Merge contracts-ssot-pkg: v2.7.13 single-source cross-app wire contracts in @boocode/contracts

Move all hand-synced cross-app wire contracts into one built workspace
package, @boocode/contracts, consumed by server/web/coder/coder-web via
workspace:* + a per-subpath exports map. The ws-frames and provider-config
Zod schemas are schema-first (z.infer); MessageMetadata, ErrorReason,
AgentSessionConfig, the provider snapshot types, and WorktreeRiskReport are
each single-sourced. Deletes the byte-identical copies and their parity
tests, fixes a live AgentSessionConfig drift (coder dead copy removed,
unified to the web required/nullable shape), removes the dead pending_change
WS arms in the fallback SPA, and inverts the build order (contracts builds
first) across root build, Dockerfile, and the coder deploy docs. Reverses
the shared-package decision declined in v2.5.12.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

BOOCHAT.md

@@ -28,6 +28,11 @@
 - Prefer codecontext (`search_symbols`, `get_symbol_info`, `get_dependencies`) over `grep` for symbol-level questions. Fall back to `grep` / `view_file` when codecontext returns degraded or empty results — that signals an unsupported language or parse failure.
 - Verify before reporting work complete: run the relevant test/build/smoke command and confirm output matches the claim. Evidence first, assertion second.
 
+## Recovery and context (v2.7)
+
+- **Heed the recovery nudge.** Native inference tracks consecutive tool **failures** (`mistake-tracker.ts`): after 3 in a row with no successful step between, a `mistake_recovery` sentinel is injected telling you to re-read tool schemas, verify a path exists before acting, and try a *different* approach — not retry variations of the same failing call. Ignoring it (a second failure run with the nudge still outstanding) **escalates and stops the turn** to protect the step budget. This complements the doom-loop guard, which only catches *identical* repeats.
+- **Files-read provenance survives compaction.** Paths you read via `view_file` / `grep` / `find_files` / `list_dir` are accumulated and merged into a cumulative `## Files Read` ledger in the rolling summary, so a file read long ago stays in context across compactions. You don't manage this — but it means you usually don't need to re-read a file just because the raw turn scrolled out of the window.
+
 ## Output format
 
 - Stay in Markdown by default for every reply, short or long.

BOOCODER.md

@@ -23,6 +23,8 @@ You are BooCoder, a write-capable coding agent. You can read AND modify files wi
 
 Every file modification queues in `pending_changes` before touching disk. The user sees a diff preview and approves/rejects each change. Never bypass this queue — it is the safety boundary between inference and the filesystem.
 
+`edit_file`'s `old_string` match is **fuzzy** (`fuzzy-match.ts`, v2.7.1): an exact → per-line-whitespace → unicode-canonicalization (curly quotes/dashes/nbsp) → Levenshtein-≥0.66 ladder, so minor whitespace/indentation/unicode drift in `old_string` still lands on the right span. Two consequences: a near-miss `old_string` may still apply (verify the queued diff is what you intended), and an `old_string` matching **more than one** place is rejected as **ambiguous** rather than editing the first — add surrounding context to disambiguate. A genuine non-match returns a clear failure, not a thrown error.
+
 ## Behavior
 
 - Show diffs clearly. Explain what you're changing and why.
@@ -102,7 +104,7 @@ Either way, **adding to config does NOT install the binary.** Until the CLI is o
 ### Deploy + smoke
 
 Two deploy targets:
-- **Routes (host service):** `pnpm -C apps/server build && pnpm -C apps/coder build && sudo systemctl restart boocoder`
+- **Routes (host service):** `pnpm -C packages/contracts build && pnpm -C apps/server build && pnpm -C apps/coder build && sudo systemctl restart boocoder`
 - **Web UI (container):** `docker compose up --build -d boocode`
 
