docs(changelog): v2.6.2-delete-guard-and-sse

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

.gitignore

@@ -16,5 +16,5 @@ data/*
 !data/AGENTS.md
 !data/skills/
 !data/mcp.json
-!data/coder-providers.json
+!data/coder-providers.example.json
 codecontext/fork.tar.gz

BOOCODER.md

@@ -44,7 +44,7 @@ BooCoder's coding agents are a **config-backed registry**: built-ins live in `pr
 
 ### Config file: `data/coder-providers.json`
 
-Resolved from `CODER_PROVIDERS_PATH` (default `/data/coder-providers.json`; dev/host path `/opt/boocode/data/coder-providers.json`). It is **tracked in git** via a `.gitignore` exception (the rest of `data/*` is ignored). A missing file, invalid JSON, or a schema mismatch all fall back to built-ins-only — loading never throws at startup.
+Resolved from `CODER_PROVIDERS_PATH` (default `/data/coder-providers.json`; dev/host path `/opt/boocode/data/coder-providers.json`). It is **gitignored** — it's live runtime config that the coder reads *and writes* (UI toggles `PATCH` it), so tracking it would churn `git status`. The tracked reference is `data/coder-providers.example.json`; copy it to `coder-providers.json` to seed overrides. A missing file, invalid JSON, or a schema mismatch all fall back to built-ins-only — loading never throws at startup.
 
 ```json
 {

CHANGELOG.md

@@ -2,6 +2,22 @@
 
 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.
 
+## v2.6.2-delete-guard-and-sse — 2026-05-30
+
+Two coder-side batches under one tag. **Session-delete work-loss guard:** deleting a BooChat session CASCADE-wipes its `session_worktrees` row, which would silently orphan uncommitted/unpushed/unmerged work — so the server's `DELETE /api/sessions/:id` now gates before the delete. It reads `session_worktrees` from the shared DB first (no row → chat-only session → delete immediately, zero round-trip), and for worktree-backed sessions calls a new BooCoder endpoint (`/worktree-risk`) that runs git on the host, since the container can't see `/tmp/booworktrees` — only the host systemd service can. `checkWorktreeWorkAtRisk` reports dirty/unpushed/unmerged via the audited `hostExec`+`shellEscape` path, default branch detected from `refs/remotes/origin/HEAD` (never the worktree's own branch, never hardcoded); any at-risk worktree returns 409 with per-worktree `RiskReport[]`, `force=true` bypasses, and the check is fail-closed (BooCoder unreachable also blocks — force still escapes). The sidebar renders a block dialog distinguishing work-at-risk (Commit/Stash/Force; stash uses `-u` and re-blocks on remaining commits) from couldn't-verify (Cancel/Force), and Commit never auto-commits. A follow-up fix gates the `unpushed` arm behind an actual upstream (`atRisk = dirty || unmerged > 0 || (hasUpstream && unpushed > 0)`) so the no-upstream `session-<id>` branches stop flagging every pristine worktree-backed session — no protection lost, since real local work always also surfaces as `unmerged > 0`. **Per-session SSE (P1.5-a):** replaces the single global SSE loop scoped to the most-recent worktree directory — the known limit flagged in `v2.6.1-phase1-opencode` — with one `event.subscribe({directory})` per live opencode session, so sessions in different worktrees stream concurrently instead of the second silently dropping the first's events. Each session owns an `AbortController` wired into `subscribe(…, {signal})`, which also fixes a latent Phase-1 bug where switching directories left the old loop parked forever in its `for await` (zombie loops); a `sessionID` demux guard drops cross-session events so two sessions sharing a worktree (possible after P1.5-b) don't double-process deltas. The opencode SDK was confirmed to open an independent SSE connection per `subscribe()` call, so N concurrent dir-scoped streams are supported.
+
+## v2.6.1-phase1-opencode — 2026-05-30
+
+v2.6 Phase 1: opencode runs as a warm HTTP server (`apps/coder/src/services/backends/opencode-server.ts`) — one `opencode serve` per BooCoder process, one opencode session per BooCode session resumed across turns via the new `agent_sessions` table, with a single SSE read loop, reasoning dedup ported from Paseo, an inactivity watchdog, and a stale-session guard (crashed-not-resumed + a `config_hash` fingerprint over `opencode_server|<model>`, deliberately excluding the ephemeral server port so cross-restart resume survives). Builds on the `v2.6.0-phase0-foundations` schema/interface scaffold. The batch's hard-won fixes: opencode streams `session.next.*` events (not `message.part.*`), and `event.subscribe()` must pass the session's worktree `directory` or events route to the server CWD and turns come back empty; model strings must be `llama-swap/`-prefixed and present in opencode's own config, with `agent-probe` now populating `available_agents.models` via `mergeLlamaSwap` so the frontend stops sending an empty model; `session_worktrees`/`agent_sessions` FKs are `ON DELETE CASCADE` so session deletion no longer 500s. Also bundled: dcp-message-id tag stripping from opencode text output, a reopen-closed-pane control, the `[+]`/split-pane button separation, auto-name using the session's loaded model, and a `systematic-debugging` slash command. Smoke 1 verified end-to-end (two turns, session reuse, turn 2 ~9x faster). Known Phase 1 limit: one SSE stream scoped to the most-recent session's directory — concurrent opencode sessions in different worktrees collide (warns; per-session SSE is Phase 2).
+
+## v2.5.15-acp-path-guard — 2026-05-29
+
+Security fix + repo hygiene. Fixes a path-traversal in the ACP filesystem bridge (`acp-client-fs.ts`, flagged by the automated push security review): the worktree guard used an unbounded `startsWith(resolve(worktreePath))`, so a sibling path sharing the worktree as a string prefix (`<worktree>-evil/…`) escaped the scope — and `writeWorktreeTextFile` writes to disk directly (no `pending_changes` gate), so a confused/buggy ACP agent could write outside its worktree. Now uses a separator-bounded check matching `write_guard.ts` (`resolve()` + `startsWith(root + sep)` / `=== root`) via a shared `resolveInWorktree`, with a regression test covering `../` traversal and the sibling-prefix bug. Symlink-swap/`O_NOFOLLOW` hardening was intentionally skipped — consistent with `write_guard`'s no-realpath stance, and the agent already runs with host FS access so this is a containment guard, not a trust boundary. Separately, stops tracking the live `data/coder-providers.json` (it's runtime config the UI reads *and writes* on provider toggles, which churned `git status`) — it's now gitignored with a tracked `data/coder-providers.example.json` reference; the loader falls back to built-ins-only when the live file is absent. The provider-type duplication (coder ↔ web) stays guarded by the existing text-identity `provider-types-parity.test.ts` — a shared package was considered and declined (drift is already prevented; not worth the Docker/build-order risk at solo scale).
+
+## v2.5.14-claude-md — 2026-05-29
+
+Docs-only — CLAUDE.md session-learnings update, no code. Adds gotchas surfaced while shipping the v2.3 provider-lifecycle batch: the host `boocoder.service` keeps running the old process after `pnpm -C apps/coder build` (stale-process tell = new routes 404 while old routes 200, restart don't re-debug); the `boocode` container `build: .` deploys the working tree, so web edits are live on the Vite dev server but not production until `docker compose up --build -d boocode`; `PATCH /api/providers/config` replaces a provider's override wholesale (send `{...existing, enabled}` or a custom ACP entry's command is wiped) and `data/coder-providers.json` is live config not to be committed as code; external agents dispatch one-shot with no context/token tracking (only native `boocode` tracks ctx; OpenCode-as-server is the unshipped `v2-6-persistent-agent-sessions` plan); the `ui/` primitive inventory with `button role=switch` / Dialog fallbacks for the absent switch/sheet; and the mobile Dialog-with-list scroll-containment recipe. Also backfills previously-uncommitted doc bullets for the `v2.5.7`–`v2.5.11` coder work (provider-type parity test, async ACP command discovery, AgentComposerBar `installed` filter, provider-registry path disambiguation).
+
 ## v2.5.13-provider-lifecycle-phase5 — 2026-05-29
 
 Closeout of the v2.3 provider-lifecycle batch — the web UI (Phase 5) plus docs (Phase 6). Provider management moved into **Settings → Providers**: a tab listing every registered provider with a status badge (Available / Disabled / Not installed / Error / Loading), an enable/disable toggle, a per-provider refresh, and a plaintext diagnostic; toggling sends the provider's *full* override (preserving a custom ACP entry's command under the wholesale-replace PATCH merge) then refetches the snapshot. The composer's provider picker now filters to `enabled && (status === 'ready' || 'loading')`, so disabled and unavailable providers drop out of the picker and are managed only in settings (native `boocode` always shows). A curated ACP catalog (`apps/web/src/data/acp-provider-catalog.ts`) + `AddProviderModal` register custom providers via `PATCH /api/providers/config` then a subset refresh, and the web client gained `getProvidersConfig` / `patchProvidersConfig` / `refreshProviders` / `getProviderDiagnostic`. Two mobile fixes ship alongside: the Settings pane is now reachable on phones (opening it pushes `?pane=` atomically so the mobile URL-sync effect keeps it active instead of snapping back to the chat pane), and the Add-provider modal caps to the viewport with a single `overscroll-contain` scroll region so the list scrolls instead of dragging the whole modal. This completes the arc begun in `v2.5.4-provider-lifecycle-phase1` (config-backed registry over the built-ins) → `v2.5.5-provider-lifecycle-phase2` (loading/unavailable snapshot lifecycle + tier-2 probe TTL gate) → `v2.5.6-provider-lifecycle-phase3` (generic `resolveLaunchSpec` ACP dispatch) → `v2.5.12-provider-lifecycle-phase4` (config GET/PATCH, subset refresh, diagnostic HTTP API). Docs landed in `BOOCODER.md` (config file, refresh contract, enable/disable, custom ACP, the honest subset-refresh known limitation) and `docs/DEFERRED-WORK.md` §2 is marked addressed; the remaining Tier-2 follow-ups (WS `provider_snapshot_updated` frame, `available_agents.enabled` column, shared types package, MCP provider tools) stay deferred.

CLAUDE.md

@@ -68,9 +68,9 @@ Key services:
 - **`messages_with_parts` view** (v1.13.1-B; `schema.sql`). Read sites that need `tool_calls` / `tool_results` / `reasoning_parts` SELECT from this view, NOT `messages` directly. v1.13.20 dropped the legacy `messages.tool_calls` / `messages.tool_results` JSON columns; the view now reads parts-only subselects. Writes target `message_parts` exclusively via `insertParts` (or via the helpers `partsFromAssistantMessage` / `partsFromToolMessage`). The `Message` wire type still carries `tool_calls?` / `tool_results?` because the view synthesizes them from parts — frontend reads are unchanged. Shapes: `tool_calls jsonb[]`, `tool_results jsonb` single object, `reasoning_parts jsonb[]` of `{text}`. If you ever need to UPDATE a message and return its full Message shape, do a two-step UPDATE returning `id` followed by SELECT from the view — RETURNING off the bare `messages` table no longer carries the tool fields.
 - **`services/file_ops.ts`** — Shared file operation implementations used by both inference tools and HTTP routes.
 - **`services/auto_name.ts`** — Non-streaming LLM call to generate 4-word session titles after first assistant reply.
-- **`services/provider-registry.ts`** — Static registry of provider metadata (label, transport, model source). `PROVIDERS` array, `PROVIDERS_BY_NAME` map. 5 providers: boocode (native), opencode (acp), goose (pty), claude (pty), qwen (pty).
-- **`services/agent-probe.ts`** — Startup probe using direct `exec()` (not SSH). Discovers installed agents on host, their versions, ACP support, and models. Qwen models read from `~/.qwen/settings.json`. Claude models are static from the registry. Results persisted to `available_agents` table.
-- **`routes/providers.ts`** — `GET /api/providers` returns installed providers with models. Transport field reflects actual capability (checks `supports_acp` from DB, not just registry preference).
+- **`apps/coder/src/services/provider-registry.ts`** (BooCoder, NOT apps/server) — Static registry of provider metadata (label, transport, model source). `PROVIDERS` array, `PROVIDERS_BY_NAME` map. 5 providers: boocode (native), opencode (acp), goose (pty), claude (pty), qwen (pty).
+- **`apps/coder/src/services/agent-probe.ts`** (BooCoder) — Startup probe using direct `exec()` (not SSH). Discovers installed agents on host, their versions, ACP support, and models. Qwen models read from `~/.qwen/settings.json`. Claude models are static from the registry. Results persisted to `available_agents` table.
+- **`apps/coder/src/routes/providers.ts`** (BooCoder) — `GET /api/providers` returns installed providers with models. Transport field reflects actual capability (checks `supports_acp` from DB, not just registry preference). The apps/server side of this flow is the "Provider picker dispatch" bullet below.
 - **Provider picker dispatch**: when `provider !== 'boocode'`, the message route creates a `tasks` row (with `session_id` set) instead of calling `inference.enqueue`. The dispatcher picks it up and dispatches via ACP or PTY using the agent's `install_path`.
 
 Route registration: all routes registered in `index.ts` via `register*Routes(app, sql, ...)` functions. Routes are in `routes/*.ts`.
@@ -80,12 +80,19 @@ Route registration: all routes registered in `index.ts` via `register*Routes(app
 - Write-capable coding agent. Runs as a **systemd service on the host** (`boocoder.service`), NOT in Docker. Fastify server at port 9502, connects to postgres at `127.0.0.1:5500`.
 - **Workspace dependency on `@boocode/server`**: imports `createInferenceRunner`, `createBroker`, `ALL_TOOLS`, `appendMcpTools` from the server's compiled `dist/`. apps/server's `package.json` has an `exports` map with `types` conditions for NodeNext resolution. apps/server must build FIRST.
 - Build + deploy: `pnpm -C apps/server build && pnpm -C apps/coder build && sudo systemctl restart boocoder`. Env file at `apps/coder/.env.host`. Service file at `/etc/systemd/system/boocoder.service`.
+- After `pnpm -C apps/coder build` the host `boocoder.service` keeps running the OLD process until `sudo systemctl restart boocoder` — a stale process shows **new routes 404 with `{error:'not found'}` while old routes still 200** (the `/api` not-found handler returns that shape). Restart, don't re-debug.
 - Agent dispatch spawns binaries directly using `install_path` from `available_agents` — no `spawn('sh', ['-c', ...])` (fails under systemd). Follows Paseo's pattern: `spawn(fullBinaryPath, argsArray, { cwd })`.
 - systemd hardening: only `NoNewPrivileges=true` is safe. `ProtectSystem`, `ProtectHome`, `PrivateTmp` all break agent dispatch (agents need full filesystem access to read configs, write to worktrees).
 - `apps/server/tsconfig.json` has `declaration: true` so `.d.ts` files exist for workspace consumers.
 - Write tools (`edit_file`, `create_file`, `delete_file`, `apply_pending`, `rewind`) queue in `pending_changes` table. Nothing hits disk until `apply_pending` is called. `write_guard.ts` validates paths (resolve + prefix-check, no realpath since files may not exist for creates).
 - Frontend: NOT a separate SPA. BooCoder is a `'coder'` pane type within BooChat's SPA (`apps/web/`). `CoderPane.tsx` in `apps/web/src/components/panes/`. API requests go through `/api/coder/*` proxy (Vite dev + Fastify production) which rewrites to the boocoder host service (`BOOCODER_URL` env var, default `http://100.114.205.53:9502`). WS connects directly to `:9502`.
 - `apps/coder/web/` is a STANDALONE fallback SPA served at `:9502` directly. The PRIMARY BooCoder frontend is the `CoderPane` in BooChat's SPA (`apps/web/src/components/panes/CoderPane.tsx`), accessible via the "Coder" pane in the workspace at `code.indifferentketchup.com`. Both exist; the pane is what Sam uses.
+- **Provider snapshot lifecycle** (`apps/coder/src/services/`): `provider-config.ts` (Zod config, never-throws on bad input) → `provider-config-registry.ts` (`buildResolvedRegistry`, singleton) → `provider-snapshot.ts` (two-tier probe: tier-1 fast presence, tier-2 cold ACP probe skipped unless force / stale `PROVIDER_PROBE_TTL_MS` 24h / dbEmpty; cached). Verify live: `curl http://100.114.205.53:9502/api/providers/snapshot` — returns providers + models + commands, the exact shape `AgentComposerBar` renders.
+- `PATCH /api/providers/config` replaces a provider id's override object **wholesale** (per-id shallow merge) — to flip one field send `{...existing, enabled}`, or a custom ACP entry's `command`/`label` is wiped and it drops out of the resolved registry. `data/coder-providers.json` is **gitignored** (it's live runtime config — the coder reads AND writes it on UI toggles); the tracked reference is `data/coder-providers.example.json`. The loader falls back to `{providers:{}}` (built-ins only) when the live file is absent, so a fresh checkout needs no copy.
