chore+docs: config, agent registry, codecontext, v2.6 spec, changelog

Working-tree config/doc changes (.gitignore, CLAUDE.md, AGENTS.md removal + data/AGENTS.md, codecontext Dockerfile/shim — pre-existing) plus this session's v2-6 persistent-agent-sessions openspec proposal/design/tasks (planning only; feature unimplemented, reserves the v2.6.0 tag) and the v2.5.2 CHANGELOG entry.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.codecontextignore

@@ -21,6 +21,7 @@ out/
 .opencode/
 .vscode/
 .idea/
+.claude/worktrees/
 
 # Test artifacts / coverage
 coverage/

.env.example

@@ -11,6 +11,11 @@ POSTGRES_PASSWORD=CHANGE_ME
 # point BooCode at a different SearXNG instance.
 SEARXNG_URL=http://100.114.205.53:8888
 
+# Task model: lightweight model for auto-naming, search rewrite, etc.
+# Direct llama-server instance (NOT llama-swap). Falls back to LLAMA_SWAP_URL
+# with FAST_MODEL when unset.
+# TASK_MODEL_URL=http://100.90.172.55:7995
+
 # v1.13.15-tools: BOOCODE_TOOLS narrows the tool whitelist sent to the LLM.
 # Unset (default) → all tools (~21k schema). Useful primarily for single-purpose
 # sessions where the model only needs read-only filesystem access.

.gitignore

@@ -16,3 +16,4 @@ data/*
 !data/AGENTS.md
 !data/skills/
 !data/mcp.json
+codecontext/fork.tar.gz

AGENTS.md

@@ -1,109 +0,0 @@
-# Agent navigation
-
-Cursor/agent entry point for the BooCode monorepo. **Deep engineering reference:** `CLAUDE.md` (Claude Code). This file is navigation + task routing only.
-
-Last updated: 2026-05-25
-
-## Doc map
-
-| Need | Read |
-|------|------|
-| Commands, gotchas, inference, DB, env | `CLAUDE.md` |
-| Read-only chat behavior | `BOOCHAT.md` |
-| Write tools, dispatch, pending changes | `BOOCODER.md` |
-| Shipped vs planned, version order | `boocode_roadmap.md` |
-| Latest release truth | `CHANGELOG.md` (top entry = current) |
-| System diagram + data flow | `docs/ARCHITECTURE.md` |
-| Current focus / blockers | `CURRENT.md` |
-| Batch convention | `openspec/README.md` |
-| Shipped batch snapshots | `openspec/changes/archived/` |
-| Chat agent personas + tool lists | `data/AGENTS.md` |
-| External repo lift inventory | `boocode_code_review.md` |
-
-## Monorepo layout (actual)
-
-Three **surfaces**, four **packages**. There is no `apps/chat/` directory.
-
-| Surface | Packages | Port | Deploy |
-|---------|----------|------|--------|
-| **BooChat** | `apps/server` (API + inference) + `apps/web` (SPA) | `100.114.205.53:9500` | Docker `boocode` container |
-| **BooTerm** | `apps/booterm` | `100.114.205.53:9501` | Docker `booterm` container |
-| **BooCoder** | `apps/coder` | host `:9502` | systemd `boocoder.service` (not Docker since v2.1.0) |
-
-Shared: Postgres 16 — Docker service `boocode_db`, **database name `boochat`**, host port `127.0.0.1:5500`.
-
-## Task routing
-
-| Task type | Start here |
-|-----------|------------|
-| Chat inference / tools / compaction | `apps/server/src/services/inference/` |
-| WS frames | `apps/server/src/types/ws-frames.ts` + `apps/web/src/api/ws-frames.ts` (keep in sync) |
-| Frontend chat UI | `apps/web/src/components/`, hooks in `apps/web/src/hooks/` |
-| BooCoder write tools / dispatch | `apps/coder/src/` — build server first (`pnpm -C apps/server build`) |
-| Provider picker / external agents | `apps/coder/src/services/provider-registry.ts`, `dispatcher.ts`, `agent-probe.ts` |
-| Terminal panes | `apps/booterm/src/`, frontend `TerminalPane.tsx` |
-| Schema changes | `apps/server/src/schema.sql` + sync `*_STATUSES` in `apps/server/src/types/api.ts` |
-| New batch / feature | `openspec/changes/<slug>/proposal.md` + `tasks.md` (see below) |
-
-## Verification (before claiming done)
-
-```bash
-pnpm -C apps/server test && pnpm -C apps/server build
-npx tsc -p apps/web/tsconfig.app.json --noEmit   # root tsc can miss web errors
-curl http://100.114.205.53:9500/api/health       # Tailscale IP, not localhost:9500
-curl http://100.114.205.53:9502/api/health       # BooCoder on host
-```
-
-Deploy truth beats source-only reads — check running health + `git log --oneline -3`.
-
-## Hard rules (from CLAUDE.md)
-
-- **Do not commit or push** unless Sam explicitly asks.
-- **No app-layer auth** — Authelia at the reverse proxy.
-- **Parts table is source of truth** — read message tool fields from `messages_with_parts` view, write via `insertParts`.
-- **New WS frame type** — update server + web schemas; publish via `publishFrame` / `publishUserFrame` only.
-- **New tool** — own file in `services/`, register in `tools.ts` `ALL_TOOLS`; whitelists derive from there, never hardcoded.
-- **Typecheck web with per-app tsconfig** — root `tsc --noEmit` uses project references and can miss errors.
-- **`includeUsage: true`** on `createOpenAICompatible` in `provider.ts` — do not remove.
-- **Agent dispatch** — direct `spawn`/`exec` on host via `install_path` (v2.1.0+); SSH helpers deprecated.
-- **Event dedup** — server publishes via broker; frontend must not duplicate `sessionEvents.emit` after API calls that already WS-broadcast.
-
-## Using openspec with Cursor
-
-Openspec is a **folder convention**, not a CLI. Use it to give agents a scoped brief before coding.
-
-### When starting a batch
-
-1. Create `openspec/changes/<slug>/` (lowercase-hyphenated, e.g. `v2-2-arena-ui`).
-2. Write `proposal.md` — why, scope, non-goals, dependencies.
-3. Write `tasks.md` — numbered checkbox steps (build + smoke).
-4. Optional `design.md` — schema/API decisions that outlive the batch.
-
-See `openspec/README.md` for the full shape. Shipped pre-v1.13.15 batches live in `openspec/changes/archived/` as snapshots only.
-
-### Prompting an agent
-
-```
-@openspec/changes/<slug>/proposal.md @openspec/changes/<slug>/tasks.md
-Implement tasks 1–3. Server tests must pass. Do not commit.
-```
-
-Attach the spec files with `@` so they load into context. Point at specific code paths when known:
-
-```
-@openspec/changes/v2-x/proposal.md
-Extend apps/coder/src/routes/providers.ts — follow provider-registry.ts patterns.
-```
-
-### After shipping
-
-- Tag: `vMAJOR.MINOR.PATCH-slug`
-- Add entry to top of `CHANGELOG.md`
-- Move or snapshot the openspec folder to `archived/` if you want history preserved
-- Update `CURRENT.md` and `boocode_roadmap.md` shipped table if the batch was roadmap-tracked
-
-### What not to use openspec for
-
-- One-line bug fixes — just describe the bug + file.
-- Exploratory questions — Ask mode + `@CLAUDE.md` is enough.
-- Duplicating `CLAUDE.md` — openspec is per-batch scope, not permanent conventions.

CHANGELOG.md

@@ -2,6 +2,10 @@
 
 All notable changes per release tag. Most recent on top, ordered by tag creation date (which matches the git history). Tag names follow `vMAJOR.MINOR.PATCH-slug` — the slug describes what shipped, so the tag name alone is enough to recall the batch.
 
+## v2.5.2-coder-ux-fixes — 2026-05-29
+
+Working-tree checkpoint bundling this session's fixes with in-progress coder UI work. This session: the BooCoder dispatcher now reacts to new tasks immediately via a Postgres `LISTEN/NOTIFY` (`tasks_new`) AFTER INSERT trigger, with the poll loop kept at 2s as a missed-notification fallback (`dispatcher.ts`, `apps/coder/src/schema.sql`); the mobile nav drawer no longer sticks open after returning to a backgrounded tab — `useViewport` re-syncs on `pageshow`/`visibilitychange`/`resize`/`orientationchange` (iOS reported a stale width on bfcache restore, leaving `isMobile=false`); assistant reasoning renders as a collapsible "Thinking" block in `MessageBubble`, surfacing ACP `agent_thought_chunk` from opencode/goose/qwen and native `reasoning_parts`; paste-to-chip inserts pasted text verbatim instead of wrapping it in a code fence; and a "New file from pasted text" affordance in the RightRail browser queues a `pending_changes` create through the new `POST /api/sessions/:id/pending/create` endpoint, paired with a fix repointing the DiffPanel's dead approve/reject calls to the real `/api/pending/:id/apply` and `/reject` routes. Also carried in the tree but not authored this session: the CoderPane `ChatInput` migration and `AgentComposerBar` refinements, plus backend tweaks to `auto_name`, inference `tool-phase`/`turn`, `secret_guard`, and `provider-registry`. Ships the `v2-6-persistent-agent-sessions` openspec proposal/design/tasks (free agent-switching with per-agent memory, opencode-as-server) as planning docs only — the feature is unimplemented and reserves the `v2.6.0` tag for it. Build green across server/coder/web; server suite 531 passing. (CHANGELOG note: the v2.3–v2.5.1 entries were never backfilled and remain absent above.)
+
 ## v2.2.2-xml-placeholder-reject — 2026-05-26
 
 Reject placeholder XML tool args at parse time in `extractToolCallBlocks` (`xml-parser.ts`). Drops calls when any string arg is `...`, empty/whitespace, `<path>`, `<file>`, `placeholder`, or angle-bracket sentinels; appends the raw XML block to flushed prose instead of silently deleting it. Fixes qwen3.6 answer-then-spurious-tools tail that caused duplicate assistant rows (full answer + failed `xml_call_*` tools + regenerated answer). Four new tests in `xml-parser.test.ts`. Known nit: rejection logs via `console.debug` instead of pino — filed in `docs/DEFERRED-WORK.md` §6 for a later cleanup.

CLAUDE.md

@@ -147,8 +147,9 @@ BooCoder at port 9502: `curl http://100.114.205.53:9502/api/health`. Runs as `bo
 - Deploy: `cd /opt/boocode && docker compose up --build -d` (or `docker compose build --no-cache boocode && docker compose up -d` if you suspect a layer-cache issue).
 - Git push to Gitea: `GIT_SSH_COMMAND="ssh -i /opt/boocode/secrets/boocode_gitea -o IdentitiesOnly=yes" git push origin <branch>`. The default agent identity is rejected; the in-repo deploy key (`secrets/`, gitignored) is the working one. Transient `Connection reset by peer` retries cleanly after `sleep 5`.
 - Don't accumulate `.bak-*` files. Clean them up in the same batch or immediately after merge.
-- DB-integration tests opt-in via env var: `DATABASE_URL='postgres://boocode:devpass@localhost:5500/boochat' pnpm -C apps/server test`. Host port is 5500 (mapped from `boocode_db:5432`); password is `${POSTGRES_PASSWORD}` from `.env` (`devpass`), NOT the literal in `.env`'s `DATABASE_URL=postgres://boocode:Ketchup1479@boocode_db:5432/...` line. Pattern: `describe.runIf(!!process.env.DATABASE_URL)(...)` with a `beforeAll` that applies the schema via `sql.unsafe(readFileSync(schemaPath))`. Tests skip cleanly when var is unset. `tool_cost_stats.test.ts` is the reference.
+- DB-integration tests opt-in via env var: `DATABASE_URL='postgres://boocode:devpass@localhost:5500/boochat' pnpm -C apps/server test`. Host port is 5500 (mapped from `boocode_db:5432`); password is `${POSTGRES_PASSWORD}` from `.env` (`devpass`), NOT the literal in `.env`'s `DATABASE_URL=postgres://boocode:Ketchup1479@boocode_db:5432/...` line. `psql` is not on the host PATH — for an interactive query use `docker exec boocode_db psql -U boocode -d boochat -c "..."`. Pattern: `describe.runIf(!!process.env.DATABASE_URL)(...)` with a `beforeAll` that applies the schema via `sql.unsafe(readFileSync(schemaPath))`. Tests skip cleanly when var is unset. `tool_cost_stats.test.ts` is the reference.
 - Host-side smoke endpoint: `curl http://100.114.205.53:9500/api/...`. The boocode container's port mapping binds to the Tailscale IP, not `0.0.0.0`, so `localhost:9500` doesn't work from the host shell. Same for booterm at `:9501`.
+- Frontend blank-screen / runtime crash: get the stack-trace column offset from the browser console, then `cut -c <start>-<end> apps/web/dist/assets/index-*.js | sed -n '<line>p'` to read the exact minified expression that threw. Faster than bisecting source. Watch for `=== null`/`!== null` on optional fields fed an `as unknown as` cast — those bypass tsc.
 - Fastify global JSON parser tolerates empty bodies (overridden in `index.ts`); bodyless POSTs (archive, unarchive, stop) work without setting `Content-Type` tricks on the client.
 - Event dedup discipline: for any mutation the server publishes via `broker.publishUser`, do NOT add a local `sessionEvents.emit(...)` after the API call — `useUserEvents` forwards the WS frame onto the bus. Frontend mutation handlers must be idempotent (dedup by id, no-op on already-present).
 - `node:20-*` base images ship a `node` user at uid/gid 1000 — delete it (`userdel`/`groupdel` on debian, `deluser`/`delgroup` on alpine) before adding samkintop at 1000.
@@ -157,8 +158,8 @@ BooCoder at port 9502: `curl http://100.114.205.53:9502/api/health`. Runs as `bo
 - A local PreToolUse hook (`security_reminder_hook.py`) regex-flags Node's older `child_process` spawn helpers as unsafe (false positive even on the File-suffixed variant). Use `spawn` — it's accepted.
 - `/opt/boolab` hosts a working sibling BooCode terminal at `boocode.indifferentketchup.com`. Useful for visual side-by-side comparison on the same iPhone when debugging booterm rendering. Boolab uses Tailwind v3 (`@tailwind base`); boocode uses v4 — many subtle build differences. Don't assume parity.
 - booterm SSHs to the host as `samkintop@100.114.205.53` (the Tailscale IP). The hostname `ubuntu-homelab` (shown in the bash prompt after login) does NOT resolve from inside the container — only the host's `/etc/hosts` knows it. Override via `BOOTERM_SSH_HOST` / `BOOTERM_SSH_USER` env vars in docker-compose if you ever move the shell to a different machine.
-- codecontext sidecar lives at `/opt/boocode/codecontext/`. Sidecar HTTP API at `http://codecontext:8080/v1/<tool_name>` over the `boocode_net` bridge (no host port). BooCode wrappers in `apps/server/src/services/tools/codecontext/`. The `.codecontextignore.template` documents recommended ignore patterns; users copy and adapt to project root manually.
+- codecontext sidecar lives at `/opt/boocode/codecontext/`. Sidecar HTTP API at `http://codecontext:8080/v1/<tool_name>` over the `boocode_net` bridge (no host port). BooCode wrappers in `apps/server/src/services/tools/codecontext/`. The `.codecontextignore` at project root is honored when `--respect-gitignore` is passed (enabled in the shim).
-- codecontext fork at `/opt/forks/codecontext/` — separate git repo (branch `boocode-ts`), pushed via the same boocode_gitea SSH key to `indifferentketchup/codecontext`. Build: `go build ./...`. Test: `go test ./...`. Docker rebuild: `docker compose build --no-cache codecontext`.
+- codecontext fork at `/opt/forks/codecontext/` — separate git repo (branch `boocode-ts`), pushed via the same boocode_gitea SSH key to `indifferentketchup/codecontext`. Build: `go build ./...`. Test: `go test ./...`. Docker rebuild requires staging the fork source first: `tar -czf codecontext/fork.tar.gz -C /opt/forks/codecontext --exclude=.git --exclude=bin .` then `docker compose build --no-cache codecontext`. The Dockerfile COPYs `fork.tar.gz` into the builder stage (Gitea is behind Authelia, no HTTP clone). `fork.tar.gz` is gitignored.
 - Go binary: `/snap/go/current/bin/go` (not on PATH by default). Use `export PATH=$PATH:/snap/go/current/bin` or full path for Go commands.
 - `os/exec` child supervisors must explicitly call `child.Wait()` in a goroutine and `os.Exit` on child death. `Signal(0)` returns nil on zombies and is NOT a liveness check. Without `Wait()`, docker's `restart: unless-stopped` policy never fires because the parent stays alive. The `codecontext/shim.go` implementation is the reference pattern.
 
@@ -185,3 +186,11 @@ BooCoder at port 9502: `curl http://100.114.205.53:9502/api/health`. Runs as `bo
 - **Workspace dependency pattern** (`apps/coder` → `@boocode/server`): the consuming package adds `"@boocode/server": "workspace:*"` in `package.json`. The provider's `package.json` needs `exports` with `types` + `default` conditions per subpath: `"./inference": { "types": "./dist/.../index.d.ts", "default": "./dist/.../index.js" }`. Without the `types` condition, NodeNext resolution can't find `.d.ts` files and tsc fails with "Cannot find module" in the consumer.
 - **JSONB columns**: use `sql.json(value as never)` — NOT `${JSON.stringify(value)}::jsonb` which double-serializes (stores a JSON string instead of a JSON object/array). Pattern established in `parts.ts`, `settings.ts`.
 - **`payload.ts:loadContext` SELECT**: must include every `Session` field that downstream code reads. The tool phase reads `session.allowed_read_paths`; if the SELECT omits it, cross-repo read grants silently fail. The `Session` TypeScript type doesn't catch this because `sql<Session[]>` doesn't enforce column coverage.
+- **Sidecar routing** (`services/inference/provider.ts`): `upstreamModel(config, modelId, agent)` routes to `LLAMA_SIDECAR_URL` when agent has `llama_extra_args`, otherwise `LLAMA_SWAP_URL`. `resolveRoute(agent)` returns `{route: 'swap'|'sidecar', flags}`. Sidecar provider created fresh per call (not cached) because `X-Agent-Flags` header varies per agent. Boot-time guard in `index.ts` refuses to start if any agent has `llama_extra_args` but `LLAMA_SIDECAR_URL` is unset.
+- **Secret guard safe patterns** (`services/secret_guard.ts`): `.env.example`, `.env.sample`, `.env.template`, `.env.defaults` are allowlisted via `SAFE_PATTERNS` set. Do NOT add `.env.production`/`.env.development`/`.env.test` — those can hold real secrets.
+- **CoderPane uses ChatInput** (`components/panes/CoderPane.tsx`): shares the same `ChatInput` component as BooChat for full parity — attachments, paste-to-chip, auto-grow textarea, queued messages during send. CoderPane's `sendOneMessage` is the send callback; queued messages drain via `useEffect` when `sending` goes false.
+- **Adding a new `SessionEvent` type**: add the interface, add it to the `SessionEvent` union, add a `case` in `useSidebar.ts` `applyEvent` switch (no-op `return prev` is fine), and subscribe in any hook that needs it (e.g. `useSessionStream` for `refetch_messages`).
+- **BooCoder provider registry** (`apps/coder/src/services/provider-registry.ts`): static list of provider defs (boocode, opencode, goose, claude, qwen). `PROBED_AGENT_NAMES` derives from it. Adding/removing providers means editing this file, not the frontend.
+- **Pane header architecture (mobile vs desktop)**: Desktop coder pane header (BooCode label + [+] [×]) lives in `Workspace.tsx` gated by `isCoder && !isMobile`. Mobile coder controls (● ×) live in `Session.tsx` header row next to `MobileTabSwitcher`/`NewPaneMenu`. `AgentComposerBar` (provider/mode/model pickers) renders inside `CoderPane.tsx` on both. The ● status dot is passed via `connected` prop from CoderPane to AgentComposerBar.
+- **MessageBubble shared between BooChat and BooCoder** (`components/MessageBubble.tsx`): accepts optional `actions?: MessageActions` callbacks (onRegenerate, onResend, onFork, onDelete) and `hideActions?: ('fork'|'delete'|'openInPane')[]`. Defaults use BooChat API; CoderPane overrides via `CoderMessageList` props. `CoderTextBubble` was removed. **`CoderMessageList` passes `CoderMessageWire as unknown as Message`** — the coder wire shape lacks `metadata`/`kind`/`summary`, so those fields are `undefined` (not `null`) on coder messages. Null-guards on any `Message` field MUST use loose `!= null`, not strict `!== null` (`undefined !== null` is `true` → `.kind` throws → blank-screen crash). The `as unknown as` cast hides this from tsc; build + typecheck pass while runtime crashes.
+- **llama-sidecar** (`/opt/forks/llama-sidecar/`): Go daemon for per-agent llama-server process pool. Cross-compile: `GOOS=windows GOARCH=amd64 /snap/go/current/bin/go build -o bin/llama-sidecar.exe ./cmd/llama-sidecar`. Gitea: `indifferentketchup/llama-sidecar`. Windows child process gotchas: use `context.Background()` for child lifetime (not request ctx), `os.Open(os.DevNull)` for stdin, `os.Pipe()` for stdout with drain goroutine, `DETACHED_PROCESS | CREATE_NEW_PROCESS_GROUP` creation flags. SSH to sam-desktop: `ssh samki@100.101.41.16`; use `schtasks` for persistent process spawning (SSH `start /B` doesn't survive session close).

apps/coder/src/routes/pending.ts

@@ -1,4 +1,5 @@
 import type { FastifyInstance } from 'fastify';
+import { z } from 'zod';
 import type { Sql } from '../db.js';
 import {
   listPending,
@@ -6,7 +7,14 @@ import {
   applyAll,
   rejectOne,
   rewindOne,
+  queueCreate,
 } from '../services/pending_changes.js';
+import { WriteGuardError } from '../services/write_guard.js';
+
+const CreateBody = z.object({
+  file_path: z.string().min(1),
+  content: z.string(),
+});
 
 /**
  * Resolve project root from a session's project path.
@@ -51,6 +59,49 @@ export function registerPendingRoutes(app: FastifyInstance, sql: Sql): void {
     },
   );
 
