (!res.ok) {
-    throw new Error(`LiteLLM request failed: ${res.status} ${await res.text()}`);
-  }
-
-  const data = await res.json();
-  const content = data.choices?.[0]?.message?.content;
-  if (!content) {
-    throw new Error(`LiteLLM returned no content: ${JSON.stringify(data)}`);
-  }
-  return content;
-}

agent/src/matrixBot.js

@@ -1,23 +1,37 @@
 import { MatrixClient, SimpleFsStorageProvider } from "matrix-bot-sdk";
 import { runChatTask } from "./runner.js";
-import { routeMessage, chatReply } from "./router.js";
+import { askOpenRouter, DEFAULT_MODEL } from "./openrouter.js";
 
 const HOMESERVER_URL = process.env.MATRIX_HOMESERVER_URL;
 const ACCESS_TOKEN = process.env.MATRIX_BOT_TOKEN;
 const CONTROL_ROOM_ID = process.env.MATRIX_CONTROL_ROOM_ID;
 const GITEA_URL = process.env.GITEA_URL;
-// Set explicitly rather than fetched via client.getUserId() — that call hits /whoami,
-// which (like /joined_rooms before it) 404s against Continuwuity for reasons unrelated
-// to the endpoint itself. This is also the only reliable way to filter the bot's own
-// messages now that there's no command prefix to naturally exclude them by.
-const BOT_USER_ID = process.env.MATRIX_BOT_USER_ID;
-const KNOWN_REPOS = (process.env.KNOWN_REPOS || "")
-  .split(",")
-  .map((r) => r.trim())
-  .filter(Boolean);
 
 const MAX_REPLY_LENGTH = 4000;
 
+// "!claude owner/repo do the thing" — everything after the repo slug is the instruction.
+function parseClaudeCommand(text) {
+  const match = text.match(/^!claude\s+([^\s/]+\/[^\s/]+)\s+(.+)$/s);
+  if (!match) return null;
+  const [, repoFullName, instruction] = match;
+  return { repoFullName, instruction: instruction.trim() };
+}
+
+// "!ai <prompt>" uses the default model. "!ai provider/model <prompt>" (first token
+// contains a "/") picks a specific OpenRouter model, e.g. "!ai google/gemini-2.0-flash-001
+// summarize this repo's README".
+function parseAiCommand(text) {
+  const match = text.match(/^!ai\s+(.+)$/s);
+  if (!match) return null;
+  const rest = match[1].trim();
+  const firstSpace = rest.search(/\s/);
+  const firstToken = firstSpace === -1 ? rest : rest.slice(0, firstSpace);
+  if (firstToken.includes("/") && firstSpace !== -1) {
+    return { model: firstToken, prompt: rest.slice(firstSpace + 1).trim() };
+  }
+  return { model: DEFAULT_MODEL, prompt: rest };
+}
+
 function truncate(text) {
   if (text.length <= MAX_REPLY_LENGTH) return text;
   return `${text.slice(0, MAX_REPLY_LENGTH)}\n\n[truncated]`;
@@ -28,14 +42,15 @@ export async function startMatrixBot() {
     console.warn("Matrix env vars not set — skipping bot startup");
     return;
   }
-  if (!BOT_USER_ID) {
-    console.warn("MATRIX_BOT_USER_ID not set — bot could reply to its own messages, skipping startup");
-    return;
-  }
 
   const storage = new SimpleFsStorageProvider("/workspace/matrix-bot-storage.json");
   const client = new MatrixClient(HOMESERVER_URL, ACCESS_TOKEN, storage);
 
+  // Not using AutojoinRoomsMixin: it calls /joined_rooms at startup to build its initial
+  // state, which — like the /whoami call removed earlier — 404s against Continuwuity for
+  // reasons unrelated to the endpoint itself (curling it directly works fine). This
+  // simpler handler does the one thing we actually need — auto-join on invite — without
+  // that startup scan.
   client.on("room.invite", async (roomId) => {
     try {
       await client.joinRoom(roomId);
@@ -45,27 +60,38 @@ export async function startMatrixBot() {
   });
 
   client.on("room.message", async (roomId, event) => {
+    // Invite-only control room enforces who can reach the bot at all; this just scopes
+    // command handling to that one room. No need to fetch/compare the bot's own user ID
+    // to filter out its own messages — its replies never match either command pattern
+    // below, so they're ignored the same as any other non-command message.
     if (roomId !== CONTROL_ROOM_ID) return;
-    if (event.sender === BOT_USER_ID) return;
     const body = event.content?.body;
     if (!body) return;
 