+- **opencode** runs as a warm HTTP server (v2.6 Phase 1, `services/backends/opencode-server.ts` — `opencode serve` per BooCoder process, one opencode session per BooCode session, resumed via `agent_sessions`). goose/qwen/claude still dispatch **one-shot** ACP/PTY with no ctx/token usage; only native `boocode` (llama-swap engine) tracks ctx. Paseo's per-provider native clients (design §12) deliberately not ported.
+- **opencode SSE** (`opencode-server.ts`): live streaming arrives as `session.next.text.delta` / `session.next.reasoning.delta` / `session.next.tool.{called,success,failed}` — NOT `message.part.*` (those are terminal/post-hoc). `client.event.subscribe({ directory })` MUST pass the session's worktree directory; omit it and opencode scopes events to the server's `process.cwd()` → zero session events (empty turns, 180s watchdog timeout). One SSE stream at a time scoped to the last session's dir — concurrent opencode sessions in different worktrees collide (known Phase 1 limit, warns). Turn completes on `session.idle`; `promptAsync` is fire-and-forget (204).
+- **opencode model strings** must be provider-prefixed (`llama-swap/<model>`) AND exist in `~/.config/opencode/opencode.json` `provider.llama-swap.models` — not merely loadable by llama-swap. `parseModel` infers `llama-swap/` for a bare id; the dispatcher coalesces empty→DEFAULT_MODEL then prefixes. `agent-probe` populates opencode's `available_agents.models` via `mergeLlamaSwap` (fetches `/v1/models`); empty model list → frontend sends `''` → no inference (`input:0`, empty turn).
+- **agent_sessions resume**: `config_hash = sha256('opencode_server|<model>')` — must NOT include the server port (random per boot; including it breaks cross-restart resume). `session_worktrees` + `agent_sessions` FKs to `sessions(id)` are `ON DELETE CASCADE` (else DELETE /api/sessions/:id 500s on FK violation). The `@opencode-ai/sdk` v2 client takes flattened params (`{sessionID, directory, parts, model:{providerID,modelID}}`), imports `createOpencodeClient` from `@opencode-ai/sdk/v2/client`.
 
 ### Frontend (`apps/web/src/`)
 
@@ -145,6 +152,7 @@ BooCoder at port 9502: `curl http://100.114.205.53:9502/api/health`. Runs as `bo
 - Tag naming: `vMAJOR.MINOR.PATCH-slug` (e.g. `v1.13.13-ws-publish`). Monotonic per minor — the slug describes the batch's content so the tag name alone is enough to recall what shipped. No letter suffixes (`-a`/`-b`), no pseudo-ranges (`v1.11.x`), no slug-only sub-versions sharing a number (`v1.13.15-tools` + `-openspec` + `-agentlint` — split into sequential patches instead).
 - `CHANGELOG.md` is the per-tag release log, most-recent on top. When a new tag is created, add a `## <tag> — <YYYY-MM-DD>` section with a 3–6 sentence paragraph summarizing what shipped, drawn from the commit body. Cross-reference other tags by name when the batch builds on, fixes, or pairs with prior work (e.g. "pairs with `v1.13.12-ws-schemas`", "fixed in `v1.13.5-stability-bundle`"). No nested bullets — one paragraph.
 - 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).
+- The `boocode` container is `build: .` — it builds web+server from the **working tree**, so uncommitted changes deploy. Web edits are live on the Vite dev server (HMR) but NOT on production (`:9500` / code.indifferentketchup.com) until `docker compose up --build -d boocode`.
 - 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. `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.
@@ -172,10 +180,12 @@ BooCoder at port 9502: `curl http://100.114.205.53:9502/api/health`. Runs as `bo
 - Discriminated unions for type narrowing: `Pane` (by `kind`), `SessionEvent` (by `type`), `InferenceFrame` (by `type`).
 - **Adding a new WS frame type** requires updating BOTH the server's `InferenceFrame` (loose `type:` union + optional fields in `services/inference/turn.ts`) AND the web `WsFrame` (strict discriminated union in `apps/web/src/api/types.ts`). Server publish is permissive; the frontend type is the wire-format gate. The `'usage'` frame added in v1.12.2 needed both sides; missing the web side silently drops the frame at JSON-parse.
 - shadcn primitives live in `components/ui/`. Don't modify them unless adding a new primitive.
+- `ui/` primitives present: button, card, context-menu, dialog, dropdown-menu, input, label, radio-group, sonner, textarea. No switch/sheet/drawer/badge/checkbox — use a `<button role="switch" aria-checked>` toggle (a hand-rolled `Switch` already lives in `SettingsPane.tsx`) and a Dialog-based panel for "drawers".
 - `inferLanguage()` from `lib/attachments.ts` is the canonical file-extension-to-language map. `CodeBlock.tsx` keeps its own `LANG_MAP` because it also resolves markdown fence names.
 - Two UI event buses: `hooks/sessionEvents.ts` for DB-state events (chat_created, session_updated); `lib/events.ts` for ephemeral UI (`sendToTerminal`, `terminalsRegistry`). Don't merge — different subscriber lifecycles.
 - `vite.config.ts` proxy entries are order-sensitive: more-specific prefixes (`/api/term`, `/ws/term`) must come BEFORE `/api`.
 - Mobile pane URL sync (`Session.tsx`): the `?pane=<id>` effect resets `activePaneIdx` whenever `panes` changes. New-pane creation on mobile must push `?pane=` atomically — `addPaneAndSwitch` is the wrapper that does this. `addSplitPane` returns the new pane id for callers.
+- A scrollable list inside a Dialog on mobile: cap `DialogContent` (`max-h-[85vh]` + `grid-rows-[auto_minmax(0,1fr)_auto]`) and make the list the single scroll region with `overscroll-contain` — otherwise touch-scroll drags the whole fixed modal / chains to the page.
 - xterm.js v5 uses canvas rendering — browser doesn't see xterm's selection; the native right-click menu has no working Copy for terminal text. App keybindings (`Cmd/Ctrl-C`, `Cmd/Ctrl-Shift-C`) are the path.
 - **New tools** live in their own `services/<name>.ts` file (see `web_search.ts`, `web_fetch.ts`) — exports a pure `executeFoo(input, ...deps)` for direct test access plus a `ToolDef` wrapper that `loadConfig()`s its real dependencies. Register the ToolDef in `tools.ts` `ALL_TOOLS` (and `READ_ONLY_TOOL_NAMES` if applicable). Inject `fetcher: typeof fetch = fetch` rather than `vi.spyOn(globalThis, 'fetch')` — cleanup is simpler and the production call site stays unchanged.
 - **Sentinels** are `role='system'` rows with structured `metadata.kind` (`cap_hit`, `doom_loop`). UI-only — `buildMessagesPayload` strips them via `isAnySentinel` so the LLM never sees them. A new kind requires arms in `MessageMetadata` in BOTH `apps/server/src/types/api.ts` AND `apps/web/src/api/types.ts`, plus a render branch in `apps/web/src/components/MessageBubble.tsx`.
@@ -191,6 +201,9 @@ BooCoder at port 9502: `curl http://100.114.205.53:9502/api/health`. Runs as `bo
 - **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.
+- **AgentComposerBar filters `e.installed`**: provider snapshot entries with `installed:false` (loading/unavailable) are dropped from the dropdown. `getProviderSnapshot` must await the full build — returning synchronous `loading` placeholders makes every provider vanish (the v2.5.7 "no providers showing up" regression); surfacing loading states needs a client poll.
+- **Coder↔web provider-type parity** (`apps/coder/src/services/provider-types.ts` ↔ `apps/web/src/api/types.ts`): enforced by runtime `provider-types-parity.test.ts` (compile-time cross-import is blocked by TS6307 on web's composite tsconfig). Mirror of the ws-frames parity pattern — edit both copies together or the test fails.
+- **ACP command discovery is async**: `acp-probe.ts` must poll after `newSession` for `available_commands_update` (commands arrive in a later notification; reading synchronously captures 0). PTY providers (claude) instead discover from disk via `claude-command-discovery.ts` (`~/.claude/commands` + `enabledPlugins` `skills/`+`commands/`, bare names, deduped). `AgentCommand.kind` tags `'command'` vs `'skill'`; `CoderPane`'s `slashGroups` splits them into icon'd groups. `SlashCommandPicker`'s `groups?` prop is opt-in — BooChat passes flat `items` (unchanged).
 - **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/package.json

@@ -16,6 +16,7 @@
     "@agentclientprotocol/sdk": "^0.22.1",
     "@boocode/server": "workspace:*",
     "@fastify/static": "^7.0.4",
+    "@opencode-ai/sdk": "~1.15.0",
     "@fastify/websocket": "^10.0.1",
     "@modelcontextprotocol/sdk": "^1.29.0",
     "fastify": "^4.28.1",

apps/coder/src/index.ts

@@ -30,9 +30,11 @@ import { registerInboxRoutes } from './routes/inbox.js';
 import { registerStatsRoutes } from './routes/stats.js';
 import { registerArenaRoutes } from './routes/arena.js';
 import { registerProviderRoutes } from './routes/providers.js';
+import { registerWorktreeSafetyRoutes } from './routes/worktree-safety.js';
 import { registerWebSocket } from './routes/ws.js';
 // Phase 4: dispatcher + agent probe
 import { createDispatcher } from './services/dispatcher.js';
+import { agentPool } from './services/agent-pool.js';
 import { probeAgents } from './services/agent-probe.js';
 import { getProviderSnapshot, persistProbedModels } from './services/provider-snapshot.js';
 import { setPermissionHooks } from './services/permission-waiter.js';
@@ -178,7 +180,12 @@ async function main() {
   // Phase 4: dispatcher — polls tasks table and runs inference
   const dispatcher = createDispatcher({ sql, inference: inferenceApi, broker, log: app.log, config });
   dispatcher.start();
-  app.addHook('onClose', () => dispatcher.stop());
+  app.addHook('onClose', async () => {
+    // stop() first so in-flight dispatcher turns settle, then drain the pool.
+    // Pool is empty in Phase 0 (nothing spawns yet) — dispose() is inert.
+    await dispatcher.stop();
+    await agentPool.dispose();
+  });
 
   // Register routes
   registerMessageRoutes(app, sql, broker, inferenceApi);
@@ -189,6 +196,7 @@ async function main() {
   registerStatsRoutes(app, sql);
   registerArenaRoutes(app, sql);
   registerProviderRoutes(app, sql, config);
+  registerWorktreeSafetyRoutes(app, sql);
   registerWebSocket(app, sql, broker);
 
   // Serve static frontend (built web app). In production, the dist/ is

apps/coder/src/routes/worktree-safety.ts

@@ -0,0 +1,45 @@
+/**
+ * Session-delete work-loss guard (coder side).
+ *
+ * Session delete itself lives in apps/server (Docker), which CANNOT see the
+ * host worktree dirs (/tmp/booworktrees) or run git on them. Only BooCoder
+ * (host systemd) can. So the server's DELETE route calls these endpoints
+ * pre-delete to learn whether a session's worktree holds work at risk, and to
+ * stash it. The server owns the gate; coder owns the git truth.
+ */
+import type { FastifyInstance } from 'fastify';
+import type { Sql } from '../db.js';
+import { checkWorktreeWorkAtRisk, stashWorktree } from '../services/worktrees.js';
+
+export function registerWorktreeSafetyRoutes(app: FastifyInstance, sql: Sql): void {
+  // GET risk for a session's worktree(s). One row per session today (PK on
+  // session_id); the loop already handles the Phase-1.5 multi-worktree case.
+  app.get<{ Params: { sessionId: string } }>(
+    '/api/sessions/:sessionId/worktree-risk',
+    async (req) => {
+      const rows = await sql<{ worktree_path: string }[]>`
+        SELECT worktree_path FROM session_worktrees WHERE session_id = ${req.params.sessionId}
+      `;
+      const reports = [];
+      for (const row of rows) {
+        reports.push(await checkWorktreeWorkAtRisk(row.worktree_path));
+      }
+      return { reports };
+    },
+  );
+
+  // Stash a session's worktree(s) — clears the dirty risk; recoverable.
+  app.post<{ Params: { sessionId: string } }>(
+    '/api/sessions/:sessionId/worktree-stash',
+    async (req) => {
+      const rows = await sql<{ worktree_path: string }[]>`
+        SELECT worktree_path FROM session_worktrees WHERE session_id = ${req.params.sessionId}
+      `;
+      const results = [];
+      for (const row of rows) {
+        results.push({ worktreePath: row.worktree_path, ...(await stashWorktree(row.worktree_path)) });
+      }
+      return { results };
+    },
+  );
+}

apps/coder/src/schema.sql

@@ -76,6 +76,60 @@ 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;
 
+-- v2.6: one shared worktree per session (all agents/panes in the session operate in it).
+CREATE TABLE IF NOT EXISTS session_worktrees (
+  session_id UUID PRIMARY KEY REFERENCES sessions(id) ON DELETE CASCADE,
+  worktree_path TEXT NOT NULL,
+  base_commit TEXT,
+  created_at TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp()
+);
+-- Migrate existing FK to CASCADE (idempotent: drops the old constraint if present).
+DO $$ BEGIN
+  IF EXISTS (
+    SELECT 1 FROM pg_constraint
+    WHERE conname = 'session_worktrees_session_id_fkey'
+      AND confdeltype <> 'c'
+  ) THEN
+    ALTER TABLE session_worktrees DROP CONSTRAINT session_worktrees_session_id_fkey;
+    ALTER TABLE session_worktrees ADD CONSTRAINT session_worktrees_session_id_fkey
+      FOREIGN KEY (session_id) REFERENCES sessions(id) ON DELETE CASCADE;
+  END IF;
+END $$;
+
+-- v2.6: one backend session per (session, agent); resumed on switch-back.
+CREATE TABLE IF NOT EXISTS agent_sessions (
+  session_id UUID NOT NULL REFERENCES sessions(id) ON DELETE CASCADE,
+  agent TEXT NOT NULL,
+  backend TEXT NOT NULL,
+  agent_session_id TEXT,
+  server_port INTEGER,
+  status TEXT NOT NULL DEFAULT 'idle',
+  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'))
+);
+
+-- Migrate existing agent_sessions FK to CASCADE.
+DO $$ BEGIN
+  IF EXISTS (
+    SELECT 1 FROM pg_constraint
+    WHERE conname = 'agent_sessions_session_id_fkey'
+      AND confdeltype <> 'c'
+  ) THEN
+    ALTER TABLE agent_sessions DROP CONSTRAINT agent_sessions_session_id_fkey;
+    ALTER TABLE agent_sessions ADD CONSTRAINT agent_sessions_session_id_fkey
+      FOREIGN KEY (session_id) REFERENCES sessions(id) ON DELETE CASCADE;
+  END IF;
+END $$;
+
+-- v2.6: config fingerprint for stale-session detection (auto-recover on model change).
+ALTER TABLE agent_sessions ADD COLUMN IF NOT EXISTS config_hash TEXT;
+
+-- v2.6: attribution for DiffPanel badges (Phase 1 UX reads this).
+ALTER TABLE pending_changes ADD COLUMN IF NOT EXISTS agent TEXT;
+
 -- 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

apps/coder/src/services/__tests__/acp-client-fs.test.ts

@@ -0,0 +1,50 @@
+import { describe, it, expect, afterEach } from 'vitest';
+import { mkdtempSync, rmSync } from 'node:fs';
+import { tmpdir } from 'node:os';
+import { join } from 'node:path';
+import { readWorktreeTextFile, writeWorktreeTextFile } from '../acp-client-fs.js';
+
+const created: string[] = [];
+function freshWorktree(): string {
+  const wt = mkdtempSync(join(tmpdir(), 'acp-wt-'));
+  created.push(wt);
+  return wt;
+}
+afterEach(() => {
+  for (const d of created.splice(0)) {
+    try {
+      rmSync(d, { recursive: true, force: true });
+      rmSync(`${d}-evil`, { recursive: true, force: true });
+    } catch {
+      /* ignore */
+    }
+  }
+});
+
+describe('acp-client-fs worktree scoping', () => {
+  it('writes then reads a file inside the worktree', async () => {
+    const wt = freshWorktree();
+    await writeWorktreeTextFile(wt, 'sub/dir/note.txt', 'hello');
+    expect(await readWorktreeTextFile(wt, 'sub/dir/note.txt')).toBe('hello');
+  });
+
+  it('rejects ../ traversal on read', async () => {
+    const wt = freshWorktree();
+    await expect(readWorktreeTextFile(wt, '../../etc/passwd')).rejects.toThrow(/escapes worktree/);
+  });
+
+  it('rejects ../ traversal on write', async () => {
+    const wt = freshWorktree();
+    await expect(writeWorktreeTextFile(wt, '../escape.txt', 'x')).rejects.toThrow(/escapes worktree/);
+  });
+
+  it('rejects a sibling-prefix path (the unbounded-startsWith bug)', async () => {
+    const wt = freshWorktree();
+    // Absolute path that shares the worktree as a STRING prefix but is a sibling
+    // dir: `<wt>-evil/...`. A bare `startsWith(<wt>)` wrongly admits it.