+  // POST /api/sessions/:sessionId/pending/create — queue a new-file create
+  // (manual create from the RightRail file browser; no inference involved).
+  // queueCreate runs resolveWritePath internally, so a path that escapes the
+  // project root or hits a secret file throws WriteGuardError → 422 with the
+  // guard message. Mirrors the { error } 404 shape used by the other routes
+  // and the 422 status used by apply/rewind on failure.
+  app.post<{ Params: { sessionId: string } }>(
+    '/api/sessions/:sessionId/pending/create',
+    async (req, reply) => {
+      const sessionId = req.params.sessionId;
+
+      const parsed = CreateBody.safeParse(req.body);
+      if (!parsed.success) {
+        reply.code(400);
+        return { error: 'invalid body', details: parsed.error.flatten() };
+      }
+
+      const projectRoot = await resolveProjectRoot(sql, sessionId);
+      if (!projectRoot) {
+        reply.code(404);
+        return { error: 'session or project not found' };
+      }
+
+      try {
+        const change = await queueCreate(
+          sql,
+          sessionId,
+          null,
+          parsed.data.file_path,
+          parsed.data.content,
+          projectRoot,
+        );
+        return change;
+      } catch (err) {
+        if (err instanceof WriteGuardError) {
+          reply.code(422);
+          return { error: err.message };
+        }
+        throw err;
+      }
+    },
+  );
+
   // POST /api/sessions/:sessionId/pending/apply — apply all pending changes
   app.post<{ Params: { sessionId: string } }>(
     '/api/sessions/:sessionId/pending/apply',

apps/coder/src/schema.sql

@@ -71,3 +71,22 @@ ALTER TABLE available_agents ADD COLUMN IF NOT EXISTS transport TEXT DEFAULT 'pt
 ALTER TABLE tasks ADD COLUMN IF NOT EXISTS mode_id TEXT;
 ALTER TABLE tasks ADD COLUMN IF NOT EXISTS thinking_option_id TEXT;
 ALTER TABLE tasks ADD COLUMN IF NOT EXISTS feature_values JSONB;
+
+-- LISTEN/NOTIFY fast path: every tasks INSERT (from any call site — routes,
+-- new_task tool, arena, MCP server) fires pg_notify('tasks_new') in the same
+-- transaction, so the dispatcher reacts immediately instead of waiting for the
+-- fallback poll. Postgres holds the notification until COMMIT, so the listener
+-- always sees the committed row. A trigger covers all insert paths with no
+-- app-code drift. Idempotent: re-applied on every startup.
+CREATE OR REPLACE FUNCTION notify_tasks_new() RETURNS trigger AS $$
+BEGIN
+  PERFORM pg_notify('tasks_new', '');
+  RETURN NEW;
+END;
+$$ LANGUAGE plpgsql;
+
+DROP TRIGGER IF EXISTS tasks_notify_new ON tasks;
+CREATE TRIGGER tasks_notify_new
+  AFTER INSERT ON tasks
+  FOR EACH ROW
+  EXECUTE FUNCTION notify_tasks_new();

apps/coder/src/services/dispatcher.ts

@@ -24,16 +24,29 @@ interface Deps {
   config: Config;
 }
 
-const POLL_INTERVAL_MS = 5_000;
+// LISTEN/NOTIFY ('tasks_new') is the fast path — the dispatcher reacts to new
+// tasks immediately. The poll is only a safety net for notifications missed
+// during a listen-connection drop (porsager auto-reconnects), so it can stay slow.
+const POLL_INTERVAL_MS = 2_000;
 const COMPLETION_POLL_MS = 2_000;
 
 export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<void> } {
   const { sql, inference, broker, log, config } = deps;
   let timer: ReturnType<typeof setInterval> | null = null;
+  let listener: { unlisten: () => Promise<void> } | null = null;
   let running = false;
   let stopping = false;
   let inflightPromise: Promise<void> | null = null;
 
+  // Shared entry point for both the poll timer and the NOTIFY listener. poll()'s
+  // `running`/`stopping` guard makes this safe to call concurrently — a notify
+  // arriving mid-task returns immediately and never double-dispatches.
+  function triggerPoll(reason: string): void {
+    poll().catch((err) => {
+      log.error({ err, reason }, 'dispatcher: poll error');
+    });
+  }
+
   async function poll(): Promise<void> {
     if (running || stopping) return;
 
@@ -463,12 +476,28 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
 
   return {
     start() {
-      log.info('dispatcher: starting poll loop');
+      log.info('dispatcher: starting poll loop + tasks_new listener');
-      timer = setInterval(() => {
+
-        poll().catch((err) => {
+      // Fallback poll — catches notifications missed while the listen connection
-          log.error({ err }, 'dispatcher: poll error');
+      // was down. The fast path is the NOTIFY listener below.
+      timer = setInterval(() => triggerPoll('interval'), POLL_INTERVAL_MS);
+
+      // Fast path: react immediately to new tasks. porsager reserves a dedicated
+      // connection and auto-resubscribes on reconnect; the onlisten callback
+      // fires on each (re)subscribe, so we kick a catch-up poll there too to
+      // sweep up anything inserted during a disconnect.
+      sql
+        .listen(
+          'tasks_new',
+          () => triggerPoll('notify'),
+          () => triggerPoll('listen-subscribed'),
+        )
+        .then((meta) => {
+          listener = meta;
+        })
+        .catch((err) => {
+          log.error({ err }, 'dispatcher: failed to LISTEN tasks_new — relying on poll fallback');
         });
-      }, POLL_INTERVAL_MS);
     },
 
     async stop() {
@@ -477,6 +506,12 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
         clearInterval(timer);
         timer = null;
       }
+      if (listener) {
+        await listener.unlisten().catch((err) => {
+          log.error({ err }, 'dispatcher: unlisten error');
+        });
+        listener = null;
+      }
       if (inflightPromise) {
         log.info('dispatcher: waiting for in-flight task');
         await inflightPromise;

apps/coder/src/services/provider-registry.ts

@@ -24,12 +24,6 @@ export const PROVIDERS: ProviderDef[] = [
     transport: 'native',
     modelSource: 'llama-swap',
   },
-  {
-    name: 'cursor',
-    label: 'Cursor Agent',
-    transport: 'acp',
-    modelSource: 'probe',
-  },
   {
     name: 'opencode',
     label: 'OpenCode',
@@ -59,12 +53,6 @@ export const PROVIDERS: ProviderDef[] = [
     transport: 'acp',
     modelSource: 'probe',
   },
-  {
-    name: 'copilot',
-    label: 'GitHub Copilot',
-    transport: 'acp',
-    modelSource: 'probe',
-  },
 ];
 
 export const PROVIDERS_BY_NAME = new Map(PROVIDERS.map((p) => [p.name, p]));

apps/server/src/config.ts

@@ -25,6 +25,8 @@ const ConfigSchema = z.object({
   // v2.0.5: cheaper model for titles, summaries, labeling. Falls back to
   // session model (auto_name) or DEFAULT_MODEL when unset.
   FAST_MODEL: z.string().optional(),
+  TASK_MODEL_URL: z.string().url().optional(),
+  LLAMA_SIDECAR_URL: z.string().url().optional(),
 });
 
 export type Config = z.infer<typeof ConfigSchema>;

apps/server/src/index.ts

@@ -28,7 +28,7 @@ import { cleanupTruncations } from './services/truncate.js';
 import { loadMcpConfig } from './services/mcp-config.js';
 import { initialize as initMcp, getTools as getMcpTools, shutdown as shutdownMcp } from './services/mcp-client.js';
 import { appendMcpTools } from './services/tools.js';
-import { refreshToolNames } from './services/agents.js';
+import { refreshToolNames, getAgentsForProject } from './services/agents.js';
 
 async function main() {
   const config = loadConfig();
@@ -91,6 +91,20 @@ async function main() {
   }
   app.addHook('onClose', async () => { await shutdownMcp(); });
 
+  // Boot-time guard: if any agent has llama_extra_args but LLAMA_SIDECAR_URL
+  // is unset, fail fast. Silent fallback would defeat per-agent flags.
+  if (!config.LLAMA_SIDECAR_URL) {
+    const { agents } = await getAgentsForProject('');
+    const offending = agents.find(a => a.llama_extra_args && a.llama_extra_args.length > 0);
+    if (offending) {
+      app.log.fatal(
+        { agent: offending.name },
+        `Agent "${offending.name}" has llama_extra_args but LLAMA_SIDECAR_URL is not set`,
+      );
+      process.exit(1);
+    }
+  }
+
   await app.register(fastifyWebsocket);
 
   app.get('/api/health', async () => {

apps/server/src/schema.sql

@@ -344,6 +344,7 @@ INSERT INTO settings (key, value) VALUES ('theme_mode', '"dark"') ON CONFLICT (k
 ALTER TABLE projects ADD COLUMN IF NOT EXISTS default_system_prompt TEXT NOT NULL DEFAULT '';
 ALTER TABLE projects ADD COLUMN IF NOT EXISTS default_web_search_enabled BOOLEAN NOT NULL DEFAULT false;
 ALTER TABLE sessions ADD COLUMN IF NOT EXISTS web_search_enabled BOOLEAN;
+ALTER TABLE sessions ADD COLUMN IF NOT EXISTS tags TEXT[] DEFAULT '{}';
 
 -- v1.11: anchored rolling compaction.
 --   compacted_at  — marks rows that are "behind the curtain" of the latest
@@ -366,3 +367,39 @@ ALTER TABLE messages ADD COLUMN IF NOT EXISTS summary BOOLEAN NOT NULL DEFAULT F
 ALTER TABLE messages ADD COLUMN IF NOT EXISTS tail_start_id UUID REFERENCES messages(id) ON DELETE SET NULL;
 ALTER TABLE chats ADD COLUMN IF NOT EXISTS needs_compaction BOOLEAN NOT NULL DEFAULT FALSE;
 CREATE INDEX IF NOT EXISTS idx_messages_chat_compacted ON messages (chat_id, compacted_at);
+
+-- tasks table (provider dispatch, arena)
+CREATE TABLE IF NOT EXISTS tasks (
+  id                UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  project_id        UUID NOT NULL REFERENCES projects(id) ON DELETE CASCADE,
+  session_id        UUID REFERENCES sessions(id) ON DELETE CASCADE,
+  parent_task_id    UUID REFERENCES tasks(id),
+  arena_id          UUID,
+  state             TEXT NOT NULL DEFAULT 'pending'
+                    CHECK (state IN ('pending','running','completed','failed','blocked','cancelled')),
+  input             TEXT NOT NULL,
+  output_summary    TEXT,
+  agent             TEXT,
+  model             TEXT,
+  mode_id           TEXT,
+  thinking_option_id TEXT,
+  feature_values    JSONB,
+  execution_path    TEXT CHECK (execution_path IS NULL OR execution_path IN ('native','acp','pty','qwen')),
+  worktree_path     TEXT,
+  cost_tokens       INTEGER,
+  started_at        TIMESTAMPTZ,
+  ended_at          TIMESTAMPTZ,
+  created_at        TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp()
+);
+
+-- Fix tasks FK to cascade on session delete (existing tables without CASCADE)
+DO $$ BEGIN
+  IF EXISTS (
+    SELECT 1 FROM pg_constraint WHERE conname = 'tasks_session_id_fkey'
+    AND confdeltype != 'c'
+  ) THEN
+    ALTER TABLE tasks DROP CONSTRAINT tasks_session_id_fkey;
+    ALTER TABLE tasks ADD CONSTRAINT tasks_session_id_fkey
+      FOREIGN KEY (session_id) REFERENCES sessions(id) ON DELETE CASCADE;
+  END IF;
+END $$;

apps/server/src/services/__tests__/agent-allowlist.test.ts

@@ -0,0 +1,107 @@
+import { describe, it, expect } from 'vitest';
+import { parseAgentsMd, matchToolGlob } from '../agents.js';
+import { toolJsonSchemas } from '../tools.js';
+
+describe('agent tool allowlist', () => {
+  const plannerMd = `# Agents
+
+## Planner
+---
+temperature: 0.6
+tools: [view_file, grep, list_dir, find_files]
+description: Read-only planner
+---
+You plan.
+`;
+
+  it('parses an agent with a restricted tool allowlist', () => {
+    const { agents, errors } = parseAgentsMd(plannerMd);
+    expect(errors).toHaveLength(0);
+    expect(agents).toHaveLength(1);
+    const planner = agents[0]!;
+    expect(planner.name).toBe('Planner');
+    expect(planner.tools).toEqual(['view_file', 'grep', 'list_dir', 'find_files']);
+  });
+
+  it('stream-phase filter: agent allowlist excludes tools not in the list', () => {
+    const { agents } = parseAgentsMd(plannerMd);
+    const planner = agents[0]!;
+    const allSchemas = toolJsonSchemas();
+    const filtered = allSchemas.filter((t) =>
+      matchToolGlob(t.function.name, planner.tools),
+    );
+    const filteredNames = filtered.map((t) => t.function.name);
+    expect(filteredNames).toContain('view_file');
+    expect(filteredNames).toContain('grep');
+    expect(filteredNames).not.toContain('edit_file');
+    expect(filteredNames).not.toContain('web_search');
+    expect(filteredNames).not.toContain('get_codebase_overview');
+    expect(filtered).toHaveLength(4);
+  });
+
+  it('tool-phase guard: rejects tool call not in agent allowlist', () => {
+    const { agents } = parseAgentsMd(plannerMd);
+    const planner = agents[0]!;
+    expect(matchToolGlob('edit_file', planner.tools)).toBe(false);
+    expect(matchToolGlob('create_file', planner.tools)).toBe(false);
+    expect(matchToolGlob('delete_file', planner.tools)).toBe(false);
+    expect(matchToolGlob('web_search', planner.tools)).toBe(false);
+  });
+
+  it('tool-phase guard: allows tool call in agent allowlist', () => {
+    const { agents } = parseAgentsMd(plannerMd);
+    const planner = agents[0]!;
+    expect(matchToolGlob('view_file', planner.tools)).toBe(true);
+    expect(matchToolGlob('grep', planner.tools)).toBe(true);
+    expect(matchToolGlob('list_dir', planner.tools)).toBe(true);
+    expect(matchToolGlob('find_files', planner.tools)).toBe(true);
+  });
+
+  it('null/absent tools field defaults to all tools (no regression)', () => {
+    const noToolsMd = `# Agents
+
+## Default
+---
+temperature: 0.7
+description: Uses all tools
+---
+Default agent.
+`;
+    const { agents } = parseAgentsMd(noToolsMd);
+    const agent = agents[0]!;
+    const allSchemas = toolJsonSchemas();
+    const filtered = allSchemas.filter((t) =>
+      matchToolGlob(t.function.name, agent.tools),
+    );
+    expect(filtered.length).toBe(allSchemas.length);
+  });
+
+  it('builder agent: write tools filtered out when not in ALL_TOOLS (BooChat context)', () => {
+    const builderMd = `# Agents
+
+## Builder
+---
+temperature: 0.6
+tools: [view_file, grep, list_dir, find_files, edit_file, create_file, delete_file, apply_pending, rewind]
+description: Read and write tools
+---
+You build.
+`;
+    const { agents } = parseAgentsMd(builderMd);
+    const builder = agents[0]!;
+    expect(matchToolGlob('view_file', builder.tools)).toBe(true);
+    expect(matchToolGlob('grep', builder.tools)).toBe(true);
+    // Write tools not in server's ALL_TOOLS are silently filtered during parsing.
+    // In BooCoder context (where ALL_TOOLS includes write tools), they'd be retained.
+    expect(builder.tools).not.toContain('edit_file');
+    expect(builder.tools).not.toContain('create_file');
+    expect(matchToolGlob('web_search', builder.tools)).toBe(false);
+  });
+
+  it('matchToolGlob rejects hallucinated tool against exact allowlist', () => {
+    const allowlist = ['view_file', 'grep', 'list_dir'];
+    expect(matchToolGlob('edit_file', allowlist)).toBe(false);
+    expect(matchToolGlob('rm_rf', allowlist)).toBe(false);
+    expect(matchToolGlob('view_file_extended', allowlist)).toBe(false);
+  });
+});

apps/server/src/services/__tests__/provider.test.ts

@@ -0,0 +1,58 @@
+import { describe, expect, it } from 'vitest';
+import { resolveRoute, upstreamModel } from '../inference/provider.js';
+
+describe('resolveRoute', () => {
+  it('routes to swap when agent is null', () => {
+    expect(resolveRoute(null)).toEqual({ route: 'swap', flags: null });
+  });
+
+  it('routes to swap when agent has no llama_extra_args', () => {
+    expect(resolveRoute({ llama_extra_args: null })).toEqual({ route: 'swap', flags: null });
+  });
+
+  it('routes to swap when agent has empty llama_extra_args', () => {
+    expect(resolveRoute({ llama_extra_args: [] })).toEqual({ route: 'swap', flags: null });
+  });
+
+  it('routes to sidecar when agent has llama_extra_args', () => {
+    const result = resolveRoute({ llama_extra_args: ['--top-k', '20'] });
+    expect(result.route).toBe('sidecar');
+    expect(result.flags).toEqual(['--top-k', '20']);
+  });
+});
+
+describe('upstreamModel', () => {
+  const swapConfig = { LLAMA_SWAP_URL: 'http://localhost:8401' };
+  const fullConfig = {
+    LLAMA_SWAP_URL: 'http://localhost:8401',
+    LLAMA_SIDECAR_URL: 'http://localhost:8402',
+  };
+
+  it('returns a model for swap route (no agent)', () => {
+    const model = upstreamModel(swapConfig, 'test-model');
+    expect(model).toBeDefined();
+    expect((model as any).modelId).toBe('test-model');
+  });
+
+  it('returns a model for swap route (agent without extra args)', () => {
+    const model = upstreamModel(swapConfig, 'test-model', { llama_extra_args: null });
+    expect(model).toBeDefined();
+  });
+
+  it('returns a model for sidecar route', () => {
+    const model = upstreamModel(fullConfig, 'test-model', { llama_extra_args: ['--top-k', '20'] });
+    expect(model).toBeDefined();
+    expect((model as any).modelId).toBe('test-model');
+  });
+
+  it('throws when sidecar route requested but URL missing', () => {
+    expect(() =>
+      upstreamModel(swapConfig, 'test-model', { llama_extra_args: ['--top-k', '20'] }),
+    ).toThrow(/LLAMA_SIDECAR_URL/);
+  });
+
+  it('routes to swap for empty llama_extra_args array', () => {
+    const model = upstreamModel(swapConfig, 'test-model', { llama_extra_args: [] });
+    expect(model).toBeDefined();
+  });
+});

apps/server/src/services/auto_name.ts

@@ -1,9 +1,10 @@
 import type { InferenceContext } from './inference/index.js';
+import { taskModelCompletion } from './task-model.js';
 
 const NAMING_SYSTEM_PROMPT =
-  'You name chat sessions based on what the assistant did. Summarize the topic or outcome — do NOT copy the first few words verbatim. Reply directly with no thinking, reasoning, or explanation. Output ONLY the title, 4 words max, no quotes, no punctuation, no prefix like "Title:".';
+  'You name chat sessions. Reply with ONLY the title. 4 to 6 words. No quotes, no punctuation, no prefix.';
 
-const MAX_TITLE_CHARS = 60;
+const MAX_TITLE_CHARS = 80;
 
 function cleanTitle(raw: string): string {
   let name = raw.trim();
@@ -18,27 +19,7 @@ function cleanTitle(raw: string): string {
   return name;
 }
 
-interface NamingResponse {
+// TODO: wire suggestTags after task model validation
-  choices?: Array<{
-    message?: {
-      content?: string;
-      reasoning_content?: string;
-    };
-  }>;
-}
-
-function pickTitleSource(data: NamingResponse): string {
-  const choice = data.choices?.[0]?.message;
-  if (!choice) return '';
-  if (choice.content && choice.content.trim().length > 0) return choice.content;
-  const reasoning = choice.reasoning_content ?? '';
-  if (reasoning.length === 0) return '';
-  const lines = reasoning
-    .split('\n')
-    .map((l) => l.trim())
-    .filter((l) => l.length > 0);
-  return lines[lines.length - 1] ?? '';
-}
 
 export async function maybeAutoNameChat(
   ctx: InferenceContext,
@@ -64,52 +45,29 @@ export async function maybeAutoNameChat(
   if (!chat) return;
   if (chat.name !== null && chat.name !== '') return;
 
-  const sessionRows = await ctx.sql<{ model: string }[]>`
+  const firstMsgs = await ctx.sql<{ role: string; content: string }[]>`
-    SELECT model FROM sessions WHERE id = ${sessionId}
+    SELECT role, content FROM messages
-  `;
-  // v2.0.5: prefer FAST_MODEL for cheap LLM calls (titles, summaries).
-  const model = ctx.config.FAST_MODEL ?? sessionRows[0]?.model;
-  if (!model) return;
-
-  const assistantMsg = await ctx.sql<{ content: string }[]>`
-    SELECT content FROM messages
     WHERE chat_id = ${chatId}
-      AND role = 'assistant'
+      AND role IN ('user', 'assistant')
-      AND status = 'complete'
+      AND status IN ('complete', 'ok')
       AND content <> ''
     ORDER BY created_at ASC
-    LIMIT 1
+    LIMIT 2
   `;
-  if (!assistantMsg[0]) return;
+  const userMsg = firstMsgs.find(m => m.role === 'user');
+  const assistantMsg = firstMsgs.find(m => m.role === 'assistant');
+  if (!assistantMsg) return;
 
-  const assistantText = assistantMsg[0].content.slice(0, 2000);
+  let namingInput = '';
+  if (userMsg) namingInput += `User: ${userMsg.content.slice(0, 1000)}\n\n`;
+  namingInput += `Assistant: ${assistantMsg.content.slice(0, 1000)}`;
 
-  const body = {
+  const raw = await taskModelCompletion({
-    model,
+    system: NAMING_SYSTEM_PROMPT,
-    messages: [
+    user: namingInput,
-      { role: 'system', content: NAMING_SYSTEM_PROMPT },
+    maxTokens: 30,
-      {
-        role: 'user',
-        content: assistantText,
-      },
-    ],
-    max_tokens: 30,
     temperature: 0.3,
-    stream: false,
-    chat_template_kwargs: { enable_thinking: false },
-  };
-
-  const res = await fetch(`${ctx.config.LLAMA_SWAP_URL}/v1/chat/completions`, {
-    method: 'POST',
-    headers: { 'Content-Type': 'application/json' },
-    body: JSON.stringify(body),
   });
-  if (!res.ok) {
-    const text = await res.text().catch(() => '');
-    throw new Error(`naming request failed: ${res.status} ${text.slice(0, 200)}`);
-  }
-  const data = (await res.json()) as NamingResponse;
-  const raw = pickTitleSource(data);
   const name = cleanTitle(raw);
   if (!name) {
     ctx.log.warn({ chatId, raw }, 'auto-name: empty title from model');

apps/server/src/services/inference/budget.ts

@@ -18,9 +18,9 @@ import { READ_ONLY_TOOL_NAMES } from '../tools.js';
 // turns + deeper exploration without changing the safety floor materially —
 // the doom-loop guard (3 identical calls → abort) catches the actual failure
 // mode this cap was guarding against.
-export const BUDGET_READ_ONLY = 50;
+export const BUDGET_READ_ONLY = 100;
-export const BUDGET_NON_READ_ONLY = 10;
+export const BUDGET_NON_READ_ONLY = 100;
-export const BUDGET_NO_AGENT = 50;
+export const BUDGET_NO_AGENT = 100;
 
 const READ_ONLY_SET: ReadonlySet<string> = new Set(READ_ONLY_TOOL_NAMES);
 

apps/server/src/services/inference/provider.ts

@@ -1,37 +1,84 @@
 import { createOpenAICompatible } from '@ai-sdk/openai-compatible';
 import type { LanguageModel } from 'ai';
 
-// TODO: When per-agent llama-server flag overrides are added, route them
-// through validateExtraArgs (./llama-args-validator.ts) first.
-
 // v1.13.1-A: AI SDK provider against llama-swap. baseURL is threaded from
 // config.LLAMA_SWAP_URL at call time (not module-load) so tests can stub the
 // upstream without touching env vars. No apiKey — llama-swap is unauth in our
 // Tailscale topology and exposing it over the public internet is gated by
 // Authelia at the Caddy layer, not by API keys.
+//
+// v2.4.1-sidecar: when the agent has llama_extra_args, route through
+// llama-sidecar instead. A fresh provider is created per call (not cached)
+// because the X-Agent-Flags header varies per agent. The llama-swap path
+// stays cached since it has no per-request headers.
 