+    const aiCmd = parseAiCommand(body);
+    if (aiCmd) {
       try {
-      const decision = await routeMessage(body, KNOWN_REPOS);
+        const reply = await askOpenRouter(aiCmd.model, aiCmd.prompt);
-
+        await client.sendText(roomId, `[${aiCmd.model}] ${truncate(reply)}`);
-      if (decision.type === "code_task") {
+      } catch (err) {
-        const [owner, repo] = decision.repo.split("/");
+        console.error("openrouter query failed", err);
-        await client.sendText(roomId, `Working on it: ${decision.repo} — ${decision.instruction}`);
+        await client.sendText(roomId, `Failed: ${err.message}`);
-        const cloneUrl = `${GITEA_URL}/${owner}/${repo}.git`;
+      }
-        const pr = await runChatTask({ owner, repo, cloneUrl, instruction: decision.instruction });
-        await client.sendText(roomId, `Opened PR: ${pr.html_url}`);
       return;
     }
 
-      const reply = await chatReply(body);
+    const cmd = parseClaudeCommand(body);
-      await client.sendText(roomId, truncate(reply));
+    if (!cmd) return;
+
+    const [owner, repo] = cmd.repoFullName.split("/");
+    await client.sendText(roomId, `Working on it: ${cmd.repoFullName} — ${cmd.instruction}`);
+
+    try {
+      const cloneUrl = `${GITEA_URL}/${owner}/${repo}.git`;
+      const pr = await runChatTask({ owner, repo, cloneUrl, instruction: cmd.instruction });
+      await client.sendText(roomId, `Opened PR: ${pr.html_url}`);
     } catch (err) {
-      console.error("message handling failed", err);
+      console.error("chat task failed", err);
       await client.sendText(roomId, `Failed: ${err.message}`);
     }
   });

agent/src/openrouter.js

@@ -0,0 +1,37 @@
+const OPENROUTER_API_KEY = process.env.OPENROUTER_API_KEY;
+const DEFAULT_MODEL = process.env.OPENROUTER_DEFAULT_MODEL || "openai/gpt-4o-mini";
+
+export async function askOpenRouter(model, prompt) {
+  if (!OPENROUTER_API_KEY) {
+    throw new Error("OPENROUTER_API_KEY is not set");
+  }
+
+  const res = await fetch("https://openrouter.ai/api/v1/chat/completions", {
+    method: "POST",
+    headers: {
+      Authorization: `Bearer ${OPENROUTER_API_KEY}`,
+      "Content-Type": "application/json",
+    },
+    body: JSON.stringify({
+      model: model || DEFAULT_MODEL,
+      messages: [{ role: "user", content: prompt }],
+      // Some models default max_tokens to their full context window (e.g. 65536),
+      // which can exceed available credit balance before a single token is generated.
+      // This is a quick chat reply, not a long-form task — cap it.
+      max_tokens: 1024,
+    }),
+  });
+
+  if (!res.ok) {
+    throw new Error(`OpenRouter request failed: ${res.status} ${await res.text()}`);
+  }
+
+  const data = await res.json();
+  const content = data.choices?.[0]?.message?.content;
+  if (!content) {
+    throw new Error(`OpenRouter returned no content: ${JSON.stringify(data)}`);
+  }
+  return content;
+}
+
+export { DEFAULT_MODEL };

agent/src/router.js

@@ -1,45 +0,0 @@
-import { chatCompletion } from "./litellm.js";
-
-const ROUTER_MODEL = "router-classifier";
-const CHAT_MODEL = "auto";
-
-function systemPrompt(knownRepos) {
-  return [
-    "You are a routing classifier for a chat bot. Given a user message, decide whether it is:",
-    '- "chat": a question, discussion, or anything that just needs a text reply.',
-    '- "code_task": a request to change a specific code repository (add/edit/fix something)',
-    "  where the repository is clearly one of the known repositories below.",
-    "",
-    `Known repositories: ${knownRepos.join(", ") || "(none configured)"}`,
-    "",
-    "Reply with ONLY a JSON object, nothing else:",
-    '{"type":"chat"}',
-    'or',
-    '{"type":"code_task","repo":"owner/repo","instruction":"clear imperative instruction"}',
-    "",
-    "If it sounds like a code change but you can't confidently match it to one of the known",
-    'repositories, reply {"type":"chat"} instead of guessing.',
-  ].join("\n");
-}
-
-function parseDecision(raw) {
-  try {
-    const cleaned = raw.trim().replace(/^```(?:json)?\n?/, "").replace(/```$/, "");
-    const parsed = JSON.parse(cleaned);
-    if (parsed.type === "code_task" && parsed.repo && parsed.instruction) {
-      return parsed;
-    }
-  } catch {
-    // fall through to chat — an unparseable classification is not a reason to edit a repo
-  }
-  return { type: "chat" };
-}
-
-export async function routeMessage(text, knownRepos) {
-  const raw = await chatCompletion(ROUTER_MODEL, `${systemPrompt(knownRepos)}\n\nMessage: ${text}`);
-  return parseDecision(raw);
-}
-
-export async function chatReply(text) {
-  return chatCompletion(CHAT_MODEL, text);
-}