+    await expect(readWorktreeTextFile(wt, `${wt}-evil/secret.txt`)).rejects.toThrow(/escapes worktree/);
+    await expect(writeWorktreeTextFile(wt, `${wt}-evil/secret.txt`, 'x')).rejects.toThrow(
+      /escapes worktree/,
+    );
+  });
+});

apps/coder/src/services/acp-client-fs.ts

@@ -1,5 +1,25 @@
 import { promises as fs } from 'node:fs';
-import { dirname, isAbsolute, join, resolve } from 'node:path';
+import { dirname, isAbsolute, resolve, sep } from 'node:path';
+
+/**
+ * Resolve an ACP-supplied path against the agent worktree and reject anything
+ * that escapes it. Mirrors `write_guard.ts`'s check: `resolve()` to normalize
+ * `../` segments, then a **separator-bounded** prefix test — a bare
+ * `startsWith(root)` wrongly admits a sibling dir like `<root>-evil/...`.
+ *
+ * No realpath (consistent with `write_guard.ts`: the target may not exist yet on
+ * write). This is a containment guard for the ACP fs bridge, not a hard trust
+ * boundary — the agent process already runs with host FS access; symlink-swap
+ * hardening (`O_NOFOLLOW`/realpath) is out of scope here.
+ */
+function resolveInWorktree(worktreePath: string, filePath: string): string {
+  const root = resolve(worktreePath);
+  const absolute = isAbsolute(filePath) ? resolve(filePath) : resolve(root, filePath);
+  if (absolute !== root && !absolute.startsWith(root + sep)) {
+    throw new Error(`path escapes worktree: ${filePath}`);
+  }
+  return absolute;
+}
 
 /** Resolve an ACP path against the agent worktree and read a slice of lines. */
 export async function readWorktreeTextFile(
@@ -8,10 +28,7 @@ export async function readWorktreeTextFile(
   line?: number | null,
   limit?: number | null,
 ): Promise<string> {
-  const absolute = isAbsolute(filePath) ? filePath : resolve(worktreePath, filePath);
-  if (!absolute.startsWith(resolve(worktreePath))) {
-    throw new Error(`path escapes worktree: ${filePath}`);
-  }
+  const absolute = resolveInWorktree(worktreePath, filePath);
   const raw = await fs.readFile(absolute, 'utf8');
   if (!line && !limit) return raw;
   const lines = raw.split(/\r?\n/);
@@ -26,10 +43,7 @@ export async function writeWorktreeTextFile(
   filePath: string,
   content: string,
 ): Promise<void> {
-  const absolute = isAbsolute(filePath) ? filePath : resolve(worktreePath, filePath);
-  if (!absolute.startsWith(resolve(worktreePath))) {
-    throw new Error(`path escapes worktree: ${filePath}`);
-  }
+  const absolute = resolveInWorktree(worktreePath, filePath);
   await fs.mkdir(dirname(absolute), { recursive: true });
   await fs.writeFile(absolute, content, 'utf8');
 }

apps/coder/src/services/agent-backend.ts

@@ -0,0 +1,85 @@
+/**
+ * v2.6 — AgentBackend abstraction (Phase 0 scaffold; types only, zero runtime logic).
+ *
+ * The core abstraction for persistent agent sessions. Two implementations land
+ * later: `OpenCodeServerBackend` (Phase 1, opencode HTTP server) and
+ * `WarmAcpBackend` (Phase 2, long-lived ACP process). Backends emit
+ * transport-agnostic `AgentEvent`s; the dispatcher maps them to WS frames.
+ *
+ * Nothing imports this file yet — it must compile standalone.
+ * Spec: openspec/changes/v2-6-persistent-agent-sessions/design.md §2.
+ */
+import type { AcpToolSnapshot } from './acp-tool-snapshot.js';
+import type { AgentCommand } from './provider-types.js';
+
+/** Backend transport kind. Mirrors `agent_sessions.backend` CHECK in schema.sql. */
+export type AgentBackendKind = 'opencode_server' | 'acp_warm';
+
+/**
+ * Normalized, transport-agnostic events a backend emits during a turn (§2).
+ * Derived from acp-dispatch's session-update handling, but WITHOUT the WS
+ * envelope (message_id/chat_id) — the dispatcher owns frame mapping.
+ *
+ * `tool_call` vs `tool_update` are kept distinct on purpose: acp-dispatch
+ * currently merges both into one snapshot frame, but opencode's SSE
+ * distinguishes tool-start from tool-result, so the contract carries both.
+ * `commands` mirrors the ACP `available_commands_update` path (v2.5.10).
+ */
+export type AgentEvent =
+  | { type: 'text'; text: string }
+  | { type: 'reasoning'; text: string }
+  | { type: 'tool_call'; toolCall: AcpToolSnapshot }
+  | { type: 'tool_update'; toolCall: AcpToolSnapshot }
+  | { type: 'commands'; commands: AgentCommand[] };
+
+/** Params to establish (or look up) a backend session (§2). */
+export interface EnsureSessionOpts {
+  agent: string;
+  /** Resolved model id. */
+  model: string;
+  /** Shared per-session worktree (one per `sessions.id`, not per pane). */
+  worktreePath: string;
+  projectId: string;
+}
+
+/** Opaque handle to a live backend session, persisted to `agent_sessions` (§2). */
+export interface AgentSessionHandle {
+  sessionId: string;
+  agent: string;
+  backend: AgentBackendKind;
+  /** Provider's own session id (resume token); null until the backend assigns one. */
+  agentSessionId: string | null;
+  /** opencode HTTP server port; null for ACP backends. */
+  serverPort: number | null;
+}
+
+/** Per-turn context passed to `prompt` (§2). */
+export interface PromptCtx {
+  worktreePath: string;
+  model: string;
+  signal: AbortSignal;
+  onEvent: (e: AgentEvent) => void;
+}
+
+/** Result of a completed turn (§2). Diff/persist happen outside the backend. */
+export interface TurnResult {
+  ok: boolean;
+  error?: string;
+}
+
+/**
+ * The core backend abstraction (§2). Implementations: OpenCodeServerBackend
+ * (Phase 1), WarmAcpBackend (Phase 2).
+ */
+export interface AgentBackend {
+  /** Lazy: spawn server / warm process if not already up for this (session, agent). §2 */
+  ensureSession(sessionId: string, opts: EnsureSessionOpts): Promise<AgentSessionHandle>;
+  /** Send a prompt; stream events via ctx.onEvent; resolves when the turn completes. §2 */
+  prompt(handle: AgentSessionHandle, input: string, ctx: PromptCtx): Promise<TurnResult>;
+  /** Graceful teardown of one session (session close or idle timeout). §2 */
+  closeSession(handle: AgentSessionHandle): Promise<void>;
+  /** Full teardown — kills all spawned servers/processes. §2 */
+  dispose(): Promise<void>;
+  /** Liveness for health endpoint + dispatcher fallback decision. §2 */
+  health(): 'up' | 'down';
+}

apps/coder/src/services/agent-pool.ts

@@ -0,0 +1,44 @@
+/**
+ * v2.6 — AgentPool (Phase 0 scaffold).
+ *
+ * Lazy get-or-create registry of `AgentBackend` instances keyed by
+ * `${sessionId}:${agent}`. Phase 0 ships the skeleton only: an in-memory Map,
+ * lookup / register / health, and clean disposal wired to the server's onClose.
+ * Spawning lands in Phase 1/2; nothing populates the map yet.
+ *
+ * Spec: openspec/changes/v2-6-persistent-agent-sessions/design.md §2.
+ */
+import type { AgentBackend } from './agent-backend.js';
+
+export class AgentPool {
+  private readonly backends = new Map<string, AgentBackend>();
+
+  private key(sessionId: string, agent: string): string {
+    return `${sessionId}:${agent}`;
+  }
+
+  /** Map lookup only. Spawning is Phase 1/2 — never creates here. */
+  get(sessionId: string, agent: string): AgentBackend | undefined {
+    return this.backends.get(this.key(sessionId, agent));
+  }
+
+  /** Store a backend instance for this (session, agent). */
+  register(sessionId: string, agent: string, backend: AgentBackend): void {
+    this.backends.set(this.key(sessionId, agent), backend);
+  }
+
+  /** Summary for the health endpoint. */
+  health(): { size: number } {
+    return { size: this.backends.size };
+  }
+
+  /** Dispose every backend and clear the map. Tolerates throwing backends. */
+  async dispose(): Promise<void> {
+    const entries = [...this.backends.values()];
+    this.backends.clear();
+    await Promise.allSettled(entries.map((b) => b.dispose()));
+  }
+}
+
+/** Single shared instance — referenced only by the server's onClose hook in Phase 0. */
+export const agentPool = new AgentPool();

apps/coder/src/services/agent-probe.ts

@@ -4,7 +4,7 @@ import { exec as execCb, execFile as execFileCb } from 'node:child_process';
 import { promisify } from 'node:util';
 import { PROVIDERS_BY_NAME } from './provider-registry.js';
 import { resolveAcpProbeBinaries } from './acp-spawn.js';
-import { clearProviderSnapshotCache } from './provider-snapshot.js';
+import { clearProviderSnapshotCache, fetchLlamaSwapModels, prefixLlamaSwapModels } from './provider-snapshot.js';
 import { readQwenSettingsModels } from './qwen-settings.js';
 import { loadConfig } from '../config.js';
 import { loadProviderConfig } from './provider-config-registry.js';
@@ -117,6 +117,15 @@ export async function probeAgents(sql: Sql, log: FastifyBaseLogger): Promise<voi
         if (agentName === 'qwen') {
           models = await readQwenSettingsModels();
         }
+        if (providerDef?.mergeLlamaSwap) {
+          try {
+            const config = loadConfig();
+            const llamaModels = prefixLlamaSwapModels(await fetchLlamaSwapModels(config));
+            models = [...models, ...llamaModels];
+          } catch (err) {
+            log.warn({ agent: agentName, err: err instanceof Error ? err.message : String(err) }, 'agent-probe: llama-swap model fetch failed (non-fatal)');
+          }
+        }
       }
 
       const label = resolved.configLabel ?? resolved.label;

apps/coder/src/services/backends/opencode-server.ts

@@ -0,0 +1,777 @@
+/**
+ * v2.6 Phase 1 — OpenCodeServerBackend.
+ *
+ * Warm, multi-turn backend for the `opencode` agent. One `opencode serve` HTTP
+ * server per BooCoder process; one opencode session per BooCode session (resumed
+ * on switch-back); one SSE read loop PER session, each scoped to that session's
+ * worktree directory so sessions in different directories stream concurrently
+ * (P1.5-a — replaced the Phase-1 single-stream-last-directory model).
+ *
+ * Implements the Phase 0 `AgentBackend` interface. Emits transport-agnostic
+ * `AgentEvent`s — the dispatcher (Phase 1.7, NOT wired in this batch) maps them
+ * to WS frames. No dispatcher/route references this file yet.
+ *
+ * Spec: openspec/changes/v2-6-persistent-agent-sessions/design.md §2 / §2a.
+ * SDK shapes verified by direct read of @opencode-ai/sdk@1.15.12 dist .d.ts:
+ *   - client methods take FLATTENED params (sessionID/directory/body all inline),
+ *     not {path,query,body}. create→{directory}, promptAsync→{sessionID,directory,
+ *     parts,model}, abort→{sessionID,directory}. model is {providerID,modelID}.
+ *   - client.event() resolves to { stream: AsyncGenerator<GlobalEvent> }; the
+ *     real event is chunk.payload (discriminate on chunk.payload.type).
+ *   - promptAsync is fire-and-forget (204); the turn completes via a
+ *     'session.idle' event for that opencode session id.
+ */
+import { spawn, type ChildProcess } from 'node:child_process';
+import { createHash } from 'node:crypto';
+import { createServer } from 'node:net';
+import type { FastifyBaseLogger } from 'fastify';
+import {
+  createOpencodeClient,
+  type OpencodeClient,
+  type Event,
+  type Part,
+  type ToolPart,
+  type ToolState,
+  type AssistantMessage,
+} from '@opencode-ai/sdk/v2/client';
+import type { ToolCallStatus } from '@agentclientprotocol/sdk';
+import type { Sql } from '../../db.js';
+import type { AcpToolSnapshot } from '../acp-tool-snapshot.js';
+import type {
+  AgentBackend,
+  AgentEvent,
+  AgentSessionHandle,
+  EnsureSessionOpts,
+  PromptCtx,
+  TurnResult,
+} from '../agent-backend.js';
+
+const READY_TIMEOUT_MS = 30_000;
+const SSE_RECONNECT_DELAY_MS = 1_000;
+/**
+ * No-activity backstop for an in-flight turn. opencode streams reasoning/text/tool
+ * deltas continuously while working, so "zero events for this long" means the turn
+ * is wedged or its terminal event (session.idle) was lost (see the reconnect race
+ * below). Generous so a legitimately slow turn never trips it.
+ */
+const TURN_INACTIVITY_MS = 180_000;
+
+/** One in-flight turn's emitter + completion settler. */
+interface TurnState {
+  onEvent: (e: AgentEvent) => void;
+  settle: (r: TurnResult) => void;
+}
+
+/** Per-(opencode session) demux state. dedup sets scoped here, cleared per turn. */
+interface SessionState {
+  boocodeSessionId: string;
+  agentSessionId: string;
+  /** Worktree directory for SDK `directory` routing; refreshed each turn from ctx. */
+  worktreePath: string;
+  /** dedup gate: `${type}:${id}` added on delta, deleted-and-tested on updated. Cleared at turn end. */
+  streamedPartKeys: Set<string>;
+  /** partID → 'text' | 'reasoning', so a delta with a non-'reasoning' field is still classed right. Cleared at turn end. */
+  partTypeById: Map<string, string>;
+  activeTurn: TurnState | null;
+  /** Inactivity backstop timer for the active turn; null when no turn in flight. */
+  watchdog: ReturnType<typeof setTimeout> | null;
+  /** Per-session SSE subscription handle. Non-null while the loop is running;
+   *  aborting it tears down the underlying fetch and exits the loop. */
+  sseAbort: AbortController | null;
+}
+
+export interface OpenCodeServerBackendDeps {
+  sql: Sql;
+  log: FastifyBaseLogger;
+  /** Absolute path to the opencode binary (resolved from available_agents at wiring time, Phase 1.7). */
+  opencodeBinary: string;
+}
+
+export class OpenCodeServerBackend implements AgentBackend {
+  readonly backend = 'opencode_server' as const;
+
+  private readonly sql: Sql;
+  private readonly log: FastifyBaseLogger;
+  private readonly opencodeBinary: string;
+
+  private child: ChildProcess | null = null;
+  private client: OpencodeClient | null = null;
+  private port: number | null = null;
+  private up = false;
+  private serverStarting: Promise<void> | null = null;
+
+  /** opencode session id → demux state. Maintained by ensureSession; read by the SSE loop. */
+  private readonly byOpencodeId = new Map<string, SessionState>();
+
+  constructor(deps: OpenCodeServerBackendDeps) {
+    this.sql = deps.sql;
+    this.log = deps.log;
+    this.opencodeBinary = deps.opencodeBinary;
+  }
+
+  /** §2: liveness for the health endpoint + dispatcher fallback decision. */
+  health(): 'up' | 'down' {
+    return this.up ? 'up' : 'down';
+  }
+
+  // ─── Server lifecycle (1.2: spawn once + client + ready) ─────────────────────
+
+  /** Lazy: start the single server on first use. Idempotent — one server per backend. */
+  private ensureServer(): Promise<void> {
+    if (!this.serverStarting) this.serverStarting = this.startServer();
+    return this.serverStarting;
+  }
+
+  private async startServer(): Promise<void> {
+    const port = await freePort();
+
+    // Phase 1: run unsecured on loopback (opencode's documented default — serve.ts
+    // only WARNS when OPENCODE_SERVER_PASSWORD is unset). The real boundary is the
+    // 127.0.0.1 bind. Defense-in-depth basic-auth is deferred: the hey-api client's
+    // auth wiring + opencode's exact scheme must be confirmed against a live server
+    // first, else every request 401s. Recon explicitly said "do NOT block on it".
+    const child = spawn(this.opencodeBinary, ['serve', '--hostname', '127.0.0.1', '--port', String(port)], {
+      stdio: ['ignore', 'pipe', 'pipe'],
+      env: { ...process.env },
+    });
+    this.child = child;
+    this.port = port;
+
+    // Child lifetime is the backend's (the pool's), NOT a request's. We never tie
+    // it to a per-turn abort signal. On unexpected exit we mark down + log; crash
+    // recovery is Phase 3.