-const cache = new Map<string, ReturnType<typeof createOpenAICompatible>>();
+const swapCache = new Map<string, ReturnType<typeof createOpenAICompatible>>();
 
-function getProvider(baseURL: string): ReturnType<typeof createOpenAICompatible> {
+function getSwapProvider(baseURL: string): ReturnType<typeof createOpenAICompatible> {
-  let provider = cache.get(baseURL);
+  let provider = swapCache.get(baseURL);
   if (!provider) {
     provider = createOpenAICompatible({
       name: 'llama-swap',
       baseURL: baseURL.endsWith('/v1') ? baseURL : `${baseURL}/v1`,
-      // v1.13.7: @ai-sdk/openai-compatible defaults includeUsage=false, which
-      // omits `stream_options.include_usage` from the request body. Without
-      // it, llama.cpp / llama-swap never emits the trailing usage block, so
-      // `result.usage` resolves with inputTokens=outputTokens=undefined and
-      // tokens_used / ctx_used land as NULL in every messages row. Setting
-      // true here re-enables the per-stream usage payload across all models
-      // served via the llama-swap provider.
       includeUsage: true,
     });
-    cache.set(baseURL, provider);
+    swapCache.set(baseURL, provider);
   }
   return provider;
 }
 
-export function upstreamModel(baseURL: string, modelId: string): LanguageModel {
+function sidecarProvider(
-  return getProvider(baseURL).chatModel(modelId);
+  baseURL: string,
+  flags: string[],
+): ReturnType<typeof createOpenAICompatible> {
+  return createOpenAICompatible({
+    name: 'llama-sidecar',
+    baseURL: baseURL.endsWith('/v1') ? baseURL : `${baseURL}/v1`,
+    includeUsage: true,
+    headers: {
+      'X-Agent-Flags': flags.join(' '),
+    },
+  });
+}
+
+export type InferenceRoute = 'swap' | 'sidecar';
+
+export interface RoutingInfo {
+  route: InferenceRoute;
+  flags: string[] | null;
+}
+
+interface AgentLike {
+  llama_extra_args: string[] | null;
+}
+
+interface ConfigLike {
+  LLAMA_SWAP_URL: string;
+  LLAMA_SIDECAR_URL?: string;
+}
+
+export function resolveRoute(agent: AgentLike | null): RoutingInfo {
+  const flags = agent?.llama_extra_args;
+  if (flags && flags.length > 0) {
+    return { route: 'sidecar', flags };
+  }
+  return { route: 'swap', flags: null };
+}
+
+export function upstreamModel(
+  config: ConfigLike,
+  modelId: string,
+  agent?: AgentLike | null,
+): LanguageModel {
+  const { route, flags } = resolveRoute(agent ?? null);
+  if (route === 'sidecar') {
+    const url = config.LLAMA_SIDECAR_URL;
+    if (!url) {
+      throw new Error(
+        `Agent has llama_extra_args but LLAMA_SIDECAR_URL is not set`,
+      );
+    }
+    return sidecarProvider(url, flags!).chatModel(modelId);
+  }
+  return getSwapProvider(config.LLAMA_SWAP_URL).chatModel(modelId);
 }

apps/server/src/services/inference/stream-phase.ts

@@ -157,7 +157,8 @@ export async function streamCompletion(
   opts: StreamOptions,
   onDelta: (content: string) => void,
   onUsage: ((prompt: number | null, completion: number | null) => void) | undefined,
-  signal?: AbortSignal
+  signal?: AbortSignal,
+  agent?: Agent | null,
 ): Promise<StreamResult> {
   const aiMessages = toModelMessages(messages);
   const hasTools = opts.tools !== null && opts.tools.length > 0;
@@ -195,7 +196,7 @@ export async function streamCompletion(
   };
 
   const result = streamText({
-    model: upstreamModel(ctx.config.LLAMA_SWAP_URL, model),
+    model: upstreamModel(ctx.config, model, agent ?? null),
     messages: aiMessages,
     ...(aiTools
       ? { tools: aiTools, toolChoice: 'auto' as const, experimental_repairToolCall: repairToolCall }
@@ -458,7 +459,8 @@ export async function executeStreamPhase(
           }, USAGE_THROTTLE_MS - elapsed);
         }
       },
-      signal
+      signal,
+      agent,
     );
   } finally {
     if (pendingFlushTimer) {

apps/server/src/services/inference/tool-phase.ts

@@ -1,7 +1,8 @@
-import type { Session, ToolCall } from '../../types/api.js';
+import type { Agent, Session, ToolCall } from '../../types/api.js';
 import * as modelContext from '../model-context.js';
 import { PathScopeError } from '../path_guard.js';
 import { TOOLS_BY_NAME } from '../tools.js';
+import { matchToolGlob } from '../agents.js';
 import { maybeFlagForCompaction } from './payload.js';
 import { insertParts, partsFromAssistantMessage, partsFromToolMessage } from './parts.js';
 // v1.13.16: richer unknown-tool error so the model can self-correct when it
@@ -98,7 +99,8 @@ export async function executeToolPhase(
   result: StreamResult,
   startedAt: string | null,
   session: Session,
-  projectRoot: string
+  projectRoot: string,
+  agent?: Agent | null,
 ): Promise<ToolPhaseResult> {
   const { sessionId, chatId, assistantMessageId } = args;
   const content = stripToolMarkup(result.content, { final: true });
@@ -262,6 +264,31 @@ export async function executeToolPhase(
         );
         return;
       }
+      if (agent && !matchToolGlob(tc.name, agent.tools)) {
+        const stored = {
+          tool_call_id: tc.id,
+          output: null,
+          truncated: false,
+          error: `tool '${tc.name}' is not allowed for agent '${agent.name}'`,
+        };
+        await insertParts(
+          ctx.sql,
+          partsFromToolMessage({ tool_results: stored }).map((p) => ({
+            ...p,
+            message_id: toolMessageId,
+          })),
+        );
+        ctx.publish(sessionId, {
+          type: 'tool_result',
+          tool_message_id: toolMessageId,
+          chat_id: chatId,
+          tool_call_id: tc.id,
+          output: stored.output,
+          truncated: false,
+          error: stored.error,
+        });
+        return;
+      }
       const tres = await executeToolCall(projectRoot, tc, session.allowed_read_paths);
       if (SYNTHESIS_TOOLS.has(tc.name)) {
         synthEntries.push({ tc, output: tres.output, ...(tres.error ? { error: tres.error } : {}) });

apps/server/src/services/inference/turn.ts

@@ -14,6 +14,7 @@ import type {
 import { ALL_TOOLS } from '../tools.js';
 import { resolveProjectRoot } from '../path_guard.js';
 import { maybeAutoNameChat } from '../auto_name.js';
+import { rewriteSearchQuery } from '../task-search-rewrite.js';
 import { getAgentById } from '../agents.js';
 import * as compaction from '../compaction.js';
 import type { Broker } from '../broker.js';
@@ -254,6 +255,16 @@ export async function runAssistantTurn(
     const webToolsEnabled =
       iterSession.web_search_enabled ?? iterProject.default_web_search_enabled ?? false;
 
+    if (stepNumber === 0 && webToolsEnabled && messages.length >= 2) {
+      const lastUserMsg = [...messages].reverse().find((m) => m.role === 'user');
+      if (lastUserMsg?.content) {
+        const hint = await rewriteSearchQuery(lastUserMsg.content);
+        if (hint && messages[0]?.role === 'system' && messages[0].content) {
+          messages[0].content += `\n\nThe user's search intent can be summarized as: "${hint}"`;
+        }
+      }
+    }
+
     const iterArgs: TurnArgs = { sessionId, chatId, assistantMessageId, toolsUsed, recentToolCalls, signal };
     const state: StreamPhaseState = { accumulated: '', startedAt: null };
     let result: StreamResult;
@@ -281,7 +292,7 @@ export async function runAssistantTurn(
     // ---- tool phase ----
     let toolPhaseResult: ToolPhaseResult;
     try {
-      toolPhaseResult = await executeToolPhase(ctx, iterArgs, result, state.startedAt, iterSession, projectRoot);
+      toolPhaseResult = await executeToolPhase(ctx, iterArgs, result, state.startedAt, iterSession, projectRoot, agent);
     } catch (err) {
       // Tool phase errors are unexpected (individual tool failures are
       // caught inside executeToolPhase). Log and break.

apps/server/src/services/secret_guard.ts

@@ -163,6 +163,13 @@ const COMPILED: ReadonlyArray<CompiledPattern> = DEFAULT_SECURITY_IGNORE_FILETYP
 // Returns true when `relPath` matches a known-secret pattern. Case-insensitive
 // (regex 'i' flag). Always normalize path separators to `/` so Windows-origin
 // paths match the same patterns. Empty or root-only paths return false.
+const SAFE_PATTERNS: ReadonlySet<string> = new Set([
+  '.env.example',
+  '.env.sample',
+  '.env.template',
+  '.env.defaults',
+]);
+
 export function isSecretPath(relPath: string): boolean {
   if (!relPath) return false;
   const normalized = relPath.replace(/\\/g, '/');
@@ -170,6 +177,8 @@ export function isSecretPath(relPath: string): boolean {
   if (segments.length === 0) return false;
   const base = segments[segments.length - 1]!;
 
+  if (SAFE_PATTERNS.has(base.toLowerCase())) return false;
+
   for (const compiled of COMPILED) {
     if (compiled.mode === 'basename') {
       if (compiled.regex.test(base)) return true;

apps/server/src/services/system-prompt.ts

@@ -21,6 +21,7 @@ import { createHash } from 'node:crypto';
 import { readFile, stat } from 'node:fs/promises';
 import type { Agent, Project, Session } from '../types/api.js';
 import { getAgentsMtimes } from './agents.js';
+import { resolveRoute } from './inference/provider.js';
 
 const BASE_SYSTEM_PROMPT = (projectPath: string) =>
   `You are BooCode Chat, a code investigation assistant. The user is working on a project located at ${projectPath}. Use the file-read tools (view_file, list_dir, grep, find_files) to investigate code when needed. Be concise. Cite file paths and line numbers when discussing code. Do not hallucinate file contents — read the file first. Tool results may be truncated; if so, narrow your query rather than guessing.`;
@@ -98,6 +99,7 @@ export interface PrefixFingerprint {
   has_agent_system_prompt: boolean;
   has_session_override: boolean;
   has_project_override: boolean;
+  route: 'swap' | 'sidecar';
 }
 
 export interface PrefixDrift {
@@ -125,6 +127,7 @@ interface ObservedInputs {
   has_agent_system_prompt: boolean;
   has_session_override: boolean;
   has_project_override: boolean;
+  route: 'swap' | 'sidecar';
 }
 
 interface ObserverEntry {
@@ -183,6 +186,7 @@ export async function buildSystemPromptWithFingerprint(
     has_agent_system_prompt: !!(agent && agent.system_prompt.trim().length > 0),
     has_session_override: sessionPrompt.length > 0,
     has_project_override: projectPrompt.length > 0,
+    route: resolveRoute(agent).route,
   };
 
   const fingerprint: PrefixFingerprint = {
@@ -199,6 +203,7 @@ export async function buildSystemPromptWithFingerprint(
     has_agent_system_prompt: inputs.has_agent_system_prompt,
     has_session_override: inputs.has_session_override,
     has_project_override: inputs.has_project_override,
+    route: inputs.route,
   };
 
   let drift: PrefixDrift | null = null;

apps/server/src/services/task-model.ts

@@ -0,0 +1,68 @@
+import { loadConfig, type Config } from '../config.js';
+
+const TIMEOUT_MS = 10_000;
+
+export async function taskModelCompletion(opts: {
+  system: string;
+  user: string;
+  maxTokens?: number;
+  temperature?: number;
+  fallbackModel?: string;
+}): Promise<string> {
+  const config = loadConfig();
+  const maxTokens = opts.maxTokens ?? 30;
+  const temperature = opts.temperature ?? 0.3;
+
+  const { url, model } = resolveEndpoint(config, opts.fallbackModel);
+
+  try {
+    const res = await fetch(`${url}/v1/chat/completions`, {
+      method: 'POST',
+      headers: { 'Content-Type': 'application/json' },
+      body: JSON.stringify({
+        model,
+        messages: [
+          { role: 'system', content: opts.system },
+          { role: 'user', content: opts.user },
+        ],
+        max_tokens: maxTokens,
+        temperature,
+        stream: false,
+        chat_template_kwargs: { enable_thinking: false },
+      }),
+      signal: AbortSignal.timeout(TIMEOUT_MS),
+    });
+    if (!res.ok) {
+      const text = await res.text().catch(() => '');
+      console.warn(`task-model: ${res.status} ${text.slice(0, 200)}`);
+      return '';
+    }
+    const data = (await res.json()) as {
+      choices?: Array<{
+        message?: { content?: string; reasoning_content?: string };
+      }>;
+    };
+    const choice = data.choices?.[0]?.message;
+    if (!choice) return '';
+    const content = (choice.content ?? '').trim();
+    if (content.length > 0) return content;
+    const reasoning = choice.reasoning_content ?? '';
+    if (reasoning.length === 0) return '';
+    const lines = reasoning.split('\n').map((l) => l.trim()).filter((l) => l.length > 0);
+    return lines[lines.length - 1] ?? '';
+  } catch (err) {
+    console.warn('task-model: request failed', err);
+    return '';
+  }
+}
+
+function resolveEndpoint(
+  config: Config,
+  fallbackModel?: string,
+): { url: string; model: string } {
+  if (config.TASK_MODEL_URL) {
+    return { url: config.TASK_MODEL_URL, model: 'gemma-3-270m-it' };
+  }
+  const model = config.FAST_MODEL ?? fallbackModel ?? config.DEFAULT_MODEL;
+  return { url: config.LLAMA_SWAP_URL, model };
+}

apps/server/src/services/task-search-rewrite.ts

@@ -0,0 +1,19 @@
+import { taskModelCompletion } from './task-model.js';
+
+const SYSTEM_PROMPT =
+  'You rewrite user messages into concise web search queries. Reply with ONLY the search query. 3 to 6 words. No quotes, no explanation.';
+
+const MAX_INPUT_CHARS = 500;
+const FALLBACK_CHARS = 60;
+
+export async function rewriteSearchQuery(userMessage: string): Promise<string> {
+  const input = userMessage.slice(0, MAX_INPUT_CHARS);
+  const result = await taskModelCompletion({
+    system: SYSTEM_PROMPT,
+    user: input,
+    maxTokens: 20,
+    temperature: 0.2,
+  });
+  if (result.length > 0) return result;
+  return userMessage.slice(0, FALLBACK_CHARS).trim();
+}

apps/server/src/services/task-summary.ts

@@ -0,0 +1,24 @@
+import { taskModelCompletion } from './task-model.js';
+
+const SYSTEM_PROMPT =
+  'Summarize this conversation in one sentence, 15 words max. No quotes, no prefix.';
+
+const MAX_INPUT_CHARS = 1000;
+
+export async function oneLineSummary(
+  messages: Array<{ role: string; content: string }>,
+): Promise<string> {
+  const lastPairs = messages.slice(-6);
+  let input = lastPairs
+    .map((m) => `${m.role}: ${m.content}`)
+    .join('\n');
+  if (input.length > MAX_INPUT_CHARS) {
+    input = input.slice(0, MAX_INPUT_CHARS);
+  }
+  return taskModelCompletion({
+    system: SYSTEM_PROMPT,
+    user: input,
+    maxTokens: 30,
+    temperature: 0.3,
+  });
+}

apps/server/src/services/task-tags.ts

@@ -0,0 +1,22 @@
+import { taskModelCompletion } from './task-model.js';
+
+const SYSTEM_PROMPT =
+  'You tag chat sessions. Reply with 1 to 3 lowercase tags separated by commas. Tags should describe the topic. No explanation. Examples: "docker, deployment", "python, debugging", "react, styling".';
+
+export async function suggestTags(
+  userMessage: string,
+  assistantReply: string,
+): Promise<string[]> {
+  const input = `User: ${userMessage.slice(0, 300)}\nAssistant: ${assistantReply.slice(0, 300)}`;
+  const result = await taskModelCompletion({
+    system: SYSTEM_PROMPT,
+    user: input,
+    maxTokens: 30,
+    temperature: 0.3,
+  });
+  if (result.length === 0) return [];
+  return result
+    .split(',')
+    .map((t) => t.trim().toLowerCase())
+    .filter((t) => t.length > 0 && t.length <= 30);
+}

apps/web/src/App.tsx

@@ -33,7 +33,7 @@ function RightRailForSession({ sessionId }: { sessionId: string }) {
   // a right-side drawer toggled by the header's FolderTree button (via
   // useRightRailDrawer). On desktop, it renders inline as before with its
   // own internal open/close state.
-  return <RightRail projectId={projectId} />;
+  return <RightRail projectId={projectId} sessionId={sessionId} />;
 }
 
 function MobileBackdrop() {

apps/web/src/api/client.ts

@@ -346,6 +346,23 @@ export const api = {
           user_message: userMessage,
         }),
       }),
+    // Queue a new-file create from the RightRail browser → BooCoder
+    // pending_changes (operation='create'). Surfaces in the CoderPane DiffPanel
+    // for explicit apply. A WriteGuardError comes back as a 422 whose { error }
+    // body ApiError exposes as .message for inline display.
+    createPendingFile: (sessionId: string, file_path: string, content: string) =>
+      request<{
+        id: string;
+        session_id: string;
+        task_id: string | null;
+        file_path: string;
+        operation: string;
+        status: string;
+        created_at: string;
+      }>(`/api/coder/sessions/${sessionId}/pending/create`, {
+        method: 'POST',
+        body: JSON.stringify({ file_path, content }),
+      }),
   },
 
   agents: {

apps/web/src/api/types.ts

@@ -182,10 +182,14 @@ export interface Message {
   // majority of messages.
   metadata: MessageMetadata | null;
   // v1.13.1-C: reasoning content captured from models that stream reasoning
-  // tokens separately (qwen3.6 etc.). Backend populates from message_parts;
+  // tokens separately (qwen3.6 etc.) and from external agents over ACP
-  // optional on the wire — frontend doesn't render this yet (reserved for
+  // (agent_thought_chunk). Backend populates from message_parts; rendered by
-  // a v1.14 UI surface).
+  // MessageBubble as a collapsible "Thinking" block.
   reasoning_parts?: Array<{ text: string }> | null;
+  // Coder wire shape pre-joins reasoning_parts into a single string
+  // (CoderPane/CoderMessageList) and streams it live via reasoning_delta
+  // frames. MessageBubble reads whichever of the two is present.
+  reasoning_text?: string | null;
   // v1.11: anchored rolling compaction fields. Optional on the wire so that
   // older API responses (or test fixtures) parse without explicit nulls.
   //   summary       — true on the assistant row that holds the active

apps/web/src/components/AgentCommandsHint.tsx

@@ -9,6 +9,7 @@ interface Props {
 
 export function AgentCommandsHint({ commands }: Props) {
   const [open, setOpen] = useState(false);
+  const [expanded, setExpanded] = useState<string | null>(null);
 
   if (commands.length === 0) return null;
 