docker-compose.yml

@@ -36,35 +36,8 @@ services:
       - "traefik.http.routers.matrix.tls.certresolver=letsencrypt"
       - "traefik.http.services.matrix.loadbalancer.server.port=8008"
 
-  litellm:
-    # Pinned deliberately, not :latest or :main-latest — litellm==1.82.7/1.82.8 on PyPI
-    # were compromised with credential-stealing malware in March 2026 (fixed within the
-    # hour, but a floating tag could still land on a bad release in the future). v1.98.0
-    # verified clean as of this writing.
-    image: ghcr.io/berriai/litellm:v1.98.0
-    container_name: litellm
-    restart: unless-stopped
-    environment:
-      OPENROUTER_API_KEY: ${OPENROUTER_API_KEY}
-      LITELLM_MASTER_KEY: ${LITELLM_MASTER_KEY}
-    volumes:
-      # Absolute host path, NOT a repo-relative one — Portainer's git-stack deploy clones
-      # into its own directory (/data/compose/N/) whose checkout doesn't reliably persist
-      # for the container's runtime (see the act_runner config comment below for the same
-      # failure mode). An absolute path on the actual host filesystem always resolves the
-      # same way regardless of which tool ran `docker compose up`. Keep this local clone
-      # (/home/william/gitops-automation) pulled to latest when the config changes.
-      - /home/william/gitops-automation/litellm-config.yaml:/app/config.yaml:ro
-    command: ["--config", "/app/config.yaml", "--port", "4000"]
-    networks:
-      - web
-    # Internal only — no Traefik labels. No reason to expose an LLM gateway holding a
-    # master key and OAuth-forwarding config to the public internet.
-
   claude-agent:
     image: ${GITEA_REGISTRY_IMAGE}
-    depends_on:
-      - litellm
     container_name: claude-agent
     restart: unless-stopped
     # Explicit vars, not env_file: .env — Portainer's git-based stack deploy clones the
@@ -80,13 +53,8 @@ services:
       MATRIX_HOMESERVER_URL: ${MATRIX_HOMESERVER_URL}
       MATRIX_BOT_TOKEN: ${MATRIX_BOT_TOKEN}
       MATRIX_CONTROL_ROOM_ID: ${MATRIX_CONTROL_ROOM_ID}
-      MATRIX_BOT_USER_ID: ${MATRIX_BOT_USER_ID}
+      OPENROUTER_API_KEY: ${OPENROUTER_API_KEY}
-      KNOWN_REPOS: ${KNOWN_REPOS}
+      OPENROUTER_DEFAULT_MODEL: ${OPENROUTER_DEFAULT_MODEL:-openai/gpt-4o-mini}
-      # All model calls now go through the local litellm service, not OpenRouter directly —
-      # one gateway for OpenRouter's models (incl. its auto-router) and, for the
-      # claude-subscription route, Anthropic itself via the forwarded OAuth token above.
-      LITELLM_BASE_URL: http://litellm:4000
-      LITELLM_MASTER_KEY: ${LITELLM_MASTER_KEY}
     volumes:
       - agent_workspace:/workspace
     networks:

litellm-config.yaml

@@ -1,23 +0,0 @@
-model_list:
-  # General chat — OpenRouter's own auto-router picks the best underlying model per prompt.
-  - model_name: auto
-    litellm_params:
-      model: openrouter/openrouter/auto
-      api_key: os.environ/OPENROUTER_API_KEY
-
-  # Cheap/fast model used by the agent's own chat-vs-code-task classifier, not by users directly.
-  - model_name: router-classifier
-    litellm_params:
-      model: openrouter/openai/gpt-4o-mini
-      api_key: os.environ/OPENROUTER_API_KEY
-
-  # 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:
-  master_key: os.environ/LITELLM_MASTER_KEY