+    child.on('exit', (code, signal) => {
+      this.up = false;
+      this.log.warn({ code, signal, port }, 'opencode-server: child exited (recovery is Phase 3)');
+    });
+
+    await waitForReady(child, READY_TIMEOUT_MS);
+
+    this.client = createOpencodeClient({ baseUrl: `http://127.0.0.1:${port}` });
+    this.up = true;
+    this.log.info({ port }, 'opencode-server: ready');
+  }
+
+  // ─── SSE read loop + demux + translate (1.3) + dedup (1.4) ───────────────────
+
+  /** Per-session SSE subscription, scoped to the session's worktree directory.
+   *  opencode scopes events by the `directory` query param (defaults to the
+   *  server's cwd if omitted), so two sessions in different worktrees each get
+   *  their own dir-scoped stream and never drop each other's events. Idempotent:
+   *  a no-op if this session's loop is already running. Started from ensureSession
+   *  (and defensively from prompt) once worktreePath is known. */
+  private startSessionEventLoop(state: SessionState): void {
+    if (state.sseAbort) return; // already running
+    const abort = new AbortController();
+    state.sseAbort = abort;
+    void this.runSessionEventLoop(state, abort).finally(() => {
+      // Only clear if this controller is still the live one (a later restart may
+      // have already installed a new one).
+      if (state.sseAbort === abort) state.sseAbort = null;
+    });
+  }
+
+  private async runSessionEventLoop(state: SessionState, abort: AbortController): Promise<void> {
+    const signal = abort.signal;
+    while (this.up && this.client && !signal.aborted) {
+      try {
+        // Re-read worktreePath each (re)subscribe so a directory refresh is picked
+        // up on reconnect. Passing `signal` lets close/dispose tear down a stream
+        // that's parked in `for await` between events.
+        const sub = await this.client.event.subscribe(
+          { directory: state.worktreePath },
+          { signal },
+        );
+        for await (const ev of sub.stream) {
+          if (signal.aborted) break;
+          // Dir-scoped streams should only carry this session's events, but two
+          // sessions sharing a worktree (possible post-P1.5-b) each receive BOTH
+          // sessions' events — so drop anything that isn't ours, else the other
+          // session's deltas get processed twice (once per loop).
+          const sid = eventSessionId(ev);
+          if (sid != null && sid !== state.agentSessionId) continue;
+          this.dispatchEvent(ev);
+        }
+        if (this.up && !signal.aborted) {
+          await this.reconcile(state); // recover an idle/error lost during the gap
+          await sleep(SSE_RECONNECT_DELAY_MS);
+        }
+      } catch (err) {
+        if (!this.up || signal.aborted) break;
+        this.log.warn(
+          { err: errMsg(err), agentSessionId: state.agentSessionId },
+          'opencode-server: session event loop error; reconnecting',
+        );
+        await this.reconcile(state);
+        await sleep(SSE_RECONNECT_DELAY_MS);
+      }
+    }
+  }
+
+  /** Demux one event to the owning session's active turn. Unknown/between-turns → drop. */
+  private dispatchEvent(ev: Event): void {
+    switch (ev.type) {
+      // ─── session.next.* — live streaming events (the primary path) ─────────
+      case 'session.next.text.delta': {
+        const p = ev.properties;
+        const st = this.byOpencodeId.get(p.sessionID);
+        if (!st?.activeTurn) return;
+        this.bumpActivity(st);
+        const cleaned = stripDcpTags(p.delta);
+        if (cleaned) st.activeTurn.onEvent({ type: 'text', text: cleaned });
+        return;
+      }
+      case 'session.next.reasoning.delta': {
+        const p = ev.properties;
+        const st = this.byOpencodeId.get(p.sessionID);
+        if (!st?.activeTurn) return;
+        this.bumpActivity(st);
+        st.activeTurn.onEvent({ type: 'reasoning', text: p.delta });
+        return;
+      }
+      case 'session.next.tool.called': {
+        const p = ev.properties;
+        const st = this.byOpencodeId.get(p.sessionID);
+        if (!st?.activeTurn) return;
+        this.bumpActivity(st);
+        const snap: AcpToolSnapshot = {
+          toolCallId: p.callID,
+          title: p.tool,
+          kind: null,
+          status: 'in_progress',
+          rawInput: p.input,
+          rawOutput: undefined,
+        };
+        st.activeTurn.onEvent({ type: 'tool_call', toolCall: snap });
+        return;
+      }
+      case 'session.next.tool.success': {
+        const p = ev.properties;
+        const st = this.byOpencodeId.get(p.sessionID);
+        if (!st?.activeTurn) return;
+        this.bumpActivity(st);
+        const output = p.content?.map((c) => ('text' in c ? (c as { text: string }).text : '')).join('') ?? '';
+        const snap: AcpToolSnapshot = {
+          toolCallId: p.callID,
+          title: p.callID,
+          kind: null,
+          status: 'completed',
+          rawInput: undefined,
+          rawOutput: output,
+        };
+        st.activeTurn.onEvent({ type: 'tool_update', toolCall: snap });
+        return;
+      }
+      case 'session.next.tool.failed': {
+        const p = ev.properties;
+        const st = this.byOpencodeId.get(p.sessionID);
+        if (!st?.activeTurn) return;
+        this.bumpActivity(st);
+        const snap: AcpToolSnapshot = {
+          toolCallId: p.callID,
+          title: p.callID,
+          kind: null,
+          status: 'failed',
+          rawInput: undefined,
+          rawOutput: errToString(p.error),
+        };
+        st.activeTurn.onEvent({ type: 'tool_update', toolCall: snap });
+        return;
+      }
+      // ─── message.part.* — terminal/post-hoc events (dedup gate) ────────────
+      case 'message.part.delta': {
+        const p = ev.properties;
+        const st = this.byOpencodeId.get(p.sessionID);
+        if (!st?.activeTurn) return;
+        this.bumpActivity(st);
+        const isReasoning = p.field === 'reasoning' || st.partTypeById.get(p.partID) === 'reasoning';
+        if (isReasoning) {
+          st.streamedPartKeys.add(`reasoning:${p.partID}`);
+          st.activeTurn.onEvent({ type: 'reasoning', text: p.delta });
+        } else if (p.field === 'text') {
+          st.streamedPartKeys.add(`text:${p.partID}`);
+          const cleaned = stripDcpTags(p.delta);
+          if (cleaned) st.activeTurn.onEvent({ type: 'text', text: cleaned });
+        }
+        return;
+      }
+      case 'message.part.updated': {
+        const part = ev.properties.part;
+        const st = this.byOpencodeId.get(part.sessionID);
+        if (!st?.activeTurn) return;
+        this.bumpActivity(st);
+        this.handleUpdatedPart(part, st);
+        return;
+      }
+      // ─── lifecycle ─────────────────────────────────────────────────────────
+      case 'session.idle': {
+        this.byOpencodeId.get(ev.properties.sessionID)?.activeTurn?.settle({ ok: true });
+        return;
+      }
+      case 'session.error': {
+        const sid = ev.properties.sessionID;
+        if (!sid) return;
+        this.byOpencodeId.get(sid)?.activeTurn?.settle({ ok: false, error: errToString(ev.properties.error) });
+        return;
+      }
+      default:
+        return;
+    }
+  }
+
+  /** Terminal part: dedup gate for text/reasoning; tool parts → tool_call/tool_update. */
+  private handleUpdatedPart(part: Part, st: SessionState): void {
+    const turn = st.activeTurn;
+    if (!turn) return;
+
+    if (part.type === 'text' || part.type === 'reasoning') {
+      st.partTypeById.set(part.id, part.type);
+      const key = resolvePartDedupeKey(part, part.type);
+      if (key && st.streamedPartKeys.delete(key)) return; // already streamed via delta
+      const raw = part.text ?? '';
+      const text = part.type === 'text' ? stripDcpTags(raw) : raw;
+      if (text && part.time?.end != null) {
+        turn.onEvent({ type: part.type, text });
+      }
+      return;
+    }
+
+    if (part.type === 'tool') {
+      const snap = toolPartToSnapshot(part);
+      const status = part.state?.status;
+      // tool_call on start (pending/running), tool_update on terminal (completed/error).
+      // The current ACP path merges both into one frame; the contract keeps them
+      // distinct because opencode's SSE distinguishes start from result.
+      const event: AgentEvent =
+        status === 'completed' || status === 'error'
+          ? { type: 'tool_update', toolCall: snap }
+          : { type: 'tool_call', toolCall: snap };
+      turn.onEvent(event);
+      return;
+    }
+    // NOTE: opencode's SSE payload union carries no available-commands event, so the
+    // AgentEvent 'commands' arm is intentionally never emitted here (1.3).
+  }
+
+  // ─── turn-completion resilience (watchdog + reconnect reconcile) ─────────────
+
+  /** Reset the inactivity backstop on any event routed to a session's active turn. */
+  private bumpActivity(st: SessionState): void {
+    if (!st.activeTurn) return;
+    if (st.watchdog) clearTimeout(st.watchdog);
+    st.watchdog = setTimeout(() => {
+      void this.onTurnStall(st);
+    }, TURN_INACTIVITY_MS);
+    st.watchdog.unref?.();
+  }
+
+  /** Watchdog fired: reconcile once; if the server says still-running we can't tell, so fail closed.
+   *  Also mark the agent_sessions row crashed so a stale session isn't resumed next turn. */
+  private async onTurnStall(st: SessionState): Promise<void> {
+    const settled = await this.reconcile(st);
+    if (!settled) {
+      this.log.warn({ agentSessionId: st.agentSessionId }, 'opencode-server: turn stalled (no activity), failing + marking crashed');
+      await this.sql`
+        UPDATE agent_sessions SET status = 'crashed'
+        WHERE agent_session_id = ${st.agentSessionId}
+      `.catch(() => {});
+      st.activeTurn?.settle({ ok: false, error: 'turn timed out (no activity)' });
+    }
+  }
+
+  /**
+   * Ask the server whether this session's turn already finished — recovers a
+   * session.idle/error lost during an SSE gap. Returns true if it settled the turn.
+   * Inconclusive (still running / call failed) → false; the watchdog covers that.
+   */
+  private async reconcile(st: SessionState): Promise<boolean> {
+    const turn = st.activeTurn;
+    if (!turn || !this.client) return false;
+    try {
+      const res = await this.client.session.messages({
+        sessionID: st.agentSessionId,
+        directory: st.worktreePath,
+      });
+      if (res.error || !res.data) return false;
+      let lastAssistant: AssistantMessage | undefined;
+      for (let i = res.data.length - 1; i >= 0; i--) {
+        const info = res.data[i]!.info;
+        if (info.role === 'assistant') {
+          lastAssistant = info;
+          break;
+        }
+      }
+      if (!lastAssistant) return false;
+      if (lastAssistant.error != null) {
+        turn.settle({ ok: false, error: errToString(lastAssistant.error) });
+        return true;
+      }
+      if (lastAssistant.time.completed != null) {
+        turn.settle({ ok: true });
+        return true;
+      }
+      return false; // still running — the live stream will deliver session.idle
+    } catch {
+      return false; // inconclusive — watchdog backstop covers it
+    }
+  }
+
+  // ─── ensureSession: create-or-resume against agent_sessions (1.5) ────────────
+
+  async ensureSession(sessionId: string, opts: EnsureSessionOpts): Promise<AgentSessionHandle> {
+    await this.ensureServer();
+    if (!this.client) throw new Error('opencode-server: client not ready after ensureServer');
+
+    const configHash = sessionConfigHash(opts.model);
+    const [row] = await this.sql<{ agent_session_id: string | null; status: string; config_hash: string | null }[]>`
+      SELECT agent_session_id, status, config_hash FROM agent_sessions
+      WHERE session_id = ${sessionId} AND agent = ${opts.agent}
+    `;
+    let agentSessionId = row?.agent_session_id ?? null;
+
+    // Don't resume crashed sessions or sessions whose config drifted (model change).
+    const shouldResume = agentSessionId
+      && row!.status !== 'crashed'
+      && (row!.config_hash == null || row!.config_hash === configHash);
+
+    if (!shouldResume) {
+      if (agentSessionId) {
+        this.log.info({ sessionId, oldStatus: row!.status, hashMatch: row!.config_hash === configHash },
+          'opencode-server: not resuming stale session, creating fresh');
+        this.byOpencodeId.delete(agentSessionId);
+      }
+      const created = await this.client.session.create({ directory: opts.worktreePath });
+      if (created.error || !created.data) {
+        throw new Error(`opencode-server: session.create failed: ${errToString(created.error)}`);
+      }
+      agentSessionId = created.data.id;
+      await this.sql`
+        INSERT INTO agent_sessions
+          (session_id, agent, backend, agent_session_id, server_port, status, last_active_at, config_hash)
+        VALUES
+          (${sessionId}, ${opts.agent}, 'opencode_server', ${agentSessionId}, ${this.port}, 'active', clock_timestamp(), ${configHash})
+        ON CONFLICT (session_id, agent) DO UPDATE SET
+          backend = 'opencode_server',
+          agent_session_id = EXCLUDED.agent_session_id,
+          server_port = EXCLUDED.server_port,
+          status = 'active',
+          last_active_at = clock_timestamp(),
+          config_hash = EXCLUDED.config_hash
+      `;
+    } else {
+      await this.sql`
+        UPDATE agent_sessions
+        SET status = 'active', last_active_at = clock_timestamp(), server_port = ${this.port}, config_hash = ${configHash}
+        WHERE session_id = ${sessionId} AND agent = ${opts.agent}
+      `;
+    }
+
+    // Both branches above guarantee agentSessionId is non-null.
+    const ocSessionId = agentSessionId!;
+
+    // Register / refresh the demux entry the SSE loop keys on. Preserve an existing
+    // entry (and any in-flight turn) — just refresh the routing fields.
+    let state = this.byOpencodeId.get(ocSessionId);
+    if (state) {
+      state.boocodeSessionId = sessionId;
+      state.worktreePath = opts.worktreePath;
+    } else {
+      state = {
+        boocodeSessionId: sessionId,
+        agentSessionId: ocSessionId,
+        worktreePath: opts.worktreePath,
+        streamedPartKeys: new Set(),
+        partTypeById: new Map(),
+        activeTurn: null,
+        watchdog: null,
+        sseAbort: null,
+      };
+      this.byOpencodeId.set(ocSessionId, state);
+    }
+
+    // Start this session's own SSE loop, scoped to its worktree directory. Both
+    // fresh-create and resume reach here; idempotent, so a re-ensure (e.g. a
+    // second turn) won't spawn a duplicate loop.
+    this.startSessionEventLoop(state);
+
+    return {
+      sessionId,
+      agent: opts.agent,
+      backend: 'opencode_server',
+      agentSessionId: ocSessionId,
+      serverPort: this.port,
+    };
+  }
+
+  // ─── prompt: send one turn (1.6) ─────────────────────────────────────────────
+
+  async prompt(handle: AgentSessionHandle, input: string, ctx: PromptCtx): Promise<TurnResult> {
+    if (!this.client) throw new Error('opencode-server: client not ready');
+    const oc = handle.agentSessionId;
+    if (!oc) throw new Error('opencode-server: handle has no agentSessionId');
+
+    let state = this.byOpencodeId.get(oc);
+    if (!state) {
+      state = {
+        boocodeSessionId: handle.sessionId,
+        agentSessionId: oc,
+        worktreePath: ctx.worktreePath,
+        streamedPartKeys: new Set(),
+        partTypeById: new Map(),
+        activeTurn: null,
+        watchdog: null,
+        sseAbort: null,
+      };
+      this.byOpencodeId.set(oc, state);
+    }
+    const session = state;
+    // Authoritative per-turn directory for SDK routing + reconcile.
+    session.worktreePath = ctx.worktreePath;
+    // Defensive: ensureSession normally starts the loop, but if prompt is reached
+    // with a freshly-created state (no loop yet), start it so the turn streams.
+    // Idempotent when ensureSession already started one.
+    this.startSessionEventLoop(session);
+    const client = this.client;
+
+    return await new Promise<TurnResult>((resolve) => {
+      let settled = false;
+      const cleanup = () => {
+        session.activeTurn = null;
+        if (session.watchdog) {
+          clearTimeout(session.watchdog);
+          session.watchdog = null;
+        }
+        session.streamedPartKeys.clear();
+        session.partTypeById.clear();
+        ctx.signal.removeEventListener('abort', onAbort);
+      };
+      const settle = (r: TurnResult) => {
+        if (settled) return;
+        settled = true;
+        cleanup();
+        resolve(r);
+      };
+      const onAbort = () => {
+        // Abort the turn only — never the server.