@@ -25,10 +26,19 @@ export function AgentCommandsHint({ commands }: Props) {
       {open && (
         <ul className="px-2 pb-2 space-y-1 border-t border-border/40 max-h-48 overflow-y-auto overscroll-contain touch-pan-y">
           {commands.map((cmd) => (
-            <li key={cmd.name} className="font-mono">
+            <li
-              <span className="text-primary/80">/{cmd.name}</span>
+              key={cmd.name}
+              className="cursor-pointer"
+              onClick={() => setExpanded((v) => v === cmd.name ? null : cmd.name)}
+            >
+              <span className="font-mono text-primary/80">/{cmd.name}</span>
               {cmd.description && (
-                <span className="ml-1.5 text-muted-foreground font-sans line-clamp-1">{cmd.description}</span>
+                <span className={cn(
+                  'ml-1.5 text-muted-foreground font-sans',
+                  expanded === cmd.name ? '' : 'line-clamp-2',
+                )}>
+                  {cmd.description}
+                </span>
               )}
             </li>
           ))}

apps/web/src/components/AgentComposerBar.tsx

@@ -1,5 +1,6 @@
 import { useEffect, useMemo, useRef, useState } from 'react';
-import { Check, ChevronDown, RefreshCw, Shield, Cpu, Brain } from 'lucide-react';
+import { Check, ChevronDown, RefreshCw, Shield, Brain, Bird, Bot, Dog, Terminal as TermIcon } from 'lucide-react';
+import { ClaudeIcon, OpenCodeIcon } from '@/components/icons/ProviderIcons';
 import { api } from '@/api/client';
 import type { AgentSessionConfig, ProviderSnapshotEntry, AgentCommand } from '@/api/types';
 import { useProviderSnapshot, refreshProviderSnapshot } from '@/hooks/useProviderSnapshot';
@@ -125,9 +126,11 @@ function CompactPicker({ label, value, disabled, options, onPick, icon }: Picker
           disabled={disabled}
           onClick={() => setOpen(true)}
           aria-label={`${label}: ${currentLabel}`}
-          className="inline-flex items-center justify-center min-h-[44px] min-w-[44px] rounded text-muted-foreground hover:text-foreground disabled:opacity-40"
+          className="inline-flex items-center gap-1 min-h-[44px] px-1.5 rounded text-xs text-muted-foreground hover:text-foreground disabled:opacity-40"
         >
-          {icon ?? <Cpu className="size-4" />}
+          {icon}
+          <span className="truncate max-w-[120px]">{currentLabel}</span>
+          <ChevronDown className="size-3 opacity-70 shrink-0" />
         </button>
         <BottomSheet open={open} onClose={() => setOpen(false)} title={label}>
           <div className="px-2">{list}</div>
@@ -142,16 +145,16 @@ function CompactPicker({ label, value, disabled, options, onPick, icon }: Picker
         <button
           type="button"
           disabled={disabled}
-          className="text-xs font-mono text-muted-foreground hover:text-foreground flex items-center gap-1 px-1.5 py-0.5 rounded hover:bg-muted/60 disabled:opacity-40 max-w-[140px]"
+          className="text-xs text-muted-foreground hover:text-foreground flex items-center gap-1 px-1.5 py-0.5 rounded hover:bg-muted/60 disabled:opacity-40"
         >
           {icon}
-          <span className="truncate">{currentLabel}</span>
+          <span className="truncate max-w-[180px]">{currentLabel}</span>
           <ChevronDown className="size-3 opacity-70 shrink-0" />
         </button>
       </DropdownMenuTrigger>
       <DropdownMenuContent align="start" className="max-h-64 overflow-y-auto min-w-[160px]">
         {options.map((o) => (
-          <DropdownMenuItem key={o.id} onSelect={() => onPick(o.id)} className="font-mono text-xs">
+          <DropdownMenuItem key={o.id} onSelect={() => onPick(o.id)} className="text-xs">
             <Check className={cn('size-3 shrink-0', o.id === value ? 'opacity-100' : 'opacity-0')} />
             {o.label}
           </DropdownMenuItem>
@@ -166,9 +169,10 @@ interface Props {
   value: AgentSessionConfig;
   onChange: (next: AgentSessionConfig) => void;
   onProviderCommandsChange?: (commands: AgentCommand[]) => void;
+  connected?: boolean;
 }
 
-export function AgentComposerBar({ projectPath, value, onChange, onProviderCommandsChange }: Props) {
+export function AgentComposerBar({ projectPath, value, onChange, onProviderCommandsChange, connected }: Props) {
   const allEntries = useProviderSnapshot(projectPath);
   const entries = useMemo(
     () => allEntries?.filter((e) => e.installed && e.status !== 'error') ?? null,
@@ -255,6 +259,16 @@ export function AgentComposerBar({ projectPath, value, onChange, onProviderComma
     );
   }
 
+  const providerIcon = (name: string) => {
+    switch (name) {
+      case 'claude': return <ClaudeIcon size={13} className="shrink-0" />;
+      case 'opencode': return <OpenCodeIcon size={13} className="shrink-0" />;
+      case 'goose': return <Bird size={13} className="shrink-0" />;
+      case 'qwen': return <TermIcon size={13} className="shrink-0" />;
+      default: return <Dog size={13} className="shrink-0" />;
+    }
+  };
+
   const providerOptions = entries.map((e) => ({ id: e.name, label: e.label }));
   const modeOptions = (currentEntry?.modes ?? []).map((m) => ({ id: m.id, label: m.label }));
   const modelOptions = (currentEntry?.models ?? []).map((m) => ({ id: m.id, label: m.label }));
@@ -267,7 +281,7 @@ export function AgentComposerBar({ projectPath, value, onChange, onProviderComma
         value={value.provider}
         options={providerOptions}
         onPick={pickProvider}
-        icon={<Cpu className="size-3 shrink-0" />}
+        icon={providerIcon(value.provider)}
       />
       <CompactPicker
         label="Mode"
@@ -283,6 +297,7 @@ export function AgentComposerBar({ projectPath, value, onChange, onProviderComma
         disabled={modelOptions.length === 0}
         options={modelOptions}
         onPick={pickModel}
+        icon={<Bot size={13} className="shrink-0" />}
       />
       {thinkingOpts.length > 0 && (
         <CompactPicker
@@ -293,11 +308,17 @@ export function AgentComposerBar({ projectPath, value, onChange, onProviderComma
           icon={<Brain className="size-3 shrink-0" />}
         />
       )}
+      {connected !== undefined && (
+        <span
+          className={cn('inline-block w-1.5 h-1.5 rounded-full shrink-0 ml-auto', connected ? 'bg-green-500' : 'bg-red-500')}
+          title={connected ? 'Connected' : 'Disconnected'}
+        />
+      )}
       <button
         type="button"
         onClick={() => void handleRefresh()}
         disabled={refreshing}
-        className="ml-auto inline-flex items-center justify-center size-7 max-md:min-h-[44px] max-md:min-w-[44px] rounded text-muted-foreground hover:text-foreground disabled:opacity-40"
+        className={cn('inline-flex items-center justify-center size-7 max-md:min-h-[44px] max-md:min-w-[44px] rounded text-muted-foreground hover:text-foreground disabled:opacity-40', connected === undefined && 'ml-auto')}
         aria-label="Refresh provider list"
         title="Refresh providers"
       >

apps/web/src/components/ChatInput.tsx

@@ -22,6 +22,7 @@ import { AttachmentPreviewModal } from '@/components/AttachmentPreviewModal';
 import { FileMentionPopover } from '@/components/FileMentionPopover';
 import { DropOverlay } from '@/components/DropOverlay';
 import { AgentPicker } from '@/components/AgentPicker';
+import { AgentCommandsHint } from '@/components/AgentCommandsHint';
 import { ContextBar } from '@/components/ContextBar';
 import { SlashCommandPicker } from '@/components/SlashCommandPicker';
 import { isSlashCommandToken, parseSlashInput, slashQuery } from '@/lib/slash-command';
@@ -560,6 +561,9 @@ export function ChatInput({ disabled, projectId, agentId, onAgentChange, session
           ))}
         </div>
       )}
+      {skills.length > 0 && (
+        <AgentCommandsHint commands={skills.map((s) => ({ name: s.name, description: s.description }))} />
+      )}
       {/* Batch 9 toolbar — agent picker + quick-toggle menu. v1.11.5.1
           inlines ContextBar in the same row so the bar lives next to the
           picker rather than as a separate header above it. The row renders

apps/web/src/components/ChatTabBar.tsx

@@ -181,7 +181,7 @@ export function ChatTabBar({
               <Plus size={12} />
             </button>
           </DropdownMenuTrigger>
-          <DropdownMenuContent align="end" className="min-w-40">
+          <DropdownMenuContent align="end" className="w-fit">
             <DropdownMenuItem onSelect={() => onAddPane('chat')}>
               <MessageSquare size={14} /> New BooChat
             </DropdownMenuItem>

apps/web/src/components/MessageBubble.tsx

@@ -1,6 +1,6 @@
 import { useEffect, useState } from 'react';
 import type { ReactNode } from 'react';
-import { ChevronDown, ChevronRight, Copy, RefreshCw, Check, Share2, RotateCw, GitFork, Trash2, PanelRightOpen } from 'lucide-react';
+import { ChevronDown, ChevronRight, Copy, RefreshCw, Check, Share2, RotateCw, GitFork, Trash2, PanelRightOpen, Brain } from 'lucide-react';
 import { toast } from 'sonner';
 import type { Chat, ErrorReason, Message } from '@/api/types';
 import { api, ApiError } from '@/api/client';
@@ -117,12 +117,20 @@ function deriveMarkdownTitle(content: string): string {
   return 'Markdown artifact';
 }
 
+export interface MessageActions {
+  onRegenerate?: (chatId: string, messageId: string) => Promise<void>;
+  onResend?: (chatId: string, content: string) => Promise<void>;
+  onFork?: (chatId: string, messageId: string) => Promise<void>;
+  onDelete?: (chatId: string, messageId: string) => Promise<void>;
+}
+
 interface Props {
   message: Message;
   sessionChats?: Chat[];
-  // v1.8.2: passed by MessageList's render-item pass for cap-hit sentinels.
-  // Only the most recent sentinel shows the Continue button.
   capHitInfo?: { position: number; isLatest: boolean };
+  actions?: MessageActions;
+  /** Hide actions that don't apply (fork, delete, open-in-pane). */
+  hideActions?: ('fork' | 'delete' | 'openInPane')[];
 }
 
 function StatsLine({ message }: { message: Message }) {
@@ -157,8 +165,12 @@ function StatsLine({ message }: { message: Message }) {
 
 function ActionRow({
   message,
+  actions,
+  hiddenSet,
 }: {
   message: Message;
+  actions?: MessageActions;
+  hiddenSet: Set<string>;
 }) {
   const [justCopied, setJustCopied] = useState(false);
   const [regenerating, setRegenerating] = useState(false);
@@ -180,7 +192,11 @@ function ActionRow({
     if (regenerating || message.status === 'streaming') return;
     setRegenerating(true);
     try {
-      await api.messages.regenerate(message.chat_id, message.id);
+      if (actions?.onRegenerate) {
+        await actions.onRegenerate(message.chat_id, message.id);
+      } else {
+        await api.messages.regenerate(message.chat_id, message.id);
+      }
     } catch (err) {
       toast.error(err instanceof Error ? err.message : 'regenerate failed');
     } finally {
@@ -188,12 +204,30 @@ function ActionRow({
     }
   }
 
+  async function resend() {
+    if (!canResend) return;
+    try {
+      if (actions?.onResend) {
+        await actions.onResend(message.chat_id, message.content!);
+      } else {
+        await api.messages.send(message.chat_id, message.content!);
+      }
+    } catch (err) {
+      toast.error(err instanceof Error ? err.message : 'resend failed');
+    }
+  }
+
   async function fork() {
     if (forking || message.status !== 'complete') return;
     setForking(true);
     try {
-      const chat = await api.chats.fork(message.chat_id, { messageId: message.id });
+      if (actions?.onFork) {
-      sessionEvents.emit({ type: 'open_chat_in_active_pane', chat_id: chat.id });
+        await actions.onFork(message.chat_id, message.id);
+      } else {
+        const chat = await api.chats.fork(message.chat_id, { messageId: message.id });
+        sessionEvents.emit({ type: 'refetch_messages' });
+        sessionEvents.emit({ type: 'open_chat_in_active_pane', chat_id: chat.id });
+      }
     } catch (err) {
       toast.error(err instanceof Error ? err.message : 'fork failed');
     } finally {
@@ -205,7 +239,11 @@ function ActionRow({
     if (deleting) return;
     setDeleting(true);
     try {
-      await api.messages.remove(message.chat_id, message.id);
+      if (actions?.onDelete) {
+        await actions.onDelete(message.chat_id, message.id);
+      } else {
+        await api.messages.remove(message.chat_id, message.id);
+      }
       setDeleteOpen(false);
     } catch (err) {
       toast.error(err instanceof Error ? err.message : 'delete failed');
@@ -215,7 +253,9 @@ function ActionRow({
   }
 
   const isAssistant = message.role === 'assistant';
+  const isUser = message.role === 'user';
   const canRegen = isAssistant && message.status !== 'streaming';
+  const canResend = isUser && message.status === 'complete' && !!message.content?.trim();
   const canFork = message.status === 'complete';
   const canDelete = message.status !== 'streaming';
   const [openingPane, setOpeningPane] = useState(false);
@@ -279,7 +319,18 @@ function ActionRow({
         >
           {justCopied ? <Check className="size-3" /> : <Copy className="size-3" />}
         </button>
-        {isAssistant && (
+        {canResend && (
+          <button
+            type="button"
+            onClick={() => void resend()}
+            className="inline-flex items-center justify-center size-6 rounded text-muted-foreground hover:bg-muted hover:text-foreground max-md:min-h-[44px] max-md:min-w-[44px]"
+            aria-label="Resend message"
+            title="Resend"
+          >
+            <RefreshCw className="size-3" />
+          </button>
+        )}
+        {isAssistant && !hiddenSet.has('openInPane') && (
           <button
             type="button"
             onClick={() => void openInPane()}
@@ -303,26 +354,30 @@ function ActionRow({
             <RefreshCw className={`size-3 ${regenerating ? 'animate-spin' : ''}`} />
           </button>
         )}
-        <button
+        {!hiddenSet.has('fork') && (
-          type="button"
+          <button
-          onClick={() => void fork()}
+            type="button"
-          disabled={!canFork || forking}
+            onClick={() => void fork()}
-          className="inline-flex items-center justify-center size-6 rounded text-muted-foreground hover:bg-muted hover:text-foreground disabled:opacity-40 disabled:cursor-not-allowed max-md:min-h-[44px] max-md:min-w-[44px]"
+            disabled={!canFork || forking}
-          aria-label="Fork from here"
+            className="inline-flex items-center justify-center size-6 rounded text-muted-foreground hover:bg-muted hover:text-foreground disabled:opacity-40 disabled:cursor-not-allowed max-md:min-h-[44px] max-md:min-w-[44px]"
-          title="Fork from here"
+            aria-label="Fork from here"
-        >
+            title="Fork from here"
-          <GitFork className="size-3" />
+          >
-        </button>
+            <GitFork className="size-3" />
-        <button
+          </button>
-          type="button"
+        )}
-          onClick={() => setDeleteOpen(true)}
+        {!hiddenSet.has('delete') && (
-          disabled={!canDelete}
+          <button
+            type="button"
+            onClick={() => setDeleteOpen(true)}
+            disabled={!canDelete}
           className="inline-flex items-center justify-center size-6 rounded text-muted-foreground hover:bg-muted hover:text-destructive disabled:opacity-40 disabled:cursor-not-allowed max-md:min-h-[44px] max-md:min-w-[44px]"
           aria-label="Delete message"
           title="Delete message"
         >
           <Trash2 className="size-3" />
         </button>
+        )}
       </div>
       <Dialog
         open={deleteOpen}
@@ -536,7 +591,39 @@ function SummaryCard({ message }: { message: Message }) {
   );
 }
 
-export function MessageBubble({ message, sessionChats, capHitInfo }: Props) {
+// Collapsible "Thinking" block for assistant reasoning. Fed by either
+// reasoning_text (coder wire / live reasoning_delta stream) or reasoning_parts
+// (native inference, persisted from message_parts). Auto-expands while the turn
+// is still streaming so the user watches it think (Paseo-style), then stays
+// where the user left it once the turn completes — initial state is captured
+// once at mount, so we never fight a manual collapse on later re-renders.
+function ReasoningBlock({ text, streaming }: { text: string; streaming: boolean }) {
+  const [expanded, setExpanded] = useState(() => streaming);
+  return (
+    <div className="max-w-[90%] rounded-lg border bg-muted/30 text-sm">
+      <button
+        type="button"
+        onClick={() => setExpanded((v) => !v)}
+        className="flex items-center gap-1.5 w-full px-3 py-1.5 text-left text-muted-foreground hover:text-foreground"
+      >
+        {expanded ? <ChevronDown size={14} /> : <ChevronRight size={14} />}
+        <Brain size={13} />
+        <span className="text-xs font-medium">Thinking</span>
+        {streaming && (
+          <span className="ml-1 inline-block w-1.5 h-3 align-baseline bg-muted-foreground/60 animate-pulse" />
+        )}
+      </button>
+      {expanded && (
+        <div className="px-3 pb-2.5 pt-0.5 text-xs leading-relaxed text-muted-foreground whitespace-pre-wrap break-words border-t">
+          {text}
+        </div>
+      )}
+    </div>
+  );
+}
+
+export function MessageBubble({ message, sessionChats, capHitInfo, actions, hideActions }: Props) {
+  const hiddenSet = new Set(hideActions ?? []);
   // v1.11: anchored rolling summary row. Checked BEFORE the kind==='compact'
   // branch because summary=true never coexists with kind='compact' (new
   // compactions emit role='assistant' rows with kind='message'+summary=true).
@@ -585,7 +672,7 @@ export function MessageBubble({ message, sessionChats, capHitInfo }: Props) {
             {message.content}
           </div>
         </SendToTerminalMenu>
-        <ActionRow message={message} />
+        <ActionRow message={message} actions={actions} hiddenSet={hiddenSet} />
       </div>
     );
   }
@@ -595,16 +682,26 @@ export function MessageBubble({ message, sessionChats, capHitInfo }: Props) {
   // v1.13.7: match the MessageList.flatten trim guard so a whitespace-only
   // assistant turn doesn't render an empty bubble + dangling ActionRow.
   const hasContent = message.content.trim().length > 0;
+  // Reasoning arrives as a pre-joined string (coder wire) or as parts (native
+  // inference). Read whichever is present; loose ?? chain tolerates the coder
+  // shape where reasoning_parts is undefined (see CLAUDE.md null-guard note).
+  const reasoningText = (
+    message.reasoning_text ??
+    message.reasoning_parts?.map((p) => p.text ?? '').join('') ??
+    ''
+  ).trim();
+  const hasReasoning = reasoningText.length > 0;
   // v1.8.2: if metadata stamps an error reason, surface it inline under the
   // generic "message failed" line. Keeps the user's eye where it already is
   // rather than introducing a separate banner.
   const errorMeta =
-    message.metadata !== null && message.metadata.kind === 'error'
+    message.metadata != null && message.metadata.kind === 'error'
       ? message.metadata
       : null;
 
   return (
     <div className="group flex flex-col gap-2">
+      {hasReasoning && <ReasoningBlock text={reasoningText} streaming={isStreaming} />}
       {(hasContent || isStreaming) && (
         <SendToTerminalMenu>
           <div className="max-w-[90%] text-sm leading-relaxed space-y-2 break-words min-w-0">
@@ -627,7 +724,7 @@ export function MessageBubble({ message, sessionChats, capHitInfo }: Props) {
         </div>
       )}
       {!isStreaming && <StatsLine message={message} />}
-      {!isStreaming && hasContent && <ActionRow message={message} />}
+      {!isStreaming && hasContent && <ActionRow message={message} actions={actions} hiddenSet={hiddenSet} />}
     </div>
   );
 }

apps/web/src/components/MobileTabSwitcher.tsx

@@ -273,7 +273,7 @@ export function MobileTabSwitcher({
                       <MoreHorizontal size={14} />
                     </button>
                   </DropdownMenuTrigger>
-                  <DropdownMenuContent align="end">
+                  <DropdownMenuContent align="end" className="min-w-44">
                     {chat && (
                       <DropdownMenuItem onSelect={() => startRename(chat.id, chat.name)}>
                         <Edit2 size={14} /> Rename chat

apps/web/src/components/NewPaneMenu.tsx

@@ -27,7 +27,7 @@ export function NewPaneMenu({ onAddPane, disabled }: Props) {
           <Plus size={16} />
         </button>
       </DropdownMenuTrigger>
-      <DropdownMenuContent align="end">
+      <DropdownMenuContent align="end" className="w-fit">
         <DropdownMenuItem onSelect={() => onAddPane('chat')}>
           <MessageSquare size={14} /> New BooChat
         </DropdownMenuItem>

apps/web/src/components/RightRail.tsx

@@ -1,6 +1,6 @@
 import { useCallback, useEffect, useMemo, useState } from 'react';
-import { ChevronRight, ChevronDown, FileText, Folder, PanelRightClose, PanelRightOpen } from 'lucide-react';
+import { ChevronRight, ChevronDown, FilePlus, FileText, Folder, PanelRightClose, PanelRightOpen } from 'lucide-react';
-import { api } from '@/api/client';
+import { api, ApiError } from '@/api/client';
 import type { FileEntry } from '@/api/types';
 import { inferLanguage } from '@/lib/attachments';
 import { sessionEvents } from '@/hooks/sessionEvents';
@@ -8,10 +8,22 @@ import { useRightRailDrawer } from '@/hooks/useRightRailDrawer';
 import { useViewport } from '@/hooks/useViewport';
 import { FileViewerOverlay } from '@/components/FileViewerOverlay';
 import { Input } from '@/components/ui/input';
+import { Textarea } from '@/components/ui/textarea';
+import { Button } from '@/components/ui/button';
+import { Label } from '@/components/ui/label';
+import {
+  Dialog,
+  DialogContent,
+  DialogDescription,
+  DialogFooter,
+  DialogHeader,
+  DialogTitle,
+} from '@/components/ui/dialog';
 import { cn } from '@/lib/utils';
 
 interface Props {
   projectId: string;
+  sessionId: string;
 }
 
 const STORAGE_KEY = 'boocode.rightrail';
@@ -27,7 +39,7 @@ function joinPath(parent: string, name: string): string {
   return `${parent}/${name}`;
 }
 
-export function RightRail({ projectId }: Props) {
+export function RightRail({ projectId, sessionId }: Props) {
   const { isMobile } = useViewport();
   const { open: drawerOpen, setOpen: setDrawerOpen } = useRightRailDrawer();
   const [open, setOpen] = useState(() => {
@@ -39,6 +51,39 @@ export function RightRail({ projectId }: Props) {
   const [fullFileList, setFullFileList] = useState<string[] | null>(null);
   const [viewerFile, setViewerFile] = useState<{ path: string; content: string } | null>(null);
 
+  // New-file-from-pasted-text modal. Queues a pending_changes create via
+  // BooCoder; it then shows in the CoderPane DiffPanel for explicit apply.
+  const [newFileOpen, setNewFileOpen] = useState(false);
+  const [newFilePath, setNewFilePath] = useState('');
+  const [newFileContent, setNewFileContent] = useState('');
+  const [creating, setCreating] = useState(false);
+  const [createError, setCreateError] = useState<string | null>(null);
+
+  const openNewFile = useCallback(() => {
+    setNewFilePath('');
+    setNewFileContent('');
+    setCreateError(null);
+    setNewFileOpen(true);
+  }, []);
+
+  const submitNewFile = useCallback(async () => {
+    const path = newFilePath.trim();
+    if (!path || creating) return;
+    setCreating(true);
+    setCreateError(null);
+    try {
+      await api.coder.createPendingFile(sessionId, path, newFileContent);
+      setNewFileOpen(false);
+      setNewFilePath('');
+      setNewFileContent('');
+    } catch (err) {
+      // 422 WriteGuardError surfaces via ApiError.message (the route's { error }).
+      setCreateError(err instanceof ApiError ? err.message : err instanceof Error ? err.message : 'Failed to create file');
+    } finally {
+      setCreating(false);
+    }
+  }, [sessionId, newFilePath, newFileContent, creating]);
+
   // Combined open state: on mobile use the global drawer state (toggled by
   // the Session header's FolderTree button); on desktop use the persistent
   // internal state.
@@ -163,6 +208,15 @@ export function RightRail({ projectId }: Props) {
       <aside className={asideCls}>
         <div className="flex items-center gap-2 px-3 py-2 border-b shrink-0">
           <span className="text-xs font-medium flex-1">Files</span>
+          <button
+            type="button"
+            onClick={openNewFile}
+            className="p-1 rounded hover:bg-muted text-muted-foreground max-md:min-h-[44px] max-md:min-w-[44px]"
+            aria-label="New file from pasted text"
+            title="New file"
+          >
+            <FilePlus size={14} />
+          </button>
           <button
             type="button"
             onClick={closeRail}
@@ -225,6 +279,48 @@ export function RightRail({ projectId }: Props) {
           onNavigate={(path) => void openFile(path)}
         />
       )}
+
+      <Dialog open={newFileOpen} onOpenChange={setNewFileOpen}>
+        <DialogContent className="sm:max-w-lg">
+          <DialogHeader>
+            <DialogTitle>New file from pasted text</DialogTitle>
+            <DialogDescription>
+              Queues a new file as a pending change. Review and apply it from the Coder pane.
+            </DialogDescription>
+          </DialogHeader>
+          <div className="space-y-3">
+            <div className="space-y-1.5">
+              <Label htmlFor="new-file-path" className="text-xs">Path (relative to project root)</Label>
+              <Input
+                id="new-file-path"
+                value={newFilePath}
+                onChange={(e) => setNewFilePath(e.target.value)}
+                placeholder="src/example.ts"
+              />
+            </div>
+            <div className="space-y-1.5">
+              <Label htmlFor="new-file-content" className="text-xs">Content</Label>
+              <Textarea
+                id="new-file-content"
+                value={newFileContent}
+                onChange={(e) => setNewFileContent(e.target.value)}
+                placeholder="Paste file contents here…"
+                autoFocus
+                className="min-h-[180px] font-mono text-xs"
+              />
+            </div>
+            {createError && <p className="text-xs text-destructive">{createError}</p>}
+          </div>
+          <DialogFooter>
+            <Button variant="ghost" onClick={() => setNewFileOpen(false)} disabled={creating}>
+              Cancel
+            </Button>
+            <Button onClick={() => void submitNewFile()} disabled={creating || !newFilePath.trim()}>
+              {creating ? 'Creating…' : 'Create'}
+            </Button>
+          </DialogFooter>
+        </DialogContent>
+      </Dialog>
     </>
   );
 }

apps/web/src/components/SessionLandingPage.tsx

@@ -1,185 +1,27 @@
-import { useCallback, useEffect, useState } from 'react';
+import { useCallback, useState } from 'react';
-import { Archive, MessageSquare, Send, ChevronDown, ChevronRight, RotateCcw, Trash2 } from 'lucide-react';
 import { toast } from 'sonner';
-import type { Chat } from '@/api/types';
 import { api } from '@/api/client';
-import { Button } from '@/components/ui/button';
 import { ChatInput } from '@/components/ChatInput';
-import {
-  ContextMenu,
-  ContextMenuContent,
-  ContextMenuItem,
-  ContextMenuSeparator,
-  ContextMenuTrigger,
-} from '@/components/ui/context-menu';
-import {
-  Dialog,
-  DialogContent,
-  DialogHeader,
-  DialogTitle,
-  DialogDescription,
-} from '@/components/ui/dialog';
-import { formatTokens } from '@/lib/format';
 
 interface Props {
-  sessionId: string;
   projectId: string;
-  chats: Chat[];
+  sessionId: string;
-  onOpenChat: (chatId: string) => void;
+  agentId?: string | null;
+  onAgentChange?: (agentId: string | null) => void | Promise<void>;
   onSend: (content: string) => void;
-  /** Create a chat and return its id. Used by slash-command handler. */
   createChat: () => Promise<{ id: string }>;
-  onReopenChat: (chatId: string) => Promise<void>;
-  onArchiveChat: (chatId: string) => Promise<void>;
-  onRenameChat: (chatId: string, name: string) => Promise<void>;
-  onDeleteChat: (chatId: string) => Promise<void>;
-}
-
-function relTime(iso: string): string {
-  const now = Date.now();
-  const t = Date.parse(iso);
-  if (Number.isNaN(t)) return '';
-  const sec = Math.max(0, Math.floor((now - t) / 1000));
-  if (sec < 60) return `${sec}s ago`;
-  const min = Math.floor(sec / 60);
-  if (min < 60) return `${min}m ago`;
-  const hr = Math.floor(min / 60);
-  if (hr < 24) return `${hr}h ago`;
-  const day = Math.floor(hr / 24);
-  return `${day}d ago`;
-}
-
-interface ChatRowProps {
-  chat: Chat;
-  onClick: () => void;
-  dimmed?: boolean;
-  trailing?: React.ReactNode;
-  actions?: React.ReactNode;
-  renamingId: string | null;
-  renameValue: string;
-  setRenameValue: (s: string) => void;
-  onFinishRename: () => void;
-  onCancelRename: () => void;
-  onContextStartRename: () => void;
-  onContextArchive: () => void;
-  onContextDelete: () => void;
-  showContextMenu: boolean;
-}
-
-function ChatRow({
-  chat,
-  onClick,
-  dimmed,
-  trailing,
-  actions,
-  renamingId,
-  renameValue,
-  setRenameValue,
-  onFinishRename,
-  onCancelRename,
-  onContextStartRename,
-  onContextArchive,
-  onContextDelete,
-  showContextMenu,
-}: ChatRowProps) {
-  const meta: string[] = [relTime(chat.updated_at)];
-  if (chat.message_count !== undefined && chat.message_count > 0) {
-    meta.push(`${chat.message_count} msg`);
-  }
-  const tokens = formatTokens(chat.effective_context_tokens);
-  if (tokens) meta.push(tokens);
-  const preview = chat.last_message_preview;
-  const isRenaming = renamingId === chat.id;
-
-  const inner = (
-    <button
-      type="button"
-      onClick={onClick}
-      className="w-full flex flex-col gap-0.5 px-3 py-2 hover:bg-muted/50 text-left"
-    >
-      <div className="flex items-center gap-2 min-w-0">
-        <MessageSquare className={`size-3.5 shrink-0 ${dimmed ? 'opacity-40' : 'opacity-70'}`} />
-        {isRenaming ? (
-          <input
-            autoFocus
-            value={renameValue}
-            onChange={(e) => setRenameValue(e.target.value)}
-            onBlur={() => onFinishRename()}
-            onKeyDown={(e) => {
-              if (e.key === 'Enter') onFinishRename();
-              if (e.key === 'Escape') onCancelRename();
-            }}
-            onClick={(e) => e.stopPropagation()}
-            className="bg-transparent border-b border-border text-sm outline-none flex-1 min-w-0"
-          />
-        ) : (
-          <span className={`truncate text-sm flex-1 ${dimmed ? 'text-muted-foreground' : ''}`}>
-            {chat.name ?? 'New chat'}
-          </span>
-        )}
-        {trailing && (
-          <span className="text-xs text-muted-foreground shrink-0">{trailing}</span>
-        )}
-        {actions && (
-          <div className="flex items-center gap-0.5 shrink-0">{actions}</div>
-        )}
-      </div>
-      <div className="ml-5 text-xs text-muted-foreground tabular-nums">
-        {meta.join(' · ')}
-      </div>
-      {preview && (
-        <div className="ml-5 text-xs italic text-muted-foreground truncate">
-          {preview}
-        </div>
-      )}
-    </button>
-  );
-
-  if (!showContextMenu) return inner;
-
-  return (
-    <ContextMenu>
-      <ContextMenuTrigger asChild>{inner}</ContextMenuTrigger>
-      <ContextMenuContent>
-        <ContextMenuItem onSelect={onClick}>Open</ContextMenuItem>
-        <ContextMenuItem onSelect={onContextStartRename}>Rename</ContextMenuItem>
-        <ContextMenuItem onSelect={onContextArchive}>Archive</ContextMenuItem>
-        <ContextMenuSeparator />
-        <ContextMenuItem variant="destructive" onSelect={onContextDelete}>
-          Delete
-        </ContextMenuItem>
-      </ContextMenuContent>
-    </ContextMenu>
-  );
 }
 
 export function SessionLandingPage({
-  chats,
-  onOpenChat,
-  onSend,
   projectId,
+  sessionId,
+  agentId,
+  onAgentChange,
+  onSend,
   createChat,
-  onReopenChat,
-  onArchiveChat,
-  onRenameChat,
-  onDeleteChat,
 }: Props) {
-  const [composerValue, setComposerValue] = useState('');
   const [chatId, setChatId] = useState<string | null>(null);
-  const [showArchived, setShowArchived] = useState(false);
-  const [renamingId, setRenamingId] = useState<string | null>(null);
-  const [renameValue, setRenameValue] = useState('');
-  const [archiveConfirm, setArchiveConfirm] = useState<Chat | null>(null);
-  const [deleteConfirm, setDeleteConfirm] = useState<Chat | null>(null);
 
-  const openChats = chats
-    .filter((c) => c.status === 'open')
-    .sort((a, b) => new Date(b.updated_at).getTime() - new Date(a.updated_at).getTime());
-  const archivedChats = chats
-    .filter((c) => c.status === 'archived')
-    .sort((a, b) => new Date(b.updated_at).getTime() - new Date(a.updated_at).getTime());
-
-  // Create a chat lazily on first send or slash command.
   const ensureChat = useCallback(async (): Promise<string> => {
     if (chatId) return chatId;
     try {
@@ -192,207 +34,46 @@ export function SessionLandingPage({
     }
   }, [chatId, createChat]);
 
-  async function handleSend() {
+  const handleSend = useCallback(async (content: string) => {
-    const text = composerValue.trim();
+    const text = content.trim();
     if (!text) return;
     try {
-      const cid = await ensureChat();
+      await ensureChat();
       onSend(text);
-      setComposerValue('');
     } catch {
       // Error already surfaced via toast.
     }
-  }
+  }, [ensureChat, onSend]);
 
-  // v2.3: slash-command dispatch on landing page. Creates a chat first if
-  // one doesn't exist, then invokes the skill on that chat.
   const handleSlashCommand = useCallback(async (skillName: string, userMessage: string) => {
     try {
       const cid = await ensureChat();
       await api.chats.skillInvoke(cid, skillName, userMessage.length > 0 ? userMessage : null);
-      setComposerValue('');
     } catch (err) {
       toast.error(err instanceof Error ? err.message : `/${skillName} failed`);
     }
   }, [ensureChat]);
 
-  function startRename(chat: Chat) {
-    setRenamingId(chat.id);
-    setRenameValue(chat.name ?? '');
-  }
-
-  async function finishRename() {
-    if (renamingId && renameValue.trim()) {
-      await onRenameChat(renamingId, renameValue.trim());
-    }
-    setRenamingId(null);
-  }
-
-  // TODO: Landing page chat counts are a snapshot at mount. New messages in
-  // visible chats won't update the per-row stats until next mount/navigation.
   return (
     <div className="flex flex-col h-full min-h-0">
-      <div className="flex-1 overflow-y-auto px-6 py-4 space-y-6">
+      <div className="flex-1 flex items-center justify-center px-6">
-        {openChats.length > 0 && (
+        <p className="text-sm text-muted-foreground">
-          <div>
+          Send a message to start.
-            <h3 className="text-xs font-medium text-muted-foreground mb-2">Open chats</h3>
+        </p>
-            <ul className="divide-y rounded-md border">
-              {openChats.map((chat) => (
-                <li key={chat.id}>
-                  <ChatRow
-                    chat={chat}
-                    onClick={() => onOpenChat(chat.id)}
-                    renamingId={renamingId}
-                    renameValue={renameValue}
-                    setRenameValue={setRenameValue}
-                    onFinishRename={() => void finishRename()}
-                    onCancelRename={() => setRenamingId(null)}
-                    onContextStartRename={() => startRename(chat)}
-                    onContextArchive={() => setArchiveConfirm(chat)}
-                    onContextDelete={() => setDeleteConfirm(chat)}
-                    showContextMenu
-                    actions={
-                      <>
-                        <Button
-                          variant="ghost"
-                          size="icon-sm"
-                          aria-label="Archive chat"
-                          title="Archive chat"
-                          onClick={(e) => {
-                            e.stopPropagation();
-                            setArchiveConfirm(chat);
-                          }}
-                        >
-                          <Archive size={14} />
-                        </Button>
-                        <Button
-                          variant="ghost"
-                          size="icon-sm"
-                          aria-label="Delete chat"
-                          title="Delete chat"
-                          className="text-destructive hover:text-destructive"
-                          onClick={(e) => {
-                            e.stopPropagation();
-                            setDeleteConfirm(chat);
-                          }}
-                        >
-                          <Trash2 size={14} />
-                        </Button>
-                      </>
-                    }
-                  />
-                </li>
-              ))}
-            </ul>
-          </div>
-        )}
-
-        {archivedChats.length > 0 && (
-          <div>
-            <button
-              type="button"
-              onClick={() => setShowArchived(!showArchived)}
-              className="flex items-center gap-1 text-xs font-medium text-muted-foreground mb-2 hover:text-foreground"
-            >
-              {showArchived ? <ChevronDown size={12} /> : <ChevronRight size={12} />}
-              Archived chats ({archivedChats.length})
-            </button>
-            {showArchived && (
-              <ul className="divide-y rounded-md border">
-                {archivedChats.map((chat) => (
-                  <li key={chat.id}>
-                    <ChatRow
-                      chat={chat}
-                      onClick={() => void onReopenChat(chat.id)}
-                      dimmed
-                      trailing={<><RotateCcw size={10} className="inline mr-1" />Restore</>}
-                      renamingId={null}
-                      renameValue=""
-                      setRenameValue={() => {}}
-                      onFinishRename={() => {}}
-                      onCancelRename={() => {}}
-                      onContextStartRename={() => {}}
-                      onContextArchive={() => {}}
-                      onContextDelete={() => {}}
-                      showContextMenu={false}
-                    />
-                  </li>
-                ))}
-              </ul>
-            )}
-          </div>
-        )}
-
-        {openChats.length === 0 && archivedChats.length === 0 && (
-          <div className="text-sm text-muted-foreground py-8 text-center">
-            No chats yet. Type below to start a conversation.
-          </div>
-        )}
       </div>
-
+      <ChatInput
-      {/* v2.3: ChatInput with slash-command support replaces the bare Textarea.
+        disabled={false}
-          chatId is created lazily on first send/slash. */}
+        projectId={projectId}
-      <div className="border-t px-4 py-3 shrink-0">
+        sessionId={sessionId}
-        <ChatInput
+        agentId={agentId ?? null}
-          projectId={projectId}
+        onAgentChange={onAgentChange}
-          onSend={handleSend}
+        onSend={handleSend}
-          onSlashCommand={handleSlashCommand}
+        onSlashCommand={handleSlashCommand}
-          chatId={chatId ?? undefined}
+        chatId={chatId ?? undefined}
-          chatLabel={chatId ? undefined : 'Chat'}
+        chatLabel="Chat"
-          disabled={false}
+        messages={[]}
-        />
+        modelContextLimit={null}
-      </div>
+      />
-
-      <Dialog open={archiveConfirm !== null} onOpenChange={(open) => { if (!open) setArchiveConfirm(null); }}>
-        <DialogContent>
-          <DialogHeader>
-            <DialogTitle>Archive chat?</DialogTitle>
-            <DialogDescription>
-              Moves {archiveConfirm ? `"${archiveConfirm.name ?? 'New chat'}"` : 'this chat'} to the Archived chats section. You can restore it any time.
-            </DialogDescription>
-          </DialogHeader>
-          <div className="flex gap-2 justify-end pt-2">
-            <Button variant="outline" onClick={() => setArchiveConfirm(null)}>
-              Cancel
-            </Button>
-            <Button
-              onClick={() => {
-                if (archiveConfirm) void onArchiveChat(archiveConfirm.id);
-                setArchiveConfirm(null);
-              }}
-            >
-              Archive
-            </Button>
-          </div>
-        </DialogContent>
-      </Dialog>
-
-      <Dialog open={deleteConfirm !== null} onOpenChange={(open) => { if (!open) setDeleteConfirm(null); }}>
-        <DialogContent>
-          <DialogHeader>
-            <DialogTitle>Delete chat?</DialogTitle>
-            <DialogDescription>
-              Permanently delete{' '}
-              <span className="font-mono font-medium text-foreground">{deleteConfirm?.name || '(unnamed)'}</span>
-              {' '}and all its messages. This cannot be undone.
-            </DialogDescription>
-          </DialogHeader>
-          <div className="flex gap-2 justify-end pt-2">
-            <Button variant="outline" onClick={() => setDeleteConfirm(null)}>
-              Cancel
-            </Button>
-            <Button
-              variant="destructive"
-              onClick={() => {
-                if (deleteConfirm) void onDeleteChat(deleteConfirm.id);
-                setDeleteConfirm(null);
-              }}
-            >
-              Delete
-            </Button>
-          </div>
-        </DialogContent>
-      </Dialog>
     </div>
   );
 }

apps/web/src/components/Workspace.tsx

@@ -37,6 +37,7 @@ interface Props {
   project: Project | null;
   /** New BooCode opens a fresh coder session; chat/terminal split in-place. */
   onAddPane: (kind: 'chat' | 'terminal' | 'coder') => void;
+  onCoderConnectedChange?: (paneId: string, connected: boolean) => void;
 }
 
 export function Workspace({
@@ -48,6 +49,7 @@ export function Workspace({
   chatsHook,
   session,
   project,
+  onCoderConnectedChange,
   onAddPane,
 }: Props) {
   const {
@@ -141,6 +143,7 @@ export function Workspace({
 
   // Per-coder-pane WS connection (status dot lives in the pane header).
   const [coderConnected, setCoderConnected] = useState<Record<string, boolean>>({});
+  const [coderLabels, setCoderLabels] = useState<Record<string, string>>({});
 
   return (
     <div className="flex flex-col h-full min-h-0">
@@ -212,24 +215,23 @@ export function Workspace({
                   onRemovePane={panes.length > 1 ? () => removePane(idx) : undefined}
                 />
               )}
-              {isCoder && (
+              {isCoder && !isMobile && (
-                <div className="flex items-center gap-2 border-b border-border bg-muted/30 px-2 py-1 shrink-0">
+                <div className="flex items-center gap-1 border-b border-border px-2 py-1 shrink-0">
                   <Code size={12} className="text-muted-foreground" />
                   <span className="text-xs text-muted-foreground">BooCode</span>
-                  <div className="ml-auto flex items-center gap-1.5">
+                  <div className="ml-auto flex items-center gap-1">
                     <DropdownMenu>
                       <DropdownMenuTrigger asChild>
                         <button
                           type="button"
                           onClick={(e) => e.stopPropagation()}
-                          className="inline-flex items-center justify-center size-5 rounded text-muted-foreground hover:bg-muted hover:text-foreground max-md:size-7"
+                          className="inline-flex items-center justify-center size-5 rounded text-muted-foreground hover:bg-muted hover:text-foreground"
                           aria-label="New pane"
-                          title="New pane"
                         >
                           <Plus size={12} />
                         </button>
                       </DropdownMenuTrigger>
-                      <DropdownMenuContent align="end" className="min-w-40">
+                      <DropdownMenuContent align="end" className="w-fit">
                         <DropdownMenuItem onSelect={() => onAddPane('chat')}>
                           <MessageSquare size={14} /> New BooChat
                         </DropdownMenuItem>
@@ -241,23 +243,12 @@ export function Workspace({
                         </DropdownMenuItem>
                       </DropdownMenuContent>
                     </DropdownMenu>
-                    <span
-                      className={cn(
-                        'inline-block w-1.5 h-1.5 rounded-full shrink-0',
-                        coderConnected[pane.id] ? 'bg-green-500' : 'bg-red-500',
-                      )}
-                      title={coderConnected[pane.id] ? 'Connected' : 'Disconnected'}
-                    />
                     {panes.length > 1 && (
                       <button
                         type="button"
-                        onClick={(e) => {
+                        onClick={(e) => { e.stopPropagation(); removePane(idx); }}
-                          e.stopPropagation();
+                        className="inline-flex items-center justify-center size-5 rounded text-muted-foreground hover:bg-muted hover:text-foreground"
-                          removePane(idx);
+                        aria-label="Close pane"
-                        }}
-                        className="inline-flex items-center justify-center size-5 rounded text-muted-foreground hover:bg-muted hover:text-foreground max-md:size-7"
-                        aria-label="Close BooCode pane"
-                        title="Close BooCode pane"
                       >
                         <X size={12} />
                       </button>
@@ -283,7 +274,7 @@ export function Workspace({
                         <Plus size={12} />
                       </button>
                     </DropdownMenuTrigger>
-                    <DropdownMenuContent align="end" className="min-w-40">
+                    <DropdownMenuContent align="end" className="w-fit">
                       <DropdownMenuItem onSelect={() => onAddPane('chat')}>
                         <MessageSquare size={14} /> New BooChat
                       </DropdownMenuItem>
@@ -354,9 +345,15 @@ export function Workspace({
                   chatId={activePaneChatId(pane)}
                   chatPending={isPaneChatPending(pane.id)}
                   projectPath={project?.path}
-                  onConnectedChange={(connected) =>
+                  onConnectedChange={(connected) => {
                     setCoderConnected((prev) =>
                       prev[pane.id] === connected ? prev : { ...prev, [pane.id]: connected },
+                    );
+                    onCoderConnectedChange?.(pane.id, connected);
+                  }}
+                  onAgentLabelChange={(label) =>
+                    setCoderLabels((prev) =>
+                      prev[pane.id] === label ? prev : { ...prev, [pane.id]: label },
                     )
                   }
                 />
@@ -384,19 +381,12 @@ export function Workspace({
                 />
               ) : (
                 <SessionLandingPage
-                  sessionId={sessionId}
                   projectId={projectId}
-                  chats={chats}
+                  sessionId={sessionId}
+                  agentId={agentId}
+                  onAgentChange={onAgentChange}
                   createChat={() => api.chats.create(sessionId)}
-                  onOpenChat={(chatId) => openChatInPane(idx, chatId)}
                   onSend={(content) => void handleLandingSend(idx, content)}
-                  onReopenChat={async (chatId) => {
-                    await unarchiveChat(chatId);
-                    openChatInPane(idx, chatId);
-                  }}
-                  onArchiveChat={archiveChat}
-                  onRenameChat={renameChat}
-                  onDeleteChat={deleteChat}
                 />
               )}
             </div>