+        client.session.abort({ sessionID: oc, directory: ctx.worktreePath }).catch(() => {});
+        settle({ ok: false, error: 'aborted' });
+      };
+
+      session.activeTurn = { onEvent: ctx.onEvent, settle };
+      this.bumpActivity(session); // arm the inactivity backstop
+
+      if (ctx.signal.aborted) {
+        onAbort();
+        return;
+      }
+      ctx.signal.addEventListener('abort', onAbort, { once: true });
+
+      const model = parseModel(ctx.model);
+      client.session
+        .promptAsync({
+          sessionID: oc,
+          directory: ctx.worktreePath,
+          parts: [{ type: 'text', text: input }],
+          ...(model ? { model } : {}),
+        })
+        .then((res) => {
+          // promptAsync is fire-and-forget (204); the turn completes via session.idle.
+          // Only a submission error settles here.
+          if (res.error) settle({ ok: false, error: errToString(res.error) });
+        })
+        .catch((err) => settle({ ok: false, error: errMsg(err) }));
+    });
+  }
+
+  // ─── teardown ────────────────────────────────────────────────────────────────
+
+  async closeSession(handle: AgentSessionHandle): Promise<void> {
+    if (handle.agentSessionId) {
+      // Stop this session's SSE loop before dropping its demux entry.
+      this.byOpencodeId.get(handle.agentSessionId)?.sseAbort?.abort();
+      this.byOpencodeId.delete(handle.agentSessionId);
+    }
+    await this.sql`
+      UPDATE agent_sessions SET status = 'closed'
+      WHERE session_id = ${handle.sessionId} AND agent = ${handle.agent}
+    `.catch(() => {});
+  }
+
+  async dispose(): Promise<void> {
+    this.up = false;
+    // Abort every per-session SSE loop so none survive the teardown.
+    for (const st of this.byOpencodeId.values()) st.sseAbort?.abort();
+    const child = this.child;
+    this.child = null;
+    this.client = null;
+    this.byOpencodeId.clear();
+    if (child && !child.killed) {
+      child.kill('SIGTERM');
+      const t = setTimeout(() => {
+        if (!child.killed) child.kill('SIGKILL');
+      }, 5_000);
+      t.unref();
+    }
+  }
+}
+
+// ─── helpers ──────────────────────────────────────────────────────────────────
+
+/** Extract the opencode sessionID an event belongs to, across event shapes.
+ *  Most carry `properties.sessionID`; `message.part.updated` nests it under
+ *  `properties.part.sessionID`. Returns null when the event has no session
+ *  (the per-session loop then leaves it to dispatchEvent, which drops it). */
+function eventSessionId(ev: Event): string | null {
+  const props = (ev as { properties?: unknown }).properties;
+  if (!props || typeof props !== 'object') return null;
+  if (ev.type === 'message.part.updated') {
+    const part = (props as { part?: { sessionID?: string } }).part;
+    return part?.sessionID ?? null;
+  }
+  return (props as { sessionID?: string }).sessionID ?? null;
+}
+
+/** BooCoder model string "provider/model" → opencode's structured {providerID, modelID}. */
+function parseModel(model: string | undefined): { providerID: string; modelID: string } | undefined {
+  if (!model || !model.trim()) return undefined;
+  const trimmed = model.trim();
+  const idx = trimmed.indexOf('/');
+  if (idx > 0 && idx < trimmed.length - 1) {
+    return { providerID: trimmed.slice(0, idx), modelID: trimmed.slice(idx + 1) };
+  }
+  // No slash but non-empty → infer llama-swap (the only configured provider).
+  // Guard against bare '/' or trailing/leading slash.
+  if (idx < 0 && trimmed.length > 0) {
+    return { providerID: 'llama-swap', modelID: trimmed };
+  }
+  return undefined;
+}
+
+/** Ported verbatim from Paseo opencode-agent.ts: id → message-id fallback → null. */
+function resolvePartDedupeKey(part: { id: string; messageID: string }, type: string): string | null {
+  if (part.id.trim().length > 0) return `${type}:${part.id}`;
+  if (part.messageID.trim().length > 0) return `${type}:message:${part.messageID}`;
+  return null;
+}
+
+/** opencode ToolPart → ACP-shaped snapshot (reuses the existing persist/render path). */
+function toolPartToSnapshot(part: ToolPart): AcpToolSnapshot {
+  const state = part.state;
+  let rawInput: unknown;
+  let rawOutput: unknown;
+  let title: string | undefined;
+  if (state) {
+    if ('input' in state) rawInput = (state as { input?: unknown }).input;
+    if ('output' in state) rawOutput = (state as { output?: unknown }).output;
+    else if ('error' in state) rawOutput = (state as { error?: unknown }).error;
+    if ('title' in state) title = (state as { title?: string }).title;
+  }
+  return {
+    toolCallId: part.callID,
+    title: title ?? part.tool,
+    kind: null,
+    status: mapToolStatus(state?.status),
+    rawInput,
+    rawOutput,
+  };
+}
+
+function mapToolStatus(s: ToolState['status'] | undefined): ToolCallStatus | null {
+  switch (s) {
+    case 'pending':
+      return 'pending';
+    case 'running':
+      return 'in_progress';
+    case 'completed':
+      return 'completed';
+    case 'error':
+      return 'failed';
+    default:
+      return null;
+  }
+}
+
+/** Bind-probe an ephemeral port on loopback. */
+function freePort(): Promise<number> {
+  return new Promise((resolve, reject) => {
+    const srv = createServer();
+    srv.unref();
+    srv.on('error', reject);
+    srv.listen(0, '127.0.0.1', () => {
+      const addr = srv.address();
+      if (addr && typeof addr === 'object') {
+        const { port } = addr;
+        srv.close(() => resolve(port));
+      } else {
+        srv.close(() => reject(new Error('opencode-server: could not determine a free port')));
+      }
+    });
+  });
+}
+
+/** Resolve when the child prints the ready line; reject on timeout or early exit. */
+function waitForReady(child: ChildProcess, timeoutMs: number): Promise<void> {
+  return new Promise((resolve, reject) => {
+    let done = false;
+    let stderrBuf = '';
+
+    const finish = (err?: Error) => {
+      if (done) return;
+      done = true;
+      clearTimeout(timer);
+      child.stdout?.off('data', onOut);
+      child.stderr?.off('data', onErr);
+      child.off('exit', onExit);
+      if (err) reject(err);
+      else resolve();
+    };
+
+    const onOut = (buf: Buffer) => {
+      if (buf.toString().includes('opencode server listening on')) finish();
+    };
+    const onErr = (buf: Buffer) => {
+      stderrBuf += buf.toString();
+    };
+    const onExit = (code: number | null) =>
+      finish(new Error(`opencode serve exited before ready (code ${code}); stderr: ${stderrBuf.slice(-2000)}`));
+    const timer = setTimeout(
+      () => finish(new Error(`opencode serve not ready in ${timeoutMs}ms; stderr: ${stderrBuf.slice(-2000)}`)),
+      timeoutMs,
+    );
+
+    child.stdout?.on('data', onOut);
+    child.stderr?.on('data', onErr);
+    child.on('exit', onExit);
+  });
+}
+
+function sleep(ms: number): Promise<void> {
+  return new Promise((r) => setTimeout(r, ms));
+}
+
+/** Strip opencode-dcp plugin tags that render as literal text in the UI. */
+function stripDcpTags(s: string): string {
+  return s.replace(/<dcp-message-id>[^<]*<\/dcp-message-id>/g, '');
+}
+
+function errMsg(e: unknown): string {
+  return e instanceof Error ? e.message : String(e);
+}
+
+function errToString(e: unknown): string {
+  if (e == null) return 'unknown error';
+  if (typeof e === 'string') return e;
+  if (e instanceof Error) return e.message;
+  try {
+    return JSON.stringify(e);
+  } catch {
+    return String(e);
+  }
+}
+
+/** Hash of stable config — detects model changes across sessions without
+ *  invalidating on ephemeral state like the random server port (which changes
+ *  every BooCoder restart). */
+function sessionConfigHash(model: string): string {
+  return createHash('sha256').update(`opencode_server|${model}`).digest('hex').slice(0, 16);
+}

apps/coder/src/services/dispatcher.ts

@@ -3,13 +3,17 @@ import type { FastifyBaseLogger } from 'fastify';
 import type { Broker } from '@boocode/server/broker';
 import type { WsFrame } from '@boocode/server/ws-frames';
 import type { Config } from '../config.js';
-import { createWorktree, diffWorktree, cleanupWorktree } from './worktrees.js';
+import { createWorktree, diffWorktree, cleanupWorktree, ensureSessionWorktree } from './worktrees.js';
 import { dispatchViaAcp } from './acp-dispatch.js';
 import { getResolvedRegistry } from './provider-config-registry.js';
 import { dispatchViaPty } from './pty-dispatch.js';
 import { clearTaskCommands, setTaskCommands } from './agent-commands-cache.js';
 import { getManifestCommands } from './provider-commands.js';
 import { persistExternalAgentTurn } from './agent-turn-persist.js';
+import { snapshotToWireToolCall, type AcpToolSnapshot } from './acp-tool-snapshot.js';
+import { agentPool } from './agent-pool.js';
+import { OpenCodeServerBackend } from './backends/opencode-server.js';
+import type { AgentBackend, AgentEvent } from './agent-backend.js';
 
 interface InferenceRunner {
   enqueue: (sessionId: string, chatId: string, assistantId: string, user: string) => void;
@@ -35,47 +39,65 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
   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 polling = false;
   let stopping = false;
-  let inflightPromise: Promise<void> | null = null;
+  // v2.6 (1.9): per-session in-flight registry replaces the global `running`
+  // boolean. Key = session_id (or `task:<id>` for sessionless tasks). Sessions
+  // without an in-flight turn run concurrently; within a session, strictly one
+  // turn at a time.
+  const inflight = new Map<string, Promise<void>>();
 
   // 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.
+  // `polling`/`stopping` guard makes this safe to call concurrently — a notify
+  // arriving mid-poll returns immediately and never double-dispatches.
   function triggerPoll(reason: string): void {
     poll().catch((err) => {
       log.error({ err, reason }, 'dispatcher: poll error');
     });
   }
 
+  function concurrencyKey(task: { id: string; session_id: string | null }): string {
+    return task.session_id ?? `task:${task.id}`;
+  }
+
   async function poll(): Promise<void> {
-    if (running || stopping) return;
-
-    // Grab one pending task
-    const rows = await sql<{
-      id: string;
-      project_id: string;
-      input: string;
-      agent: string | null;
-      model: string | null;
-      mode_id: string | null;
-      thinking_option_id: string | null;
-      session_id: string | null;
-    }[]>`
-      SELECT id, project_id, input, agent, model, mode_id, thinking_option_id, session_id
-      FROM tasks
-      WHERE state = 'pending'
-      ORDER BY created_at
-      LIMIT 1
-    `;
-    if (rows.length === 0) return;
-
-    const task = rows[0]!;
-    running = true;
-    inflightPromise = runTask(task).finally(() => {
-      running = false;
-      inflightPromise = null;
-    });
+    // `polling` serializes poll() execution itself (timer + NOTIFY can fire
+    // concurrently) so we never double-select a task. It does NOT serialize task
+    // execution — that's what `inflight` (keyed per session) governs.
+    if (polling || stopping) return;
+    polling = true;
+    try {
+      // Oldest-first; start every pending task whose session isn't already busy.
+      const rows = await sql<{
+        id: string;
+        project_id: string;
+        input: string;
+        agent: string | null;
+        model: string | null;
+        mode_id: string | null;
+        thinking_option_id: string | null;
+        session_id: string | null;
+      }[]>`
+        SELECT id, project_id, input, agent, model, mode_id, thinking_option_id, session_id
+        FROM tasks
+        WHERE state = 'pending'
+        ORDER BY created_at
+        LIMIT 50
+      `;
+      for (const task of rows) {
+        if (stopping) break;
+        const key = concurrencyKey(task);
+        if (inflight.has(key)) continue; // this session already has an in-flight turn
+        // Register synchronously (before any await) so a later row in this pass
+        // with the same key is skipped and a concurrent poll can't re-pick it.
+        const p = runTask(task).finally(() => {
+          inflight.delete(key);
+        });
+        inflight.set(key, p);
+      }
+    } finally {
+      polling = false;
+    }
   }
 
   async function runTask(task: {
@@ -96,7 +118,13 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
         SELECT name, supports_acp, install_path FROM available_agents WHERE name = ${task.agent}
       `;
       if (agentRow) {
-        await runExternalAgent(task, agentRow.supports_acp, agentRow.install_path);
+        // v2.6 (1.7): opencode routes to the warm pool backend; every other
+        // external agent keeps the existing one-shot ACP/PTY path untouched.
+        if (task.agent === 'opencode') {
+          await runOpenCodeServerTask(task, agentRow.install_path);
+        } else {
+          await runExternalAgent(task, agentRow.supports_acp, agentRow.install_path);
+        }
         return;
       }
       // Agent specified but not available — fall through to Path A with a warning
@@ -456,6 +484,274 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
     }
   }
 
+  // ─── Path B (opencode): warm OpenCode server backend (v2.6 1.7 + 1.10) ───────
+
+  // OpenCode runs ONE server per BooCoder process, shared across all sessions
+  // (the backend multiplexes sessions internally), so it's pooled under a fixed
+  // key rather than per-session. Warm ACP backends (Phase 2) will be per-session.
+  const OPENCODE_POOL_KEY = '__opencode_server__';
+
+  function getOpenCodeBackend(installPath: string | null): AgentBackend {
+    let backend = agentPool.get(OPENCODE_POOL_KEY, 'opencode');
+    if (!backend) {
+      backend = new OpenCodeServerBackend({ sql, log, opencodeBinary: installPath ?? 'opencode' });
+      agentPool.register(OPENCODE_POOL_KEY, 'opencode', backend);
+    }
+    return backend;
+  }
+
+  async function runOpenCodeServerTask(
+    task: {
+      id: string;
+      project_id: string;
+      input: string;
+      agent: string | null;
+      model: string | null;
+      mode_id: string | null;
+      thinking_option_id: string | null;
+      session_id: string | null;
+    },
+    installPath: string | null,
+  ): Promise<void> {
+    const taskId = task.id;
+    const agent = 'opencode';
+    log.info({ taskId, agent }, 'dispatcher: starting task (path B — opencode server)');
+
+    const [project] = await sql<{ path: string | null }[]>`
+      SELECT path FROM projects WHERE id = ${task.project_id}
+    `;
+    const projectPath = project?.path;
+    if (!projectPath) {
+      await sql`
+        UPDATE tasks
+        SET state = 'failed', ended_at = clock_timestamp(), output_summary = 'Project has no path — cannot create worktree'
+        WHERE id = ${taskId}
+      `;
+      return;
+    }
+
+    const ac = new AbortController();
+
+    try {
+      // execution_path = 'acp' — the schema CHECK has no 'opencode_server' value
+      // (schema is frozen at Phase 0); the warm-vs-one-shot distinction lives in
+      // agent_sessions.backend. Reuse the closest existing value.
+      await sql`
+        UPDATE tasks
+        SET state = 'running', started_at = clock_timestamp(), execution_path = 'acp'
+        WHERE id = ${taskId}
+      `;
+
+      // Resolve session + chat (mirrors runExternalAgent).
+      let sessionId: string;
+      let chatId: string;
+      if (task.session_id) {
+        sessionId = task.session_id;
+        const chats = await sql<{ id: string }[]>`
+          SELECT id FROM chats WHERE session_id = ${sessionId} AND status = 'open' ORDER BY created_at DESC LIMIT 1
+        `;
+        if (chats.length === 0) {
+          const [chat] = await sql<{ id: string }[]>`
+            INSERT INTO chats (session_id, name, status)
+            VALUES (${sessionId}, 'External agent execution', 'open')
+            RETURNING id
+          `;
+          chatId = chat!.id;
+        } else {
+          chatId = chats[0]!.id;
+        }
+      } else {
+        const sessionName = `Task [${agent}]: ${task.input.slice(0, 30)}`;
+        const [session] = await sql<{ id: string }[]>`
+          INSERT INTO sessions (project_id, name, model, status)
+          VALUES (${task.project_id}, ${sessionName}, ${task.model ?? config.DEFAULT_MODEL}, 'open')
+          RETURNING id
+        `;
+        sessionId = session!.id;
+        const [chat] = await sql<{ id: string }[]>`
+          INSERT INTO chats (session_id, name, status)
+          VALUES (${sessionId}, 'External agent execution', 'open')
+          RETURNING id
+        `;
+        chatId = chat!.id;
+        await sql`UPDATE tasks SET session_id = ${sessionId} WHERE id = ${taskId}`;
+      }
+
+      if (!task.session_id) {
+        await sql`
+          INSERT INTO messages (session_id, chat_id, role, content, status, created_at)
+          VALUES (${sessionId}, ${chatId}, 'user', ${task.input}, 'complete', clock_timestamp())
+        `;
+      }
+
+      // Persistent, session-keyed worktree (shared across turns; NOT torn down
+      // per turn — Phase 3 reaps it). Captures base_commit for a stable diff.