apps/web/src/components/icons/ProviderIcons.tsx

@@ -0,0 +1,21 @@
+interface IconProps {
+  size?: number;
+  className?: string;
+}
+
+export function ClaudeIcon({ size = 14, className }: IconProps) {
+  return (
+    <svg width={size} height={size} viewBox="0 0 24 24" fill="currentColor" fillRule="evenodd" className={className}>
+      <path d="M4.709 15.955l4.72-2.647.08-.23-.08-.128H9.2l-.79-.048-2.698-.073-2.339-.097-2.266-.122-.571-.121L0 11.784l.055-.352.48-.321.686.06 1.52.103 2.278.158 1.652.097 2.449.255h.389l.055-.157-.134-.098-.103-.097-2.358-1.596-2.552-1.688-1.336-.972-.724-.491-.364-.462-.158-1.008.656-.722.881.06.225.061.893.686 1.908 1.476 2.491 1.833.365.304.145-.103.019-.073-.164-.274-1.355-2.446-1.446-2.49-.644-1.032-.17-.619a2.97 2.97 0 01-.104-.729L6.283.134 6.696 0l.996.134.42.364.62 1.414 1.002 2.229 1.555 3.03.456.898.243.832.091.255h.158V9.01l.128-1.706.237-2.095.23-2.695.08-.76.376-.91.747-.492.584.28.48.685-.067.444-.286 1.851-.559 2.903-.364 1.942h.212l.243-.242.985-1.306 1.652-2.064.73-.82.85-.904.547-.431h1.033l.76 1.129-.34 1.166-1.064 1.347-.881 1.142-1.264 1.7-.79 1.36.073.11.188-.02 2.856-.606 1.543-.28 1.841-.315.833.388.091.395-.328.807-1.969.486-2.309.462-3.439.813-.042.03.049.061 1.549.146.662.036h1.622l3.02.225.79.522.474.638-.079.485-1.215.62-1.64-.389-3.829-.91-1.312-.329h-.182v.11l1.093 1.068 2.006 1.81 2.509 2.33.127.578-.322.455-.34-.049-2.205-1.657-.851-.747-1.926-1.62h-.128v.17l.444.649 2.345 3.521.122 1.08-.17.353-.608.213-.668-.122-1.374-1.925-1.415-2.167-1.143-1.943-.14.08-.674 7.254-.316.37-.729.28-.607-.461-.322-.747.322-1.476.389-1.924.315-1.53.286-1.9.17-.632-.012-.042-.14.018-1.434 1.967-2.18 2.945-1.726 1.845-.414.164-.717-.37.067-.662.401-.589 2.388-3.036 1.44-1.882.93-1.086-.006-.158h-.055L4.132 18.56l-1.13.146-.487-.456.061-.746.231-.243 1.908-1.312-.006.006z" />
+    </svg>
+  );
+}
+
+export function OpenCodeIcon({ size = 14, className }: IconProps) {
+  return (
+    <svg width={size} height={size} viewBox="96 64 288 384" fill="currentColor" className={className}>
+      <path d="M320 224V352H192V224H320Z" opacity={0.4} />
+      <path fillRule="evenodd" clipRule="evenodd" d="M384 416H128V96H384V416ZM320 160H192V352H320V160Z" />
+    </svg>
+  );
+}

apps/web/src/components/panes/CoderMessageList.tsx

@@ -1,9 +1,10 @@
 import { useCallback, useEffect, useMemo, useRef, type ReactNode } from 'react';
-import { MarkdownRenderer } from '@/components/MarkdownRenderer';
+import { MessageBubble, type MessageActions } from '@/components/MessageBubble';
 import { ToolCallGroup } from '@/components/ToolCallGroup';
 import { ToolCallLine, type ToolRun } from '@/components/ToolCallLine';
 import { AskUserInputCard } from '@/components/AskUserInputCard';
 import { wireToolCallToRun, type CoderToolCallWire } from '@/lib/coder-tools';
+import type { Message } from '@/api/types';
 
 export interface CoderMessageWire {
   id: string;
@@ -141,54 +142,16 @@ function groupToolRuns(items: RenderItem[]): RenderItem[] {
   return out;
 }
 
-function CoderTextBubble({ message }: { message: CoderMessageWire }) {
-  const isUser = message.role === 'user';
-  const isStreaming = message.status === 'streaming';
-  const hasText = message.content.trim().length > 0;
-  const hasReasoning = (message.reasoning_text?.trim().length ?? 0) > 0;
-
-  if (isUser) {
-    return (
-      <div className="flex flex-col items-end gap-1">
-        <div className="max-w-[80%] rounded-lg bg-primary text-primary-foreground px-3 py-2 text-sm whitespace-pre-wrap break-words min-w-0">
-          {message.content}
-        </div>
-      </div>
-    );
-  }
-
-  return (
-    <div className="flex flex-col gap-2">
-      {hasReasoning && (
-        <details className="rounded border border-border/40 bg-muted/20 px-2 py-1">
-          <summary className="cursor-pointer text-xs text-muted-foreground select-none">Reasoning</summary>
-          <pre className="mt-1 max-h-48 overflow-y-auto whitespace-pre-wrap text-[11px] text-muted-foreground font-mono">
-            {message.reasoning_text}
-          </pre>
-        </details>
-      )}
-      {(hasText || (isStreaming && !hasReasoning)) && (
-        <div className="max-w-[90%] text-sm leading-relaxed space-y-2 break-words min-w-0">
-          {hasText ? <MarkdownRenderer content={message.content} /> : null}
-          {isStreaming && (
-            <span className="inline-block w-1.5 h-3.5 align-baseline bg-muted-foreground/60 animate-pulse" />
-          )}
-        </div>
-      )}
-      {message.status === 'failed' && (
-        <div className="text-xs text-destructive">message failed</div>
-      )}
-    </div>
-  );
-}
-
 interface Props {
   messages: CoderTimelineWire[];
   chatId?: string;
   footer?: ReactNode;
+  actions?: MessageActions;
 }
 
-export function CoderMessageList({ messages, chatId, footer }: Props) {
+const CODER_HIDDEN_ACTIONS: ('fork' | 'delete' | 'openInPane')[] = ['fork', 'openInPane'];
+
+export function CoderMessageList({ messages, chatId, footer, actions }: Props) {
   const endRef = useRef<HTMLDivElement>(null);
   const scrollRef = useRef<HTMLDivElement>(null);
   const isNearBottomRef = useRef(true);
@@ -220,7 +183,14 @@ export function CoderMessageList({ messages, chatId, footer }: Props) {
       <div className="max-w-[1000px] mx-auto w-full px-6 py-4 space-y-4">
         {renderItems.map((item) => {
           if (item.kind === 'message') {
-            return <CoderTextBubble key={item.message.id} message={item.message} />;
+            return (
+              <MessageBubble
+                key={item.message.id}
+                message={item.message as unknown as Message}
+                actions={actions}
+                hideActions={CODER_HIDDEN_ACTIONS}
+              />
+            );
           }
           if (item.kind === 'tool_run') {
             if (item.run.call.name === 'ask_user_input' && chatId) {

apps/web/src/components/panes/CoderPane.tsx

@@ -4,11 +4,10 @@
 // WS: /api/coder/ws/sessions/:id (Vite dev proxies to :9502).
 
 import { useCallback, useEffect, useMemo, useRef, useState } from 'react';
-import { Code, Send, Check, X, RefreshCw } from 'lucide-react';
+import { Code, Check, X, RefreshCw } from 'lucide-react';
 import { AgentComposerBar } from '@/components/AgentComposerBar';
 import { PermissionCard } from '@/components/PermissionCard';
-import { AgentCommandsHint } from '@/components/AgentCommandsHint';
+import { ChatInput } from '@/components/ChatInput';
-import { SlashCommandPicker } from '@/components/SlashCommandPicker';
 import { api } from '@/api/client';
 import type { AgentSessionConfig, PermissionPrompt, AgentCommand } from '@/api/types';
 import { useSkills } from '@/hooks/useSkills';
@@ -32,6 +31,8 @@ interface CoderMessage {
     id: string;
     function: { name: string; arguments: string };
   }>;
+  ctx_used?: number | null;
+  ctx_max?: number | null;
 }
 
 interface CoderToolMessage {
@@ -63,6 +64,7 @@ interface Props {
   chatPending?: boolean;
   projectPath?: string;
   onConnectedChange?: (connected: boolean) => void;
+  onAgentLabelChange?: (label: string) => void;
 }
 
 interface WsHandlers {
@@ -91,6 +93,8 @@ type RawCoderMessage = {
     | { id: string; name: string; args?: Record<string, unknown> }
     | { id: string; function: { name: string; arguments: string } }
   > | null;
+  ctx_used?: number | null;
+  ctx_max?: number | null;
 };
 
 function mapCoderTimelineRow(raw: RawCoderMessage): CoderTimelineMessage | null {
@@ -126,6 +130,8 @@ function mapCoderTimelineRow(raw: RawCoderMessage): CoderTimelineMessage | null
     status: (raw.status ?? 'complete') as CoderMessage['status'],
     ...(reasoning_text ? { reasoning_text } : {}),
     ...(tool_calls?.length ? { tool_calls } : {}),
+    ctx_used: raw.ctx_used ?? null,
+    ctx_max: raw.ctx_max ?? null,
   };
 }
 
@@ -228,7 +234,12 @@ function useCoderMessages(sessionId: string, chatId: string | undefined, handler
             );
             const next = prev.map((m) =>
               m.id === frame.message_id && m.role !== 'tool'
-                ? { ...m, status: 'complete' as const }
+                ? {
+                    ...m,
+                    status: 'complete' as const,
+                    ctx_used: (frame as any).ctx_used ?? (m as any).ctx_used ?? null,
+                    ctx_max: (frame as any).ctx_max ?? (m as any).ctx_max ?? null,
+                  }
                 : m,
             );
             if (completed) {
@@ -343,7 +354,7 @@ function usePendingChanges(sessionId: string) {
   useEffect(() => { refresh(); }, [refresh]);
 
   const approve = useCallback(async (changeId: string) => {
-    const res = await fetch(`/api/coder/sessions/${sessionId}/pending/${changeId}/approve`, {
+    const res = await fetch(`/api/coder/pending/${changeId}/apply`, {
       method: 'POST',
     });
     if (res.ok) {
@@ -352,7 +363,7 @@ function usePendingChanges(sessionId: string) {
   }, [sessionId]);
 
   const reject = useCallback(async (changeId: string) => {
-    const res = await fetch(`/api/coder/sessions/${sessionId}/pending/${changeId}/reject`, {
+    const res = await fetch(`/api/coder/pending/${changeId}/reject`, {
       method: 'POST',
     });
     if (res.ok) {
@@ -463,6 +474,7 @@ export function CoderPane({
   chatPending = false,
   projectPath,
   onConnectedChange,
+  onAgentLabelChange,
 }: Props) {
   const [agentConfig, setAgentConfig] = useState<AgentSessionConfig>({
     provider: 'boocode',
@@ -470,6 +482,12 @@ export function CoderPane({
     modeId: null,
     thinkingOptionId: null,
   });
+
+  useEffect(() => {
+    const parts = [agentConfig.provider || 'boocode'];
+    if (agentConfig.model) parts.push(agentConfig.model);
+    onAgentLabelChange?.(parts.join(' · '));
+  }, [agentConfig.provider, agentConfig.model, onAgentLabelChange]);
   const [activeTaskId, setActiveTaskId] = useState<string | null>(null);
   const [permissionPrompt, setPermissionPrompt] = useState<PermissionPrompt | null>(null);
   const [permissionBusy, setPermissionBusy] = useState(false);
@@ -515,6 +533,8 @@ export function CoderPane({
   const { changes, loading, refresh, approve, reject } = usePendingChanges(sessionId);
   const [input, setInput] = useState('');
   const [sending, setSending] = useState(false);
+  const [queue, setQueue] = useState<string[]>([]);
+  const queueProcessing = useRef(false);
   const inputRef = useRef<HTMLTextAreaElement>(null);
 
   // Refresh pending changes when a message_complete arrives
@@ -658,43 +678,87 @@ export function CoderPane({
     setMessages,
   ]);
 
-  const handleSlashSelect = useCallback((name: string) => {
-    const next = `/${name} `;
-    setInput(next);
-    setSlashState(null);
-    requestAnimationFrame(() => {
-      const ta = inputRef.current;
-      if (ta) {
-        ta.selectionStart = ta.selectionEnd = next.length;
-        ta.focus();
-      }
-    });
-  }, []);
 
-  const handleInputChange = useCallback((e: React.ChangeEvent<HTMLTextAreaElement>) => {
+  const sendOneMessage = useCallback(async (text: string) => {
-    const newValue = e.target.value;
+    if (!chatId) return;
-    setInput(newValue);
+    setSending(true);
-    if (isSlashCommandToken(newValue)) {
+    setPermissionPrompt(null);
-      setSlashState({ query: slashQuery(newValue) });
+    setLiveTaskCommands([]);
-    } else {
+
-      setSlashState(null);
+    const tempId = `temp-${Date.now()}`;
+    setMessages((prev) => [...prev, { id: tempId, role: 'user', content: text, status: 'complete' }]);
+
+    try {
+      const data = await api.coder.sendMessage(sessionId, {
+        content: text,
+        pane_id: paneId,
+        chat_id: chatId,
+        provider: agentConfig.provider !== 'boocode' ? agentConfig.provider : undefined,
+        model: agentConfig.model || undefined,
+        mode_id: agentConfig.modeId ?? undefined,
+        thinking_option_id: agentConfig.thinkingOptionId ?? undefined,
+      });
+      if (data.user_message_id) {
+        setMessages((prev) =>
+          prev.map((m) => (m.id === tempId ? { ...m, id: data.user_message_id! } : m))
+        );
+      }
+      if (data.task_id) {
+        setActiveTaskId(data.task_id);
+      } else {
+        setActiveTaskId(null);
+      }
+    } catch (err) {
+      toast.error(err instanceof Error ? err.message : 'failed to send');
+    } finally {
+      setSending(false);
     }
-  }, []);
+  }, [sessionId, paneId, chatId, agentConfig, setMessages]);
 
-  const handleKeyDown = useCallback(
+  // Drain queue when not busy
-    (e: React.KeyboardEvent) => {
+  useEffect(() => {
-      if (slashState) return;
+    if (sending || queue.length === 0 || queueProcessing.current) return;
-      if (e.nativeEvent.isComposing) return;
+    queueProcessing.current = true;
-      if (e.key === 'Enter' && !e.shiftKey) {
+    const next = queue[0]!;
-        e.preventDefault();
+    setQueue((prev) => prev.slice(1));
-        void handleSend();
+    sendOneMessage(next).finally(() => { queueProcessing.current = false; });
+  }, [sending, queue, sendOneMessage]);
+
+  const handleChatInputSend = useCallback(async (content: string) => {
+    const text = content.trim();
+    if (!text || !chatId) return;
+    if (sending) {
+      setQueue((prev) => [...prev, text]);
+      return;
+    }
+    await sendOneMessage(text);
+  }, [sending, chatId, sendOneMessage]);
+
+  const handleChatInputSlash = useCallback(async (skillName: string, userMessage: string) => {
+    if (!chatId) return;
+    if (agentConfig.provider === 'boocode' && skillsByName.has(skillName)) {
+      setSending(true);
+      setPermissionPrompt(null);
+      setLiveTaskCommands([]);
+      try {
+        await api.coder.skillInvoke(sessionId, paneId, skillName, userMessage.length > 0 ? userMessage : null);
+      } catch (err) {
+        toast.error(err instanceof Error ? err.message : 'skill invocation failed');
+      } finally {
+        setSending(false);
       }
-    },
+    }
-    [handleSend, slashState]
+  }, [chatId, sessionId, paneId, agentConfig.provider, skillsByName]);
-  );
 
   return (
     <div className="flex flex-col h-full bg-background">
+      <AgentComposerBar
+        projectPath={projectPath}
+        value={agentConfig}
+        onChange={setAgentConfig}
+        onProviderCommandsChange={handleProviderCommandsChange}
+        connected={connected}
+      />
       {/* Chat area — BooChat-style timeline (text + tool runs as siblings) */}
       <div className="flex-1 min-h-0 flex flex-col">
         {messages.length === 0 ? (
@@ -706,6 +770,9 @@ export function CoderPane({
           <CoderMessageList
             messages={messages as CoderTimelineWire[]}
             chatId={chatId}
+            actions={{
+              onResend: async (_chatId, content) => { await sendOneMessage(content); },
+            }}
             footer={
               activeTaskId && !permissionPrompt && sending === false ? (
                 <p className="text-xs text-muted-foreground animate-pulse">Agent running…</p>
@@ -738,44 +805,16 @@ export function CoderPane({
 
       {/* Composer + input */}
       <div className="shrink-0 border-t border-border">
-        {displayedCommands.length > 0 && <AgentCommandsHint commands={displayedCommands} />}
+        <ChatInput
-        <AgentComposerBar
+          disabled={sending || !chatId || chatPending}
-          projectPath={projectPath}
+          projectId={projectPath ?? ''}
-          value={agentConfig}
+          onSend={handleChatInputSend}
-          onChange={setAgentConfig}
+          onSlashCommand={handleChatInputSlash}
-          onProviderCommandsChange={handleProviderCommandsChange}
+          chatId={chatId ?? undefined}
+          chatLabel="BooCode"
+          messages={messages as unknown as import('@/api/types').Message[]}
+          modelContextLimit={null}
         />
-        <div className="p-2">
-        <div className="flex items-end gap-2">
-          <textarea
-            ref={inputRef}
-            value={input}
-            onChange={handleInputChange}
-            onKeyDown={handleKeyDown}
-            placeholder="Type / for commands…"
-            rows={1}
-            className="flex-1 resize-none rounded-md border border-input bg-background px-3 py-2 text-sm placeholder:text-muted-foreground focus-visible:outline-none focus-visible:ring-1 focus-visible:ring-ring max-h-32 min-h-[36px] max-md:min-h-[44px]"
-          />
-          <button
-            type="button"
-            onClick={() => void handleSend()}
-            disabled={!input.trim() || sending || !chatId || chatPending}
-            className="inline-flex items-center justify-center size-9 max-md:min-h-[44px] max-md:min-w-[44px] rounded-md bg-primary text-primary-foreground hover:bg-primary/90 disabled:opacity-40 disabled:cursor-not-allowed shrink-0"
-            aria-label="Send message"
-          >
-            <Send size={16} />
-          </button>
-        </div>
-        </div>
-        {slashState && (
-          <SlashCommandPicker
-            query={slashState.query}
-            items={displayedCommands}
-            inputRef={inputRef}
-            onSelect={handleSlashSelect}
-            onClose={() => setSlashState(null)}
-          />
-        )}
       </div>
     </div>
   );

apps/web/src/hooks/sessionEvents.ts

@@ -162,6 +162,10 @@ export interface ChatStatusEvent {
   reason?: ErrorReason;
 }
 
+export interface RefetchMessagesEvent {
+  type: 'refetch_messages';
+}
+
 export type SessionEvent =
   | SessionRenamedEvent
   | ProjectCreatedEvent
@@ -186,7 +190,8 @@ export type SessionEvent =
   | ProjectArchivedEvent
   | ProjectUnarchivedEvent
   | ProjectUpdatedEvent
-  | ChatStatusEvent;
+  | ChatStatusEvent
+  | RefetchMessagesEvent;
 type Listener = (event: SessionEvent) => void;
 
 const listeners = new Set<Listener>();

apps/web/src/hooks/useSessionStream.ts

@@ -294,5 +294,21 @@ export function useSessionStream(sessionId: string | undefined) {
     };
   }, [sessionId]);
 
+  useEffect(() => {
+    if (!sessionId) return;
+    return sessionEvents.subscribe((event) => {
+      if (event.type === 'refetch_messages') {
+        void api.messages
+          .list(sessionId)
+          .then((messages) => {
+            setState((s) => applyFrame(s, { type: 'snapshot', messages }));
+          })
+          .catch((err: unknown) => {
+            console.warn('refetch_messages failed', err);
+          });
+      }
+    });
+  }, [sessionId]);
+
   return state;
 }

apps/web/src/hooks/useSidebar.ts

@@ -184,6 +184,7 @@ function applyEvent(prev: SidebarResponse, event: import('./sessionEvents').Sess
     case 'chat_unarchived':
     case 'chat_deleted':
     case 'chat_status':
+    case 'refetch_messages':
       return prev;
     case 'project_archived': {
       const next = prev.projects.filter((p) => p.id !== event.project_id);

apps/web/src/hooks/useSidebarDrawer.tsx

@@ -1,6 +1,7 @@
 import { createContext, useCallback, useContext, useEffect, useState } from 'react';
 import type { ReactNode } from 'react';
 import { useLocation } from 'react-router-dom';
+import { useViewport } from './useViewport';
 
 interface SidebarDrawerState {
   open: boolean;
@@ -13,13 +14,17 @@ const Ctx = createContext<SidebarDrawerState | null>(null);
 export function SidebarDrawerProvider({ children }: { children: ReactNode }) {
   const [open, setOpen] = useState(false);
   const location = useLocation();
+  const { isMobile } = useViewport();
 
-  // Auto-close on navigation. Effect fires once on mount too (open default
-  // is false, so no observable effect) and on every pathname change after.
   useEffect(() => {
     setOpen(false);
   }, [location.pathname]);
 
+  // Close drawer on orientation change (landscape→portrait transition).
+  useEffect(() => {
+    setOpen(false);
+  }, [isMobile]);
+
   const toggle = useCallback(() => setOpen((v) => !v), []);
 
   return <Ctx.Provider value={{ open, setOpen, toggle }}>{children}</Ctx.Provider>;

apps/web/src/hooks/useViewport.ts

@@ -31,13 +31,48 @@ export function useViewport(): ViewportSnapshot {
     if (typeof window === 'undefined') return;
     const mobileMq = window.matchMedia(`(max-width: ${MOBILE_MAX}px)`);
     const tabletMq = window.matchMedia(`(min-width: ${MOBILE_MAX + 1}px) and (max-width: ${TABLET_MAX}px)`);
-    const update = () => setState(snapshot());
+    const update = () =>
+      setState((prev) => {
+        const next = snapshot();
+        // Bail if nothing changed — visualViewport 'resize' fires on every
+        // URL-bar show/hide and scroll, and a fresh object would re-render
+        // every consumer needlessly.
+        if (
+          prev.isMobile === next.isMobile &&
+          prev.isTablet === next.isTablet &&
+          prev.width === next.width
+        ) {
+          return prev;
+        }
+        return next;
+      });
+
+    // matchMedia 'change' alone is not enough on iOS Safari/Vivaldi: when a
+    // backgrounded tab is restored (bfcache) or refocused, no 'change' fires,
+    // and the width captured at first paint can be a stale/oversized value
+    // (iOS reports the wrong innerWidth for a beat before layout settles). That
+    // leaves isMobile=false on a phone, so the sidebar renders as a permanent
+    // desktop column with no way to close it. Re-snapshot on every signal that
+    // accompanies a rejoin/viewport correction, not just breakpoint crossings.
+    const onVisibility = () => {
+      if (document.visibilityState === 'visible') update();
+    };
     mobileMq.addEventListener('change', update);
     tabletMq.addEventListener('change', update);
+    window.addEventListener('resize', update);
+    window.addEventListener('orientationchange', update);
+    window.addEventListener('pageshow', update);
+    document.addEventListener('visibilitychange', onVisibility);
+    window.visualViewport?.addEventListener('resize', update);
     update();
     return () => {
       mobileMq.removeEventListener('change', update);
       tabletMq.removeEventListener('change', update);
+      window.removeEventListener('resize', update);
+      window.removeEventListener('orientationchange', update);
+      window.removeEventListener('pageshow', update);
+      document.removeEventListener('visibilitychange', onVisibility);
+      window.visualViewport?.removeEventListener('resize', update);
     };
   }, []);
 

apps/web/src/lib/attachments.ts

@@ -57,15 +57,17 @@ export function inferLanguage(filename: string): string | null {
 export function flattenToMessage(attachments: Attachment[], text: string): string {
   if (attachments.length === 0) return text;
   const blocks = attachments.map(a => {
-    const fence = '```' + (a.language ?? '');
+    // Pasted text is raw context, not code from a file — insert it verbatim with
-    let header: string;
+    // no ``` fence or provenance header. The chip only exists to keep the textarea
-    if (a.kind === 'lines') {
+    // tidy while composing; on send it should be exactly what the user pasted.
-      header = `// from: ${a.filename}:${a.range?.[0] ?? '?'}-${a.range?.[1] ?? '?'}`;
+    if (a.kind === 'paste') {
-    } else if (a.kind === 'paste') {
+      return a.content;
-      header = `// from: pasted text (${a.content.split('\n').length} lines)`;
-    } else {
-      header = `// from: ${a.filename}`;
     }
+    const fence = '```' + (a.language ?? '');
+    const header =
+      a.kind === 'lines'
+        ? `// from: ${a.filename}:${a.range?.[0] ?? '?'}-${a.range?.[1] ?? '?'}`
+        : `// from: ${a.filename}`;
     return `${fence}\n${header}\n${a.content}\n\`\`\``;
   });
   return [...blocks, text].filter(Boolean).join('\n\n');

apps/web/src/pages/Session.tsx

@@ -6,7 +6,7 @@ import {
   useParams,
   useSearchParams,
 } from 'react-router-dom';
-import { ChevronRight, FolderTree, Menu } from 'lucide-react';
+import { ChevronRight, FolderTree, Menu, X } from 'lucide-react';
 import { api } from '@/api/client';
 import type { Project, Session as SessionType } from '@/api/types';
 import { sessionEvents } from '@/hooks/sessionEvents';
@@ -61,6 +61,9 @@ function SessionInner({ sessionId }: { sessionId: string }) {
     initializeFirstChatIfEmpty,
     validatePanes,
   } = panesHook;
+  const [coderConnected, setCoderConnected] = useState<Record<string, boolean>>({});
+  const activePane = panes[activePaneIdx];
+  const activeIsCoder = activePane?.kind === 'coder';
 
   const openChatInActivePane = useCallback(
     (chatId: string) => openChatInPane(activePaneIdxRef.current, chatId),
@@ -402,6 +405,16 @@ function SessionInner({ sessionId }: { sessionId: string }) {
                 onAddPane={addPaneAndSwitch}
                 disabled={panes.length >= MAX_PANES}
               />
+              {activeIsCoder && activePane && panes.length > 1 && (
+                <button
+                  type="button"
+                  onClick={() => removePane(activePaneIdx)}
+                  className="inline-flex items-center justify-center min-h-[44px] min-w-[44px] rounded-full bg-muted/40 hover:bg-muted/70 text-foreground shrink-0"
+                  aria-label="Close pane"
+                >
+                  <X size={16} />
+                </button>
+              )}
             </div>
           </>
         ) : (
@@ -495,6 +508,11 @@ function SessionInner({ sessionId }: { sessionId: string }) {
           session={session}
           project={project}
           onAddPane={addPaneAndSwitch}
+          onCoderConnectedChange={(paneId, connected) =>
+            setCoderConnected((prev) =>
+              prev[paneId] === connected ? prev : { ...prev, [paneId]: connected },
+            )
+          }
         />
       )}
     </div>

codecontext/Dockerfile

@@ -15,9 +15,12 @@ WORKDIR /build
 
 RUN apk add --no-cache git ca-certificates build-base
 
-# Build codecontext from the v3.2.1 tag.
+# Build codecontext from the boocode-ts fork (has .codecontextignore support).
+# Source is staged into the build context by the pre-build step:
+#   tar -czf codecontext/fork.tar.gz -C /opt/forks/codecontext .
 # CGO is required: codecontext binds tree-sitter via cgo.
-RUN git clone --depth=1 --branch v3.2.1 https://github.com/nmakod/codecontext.git /build/codecontext
+COPY fork.tar.gz /build/fork.tar.gz
+RUN mkdir -p /build/codecontext && tar -xzf /build/fork.tar.gz -C /build/codecontext
 WORKDIR /build/codecontext
 RUN CGO_ENABLED=1 GOOS=linux go build -o /build/codecontext-bin ./cmd/codecontext
 

codecontext/shim.go

@@ -191,7 +191,7 @@ func startChild() error {
 	// initial scan target — codecontext rebuilds the graph against whatever
 	// target_dir each call carries, so this is just a valid bootstrap path
 	// (the default "." is the alpine root and trips on transient /proc fds).
-	child = exec.Command("codecontext", "mcp", "--target=/opt/projects", "--watch=true")
+	child = exec.Command("codecontext", "mcp", "--target=/opt/projects", "--watch=true", "--respect-gitignore")
 	var err error
 	childStdin, err = child.StdinPipe()
 	if err != nil {

data/AGENTS.md

@@ -7,7 +7,7 @@ top_p: 0.95
 top_k: 20
 min_p: 0.0
 presence_penalty: 0.0
-tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes]
+tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes, request_read_access, view_truncated_output, ask_user_input, git_status, get_blast_radius, get_hot_files, get_middleware, get_routes]
 description: Reviews code for bugs, security issues, and maintainability. Read-only.
 ---
 You review code. Find real problems, not style nits.
@@ -46,7 +46,7 @@ top_p: 0.95
 top_k: 20
 min_p: 0.0
 presence_penalty: 0.0
-tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes]
+tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes, request_read_access, view_truncated_output, ask_user_input, git_status, get_blast_radius, get_hot_files, get_middleware, get_routes]
 description: Diagnoses bugs from error messages, logs, or described symptoms.
 ---
 You diagnose bugs. Form a hypothesis, prove it with evidence from the code.
@@ -72,7 +72,7 @@ top_k: 20
 min_p: 0.0
 presence_penalty: 0.0
 steps: 5
-tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes]
+tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes, request_read_access, view_truncated_output, ask_user_input, git_status, get_blast_radius, get_hot_files, get_middleware, get_routes]
 description: Proposes refactors for clarity, deduplication, or decoupling. Read-only — outputs plans, not edits.
 ---
 You propose refactors. You do not apply them. The user applies via OpenCode or Claude Code.
@@ -115,7 +115,7 @@ top_k: 20
 min_p: 0.0
 presence_penalty: 1.5
 steps: 20
-tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes]
+tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes, request_read_access, view_truncated_output, ask_user_input, git_status, get_blast_radius, get_hot_files, get_middleware, get_routes]
 description: Designs new features, modules, or architectural changes. Outputs a build plan.
 ---
 You design. You produce build plans, not code.
@@ -157,7 +157,7 @@ top_p: 0.95
 top_k: 20
 min_p: 0.0
 presence_penalty: 0.0
-tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes]
+tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes, request_read_access, view_truncated_output, ask_user_input, git_status, get_blast_radius, get_hot_files, get_middleware, get_routes]
 description: Audits code for security vulnerabilities. Read-only.
 ---
 You audit for security issues. Concrete findings only, no generic warnings.
@@ -240,7 +240,7 @@ top_p: 0.95
 top_k: 20
 min_p: 0.0
 presence_penalty: 0.0
-tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes]
+tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes, request_read_access, view_truncated_output, ask_user_input, git_status, get_blast_radius, get_hot_files, get_middleware, get_routes]
 description: Discovers and maps unfamiliar codebases. Reads architecture, traces data flow, identifies key symbols.
 ---
 You map codebases. Start broad, then drill into specifics.
@@ -258,3 +258,67 @@ Output:
 - Data flow map (entry → transform → output)
 - Conventions observed
 - Areas that need deeper investigation
+
+
+## Planner
+---
+temperature: 0.6
+top_p: 0.95
+top_k: 20
+min_p: 0.0
+presence_penalty: 0.0
+steps: 10
+tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes, request_read_access, view_truncated_output, ask_user_input, git_status, get_blast_radius, get_hot_files, get_middleware, get_routes]
+description: Produces actionable step plans from requirements. Read-only — never modifies files.
+---
+You produce actionable step plans. You do not modify files.
+
+Process:
+1. Restate the goal. Confirm scope and constraints.
+2. Read the relevant code areas with view_file, list_dir, grep. Understand the current state before planning.
+3. Identify dependencies between steps. Order them so each step has its prerequisites met.
+4. Estimate complexity per step (small / medium / large).
+5. Call out risks and assumptions that could invalidate the plan.
+
+Output:
+- Goal: one line
+- Prerequisites: what must be true before starting
+- Steps: numbered, each with file paths, what changes, and acceptance criteria
+- Risks: what could go wrong, how to detect it
+- Verification: how to confirm the plan succeeded (test commands, type checks, manual checks)
+
+Rules:
+- Every step must be independently verifiable.
+- Do not produce code. Describe what to change, not the change itself.
+- If a step affects more than 3 files, break it into sub-steps.
+- Flag any step that requires a database migration or env var change.
+
+
+## Builder
+---
+temperature: 0.6
+top_p: 0.95
+top_k: 20
+min_p: 0.0
+presence_penalty: 0.0
+steps: 50
+tools: [find_files, get_codebase_overview, get_dependencies, get_file_analysis, get_framework_analysis, get_semantic_neighborhoods, get_symbol_info, grep, list_dir, search_symbols, view_file, watch_changes, request_read_access, view_truncated_output, ask_user_input, git_status, get_blast_radius, get_hot_files, get_middleware, get_routes, edit_file, create_file, delete_file, apply_pending, rewind]
+description: Implements changes using read and write tools. Routes all writes through pending changes.
+---
+You implement. Read the code, make the changes, verify they work.
+
+Process:
+1. Read the target files and understand the current state.
+2. Use grep and get_dependencies to find all call sites and dependents.
+3. Make changes via edit_file / create_file. All writes queue in pending_changes.
+4. Review pending changes before calling apply_pending.
+5. After applying, verify: read the modified files, check that the change is correct.
+
+Rules:
+- All file modifications go through edit_file / create_file / delete_file. Never bypass pending_changes.
+- Read before writing. Understand what exists before changing it.
+- Match existing code conventions: naming, imports, error handling patterns.
+- One logical change per edit. Do not bundle unrelated changes.
+- If a change breaks an import or type, fix it in the same batch before applying.
+- Use rewind if a batch of changes is wrong. Do not apply broken changes.
+- When done, state what changed and what the user should verify (type check, test, manual check)

docker-compose.yml

@@ -11,6 +11,7 @@ services:
       CONTAINER_GUIDANCE_FILE: /app/BOOCHAT.md
       DATABASE_URL: postgres://boocode:${POSTGRES_PASSWORD}@boocode_db:5432/boochat
       BOOCODER_URL: http://100.114.205.53:9502
+      LLAMA_SIDECAR_URL: http://100.101.41.16:8402
     volumes:
       - /opt:/opt
       - /opt/projects:/opt/projects:rw

openspec/changes/v2-6-persistent-agent-sessions/design.md

@@ -0,0 +1,283 @@
+# v2.6 Design — Persistent agent sessions
+
+Reference implementations: `/opt/forks/opencode` (server + SDK),
+`/opt/forks/paseo` (warm ACP + opencode server-manager + reasoning dedup).
+
+## 1. Architecture overview
+
+```
+                         BooCoder (systemd host service)
+  ┌─────────────────────────────────────────────────────────────────┐
+  │  dispatcher (per-turn unit = tasks row)                           │
+  │      │ resolve backend + worktree + agent-session for the chat    │
+  │      ▼                                                            │
+  │  agent-pool ──────────────────────────────────────────────────┐  │
+  │   ├─ OpenCodeServerBackend (1 process, N sessions)             │  │
+  │   │     `opencode serve` ◄── @opencode-ai/sdk ──► /event SSE   │  │
+  │   └─ WarmAcpBackend[session]  (1 stdio process per session)    │  │
+  │         `goose acp` / `qwen --acp` ◄── ClientSideConnection    │  │
+  └──────────────────────────────────────────────────────────────┘  │
+        │ broker.publishFrame (delta / reasoning_delta / tool_call)   │
+        ▼                                                            │
+     web (CoderPane) — unchanged                                     │
+```
+
+The **task row stays the per-turn unit**. What changes: instead of building a
+fresh world per task, the dispatcher resolves the chat's *persistent* backend,
+worktree, and agent-session, sends one prompt, streams events, diffs, and leaves
+everything warm.
+
+## 2. Backends
+
+Common interface (`AgentBackend`):
+
+```
+interface AgentBackend {
+  ensureSession(sessionId, opts): Promise<AgentSessionHandle>  // create-or-reuse
+  prompt(handle, input, { worktreePath, model, signal, onEvent }): Promise<TurnResult>
+  closeSession(handle): Promise<void>
+  dispose(): Promise<void>                                     // backend teardown
+  health(): 'up' | 'down'
+}
+```
+
+`onEvent` emits the same normalized events the current `acp-dispatch.ts` produces
+(`text`, `reasoning`, `tool_call`, `tool_update`) so the broker-frame publishing and
+`persistExternalAgentTurn` paths are reused unchanged.
+
+### 2a. OpenCodeServerBackend (shared HTTP server)
+
+- **Spawn once per BooCoder process:** `opencode serve --hostname 127.0.0.1 --port <p>`
+  with `OPENCODE_SERVER_PASSWORD=<random-at-boot>` (verified: `serve.ts`, `network.ts`;
+  default port 4096, prints `opencode server listening on http://…`). Use the official
+  `@opencode-ai/sdk` (`createOpencodeServer` / `createOpencodeClient`) rather than
+  hand-rolling HTTP — it already parses the ready line and wraps routes.
+- **One SSE subscription** to `GET /event`, consumed in a single read loop; events
+  demuxed by `properties.sessionID` → BooCode session. Reasoning arrives as
+  `message.part.delta` (`field: "reasoning"`) and `message.part.updated`
+  (`part.type: "reasoning"`); text as the `text` field; tool calls as tool parts.
+- **One opencode session per BooCode chat.** `client.session.create()` once, store the
+  returned `id` in `agent_sessions.agent_session_id`. Per-turn: `client.session.prompt({
+  path:{id}, body:{ parts:[{type:'text',text}], model:"provider/model" }})`. Worktree
+  routing via the `x-opencode-directory` header (set to the session's persistent
+  worktree) so the agent operates inside it.
+- **Reasoning dedup (port from Paseo `opencode-agent.ts`):** track
+  `streamedPartKeys` of `reasoning:${partID}`; when a `message.part.updated` reasoning
+  part arrives whose key was already streamed via delta, drop it. Prevents the
+  double-thought bug (covered by Paseo's `opencode-reasoning-dedup` e2e test).
+
+### 2b. WarmAcpBackend (goose, qwen — stdio)
+
+- **One persistent process + ACP connection per (chat, agent)** (Paseo's
+  `SpawnedACPProcess`): spawn `goose acp` / `qwen --acp` once, NDJSON over stdio,
+  `initialize` → `session/new` once; store the ACP session id in the
+  `agent_sessions` row. Each turn calls `session/prompt` on the same connection;
+  switching away and back resumes this same connection/session. Reuses the existing `acp-dispatch.ts`
+  `handleSessionUpdate` switch verbatim for `agent_message_chunk` /
+  `agent_thought_chunk` / `tool_call*`.
+- **Child lifetime is the pool's, not a request's.** Spawn detached/managed; do not
+  tie the process to a single dispatch's abort signal (only the in-flight `prompt`
+  gets the per-turn signal). Mirrors the codecontext shim rule (CLAUDE.md): supervise
+  the child and react to its exit, don't let a request scope kill it.
+
+## 3. Data model
+
+Agent switching is **free** within a chat (the picker is per-turn, not locked), so
+the worktree is shared across agents but each agent keeps its own backend session.
+That splits into two tables: one **shared worktree per chat**, and one **backend
+session per (chat, agent)** pair.
+
+```sql
+-- One shared worktree per BooCode chat. All agents used in the chat operate in it.
+CREATE TABLE IF NOT EXISTS session_worktrees (
+  session_id     UUID PRIMARY KEY REFERENCES sessions(id),
+  worktree_path  TEXT NOT NULL,
+  base_commit    TEXT,                          -- project HEAD captured at create (diff baseline)
+  created_at     TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp()
+);
+
+-- One backend session per (chat, agent). Resumed when the user switches back to
+-- that agent, so each agent retains its own conversation memory across switches.
+CREATE TABLE IF NOT EXISTS agent_sessions (
+  session_id        UUID NOT NULL REFERENCES sessions(id),
+  agent             TEXT NOT NULL,             -- opencode | goose | qwen (native boocode needs no row)
+  backend           TEXT NOT NULL,             -- opencode_server | acp_warm
+  agent_session_id  TEXT,                      -- opencode/ACP native session id (the memory handle)
+  server_port       INTEGER,                   -- opencode server port (nullable)
+  status            TEXT NOT NULL DEFAULT 'idle', -- idle | active | crashed | closed
+  last_active_at    TIMESTAMPTZ,
+  created_at        TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp(),
+  PRIMARY KEY (session_id, agent),
+  CONSTRAINT agent_sessions_backend_chk CHECK (backend IN ('opencode_server','acp_warm')),
+  CONSTRAINT agent_sessions_status_chk  CHECK (status IN ('idle','active','crashed','closed'))
+);
+```
+
+Plus one column for attribution (drives the DiffPanel badges in §9):
+
+```sql
+-- Which agent staged each pending change. Stamped at queue time:
+--   worktree-diff path → the task's agent; native boocode write tools → 'boocode';
+--   manual RightRail create (v2.5.x) → NULL (renders as "manual").
+ALTER TABLE pending_changes ADD COLUMN IF NOT EXISTS agent TEXT;
+```
+
+`tasks.worktree_path` already exists but was per-task; the persistent worktree now
+lives on `session_worktrees`. `tasks` stays the per-turn record (state machine
+unchanged) and gains nothing required. **Native boocode** keeps no `agent_sessions`
+row — it has no warm backend; it reconstructs conversation context from the chat's
+`messages` rows each turn (so it transparently sees every other agent's prior turns).
+DB is the source of truth for reconnect after a BooCoder restart (the in-memory pool
+rebuilds lazily from these tables on the next turn).
+
+## 3a. Agent switching & continuity (the decided model)
+
+Per the design review: **free switch, per-agent memory.** Concretely:
+
+- **Picker is per-turn.** The message route already sends `provider`/`model` per
+  message; nothing locks a chat to one agent. v2.6 keeps that.
+- **Worktree is shared.** All agents in a chat resolve the same `session_worktrees`
+  row, so file state carries across switches — *once applied*. (See the staging
+  boundary caveat below.)
+- **Each agent resumes its own session.** Switching opencode → boocode → opencode
+  reuses opencode's stored `agent_session_id` (its memory intact), not a fresh one.
+  Lazy-create on first use of an agent in the chat; resume thereafter.
+- **Native boocode is the universal reader.** It rebuilds from the `messages` table,
+  so it always sees the full transcript including other agents' turns.
+- **Gap turns are NOT auto-replayed** into a resumed agent. When you return to
+  opencode, it sees the shared worktree + your new prompt, but did not "hear" the
+  boocode/goose turns in between. (A future refinement could inject a short
+  "changes since you last ran" preamble; out of scope for v2.6.)
+- **Staging-boundary caveat (must be documented in the UI):** external agents edit
+  *inside the worktree*; native boocode reads/writes the *project root* via
+  `pending_changes`. So unapplied edits do **not** cross between a worktree agent and
+  native boocode — file continuity between the two only exists after apply. This is
+  an inherent consequence of v2.5's review-before-apply model, not a v2.6 bug.
+- **No mid-turn switch.** Per-chat turns are serialized (§5); the agent is fixed for
+  the duration of an in-flight turn. The user can switch the picker for the *next*
+  turn while one is running, but it won't retarget the running turn.
+
+## 4. Persistent worktree + incremental diff
+
+- **Create** on the first turn of a chat (`createWorktree(projectPath, sessionId)`
+  — keyed by chat, not task), capturing project HEAD as `base_commit`. Persist the
+  `session_worktrees` row; all agents in the chat share it.
+- **Reuse** every subsequent turn — no new worktree, no cleanup between turns.
+- **Diff strategy (per turn):** diff the worktree against the **project HEAD baseline**
+  captured when the worktree was created. Each turn supersedes the prior
+  `pending_changes` row for that session (one accumulating unified diff, latest wins) —
+  mirrors how the anchored rolling summary supersedes itself. Avoids stacking N partial
+  diffs the user must reason about; the pending change always reflects the full current
+  delta of the worktree.
+- **Apply** merges the worktree delta back to the project (existing `apply_pending`
+  path); after apply, re-baseline so the next turn's diff is relative to applied state.
+- **Cleanup** on chat close/archive (new hook) and on `dispose()`; removes the
+  `session_worktrees` row + all `agent_sessions` rows for the chat. Orphan reaper
+  sweeps worktrees with no live `session_worktrees` row (extends the periodic sweeper).
+
+## 5. Concurrency
+
+Current dispatcher: global `running` boolean → strictly one task at a time.
+Target: **per-session serialization, cross-session concurrency.**
+
+- Replace the single `running` flag with a `Map<sessionId, Promise>` in-flight registry.
+- `poll()` selects the oldest pending task whose **session has no in-flight turn**, so
+  two different chats run concurrently but a chat never has two turns at once (the agent
+  holds conversational state — overlapping prompts would corrupt it).
+- The LISTEN/NOTIFY `tasks_new` fast path (v2.5.x) already triggers immediate polls;
+  the registry replaces the boolean guard there too.
+
+## 6. Lifecycle & failure
+
+- **Lazy spawn:** backend/worktree/agent-session created on first turn for a session.
+- **Idle eviction:** pool evicts a backend/session after an idle TTL (e.g. 30 min);
+  worktree persists (DB-backed); next turn re-spawns and reattaches via stored
+  `agent_session_id` (opencode persists sessions on disk; ACP re-`session/new` if the
+  native id is gone).
+- **Crash recovery:** supervise children; on exit mark `agent_sessions.status='crashed'`,
+  publish `chat_status='error'`, and rebuild on the next turn. opencode server crash
+  takes all opencode sessions down → restart server, recreate sessions.
+- **Shutdown drain:** `app.addHook('onClose')` disposes the pool (close opencode server,
+  kill warm ACP children) after in-flight turns settle — extends the existing
+  dispatcher `stop()`.
+- **systemd:** BooCoder already spawns agent children under `NoNewPrivileges`; long-lived
+  pool children are fine. Use `context.Background`-equivalent detachment so children
+  outlive the dispatch that created them.
+
+## 7. Risks / open questions
+
+- **opencode single-server blast radius:** one crash drops all opencode sessions. Mitigated
+  by on-disk session persistence + lazy re-create. Could later shard one server per project
+  if it bites.
+- **Worktree disk growth:** persistent worktrees per session accumulate; the close-hook +
+  orphan reaper must be reliable or disk leaks. Add a max-live-worktrees cap with LRU evict.
+- **SDK version coupling:** `@opencode-ai/sdk` is a new workspace dep pinned to the installed
+  opencode (1.15.x). Probe-time version check should warn on major drift.
+- **Incremental-diff baseline correctness:** re-baselining after apply must handle the user
+  editing the project out-of-band; diff vs a stored base commit, not vs a moving target.
+- **Reconnect fidelity:** after BooCoder restart, reattaching to a stored opencode session id
+  assumes the server (also restarted) still has it on disk — verify the SDK reattach path.
+- **Cross-agent staging gap:** worktree agents and native boocode don't see each other's
+  *unapplied* edits (worktree vs project root). The UI must make this legible (e.g. show
+  which agent staged a pending change) so a switch doesn't look like lost work. A resumed
+  agent also won't have heard other agents' in-between turns — acceptable per the decided
+  model, but worth a small "N turns by other agents since you last ran" hint later.
+- **Per-(chat,agent) session sprawl:** a chat that cycles through many agents accumulates
+  warm backends/worktree co-tenants; idle eviction (§6) must key on (chat,agent), and the
+  opencode server's session count is bounded by eviction, not per-chat.
+
+## 8. File map (anticipated)
+
+| File | Change |
+|------|--------|
+| `apps/coder/src/services/agent-pool.ts` | NEW — pool + backend interface |
+| `apps/coder/src/services/backends/opencode-server.ts` | NEW — SDK + SSE demux + dedup |
+| `apps/coder/src/services/backends/warm-acp.ts` | NEW — persistent ACP connection |
+| `apps/coder/src/services/dispatcher.ts` | per-chat concurrency; resolve-or-create shared worktree + per-(chat,agent) backend session; no per-turn teardown |
+| `apps/coder/src/services/worktrees.ts` | chat-keyed create; baseline capture; re-baseline-on-apply |
+| `apps/coder/src/services/agent-turn-persist.ts` | reused as-is |
+| `apps/coder/src/schema.sql` | `session_worktrees` + `agent_sessions` (per (chat,agent)) + `pending_changes.agent` column |
+| `apps/coder/src/routes/sessions|tasks` | chat-close cleanup hook |
+| `apps/coder/src/routes/pending.ts` | `agent` on `listPending` response; stamp `agent` in queue paths |
+| `apps/coder/src/routes/agent-sessions.ts` | NEW — `GET /api/sessions/:id/agent-sessions` (§9b) |
+| `apps/coder/package.json` | add `@opencode-ai/sdk` dep |
+| `apps/web/src/components/panes/CoderPane.tsx` | `PendingChange.agent`; DiffPanel badges + staging hint; pass `sessionId` to composer |
+| `apps/web/src/components/AgentComposerBar.tsx` | optional `sessionId` prop; resumed/new chip; export `providerIcon` |
+| `apps/web/src/hooks/useAgentSessions.ts` | NEW — chat-scoped agent-session fetch |
+| `apps/web/src/api/client.ts` | `api.coder.agentSessions(sessionId)` |
+
+## 9. Frontend UX — agent attribution & switch affordances
+
+The switching model (§3a) is only good if it's **legible**: the user must see which
+agent did what, and whether switching back resumes or starts fresh. Pure read+display
+over the new `agent` column and `agent_sessions` — no dispatch-logic change.
+
+### 9a. Per-change agent attribution (DiffPanel) — Phase 1
+- **Wire:** `listPending` returns the row; add `agent` to the response and to the
+  frontend `PendingChange` type (`CoderPane.tsx`, today `{id, file_path, operation, diff?, status}`).
+- **UI:** each DiffPanel row gains a small agent badge before the file path — reuse the
+  `providerIcon()` switch from `AgentComposerBar` (extract to a shared helper / the new
+  `icons/ProviderIcons` module) + the provider label; `agent === null` → a neutral
+  "manual" chip. When the pending set spans >1 distinct agent, a one-line header note
+  ("Changes from opencode, boocode") makes mixed provenance obvious.
+
+### 9b. "Resumed" vs "new session" indicator (AgentComposerBar) — Phase 1
+- **API:** `GET /api/sessions/:id/agent-sessions` → `[{ agent, status, has_session, last_active_at }]`
+  (reads `agent_sessions` for the chat). Chat-scoped, so it is NOT foldable into the
+  project-level provider snapshot.
+- **Hook:** `useAgentSessions(sessionId)` — fetch on mount, refetch on `message_complete`
+  (same trigger `usePendingChanges` already uses).
+- **UI:** a subtle chip right of the Provider picker:
+  - current provider has a live row → muted **"resumed"** (title: "Resuming <agent> · last active <relative>").
+  - native boocode (never has a row) → **"history"** (it reconstructs from the transcript).
+  - otherwise → **"new session"**.
+  - Render only when connected and the chat has ≥1 prior turn; hidden on a fresh chat.
+  - `AgentComposerBar` gains an optional `sessionId?: string` prop (CoderPane has it);
+    absent → render nothing, so BooChat and other callers are unaffected.
+
+### 9c. Staging-boundary hint (DiffPanel) — Phase 3 polish
+- When the selected provider is **native boocode** and pending changes were staged by a
+  **worktree agent** (or vice-versa), show a one-line muted caveat:
+  "opencode's edits live in its worktree — boocode won't see them until applied."
+  Derived purely from per-change `agent` + current `value.provider`; no new state.
+  Keeps the §3a staging caveat from biting silently.