+      const { worktreePath, baseCommit } = await ensureSessionWorktree(sql, projectPath, sessionId, {
+        signal: ac.signal,
+      });
+      log.info({ taskId, worktreePath }, 'dispatcher: session worktree ready');
+
+      const [assistantMsg] = await sql<{ id: string }[]>`
+        INSERT INTO messages (session_id, chat_id, role, content, status, created_at)
+        VALUES (${sessionId}, ${chatId}, 'assistant', '', 'streaming', clock_timestamp())
+        RETURNING id
+      `;
+      const assistantId = assistantMsg!.id;
+
+      broker.publishFrame(sessionId, {
+        type: 'message_started',
+        message_id: assistantId,
+        chat_id: chatId,
+        role: 'assistant',
+      } as WsFrame);
+
+      const manifestCommands = getManifestCommands(agent);
+      if (manifestCommands.length > 0) {
+        setTaskCommands(taskId, manifestCommands);
+        broker.publishFrame(sessionId, {
+          type: 'agent_commands',
+          task_id: taskId,
+          session_id: sessionId,
+          commands: manifestCommands,
+        } as WsFrame);
+      }
+
+      // Accumulate the turn's stream for persistence + the final message content.
+      const textChunks: string[] = [];
+      const reasoningChunks: string[] = [];
+      const toolSnaps = new Map<string, AcpToolSnapshot>();
+
+      // Map transport-agnostic AgentEvents → the SAME WS frames the ACP path emits.
+      // This boundary is where message_id/chat_id get attached (the backend never
+      // owns them).
+      const onEvent = (e: AgentEvent): void => {
+        switch (e.type) {
+          case 'text':
+            textChunks.push(e.text);
+            broker.publishFrame(sessionId, {
+              type: 'delta',
+              message_id: assistantId,
+              chat_id: chatId,
+              content: e.text,
+            } as WsFrame);
+            break;
+          case 'reasoning':
+            reasoningChunks.push(e.text);
+            broker.publishFrame(sessionId, {
+              type: 'reasoning_delta',
+              message_id: assistantId,
+              chat_id: chatId,
+              content: e.text,
+            } as WsFrame);
+            break;
+          case 'tool_call':
+          case 'tool_update':
+            toolSnaps.set(e.toolCall.toolCallId, e.toolCall);
+            broker.publishFrame(sessionId, {
+              type: 'tool_call',
+              message_id: assistantId,
+              chat_id: chatId,
+              tool_call: snapshotToWireToolCall(e.toolCall),
+            } as WsFrame);
+            break;
+          case 'commands':
+            // opencode-server doesn't emit these today; ignore if it ever does.
+            break;
+        }
+      };
+
+      // opencode expects provider-prefixed model ids (e.g. 'llama-swap/qwen3.6-35b…').
+      // DEFAULT_MODEL is bare (no prefix) because native inference uses it directly
+      // against llama-swap. Coalesce empty string (frontend sends '' when no models
+      // listed) and prefix bare ids so parseModel always succeeds.
+      const rawModel = (task.model && task.model.trim()) || config.DEFAULT_MODEL;
+      const model = rawModel.includes('/') ? rawModel : `llama-swap/${rawModel}`;
+      const backend = getOpenCodeBackend(installPath);
+      const handle = await backend.ensureSession(sessionId, {
+        agent,
+        model,
+        worktreePath,
+        projectId: task.project_id,
+      });
+      const result = await backend.prompt(handle, task.input, {
+        worktreePath,
+        model,
+        signal: ac.signal,
+        onEvent,
+      });
+
+      const assistantContent = textChunks.join('').slice(0, 50_000);
+      const reasoningText = reasoningChunks.join('').slice(0, 200_000);
+      const outputSummary = (result.ok ? textChunks.join('') : result.error ?? 'opencode turn failed').slice(0, 500);
+
+      await persistExternalAgentTurn(sql, assistantId, [...toolSnaps.values()], reasoningText);
+
+      await sql`
+        UPDATE messages
+        SET content = ${assistantContent}, status = 'complete', finished_at = clock_timestamp()
+        WHERE id = ${assistantId}
+      `;
+      broker.publishFrame(sessionId, {
+        type: 'message_complete',
+        message_id: assistantId,
+        chat_id: chatId,
+      } as WsFrame);
+
+      if (stopping) {
+        await sql`UPDATE tasks SET state = 'cancelled', ended_at = clock_timestamp() WHERE id = ${taskId}`;
+        return; // worktree persists (no cleanup); backend stays warm
+      }
+
+      // 1.10: diff the persistent worktree against its captured baseline and
+      // SUPERSEDE the session's prior pending row (latest-wins, one accumulating
+      // diff) instead of stacking. Stamp agent for DiffPanel attribution.
+      const diff = await diffWorktree(worktreePath, projectPath, {
+        signal: ac.signal,
+        baseRef: baseCommit ?? 'HEAD',
+      });
+      if (diff) {
+        await sql`
+          DELETE FROM pending_changes WHERE session_id = ${sessionId} AND status = 'pending'
+        `;
+        await sql`
+          INSERT INTO pending_changes (session_id, task_id, file_path, operation, diff, agent)
+          VALUES (${sessionId}, ${taskId}, ${projectPath}, 'edit', ${diff}, ${agent})
+        `;
+        log.info({ taskId, diffLength: diff.length }, 'dispatcher: diff superseded prior pending change');
+      } else {
+        log.info({ taskId }, 'dispatcher: no changes detected in session worktree');
+      }
+
+      // NO worktree cleanup — it's persistent (Phase 3 reaps it). Backend stays warm.
+
+      const [extCostRow] = await sql<{ total: number | null }[]>`
+        SELECT SUM(tokens_used)::int AS total
+        FROM messages
+        WHERE session_id = ${sessionId} AND tokens_used IS NOT NULL
+      `;
+      const extCostTokens = extCostRow?.total ?? null;
+
+      const finalState = result.ok ? 'completed' : 'failed';
+      await sql`
+        UPDATE tasks
+        SET state = ${finalState}, ended_at = clock_timestamp(), output_summary = ${outputSummary}, cost_tokens = ${extCostTokens}
+        WHERE id = ${taskId}
+      `;
+      log.info({ taskId, agent, finalState, costTokens: extCostTokens }, 'dispatcher: task finished (opencode server)');
+      clearTaskCommands(taskId);
+    } catch (err) {
+      const errMsg = err instanceof Error ? err.message : String(err);
+      log.error({ taskId, agent, err: errMsg }, 'dispatcher: opencode server error');
+      await sql`
+        UPDATE tasks
+        SET state = 'failed', ended_at = clock_timestamp(), output_summary = ${errMsg.slice(0, 500)}
+        WHERE id = ${taskId}
+      `.catch(() => {});
+      clearTaskCommands(taskId);
+      // No worktree cleanup (persistent); backend stays warm for the next turn.
+    }
+  }
+
   // ─── Helpers ────────────────────────────────────────────────────────────────
 
   async function waitForCompletion(assistantId: string): Promise<string> {
@@ -514,9 +810,9 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
         });
         listener = null;
       }
-      if (inflightPromise) {
-        log.info('dispatcher: waiting for in-flight task');
-        await inflightPromise;
+      if (inflight.size > 0) {
+        log.info({ count: inflight.size }, 'dispatcher: waiting for in-flight tasks');
+        await Promise.allSettled([...inflight.values()]);
       }
       log.info('dispatcher: stopped');
     },

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

@@ -29,7 +29,7 @@ interface AgentRow {
   last_probed_at: string | Date | null;
 }
 
-async function fetchLlamaSwapModels(config: Config): Promise<ProviderModel[]> {
+export async function fetchLlamaSwapModels(config: Config): Promise<ProviderModel[]> {
   try {
     const res = await fetch(`${config.LLAMA_SWAP_URL}/v1/models`);
     if (!res.ok) return [];

apps/coder/src/services/worktrees.ts

@@ -6,6 +6,7 @@
  * After the agent completes, we diff the worktree against HEAD and
  * queue the diff into pending_changes.
  */
+import type { Sql } from '../db.js';
 import { hostExec } from './host-exec.js';
 
 const WORKTREE_BASE = '/tmp/booworktrees';
@@ -45,7 +46,7 @@ export async function createWorktree(
 export async function diffWorktree(
   worktreePath: string,
   projectPath: string,
-  opts?: { signal?: AbortSignal },
+  opts?: { signal?: AbortSignal; baseRef?: string },
 ): Promise<string> {
   // First, commit any uncommitted changes in the worktree so we can diff branches
   // Stage all changes
@@ -74,9 +75,13 @@ export async function diffWorktree(
     { signal: opts?.signal, timeoutMs: 15_000 },
   );
 
-  // Diff the worktree branch against the parent commit (HEAD of main tree)
+  // Diff the worktree branch against the baseline. Per-task callers default to the
+  // main tree's current HEAD; the session-worktree (opencode) path passes the
+  // captured base_commit so the accumulated diff is stable across turns even if
+  // project HEAD advances.
+  const baseRef = opts?.baseRef ?? 'HEAD';
   const diffResult = await hostExec(
-    `git -C ${shellEscape(projectPath)} diff HEAD...$(git -C ${shellEscape(worktreePath)} rev-parse HEAD)`,
+    `git -C ${shellEscape(projectPath)} diff ${shellEscape(baseRef)}...$(git -C ${shellEscape(worktreePath)} rev-parse HEAD)`,
     { signal: opts?.signal, timeoutMs: 60_000 },
   );
 
@@ -111,6 +116,231 @@ export async function cleanupWorktree(
   ).catch(() => {});
 }
 
+// ─── v2.6: session-keyed persistent worktree ────────────────────────────────
+
+export interface SessionWorktree {
+  worktreePath: string;
+  baseCommit: string | null;
+}
+
+/**
+ * v2.6: create-or-reuse ONE worktree per BooCode session (shared across all
+ * agents/turns in the session), recorded in `session_worktrees`. Unlike the
+ * per-task `createWorktree`, this persists — it is NOT torn down per turn
+ * (cleanup is Phase 3). Captures the project's current HEAD as `base_commit`
+ * so the accumulating diff has a stable baseline across turns.
+ *
+ * Distinct path namespace (`session-<id>` branch, `/sess-<id>` dir) so it never
+ * collides with the per-task worktrees that arena/new_task/MCP still use.
+ */
+export async function ensureSessionWorktree(
+  sql: Sql,
+  projectPath: string,
+  sessionId: string,
+  opts?: { signal?: AbortSignal },
+): Promise<SessionWorktree> {
+  const [existing] = await sql<{ worktree_path: string; base_commit: string | null }[]>`
+    SELECT worktree_path, base_commit FROM session_worktrees WHERE session_id = ${sessionId}
+  `;
+  if (existing) {
+    return { worktreePath: existing.worktree_path, baseCommit: existing.base_commit };
+  }
+
+  const worktreePath = `${WORKTREE_BASE}/sess-${sessionId}`;
+  const branchName = `session-${sessionId}`;
+
+  await hostExec(`mkdir -p ${WORKTREE_BASE}`, { signal: opts?.signal });
+
+  // Capture the baseline commit BEFORE branching, so the diff is stable even if
+  // project HEAD later advances.
+  const headResult = await hostExec(
+    `git -C ${shellEscape(projectPath)} rev-parse HEAD`,
+    { signal: opts?.signal, timeoutMs: 10_000 },
+  );
+  const baseCommit = headResult.exitCode === 0 ? headResult.stdout.trim() || null : null;
+
+  const result = await hostExec(
+    `git -C ${shellEscape(projectPath)} worktree add ${shellEscape(worktreePath)} -b ${shellEscape(branchName)} HEAD`,
+    { signal: opts?.signal, timeoutMs: 30_000 },
+  );
+  if (result.exitCode !== 0) {
+    throw new Error(`Failed to create session worktree: ${result.stderr.trim() || result.stdout.trim()}`);
+  }
+
+  // Persist. ON CONFLICT keeps the first writer's row if two turns race the create.
+  await sql`
+    INSERT INTO session_worktrees (session_id, worktree_path, base_commit)
+    VALUES (${sessionId}, ${worktreePath}, ${baseCommit})
+    ON CONFLICT (session_id) DO NOTHING
+  `;
+  const [row] = await sql<{ worktree_path: string; base_commit: string | null }[]>`
+    SELECT worktree_path, base_commit FROM session_worktrees WHERE session_id = ${sessionId}
+  `;
+  return {
+    worktreePath: row?.worktree_path ?? worktreePath,
+    baseCommit: row?.base_commit ?? baseCommit,
+  };
+}
+
+// ─── Session-delete work-loss guard ─────────────────────────────────────────
+
+/**
+ * Risk report for a single worktree, returned by checkWorktreeWorkAtRisk.
+ * `atRisk` is the gate the server reads before allowing a session delete.
+ * A git error never silently passes — it forces `atRisk` true and surfaces
+ * the message in `error` (fail-closed).
+ */
+export interface RiskReport {
+  worktreePath: string;
+  branch: string;
+  dirty: boolean;   // uncommitted working-tree changes (incl. untracked)
+  unpushed: number; // commits ahead of upstream, or -1 if no upstream is set
+  unmerged: number; // commits on this branch not in the project default branch
+  atRisk: boolean;  // dirty || unmerged > 0 || (upstream && unpushed > 0) || git error
+  error?: string;   // populated on a git failure; presence forces atRisk
+}
+
+/**
+ * Resolve the project's default branch as a git-usable ref (e.g. "origin/main").
+ *
+ * `refs/remotes/origin/HEAD` lives in the repo's COMMON git dir and is shared
+ * across every linked worktree, so reading it from the session worktree returns
+ * the REMOTE's default branch — never this worktree's own `session-<id>` branch
+ * (that would be `symbolic-ref HEAD`, a different ref). Falls back to probing
+ * common defaults by verified existence when origin/HEAD isn't set (e.g. a repo
+ * that never ran `git remote set-head`). Returns null if none resolve, in which
+ * case the unmerged check is skipped (dirty + unpushed still protect the work).
+ */
+async function detectDefaultBranchRef(
+  worktreePath: string,
+  opts?: { signal?: AbortSignal },
+): Promise<string | null> {
+  const head = await hostExec(
+    `git -C ${shellEscape(worktreePath)} symbolic-ref --short refs/remotes/origin/HEAD`,
+    { signal: opts?.signal, timeoutMs: 10_000 },
+  );
+  if (head.exitCode === 0) {
+    const ref = head.stdout.trim(); // e.g. "origin/main"
+    if (ref) {
+      const verify = await hostExec(
+        `git -C ${shellEscape(worktreePath)} rev-parse --verify --quiet ${shellEscape(ref + '^{commit}')}`,
+        { signal: opts?.signal, timeoutMs: 10_000 },
+      );
+      if (verify.exitCode === 0 && verify.stdout.trim()) return ref;
+    }
+  }
+  // origin/HEAD unset or unresolvable — probe common defaults. Prefer the
+  // remote-tracking ref (always resolvable in a fresh worktree) over the local
+  // head, which may not exist if the default branch lives only in the main tree.
+  for (const cand of ['origin/main', 'origin/master', 'main', 'master']) {
+    const verify = await hostExec(
+      `git -C ${shellEscape(worktreePath)} rev-parse --verify --quiet ${shellEscape(cand + '^{commit}')}`,
+      { signal: opts?.signal, timeoutMs: 10_000 },
+    );
+    if (verify.exitCode === 0 && verify.stdout.trim()) return cand;
+  }
+  return null;
+}
+
+/**
+ * Inspect a worktree for work that would be lost if its session were deleted.
+ * Three checks, all via the audited hostExec + shellEscape path (every
+ * interpolated value — paths, refs — is single-quote-escaped; no bare
+ * interpolation). Any unexpected git failure is treated as at-risk, never a
+ * silent pass.
+ */
+export async function checkWorktreeWorkAtRisk(
+  worktreePath: string,
+  opts?: { signal?: AbortSignal },
+): Promise<RiskReport> {
+  // Branch name — also doubles as the "is this still a git worktree?" probe.
+  const br = await hostExec(
+    `git -C ${shellEscape(worktreePath)} rev-parse --abbrev-ref HEAD`,
+    { signal: opts?.signal, timeoutMs: 10_000 },
+  );
+  if (br.exitCode !== 0) {
+    return {
+      worktreePath,
+      branch: '',
+      dirty: false,
+      unpushed: 0,
+      unmerged: 0,
+      atRisk: true,
+      error: `git rev-parse failed: ${br.stderr.trim() || 'not a git worktree'}`,
+    };
+  }
+  const branch = br.stdout.trim();
+
+  // (a) Uncommitted (dirty working tree, including untracked files).