openspec/changes/v2-6-persistent-agent-sessions/proposal.md

@@ -0,0 +1,114 @@
+# v2.6 Persistent agent sessions (warm processes + OpenCode server)
+
+**Status:** Planned
+**Depends on:** v2.2 Paseo providers (ACP dispatch), v2.3 provider lifecycle (registry/snapshot)
+**Reference fork:** `/opt/forks/paseo`, `/opt/forks/opencode`
+**Pairs with:** the v2.5.x MessageBubble "Thinking" render fix — reasoning already flows; this batch is about persistence, not capability.
+
+## Why
+
+BooCode dispatches external agents (opencode, goose, qwen) **one-shot per task**:
+per task the dispatcher cuts a fresh worktree (`createWorktree(projectPath, taskId)`),
+spawns `opencode acp` / `goose acp` / `qwen --acp`, runs **one** turn, then tears
+down the process *and* the worktree (`dispatcher.ts:runExternalAgent`). Consequences:
+
+- **No session continuity.** A follow-up message in the same chat creates a new
+  task with a new worktree and a new agent process. The agent has no memory of
+  the prior turn beyond what BooCode replays as chat history, and it cannot see
+  the files it edited last turn (fresh worktree every time).
+- **Cold start every turn.** Each turn pays the process spawn + ACP `initialize`
+  handshake (and, for some agents, model load) before any work happens.
+- **Diverges from Paseo.** Paseo runs **OpenCode as a long-lived HTTP server**
+  (`opencode serve` + `@opencode-ai/sdk`, SSE `/event` stream) and keeps **goose /
+  qwen as warm stdio-ACP processes** (`SpawnedACPProcess`: one ACP connection,
+  `newSession()` once, many `prompt()`s). BooCode rebuilds the world per turn.
+
+This batch makes a BooCode chat map to a **persistent agent backend + a persistent
+worktree** that live for the whole conversation, so turns are warm and the agent
+sees its own accumulating edits. Reasoning passthrough is **already solved** (ACP
+`agent_thought_chunk` → `reasoning_delta` → the new MessageBubble Thinking block);
+this batch does not touch it beyond porting OpenCode's reasoning-dedup.
+
+## Decisions locked (from design review)
+
+- **Worktree model:** *Persistent worktree per session.* A chat owns one worktree
+  for the whole conversation; each turn the agent sees prior edits; pending_changes
+  accumulate; worktree is cleaned on session close, not per turn.
+- **Agent switching:** *Free switch, per-agent memory.* The picker stays per-turn
+  (not locked to a chat). The worktree is shared across agents; each agent keeps its
+  own backend session, resumed when you switch back to it. Native boocode reconstructs
+  from chat history (so it sees every agent's turns); a resumed agent does not auto-
+  ingest the gap turns. Data model: one shared worktree per chat + one backend session
+  per `(chat, agent)` pair. Caveat: unapplied edits don't cross the worktree↔project
+  boundary between external agents and native boocode (a v2.5 review-model consequence).
+- **Transport per agent (matches Paseo exactly):**
+  - **OpenCode** → one shared `opencode serve` HTTP server, driven via
+    `@opencode-ai/sdk`; one opencode *session* per BooCode chat (multi-session,
+    directory-routed via `x-opencode-directory`).
+  - **Goose / Qwen** → warm **stdio** ACP process per live session. Their HTTP
+    "server" modes are just ACP-over-HTTP wrappers (goose: undocumented/internal;
+    qwen `serve`: an HTTP bridge around a single `qwen --acp` child) — no gain over
+    stdio, so we keep stdio ACP like Paseo does.
+
+## Scope
+
+### In scope
+
+1. **Agent process pool** (`apps/coder/src/services/agent-pool.ts`) — owns long-lived
+   backends, lazy spawn, idle eviction, crash restart, shutdown drain.
+2. **OpenCode server backend** — spawn `opencode serve`, hold SDK client + single
+   SSE subscription demuxed by opencode `sessionID` → BooCode session; port +
+   `OPENCODE_SERVER_PASSWORD` managed at boot.
+3. **Warm ACP backend** — persistent `SpawnedACPProcess`-style connection for
+   goose/qwen reused across turns (one `newSession()`, many prompts).
+4. **Persistent worktree lifecycle** — worktree created on first turn of a session,
+   reused, diffed incrementally into `pending_changes`, cleaned on session close.
+5. **Session ↔ backend ↔ worktree mapping** — new `agent_sessions` table.
+6. **Per-session concurrency** — replace the dispatcher's global single-flight
+   `running` guard with per-session serialization (different sessions run
+   concurrently; one turn at a time within a session).
+7. **OpenCode reasoning dedup** — port Paseo's `streamedPartKeys` partID dedup so
+   reasoning isn't double-emitted (delta + final part).
+8. **Switch-aware UI** (design §9) — per-change agent attribution in the DiffPanel
+   (`pending_changes.agent` column + badges), a resumed/new-session chip on the
+   AgentComposerBar (chat-scoped `agent-sessions` endpoint), and a staging-boundary
+   hint so the worktree↔project gap is legible.
+9. **Tests + smoke** — pool lifecycle unit tests; multi-turn opencode smoke; switch
+   round-trip smoke; attribution/indicator smoke.
+
+### Out of scope (this batch)
+
+- Claude PTY→structured transport (separate deferred work — claude stays PTY here).
+- Goose/qwen HTTP server modes (intentionally not used).
+- Frontend redesign — existing CoderPane multi-turn chat UI already supports
+  follow-ups; only backend continuity changes.
+- Replacing `acp-dispatch.ts` wholesale — warm backend reuses its event handlers.
+- Cross-host agent servers (opencode server stays local to the BooCoder host).
+
+## Non-goals
+
+- Multi-user session sharing (single-user homelab).
+- Multiple concurrent turns within one agent session (the agent holds conversational
+  state; turns within a session are serialized).
+
+## Success criteria
+
+- Send two messages in one external-agent chat → second turn reuses the same agent
+  session **and** the same worktree (verified: no second `createWorktree`, agent
+  references files it edited in turn 1).
+- Warm-start latency for turn 2 materially below turn 1 (no spawn/handshake).
+- opencode reasoning shows once per thought (no dupes) in the Thinking block.
+- Killing the opencode server mid-session → pool restarts it and the next turn
+  recovers (opencode persists sessions on disk).
+- Switch opencode → boocode → opencode in one chat → opencode resumes its *same*
+  session (its memory intact), boocode saw opencode's turns as history, and all three
+  shared the one worktree. No agent is locked to the chat.
+- Closing/archiving a session removes its worktree; BooCoder restart drains cleanly.
+- Existing one-shot paths (arena, `new_task` tool, MCP create-task) still work.
+
+## Deliverables
+
+| Doc | Purpose |
+|-----|---------|
+| [`design.md`](./design.md) | Architecture, backends, data model, worktree/diff strategy, lifecycle, risks |
+| [`tasks.md`](./tasks.md) | Phased implementation checklist |

openspec/changes/v2-6-persistent-agent-sessions/tasks.md

@@ -0,0 +1,94 @@
+# v2.6 Tasks — Persistent agent sessions
+
+Phased so each phase is independently shippable and smoke-testable. Phase 1
+(OpenCode server) delivers the most value on the cleanest API; goose/qwen warm
+ACP follows; hardening last.
+
+## Phase 0 — Foundations (no behavior change)
+
+- [ ] 0.1 Add `session_worktrees` + `agent_sessions` tables (per `(session_id, agent)`)
+      to `apps/coder/src/schema.sql` (idempotent; see design §3).
+- [ ] 0.2 Define `AgentBackend` / `AgentSessionHandle` interface + normalized `onEvent`
+      event union (reuse shapes from `acp-dispatch.ts`).
+- [ ] 0.3 Scaffold `agent-pool.ts` with lazy get-or-create keyed by `(chat, agent)`,
+      health, `dispose()`; wire `app.addHook('onClose')` to dispose alongside dispatcher `stop()`.
+
+## Phase 1 — OpenCode server backend (multi-turn, warm)
+
+- [ ] 1.1 Add `@opencode-ai/sdk` to `apps/coder/package.json`; pin to installed opencode major.
+- [ ] 1.2 `backends/opencode-server.ts`: spawn `opencode serve` once (random
+      `OPENCODE_SERVER_PASSWORD`, allocated port), `createOpencodeClient`, wait for ready line.
+- [ ] 1.3 Single `/event` SSE read loop; demux by `properties.sessionID`; map
+      `message.part.delta`/`updated` (text + reasoning) + tool parts to `onEvent`.
+- [ ] 1.4 Port Paseo `streamedPartKeys` reasoning dedup (delta vs final part).
+- [ ] 1.5 `ensureSession`: reuse the `(chat, opencode)` `agent_sessions` row if present
+      (resume on switch-back), else `client.session.create()` → store `agent_session_id`.
+- [ ] 1.6 `prompt`: send via SDK with `x-opencode-directory` = session worktree + `model`.
+- [ ] 1.7 Dispatcher: when `agent==='opencode'`, route to pool backend instead of
+      `dispatchViaAcp`; keep broker frames + `persistExternalAgentTurn` identical.
+- [ ] 1.8 Persistent worktree: chat-keyed `createWorktree` (shared across agents);
+      capture base commit in `session_worktrees`; reuse across turns and agents.
+- [ ] 1.9 Per-session concurrency: replace global `running` with `Map<sessionId,Promise>`;
+      `poll()` skips sessions with an in-flight turn.
+- [ ] 1.10 Per-turn diff → supersede prior `pending_changes` row for the session (latest-wins).
+- [ ] **Smoke 1:** two messages in one opencode chat → same `agent_session_id`, same worktree,
+      no second `createWorktree`; agent references turn-1 edits; reasoning shows once; turn-2 faster.
+
+## Phase 1 (UX) — Attribution & switch affordances (design §9)
+
+- [ ] U.1 Stamp `pending_changes.agent` at queue time (worktree path → task agent;
+      native write tools → `'boocode'`; manual RightRail create → NULL).
+- [ ] U.2 Add `agent` to `listPending` response + frontend `PendingChange` type.
+- [ ] U.3 Extract `providerIcon()` to a shared helper; DiffPanel renders an agent badge
+      per row + a "Changes from X, Y" note when the pending set spans >1 agent (§9a).
+- [ ] U.4 `GET /api/sessions/:id/agent-sessions` route + `api.coder.agentSessions` +
+      `useAgentSessions(sessionId)` (refetch on `message_complete`) (§9b).
+- [ ] U.5 `AgentComposerBar` optional `sessionId` prop → resumed / history / new-session
+      chip beside the Provider picker; hidden on fresh chats and other callers (§9b).
+- [ ] **Smoke U:** stage edits with opencode then boocode → DiffPanel badges each row to the
+      right agent; composer shows "resumed" when re-selecting opencode, "new session" for goose.
+
+## Phase 2 — Warm ACP backend (goose, qwen)
+
+- [ ] 2.1 `backends/warm-acp.ts`: persistent spawn + `ClientSideConnection`; `initialize` +
+      `session/new` once; reuse `acp-dispatch.ts` `handleSessionUpdate`.
+- [ ] 2.2 `prompt`: `session/prompt` on the warm connection per turn; per-turn abort signal only.
+- [ ] 2.3 Child supervision: detached lifetime, exit handler marks `status='crashed'`.
+- [ ] 2.4 Dispatcher routes `goose`/`qwen` to warm backend; keep one-shot fallback for arena/MCP
+      (or opt those into pool too — decide in review).
+- [ ] **Smoke 2:** two messages in a goose chat reuse the same process + ACP session + worktree;
+      reasoning still renders; no per-turn respawn.
+- [ ] **Smoke 2b (switch round-trip):** opencode → boocode → opencode in one chat — opencode
+      resumes the SAME `agent_session_id` (memory intact), boocode saw opencode's turns as
+      history, all three shared the one worktree, and no agent was locked to the chat.
+
+## Phase 3 — Lifecycle hardening
+
+- [ ] 3.1 Idle TTL eviction keyed per `(chat, agent)`; reattach-on-next-turn from `agent_sessions`.
+- [ ] 3.2 Crash recovery: opencode server restart recreates sessions; ACP re-`session/new`.
+- [ ] 3.3 Chat close/archive hook → `closeSession` for every `(chat, agent)` + remove the
+      shared `session_worktrees` row + worktree; mark agent rows `status='closed'`.
+- [ ] 3.4 Orphan worktree reaper (extend periodic sweeper) + max-live-worktrees LRU cap.
+- [ ] 3.5 Re-baseline worktree diff after `apply_pending`.
+- [ ] 3.6 Reconnect test: restart BooCoder mid-session → next turn reattaches/recreates cleanly.
+- [ ] 3.7 Staging-boundary hint in DiffPanel (§9c): muted one-liner when the selected
+      provider can't see another agent's unapplied worktree edits (derived from per-change
+      `agent` + current provider; no new state).
+
+## Tests
+
+- [ ] T.1 `agent-pool` unit: get-or-create, idle evict, dispose drains in-flight (DB-opt-in pattern).
+- [ ] T.2 opencode SSE demux + reasoning dedup unit (fixture event stream).
+- [ ] T.3 per-session concurrency: two sessions run concurrently, one session serializes.
+
+## Docs
+
+- [ ] D.1 Update `CLAUDE.md` (BooCoder dispatch section) + `BOOCODER.md` health/contract.
+- [ ] D.2 Note opencode `@opencode-ai/sdk` dep + `OPENCODE_SERVER_PASSWORD` env in env docs.
+- [ ] D.3 `CHANGELOG.md` entry on tag (`v2.6.0-persistent-agent-sessions`).
+
+## Build / deploy gate
+
+- [ ] B.1 `pnpm -C apps/server build && pnpm -C apps/coder build` clean.
+- [ ] B.2 `pnpm -C apps/server test` (+ DB-opt-in) green.
+- [ ] B.3 Deploy: `sudo systemctl restart boocoder`; `curl :9502/api/health` reports tool count.