+  const st = await hostExec(
+    `git -C ${shellEscape(worktreePath)} status --porcelain`,
+    { signal: opts?.signal, timeoutMs: 15_000 },
+  );
+  if (st.exitCode !== 0) {
+    return {
+      worktreePath,
+      branch,
+      dirty: false,
+      unpushed: 0,
+      unmerged: 0,
+      atRisk: true,
+      error: `git status failed: ${st.stderr.trim()}`,
+    };
+  }
+  const dirty = st.stdout.trim().length > 0;
+
+  // (b) Unpushed commits. No upstream configured => work exists only locally;
+  // treat as unpushed-by-definition (-1) rather than an error.
+  const up = await hostExec(
+    `git -C ${shellEscape(worktreePath)} rev-list --count ${shellEscape('@{u}..HEAD')}`,
+    { signal: opts?.signal, timeoutMs: 15_000 },
+  );
+  const unpushed = up.exitCode === 0 ? (parseInt(up.stdout.trim() || '0', 10) || 0) : -1;
+
+  // (c) Unmerged commits — on this branch but not in the project default branch.
+  const defaultRef = await detectDefaultBranchRef(worktreePath, opts);
+  let unmerged = 0;
+  if (defaultRef) {
+    const rl = await hostExec(
+      `git -C ${shellEscape(worktreePath)} rev-list --count ${shellEscape(defaultRef + '..HEAD')}`,
+      { signal: opts?.signal, timeoutMs: 15_000 },
+    );
+    if (rl.exitCode === 0) unmerged = parseInt(rl.stdout.trim() || '0', 10) || 0;
+  }
+
+  // unpushed only contributes when an upstream actually exists. Session branches
+  // (session-<id>) never have one (unpushed === -1), and any real local-only work
+  // there already surfaces as unmerged > 0 — so the no-upstream case adds no
+  // protection, only friction (it flagged every pristine worktree-backed session).
+  // The unpushed > 0 arm stays forward-compatible with P1.5 pushable branches.
+  const hasUpstream = unpushed !== -1;
+  const atRisk = dirty || unmerged > 0 || (hasUpstream && unpushed > 0);
+  return { worktreePath, branch, dirty, unpushed, unmerged, atRisk };
+}
+
+/**
+ * Stash a worktree's uncommitted changes (including untracked, via -u) so the
+ * working tree is clean. Stash entries live in the repo's common git dir, so
+ * they survive worktree-dir removal — this is the recoverable, safe-by-default
+ * escape. Note it only clears the *dirty* risk; unpushed/unmerged commits
+ * remain on the branch, so a re-attempted delete may still block on those.
+ */
+export async function stashWorktree(
+  worktreePath: string,
+  opts?: { signal?: AbortSignal },
+): Promise<{ stashed: boolean; error?: string }> {
+  const r = await hostExec(
+    `git -C ${shellEscape(worktreePath)} stash push -u -m ${shellEscape('boocode: pre-delete stash')}`,
+    { signal: opts?.signal, timeoutMs: 30_000 },
+  );
+  if (r.exitCode !== 0) {
+    return { stashed: false, error: r.stderr.trim() || r.stdout.trim() };
+  }
+  // "No local changes to save" => exit 0, nothing stashed — not an error.
+  const stashed = !/no local changes to save/i.test(r.stdout);
+  return { stashed };
+}
+
 /** Minimal shell escape for paths (single-quote wrapping). */
 function shellEscape(s: string): string {
   // Replace single quotes with escaped version, wrap in single quotes

apps/server/src/routes/sessions.ts

@@ -3,7 +3,7 @@ import { z } from 'zod';
 import type { Sql } from '../db.js';
 import type { Config } from '../config.js';
 import type { Broker } from '../services/broker.js';
-import type { Session } from '../types/api.js';
+import type { Session, WorktreeRiskReport } from '../types/api.js';
 import { getSetting } from './settings.js';
 
 const CreateBody = z.object({
@@ -426,10 +426,53 @@ export function registerSessionRoutes(
     }
   );
 
-  app.delete<{ Params: { id: string } }>(
+  app.delete<{ Params: { id: string }; Querystring: { force?: string } }>(
     '/api/sessions/:id',
     async (req, reply) => {
       const id = req.params.id;
+      const force = req.query.force === 'true' || req.query.force === '1';
+
+      // Session-delete work-loss guard. CASCADE on session_worktrees means the
+      // DELETE below auto-wipes the worktree row, so the safety check MUST run
+      // BEFORE it (paths read while the row still exists, pre-CASCADE).
+      //
+      // Optimization: read session_worktrees from our own (shared) DB first.
+      // No row => chat-only session => nothing on disk => delete immediately,
+      // zero round-trip. Only worktree-backed sessions pay the host git check.
+      if (!force) {
+        const worktrees = await sql<{ worktree_path: string }[]>`
+          SELECT worktree_path FROM session_worktrees WHERE session_id = ${id}
+        `;
+        if (worktrees.length > 0) {
+          // Worktree dirs live on the host; only BooCoder can run git on them.
+          const origin = process.env.BOOCODER_URL ?? 'http://boocoder:3000';
+          let reports: WorktreeRiskReport[];
+          try {
+            const res = await fetch(`${origin}/api/sessions/${id}/worktree-risk`);
+            if (!res.ok) {
+              // Fail-closed: can't verify => don't risk silent loss. Force escapes.
+              reply.code(409);
+              return {
+                error: 'could not verify worktree safety (BooCoder check failed). Use force to delete anyway.',
+                reports: [] as WorktreeRiskReport[],
+              };
+            }
+            reports = ((await res.json()) as { reports?: WorktreeRiskReport[] }).reports ?? [];
+          } catch {
+            // Fail-closed: BooCoder unreachable. Force bypasses this path entirely.
+            reply.code(409);
+            return {
+              error: 'BooCoder unreachable; cannot verify worktree safety. Use force to delete anyway.',
+              reports: [] as WorktreeRiskReport[],
+            };
+          }
+          if (reports.some((r) => r.atRisk)) {
+            reply.code(409);
+            return { error: 'This session has work at risk in its worktree.', reports };
+          }
+        }
+      }
+
       const deleted = await sql<{ project_id: string }[]>`
         DELETE FROM sessions WHERE id = ${id} RETURNING project_id
       `;

apps/server/src/services/auto_name.ts

@@ -37,9 +37,11 @@ export async function maybeAutoNameChat(
   if ((counts[0]?.n ?? 0) < 1) return;
 
   const chatRows = await ctx.sql<
-    { id: string; name: string | null; session_id: string }[]
+    { id: string; name: string | null; session_id: string; model: string | null }[]
   >`
-    SELECT id, name, session_id FROM chats WHERE id = ${chatId}
+    SELECT c.id, c.name, c.session_id, s.model
+    FROM chats c JOIN sessions s ON s.id = c.session_id
+    WHERE c.id = ${chatId}
   `;
   const chat = chatRows[0];
   if (!chat) return;
@@ -67,6 +69,7 @@ export async function maybeAutoNameChat(
     user: namingInput,
     maxTokens: 30,
     temperature: 0.3,
+    fallbackModel: chat.model ?? undefined,
   });
   const name = cleanTitle(raw);
   if (!name) {

apps/server/src/types/api.ts

@@ -25,6 +25,20 @@ export interface AvailableProject {
 
 export type SessionStatus = 'open' | 'archived';
 
+// Session-delete work-loss guard. Returned (as `reports`) in the 409 body when
+// a delete is blocked because the session's worktree holds work at risk. The
+// shape is produced by BooCoder's checkWorktreeWorkAtRisk and passed through
+// verbatim; mirrored byte-for-byte in apps/web/src/api/types.ts for the dialog.
+export interface WorktreeRiskReport {
+  worktreePath: string;
+  branch: string;
+  dirty: boolean;
+  unpushed: number; // commits ahead of upstream, or -1 if no upstream
+  unmerged: number; // commits not in the project default branch
+  atRisk: boolean;
+  error?: string;
+}
+
 export interface Session {
   id: string;
   project_id: string;

apps/web/src/api/client.ts

@@ -151,8 +151,17 @@ export const api = {
         method: 'PATCH',
         body: JSON.stringify(body),
       }),
-    remove: (id: string) =>
-      request<void>(`/api/sessions/${id}`, { method: 'DELETE' }),
+    // force=true bypasses the server-side worktree work-loss guard. A blocked
+    // delete throws ApiError(409) whose body carries { error, reports }.
+    remove: (id: string, force = false) =>
+      request<void>(`/api/sessions/${id}${force ? '?force=true' : ''}`, { method: 'DELETE' }),
+    // Stash the session's worktree (uncommitted changes) on the host, via the
+    // BooCoder proxy. Recoverable escape from the work-at-risk dialog.
+    worktreeStash: (id: string) =>
+      request<{ results: { worktreePath: string; stashed: boolean; error?: string }[] }>(
+        `/api/coder/sessions/${id}/worktree-stash`,
+        { method: 'POST' },
+      ),
     archive: (id: string) =>
       request<void>(`/api/sessions/${id}/archive`, { method: 'POST' }),
     unarchive: (id: string) =>

apps/web/src/api/types.ts

@@ -34,6 +34,19 @@ export interface AvailableProject {
 
 export type SessionStatus = 'open' | 'archived';
 
+// Session-delete work-loss guard. Mirror of WorktreeRiskReport in
+// apps/server/src/types/api.ts — edit both copies together. Arrives as the
+// `reports` field of the 409 body when a delete is blocked.
+export interface WorktreeRiskReport {
+  worktreePath: string;
+  branch: string;
+  dirty: boolean;
+  unpushed: number; // commits ahead of upstream, or -1 if no upstream
+  unmerged: number; // commits not in the project default branch
+  atRisk: boolean;
+  error?: string;
+}
+
 export interface Session {
   id: string;
   project_id: string;

apps/web/src/components/ChatTabBar.tsx

@@ -1,5 +1,5 @@
 import { useState } from 'react';
-import { Code, History, MessageSquare, Plus, Terminal, X } from 'lucide-react';
+import { Code, Columns2, History, MessageSquare, Plus, RotateCcw, Terminal, X } from 'lucide-react';
 import type { Chat, WorkspacePane } from '@/api/types';
 import { StatusDot } from '@/components/StatusDot';
 import {
@@ -26,7 +26,9 @@ interface Props {
   onCloseOthers: (chatId: string) => void;
   onCloseToRight: (chatId: string) => void;
   onCloseAll: () => void;
-  onAddPane: (kind: 'chat' | 'terminal' | 'coder') => void;
+  onNewTab: () => void;
+  onSplitPane: (kind: 'chat' | 'terminal' | 'coder') => void;
+  onReopenPane?: () => void;
   onShowHistory: () => void;
   onRename: (chatId: string, name: string) => Promise<void>;
   onRemovePane?: () => void;
@@ -40,7 +42,9 @@ export function ChatTabBar({
   onCloseOthers,
   onCloseToRight,
   onCloseAll,
-  onAddPane,
+  onNewTab,
+  onSplitPane,
+  onReopenPane,
   onShowHistory,
   onRename,
   onRemovePane,
@@ -131,7 +135,7 @@ export function ChatTabBar({
               </div>
             </ContextMenuTrigger>
             <ContextMenuContent>
-              <ContextMenuItem onSelect={() => onAddPane('chat')}>
+              <ContextMenuItem onSelect={onNewTab}>
                 New chat
               </ContextMenuItem>
               <ContextMenuSeparator />
@@ -170,29 +174,49 @@ export function ChatTabBar({
       )}
 
       <div className="flex items-center ml-auto gap-0.5 px-1 shrink-0">
+        <button
+          type="button"
+          onClick={onNewTab}
+          className="inline-flex items-center justify-center p-1 rounded text-muted-foreground hover:bg-muted hover:text-foreground max-md:min-h-[44px] max-md:min-w-[44px]"
+          aria-label="New tab"
+          title="New tab"
+        >
+          <Plus size={12} />
+        </button>
         <DropdownMenu>
           <DropdownMenuTrigger asChild>
             <button
               type="button"
               className="inline-flex items-center justify-center p-1 rounded text-muted-foreground hover:bg-muted hover:text-foreground max-md:min-h-[44px] max-md:min-w-[44px]"
-              aria-label="New pane"
-              title="New pane"
+              aria-label="Split pane"
+              title="Split pane"
             >
-              <Plus size={12} />
+              <Columns2 size={12} />
             </button>
           </DropdownMenuTrigger>
           <DropdownMenuContent align="end" className="w-fit">
-            <DropdownMenuItem onSelect={() => onAddPane('chat')}>
+            <DropdownMenuItem onSelect={() => onSplitPane('chat')}>
               <MessageSquare size={14} /> New BooChat
             </DropdownMenuItem>
-            <DropdownMenuItem onSelect={() => onAddPane('terminal')}>
+            <DropdownMenuItem onSelect={() => onSplitPane('terminal')}>
               <Terminal size={14} /> New BooTerm
             </DropdownMenuItem>
-            <DropdownMenuItem onSelect={() => onAddPane('coder')}>
+            <DropdownMenuItem onSelect={() => onSplitPane('coder')}>
               <Code size={14} /> New BooCode
             </DropdownMenuItem>
           </DropdownMenuContent>
         </DropdownMenu>
+        {onReopenPane && (
+          <button
+            type="button"
+            onClick={onReopenPane}
+            className="inline-flex items-center justify-center p-1 rounded text-muted-foreground hover:bg-muted hover:text-foreground max-md:min-h-[44px] max-md:min-w-[44px]"
+            aria-label="Reopen closed pane"
+            title="Reopen closed pane"
+          >
+            <RotateCcw size={12} />
+          </button>
+        )}
         <button
           type="button"
           onClick={onShowHistory}

apps/web/src/components/ProjectSidebar.tsx

@@ -19,12 +19,12 @@ import {
   DialogDescription,
 } from '@/components/ui/dialog';
 import { AddProjectModal } from './AddProjectModal';
-import { api } from '@/api/client';
+import { api, ApiError } from '@/api/client';
 import { useSidebar } from '@/hooks/useSidebar';
 import { useSidebarDrawer } from '@/hooks/useSidebarDrawer';
 import { useViewport } from '@/hooks/useViewport';
 import { usePullToRefresh } from '@/hooks/usePullToRefresh';
-import type { SidebarProject } from '@/api/types';
+import type { SidebarProject, WorktreeRiskReport } from '@/api/types';
 import { giteaUrlFor } from '@/lib/projectUrls';
 import { isCoderSessionName } from '@/lib/coder-session';
 import { cn } from '@/lib/utils';
@@ -110,6 +110,16 @@ export function ProjectSidebar() {
   const [renamingProject, setRenamingProject] = useState<string | null>(null);
   const [renameProjectValue, setRenameProjectValue] = useState('');
   const [archiveProjectConfirm, setArchiveProjectConfirm] = useState<{ id: string; name: string } | null>(null);
+  // Work-at-risk dialog: shown when a delete is blocked (409) because the
+  // session's worktree holds uncommitted/unpushed/unmerged work.
+  const [riskState, setRiskState] = useState<{
+    sessionId: string;
+    projectId: string;
+    name: string;
+    message: string;
+    reports: WorktreeRiskReport[];
+  } | null>(null);
+  const [riskBusy, setRiskBusy] = useState(false);
   const navigate = useNavigate();
   const location = useLocation();
   const lastToastedError = useRef<string | null>(null);
@@ -174,16 +184,81 @@ export function ProjectSidebar() {
     }
   }
 
-  async function handleDeleteSession(sessionId: string, projectId: string) {
+  async function handleDeleteSession(
+    sessionId: string,
+    projectId: string,
+    name: string,
+    force = false,
+  ) {
     try {
-      await api.sessions.remove(sessionId);
+      await api.sessions.remove(sessionId, force);
       // Server publishes session_deleted via WS; useUserEvents delivers it.
+      setRiskState(null);
       if (activeSession === sessionId) navigate(`/project/${projectId}`);
     } catch (err) {
+      // 409 => the server's work-loss guard blocked the delete. Open the
+      // work-at-risk dialog with the per-worktree reports instead of toasting.
+      if (
+        err instanceof ApiError &&
+        err.status === 409 &&
+        err.body && typeof err.body === 'object' && 'reports' in err.body
+      ) {
+        const body = err.body as { error?: string; reports?: WorktreeRiskReport[] };
+        setRiskState({
+          sessionId,
+          projectId,
+          name,
+          message: body.error ?? 'This session has work at risk.',
+          reports: body.reports ?? [],
+        });
+        return;
+      }
       toast.error(err instanceof Error ? err.message : 'failed to delete session');
     }
   }
 
+  // Stash the worktree's uncommitted changes (recoverable), then re-attempt the
+  // delete. If unpushed/unmerged commits remain, the retry 409s again and the
+  // dialog re-renders with the narrowed risk.
+  async function handleStashAndRetry() {
+    if (!riskState || riskBusy) return;
+    setRiskBusy(true);
+    try {
+      const { results } = await api.sessions.worktreeStash(riskState.sessionId);
+      const failed = results.find((r) => r.error);
+      if (failed) {
+        toast.error(`stash failed: ${failed.error}`);
+        return;
+      }
+      await handleDeleteSession(riskState.sessionId, riskState.projectId, riskState.name, false);
+    } catch (err) {
+      toast.error(err instanceof Error ? err.message : 'stash failed');
+    } finally {
+      setRiskBusy(false);
+    }
+  }
+
+  // Explicit, destructive override — deletes despite work at risk.
+  async function handleForceDelete() {
+    if (!riskState || riskBusy) return;
+    setRiskBusy(true);
+    try {
+      await handleDeleteSession(riskState.sessionId, riskState.projectId, riskState.name, true);
+    } finally {
+      setRiskBusy(false);
+    }
+  }
+
+  // Route the user to commit it themselves — never auto-commit. Opens the
+  // session workspace where they can use a terminal or agent pane.
+  function handleGoCommit() {
+    if (!riskState) return;
+    const sessionId = riskState.sessionId;
+    setRiskState(null);
+    navigate(`/session/${sessionId}`);
+    toast.info('Open a terminal or agent in this session, commit and push your work, then delete again.');
+  }
+
   async function handleRenameSession(sessionId: string) {
     const trimmed = renameValue.trim();
     setRenamingSession(null);
@@ -216,6 +291,20 @@ export function ProjectSidebar() {
       )
     : 'w-60 shrink-0 border-r bg-sidebar text-sidebar-foreground flex flex-col h-screen';
 
+  // Work-at-risk dialog framing. The server returns 409 in two distinct
+  // situations: (1) work genuinely at risk (reports has ≥1 atRisk entry), or
+  // (2) it couldn't verify (BooCoder down/errored → reports is empty). These
+  // are different user stories — "your work is in danger" vs "the checker is
+  // offline" — so the dialog must not show one generic message for both.
+  const atRiskReports = riskState?.reports.filter((r) => r.atRisk) ?? [];
+  const verifyFailed = riskState !== null && atRiskReports.length === 0;
+  const anyDirty = atRiskReports.some((r) => r.dirty);
+  // Commit-based risk (unpushed/unmerged) that stash can NOT clear. When this is
+  // all that remains (e.g. after a stash cleared the dirty changes), the dialog
+  // explains why it re-blocked and hides the Stash button so it doesn't look
+  // like stash "didn't work".
+  const anyCommits = atRiskReports.some((r) => r.unpushed !== 0 || r.unmerged > 0);
+
   return (
     <aside className={asideCls}>
       <div className="px-4 py-3 border-b flex items-center justify-between">
@@ -499,7 +588,7 @@ export function ProjectSidebar() {
                   const projectId = projects.find((p) =>
                     p.recent_sessions.some((s) => s.id === deleteConfirm.id)
                   )?.id;
-                  if (projectId) void handleDeleteSession(deleteConfirm.id, projectId);
+                  if (projectId) void handleDeleteSession(deleteConfirm.id, projectId, deleteConfirm.name);
                 }
                 setDeleteConfirm(null);
               }}
@@ -509,6 +598,77 @@ export function ProjectSidebar() {
           </div>
         </DialogContent>
       </Dialog>
+
+      <Dialog open={riskState !== null} onOpenChange={(open) => { if (!open && !riskBusy) setRiskState(null); }}>
+        <DialogContent>
+          <DialogHeader>
+            <DialogTitle>
+              {verifyFailed ? 'Could not verify worktree safety' : 'This session has work at risk'}
+            </DialogTitle>
+            <DialogDescription>
+              {verifyFailed ? (
+                <>
+                  {riskState?.message ?? 'The worktree safety check is unavailable.'} Your work may be
+                  fine, but it couldn&apos;t be checked — only force-delete if you&apos;re sure.
+                </>
+              ) : anyDirty && anyCommits ? (
+                <>
+                  Deleting {riskState ? `"${riskState.name}"` : 'this session'} would orphan uncommitted
+                  changes <em>and</em> commits that aren&apos;t pushed or merged. Stash clears the
+                  changes (recoverable), but the commits will still block — push them or force-delete.
+                </>
+              ) : anyDirty ? (
+                <>
+                  Deleting {riskState ? `"${riskState.name}"` : 'this session'} would orphan uncommitted
+                  changes in its worktree. Stash them (recoverable), commit them, or force-delete.
+                </>
+              ) : (
+                <>
+                  Deleting {riskState ? `"${riskState.name}"` : 'this session'} would orphan commits that
+                  aren&apos;t pushed or merged. Stashing won&apos;t recover these — push them, or
+                  force-delete.
+                </>
+              )}
+            </DialogDescription>
+          </DialogHeader>
+          {!verifyFailed && (
+            <div className="flex flex-col gap-2 py-1 text-sm">
+              {atRiskReports.map((r) => (
+                <div key={r.worktreePath} className="rounded border border-border/60 px-3 py-2">
+                  <div className="font-mono text-xs text-muted-foreground truncate" title={r.worktreePath}>
+                    {r.branch || r.worktreePath}
+                  </div>
+                  <ul className="mt-1 list-disc pl-5 text-foreground/90">
+                    {r.error && <li className="text-destructive">git error: {r.error}</li>}
+                    {r.dirty && <li>uncommitted changes</li>}
+                    {r.unpushed === -1 && <li>local-only branch (no upstream)</li>}
+                    {r.unpushed > 0 && <li>{r.unpushed} unpushed commit{r.unpushed === 1 ? '' : 's'}</li>}
+                    {r.unmerged > 0 && <li>{r.unmerged} unmerged commit{r.unmerged === 1 ? '' : 's'}</li>}
+                  </ul>
+                </div>
+              ))}
+            </div>
+          )}
+          <div className="flex flex-wrap gap-2 justify-end pt-2">
+            <Button variant="outline" disabled={riskBusy} onClick={() => setRiskState(null)}>
+              Cancel
+            </Button>
+            {!verifyFailed && (
+              <Button variant="outline" disabled={riskBusy} onClick={handleGoCommit}>
+                Commit&hellip;
+              </Button>
+            )}
+            {!verifyFailed && anyDirty && (
+              <Button variant="outline" disabled={riskBusy} onClick={() => void handleStashAndRetry()}>
+                Stash &amp; delete
+              </Button>
+            )}
+            <Button variant="destructive" disabled={riskBusy} onClick={() => void handleForceDelete()}>
+              Force delete
+            </Button>
+          </div>
+        </DialogContent>
+      </Dialog>
     </aside>
   );
 }

apps/web/src/components/Workspace.tsx

@@ -65,6 +65,8 @@ export function Workspace({
     showLandingPage,
     addSplitPane,
     removePane,
+    reopenPane,
+    hasClosedPanes,
     isPaneChatPending,
     handlePaneDragStart,
     handlePaneDragOver,
@@ -207,10 +209,9 @@ export function Workspace({
                   onCloseOthers={(chatId) => closeOtherTabs(idx, chatId)}
                   onCloseToRight={(chatId) => closeTabsToRight(idx, chatId)}
                   onCloseAll={() => closeAllTabs(idx)}
-                  onAddPane={(kind) => {
-                    if (kind === 'chat') void createChat(idx);
-                    else onAddPane(kind);
-                  }}
+                  onNewTab={() => void createChat(idx)}
+                  onSplitPane={(kind) => onAddPane(kind)}
+                  onReopenPane={hasClosedPanes ? reopenPane : undefined}
                   onShowHistory={() => showLandingPage(idx)}
                   onRename={renameChat}
                   onRemovePane={panes.length > 1 ? () => removePane(idx) : undefined}

apps/web/src/hooks/useWorkspacePanes.ts

@@ -32,6 +32,21 @@ function chatPane(chatId: string): WorkspacePane {
   return { id: generateId(), kind: 'chat', chatId, chatIds: [chatId], activeChatIdx: 0 };
 }
 
+interface ClosedPaneEntry {
+  kind: WorkspacePane['kind'];
+  chatIds: string[];
+  activeChatIdx: number;
+}
+const MAX_CLOSED = 10;
+const closedPaneStack: ClosedPaneEntry[] = [];
+
+function pushClosed(pane: WorkspacePane): void {
+  if (pane.kind === 'empty' || pane.kind === 'settings') return;
+  if (pane.chatIds.length === 0) return;
+  closedPaneStack.push({ kind: pane.kind, chatIds: [...pane.chatIds], activeChatIdx: pane.activeChatIdx });
+  if (closedPaneStack.length > MAX_CLOSED) closedPaneStack.shift();
+}
+
 function chatNameForPaneKind(kind: 'coder' | 'terminal'): string {
   return kind === 'coder' ? 'BooCoder' : 'Terminal';
 }
@@ -137,6 +152,8 @@ export interface UseWorkspacePanesResult {
   // falls back to an empty pane to preserve the "always one pane" invariant.
   toggleSettingsPane: () => string | null;
   removePane: (idx: number) => void;
+  reopenPane: () => void;
+  hasClosedPanes: boolean;
   removeChatFromPanes: (chatId: string) => void;
   initializeFirstChatIfEmpty: (chatId: string) => void;
   validatePanes: (validChatIds: Set<string>) => void;
@@ -391,6 +408,14 @@ export function useWorkspacePanes(sessionId: string): UseWorkspacePanesResult {
       const pane = next[paneIdx]!;
       const nextIds = pane.chatIds.filter((id) => id !== chatId);
       if (nextIds.length === 0) {
+        if (next.length > 1) {
+          // Last tab closed and other panes exist — remove the whole pane
+          // instead of leaving an orphaned empty panel.
+          pushClosed(pane); setHasClosedPanes(true);
+          const spliced = next.filter((_, i) => i !== paneIdx);
+          setActivePaneIdx((ai) => Math.min(ai, spliced.length - 1));
+          return spliced;
+        }
         next[paneIdx] = { ...pane, kind: 'empty', chatId: undefined, chatIds: [], activeChatIdx: -1 };
       } else {
         const nextActiveIdx = Math.min(pane.activeChatIdx, nextIds.length - 1);
@@ -534,6 +559,7 @@ export function useWorkspacePanes(sessionId: string): UseWorkspacePanesResult {
       // The endpoint is idempotent (404 on missing session) so a strict-mode
       // double-invoke of the updater is safe.
       const removed = prev[idx];
+      if (removed) { pushClosed(removed); setHasClosedPanes(true); }
       if (removed?.kind === 'terminal') {
         api.terminals.kill(sessionId, removed.id).catch(() => { /* non-fatal */ });
       }
@@ -543,6 +569,26 @@ export function useWorkspacePanes(sessionId: string): UseWorkspacePanesResult {
     });
   }, [sessionId]);
 
+  const [hasClosedPanes, setHasClosedPanes] = useState(closedPaneStack.length > 0);
+
+  const reopenPane = useCallback(() => {
+    const entry = closedPaneStack.pop();
+    setHasClosedPanes(closedPaneStack.length > 0);
+    if (!entry) return;
+    setPanes((prev) => {
+      const restored: WorkspacePane = {
+        id: generateId(),
+        kind: entry.kind,
+        chatId: entry.chatIds[entry.activeChatIdx] ?? entry.chatIds[0],
+        chatIds: entry.chatIds,
+        activeChatIdx: Math.min(entry.activeChatIdx, entry.chatIds.length - 1),
+      };
+      const next = [...prev, restored];
+      setActivePaneIdx(next.length - 1);
+      return next;
+    });
+  }, []);
+
   // Replaces a single empty default pane with a chat pane. Used by the initial
   // chat fetch to land on the most-recent open chat if no saved pane state.
   const initializeFirstChatIfEmpty = useCallback((chatId: string) => {
@@ -672,6 +718,8 @@ export function useWorkspacePanes(sessionId: string): UseWorkspacePanesResult {
     addSplitPane,
     toggleSettingsPane,
     removePane,
+    reopenPane,
+    hasClosedPanes,
     removeChatFromPanes,
     initializeFirstChatIfEmpty,
     validatePanes,

data/coder-providers.example.json

@@ -0,0 +1,12 @@
+{
+  "providers": {
+    "goose": { "enabled": false },
+    "amp-acp": {
+      "extends": "acp",
+      "label": "Amp",
+      "description": "ACP wrapper for Amp",
+      "command": ["amp-acp"],
+      "enabled": true
+    }
+  }
+}

data/coder-providers.json

@@ -1,3 +0,0 @@
-{
-  "providers": {}
-}

data/skills/boocode/systematic-debugging/SKILL.md

@@ -0,0 +1,61 @@
+---
+name: systematic-debugging
+description: Guided root-cause debugging. Use when encountering any bug, test failure, unexpected behavior, or performance problem. Enforces investigation before fixes.
+---
+
+# Systematic Debugging
+
+No fixes without root cause. Symptom fixes mask real bugs and waste time.
+
+## The Rule
+
+Complete Phase 1 before proposing ANY fix. If you haven't investigated, you cannot fix.
+
+## Phase 1: Root Cause Investigation
+
+1. **Read error messages carefully.** Stack traces, line numbers, error codes. Don't skip past them.
+2. **Reproduce consistently.** Exact steps, every time. If not reproducible, gather more data instead of guessing.
+3. **Check recent changes.** Git diff, recent commits, new deps, config changes, env differences.
+4. **Trace data flow.** Where does the bad value originate? Trace backward through the call stack to the source. Fix at the source, not the symptom.
+5. **Multi-component systems:** Before fixing, add diagnostic logging at each component boundary (what enters, what exits). Run once to locate the failing layer, THEN investigate that layer.
+
+## Phase 2: Pattern Analysis
+
+1. Find working examples of similar code in the same codebase.
+2. Compare working vs broken — list every difference.
+3. If implementing a pattern, read the reference implementation completely, not skimmed.
+4. Understand all dependencies, config, and assumptions.
+
+## Phase 3: Hypothesis and Testing
+
+1. State one hypothesis clearly: "X is the root cause because Y."
+2. Make the smallest possible change to test it. One variable at a time.
+3. If it didn't work, form a NEW hypothesis. Don't stack more fixes on top.
+4. After 3 failed fixes: STOP. Question the architecture, not the symptoms.
+
+## Phase 4: Implementation
+
+1. Create a failing test case first (simplest reproduction).
+2. Implement a single fix addressing the root cause.
+3. Verify: test passes, no regressions, issue actually resolved.
+4. If the fix doesn't work and you've tried 3+: the problem is architectural. Discuss before attempting more.
+
+## Red Flags — STOP and return to Phase 1
+
+- "Quick fix for now, investigate later"
+- "Just try changing X and see"
+- "I don't fully understand but this might work"
+- "One more fix attempt" after 2+ failures
+- Proposing solutions before tracing data flow
+- Each fix reveals a new problem in a different place
+
+## Apply This Skill
+
+Use these tools to investigate before proposing changes:
+
+- `view_file` to read error sites and suspect code paths
+- `grep` to find all callers / references to the failing function
+- `find_files` to locate related config, test fixtures, schema
+- `list_dir` to understand the module layout around the bug
+
+Report your Phase 1 findings (what you observed, what you traced, what you ruled out) before moving to Phase 3.

pnpm-lock.yaml

@@ -63,6 +63,9 @@ importers:
       '@modelcontextprotocol/sdk':
         specifier: ^1.29.0
         version: 1.29.0(zod@3.25.76)
+      '@opencode-ai/sdk':
+        specifier: ~1.15.0
+        version: 1.15.12
       fastify:
         specifier: ^4.28.1
         version: 4.29.1
@@ -920,6 +923,9 @@ packages:
   '@open-draft/until@2.1.0':
     resolution: {integrity: sha512-U69T3ItWHvLwGg5eJ0n3I62nWuE6ilHlmz7zM0npLBRvPRd7e6NYmg54vvRtP5mZG7kZqZCFVdsTWo7BPtBujg==}
 
+  '@opencode-ai/sdk@1.15.12':
+    resolution: {integrity: sha512-lOaBNX93dkakZe6C42ttX1bkSx3K2c6+Yv+w8Qv02v5rPlu1vCXbmdfYDh9/bw+oq+NKPSaBm9d6kPA19hA5Lg==}
+
   '@opentelemetry/api@1.9.1':
     resolution: {integrity: sha512-gLyJlPHPZYdAk1JENA9LeHejZe1Ti77/pTeFm/nMXmQH/HFZlcS/O2XJB+L8fkbrNSqhdtlvjBVjxwUYanNH5Q==}
     engines: {node: '>=8.0.0'}
@@ -4702,6 +4708,10 @@ snapshots:
 
   '@open-draft/until@2.1.0': {}
 
+  '@opencode-ai/sdk@1.15.12':
+    dependencies:
+      cross-spawn: 7.0.6
+
   '@opentelemetry/api@1.9.1': {}
 
   '@pinojs/redact@0.4.0': {}