 Green gate (verified across phases 1–5): `pnpm -C apps/coder test` (134 passing) `&& pnpm -C apps/coder build`.
@@ -115,3 +117,35 @@ curl http://100.114.205.53:9500/api/coder/providers/config   # raw config, throu
 # Settings → Providers: disable goose → it leaves the composer picker, stays in the tab
 # POST refresh → models repopulate; Add a catalog entry → it appears after refresh (unavailable until its CLI is installed)
 ```
+
+## Persistent agent sessions (v2.6)
+
+When you `dispatch_external_agent` to a chat-tab provider, BooCoder keeps that agent **warm and resumable** instead of spawning a fresh process per turn. This is mostly transparent — but the model below explains why turn 2 is fast, why an external agent remembers earlier turns, and how edits flow.
+
+### Backends and keying
+
+- One live backend per **`(chat_id, agent)`** pair, owned by the `agent-pool` (`agent-pool.ts`). State lives in `agent_sessions` (the resumable session id) and `worktrees` (the per-chat working copy).
+- **opencode** runs a long-lived `opencode serve` (`backends/opencode-server.ts`) with per-session SSE; turns after the first reuse the same session (memory intact, ~9× faster).
+- **goose / qwen** run a warm ACP connection (`backends/warm-acp.ts`) — `initialize` + `session/new` once per `(chat,agent)`, then `session/prompt` per turn. Interrupt cancels the prompt (`session/cancel`), never the child.
+- **claude** runs the Claude Agent SDK backend (`backends/claude-sdk.ts`) over a clean-room Postgres session store.
+- Arena, MCP `new_task`, and one-shot dispatches still use the cold `runExternalAgent` path — warm reuse needs both a `session_id` and a `chat_id`.
+
+### Worktrees
+
+- External agents write **directly into a persistent per-chat worktree** (`/tmp/booworktrees/sess-<id>`), not into the project root via `pending_changes`. The worktree is created once, base commit captured, and **reused across turns and across agents in the same chat** — so opencode and goose in one chat share one worktree.
+- Each turn's worktree diff supersedes the prior `pending_changes` row for that `(chat,agent)` (latest-wins) and is badged with the authoring agent in the DiffPanel.
+- **Staging boundary:** a provider only sees another agent's edits once they are **applied**. Unapplied worktree edits from a different agent are invisible to you — the DiffPanel shows a muted hint when that's the case.
+
+### Lifecycle (v2.6.10–v2.6.11)
+
+- **Idle eviction:** a backend idle past `AGENT_POOL_IDLE_TTL_MS` (default 30 min) is disposed; an LRU cap of `AGENT_POOL_MAX_LIVE` (default 10) bounds live backends. A busy backend is never evicted, and the next turn transparently re-attaches or re-creates from `agent_sessions`/`worktrees`.
+- **Crash recovery:** a health monitor restarts a crashed server (opencode → fresh sessions; ACP → re-`session/new`) and reclaims its port.
+- **Close cleanup:** closing/deleting a chat or session evicts its backends, archives the `worktrees` row, and removes the worktree. An hourly reaper sweeps orphaned worktrees (dirty/unpushed preflight before removal).
+
+### Checkpoints (v2.7.1)
+
+Because external agents write the worktree directly (outside `pending_changes`), a worktree **checkpoint** is shadow-committed before each external-agent turn (tracked + untracked, into `refs/boocode/checkpoints/<id>`), anchored to that turn's assistant message. The per-message **"Restore to here"** affordance resets the worktree (`reset --hard` + `clean -fd`), trims the transcript past that message, and resets the `(chat,agent)` backend session — so files, transcript, and agent context land consistent at the restore point. `rewind` still only reverses BooCoder's own applied `pending_changes`; checkpoints are what cover external-agent worktree edits.
+
+### Normalized status (v2.6 / v2.7.6)
+
+Turn boundaries publish a normalized per-`(chat,agent)` status — `working | blocked | idle | error` — to the UI (`agent_status_updated` frame), so blocked-on-permission and crash/idle are visible, not just WS liveness.

CHANGELOG.md

@@ -2,9 +2,9 @@
 
 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.
 
-## v2.7.12-audit-cleanup — 2026-06-02
+## v2.7.13-contracts-ssot — 2026-06-02
 
-A repo-wide audit and aggressive cleanup pass, run as a multi-agent orchestration (five read-only Opus auditors over server/web/coder/booterm + cross-cutting deps/build/parity + a structural-architecture lens) followed by phased, behavior-preserving implementation — every change gated on the per-app test suites and delivered behind a strict DEFER discipline that never touched the files in flight for `v2.7.9`–`v2.7.11` (`mcp-config`, the `ws-frames` pair, `dispatcher`, `claude-sdk-map`, `AgentComposerBar`/`CoderMessageList`/`CoderPane`), so the branch rebased onto current main with zero conflicts. **Dead code/deps/schema**: removed ~9 dead files and a swathe of dead exports/write-only state across all four apps, dropped dead deps (`next-themes`, `@xterm/addon-webgl`, booterm `tslib`; `shadcn`→devDep), and idempotently dropped dead schema columns/tables (`sessions.tags`, `tasks.worktree_path`/`feature_values`, `available_agents.supports_mcp_client`, the superseded `session_worktrees` table, the always-empty `list_worktrees` MCP tool) — chat/session/message DATA untouched, only never-read columns. **Server dedup + reshapes**: collapsed the dead `budget.ts` tier system (surfacing a latent `READ_ONLY_TOOL_NAMES` drift, then deleted), extracted shared `MESSAGE_COLUMNS`/`selectProject`/`stripQuotes`/`SENTINEL_KINDS`/`samplerOptsFromAgent`/`createContentFlusher`/`insertSentinel`/a `makeCodecontextTool` factory/a pending-tool-call resolver, split `tools.ts` (799→46 barrel + `tools/{types,fs-tools,misc-tools,registry,tiers}`, register-through registry preserved so coder's import contract stays byte-stable), and decomposed the inference pipeline (`sentinel-summaries`→`runWrapUpSummary`, `turn.ts`→`turn-config`+`step-decision`, a pure `stream-phase-adapter`, shared finalize atoms — stopping short of fusing synthesis to preserve frame timing). **Coder reshapes**: split the 1062-line `opencode-server.ts` god-class into supervisor / sse-loop / pure event-map / port-utils + extracted `buildAcpClient`/`makeFrameEmitter`/`worktree-risk`, plus happy-path-safe concurrency hardening (reconnect backoff, double-spawn guard; a defensive busy-assert + ensureSession coalescing flagged for review). **Web**: `React.memo` on `MessageBubble`/`MarkdownRenderer` + module-hoisted markdown components (the streaming re-parse was the biggest perf cost), shared `linkifyPaths`/artifact/tab dedup, two latent bug fixes (`ChatPane` index-keys → stable ids; `FileViewerOverlay` blank-line line-number desync), and decomposed the 1298-line `TerminalPane.tsx` into fit/socket/selection hooks + presentational pieces (verbatim move, all ~30 listeners/timers inventoried; the label-dep fix stops a live terminal tearing down on pane renumber). +78 parity/unit tests (server 597, coder 328 green; `apps/web` has no harness, so its changes are typecheck + manual/device QA). Net ≈ −4,600 LOC. Deferred (designed; blueprints in the audit reports): the `tasks` dual-CREATE / `project_id` FK (a cross-service deploy-ordering decision, not a data migration), web structural decomposition of `useWorkspacePanes`/`MessageBubble` (needs a web test harness first), a `@boocode/contracts` shared package, and the `dispatcher.ts` split — the last two now unblocked since their in-flight files shipped in `v2.7.9`–`v2.7.11`. Rebased clean onto `v2.7.11-coder-model-snapshot`.
+Creates `@boocode/contracts` (`packages/contracts`), a new workspace package that becomes the single source of truth for every cross-app wire contract — reversing the decision recorded in `v2.5.12-provider-lifecycle-phase4` that declined a shared types package as not worth the Docker/build-order risk at solo scale; a live `AgentSessionConfig` drift that had since appeared between `apps/coder` and `apps/web` justified the investment. Six contracts are now defined exactly once: the `WsFrameSchema` Zod runtime schema, the provider snapshot types (`ProviderSnapshotEntry` and family), the Zod provider-config schemas, `MessageMetadata` + `ErrorReason`, `AgentSessionConfig`, and `WorktreeRiskReport`; both Zod-backed contracts use `z.infer` so validator and type derive from the same definition and cannot drift independently. All four consumers — `apps/server`, `apps/web`, `apps/coder`, and the fallback SPA `apps/coder/web` — import via `workspace:*` through a per-subpath exports map consuming built dist only (no tsconfig project references); the hand-synced copies and their parity tests (`provider-types-parity.test.ts`; the ws-frames byte-parity assertion) are deleted while the KNOWN_FRAME_TYPES drift test and broker fail-closed tests are preserved. Build order is inverted in the root build script, Dockerfile, and coder deploy docs; `apps/coder/web`'s migration also removed dead `pending_change_*` reducer arms (no frame publisher exists for these — pending changes are HTTP-delivered), closing a latent missing-default-arm crash, and reconciled field-type conflicts with the canonical `WsFrame`; zod is pinned to a single version across the workspace. Server 543 / coder 293 / contracts 11 tests passing; human smoke verified on the live stack 2026-06-02.
 
 ## v2.7.11-coder-model-snapshot — 2026-06-02
 

CLAUDE.md

@@ -73,7 +73,7 @@ Schema CHECK migration order when renaming allowed values: (1) `ALTER TABLE ...
 
 Required: `DATABASE_URL`, `LLAMA_SWAP_URL`. Optional: `PORT` (3000), `HOST` (0.0.0.0), `PROJECT_ROOT_WHITELIST` (/opt, read-only add-existing scope), `BOOTSTRAP_ROOT` (/opt/projects, writable bootstrap mkdir target — host must `mkdir -p` it before container start), `DEFAULT_MODEL`, `LOG_LEVEL`, `SEARXNG_URL` (default `http://100.114.205.53:8888` — internal Tailscale; the public host is behind Authelia, unusable from server context), `BOOCODE_TOOLS` (`core`|`standard`|`all`, default `all`; a ceiling, never expands an agent's whitelist), `MCP_CONFIG_PATH` (default `/data/mcp.json`, opencode `mcpServers` shape; missing = no MCP), `CONTEXT7_API_KEY` (the Context7 MCP key, referenced from `data/mcp.json` as `"{env:CONTEXT7_API_KEY}"`). `data/mcp.json` is **gitignored** but no longer holds secrets — string values support opencode-style `{env:VAR}` substitution (`mcp-config.ts:substituteEnvVars`, applied before Zod validation; unset var → `''` + warn), so real keys live in `.env`; template `data/mcp.example.json`. A config-only edit there needs only `docker compose restart boocode` (data/ is bind-mounted); changing a referenced secret edits `.env`. MCP loads at server startup with per-server graceful degradation; the coder does NOT load MCP (BooChat only).
 
-BooCoder at port 9502: `curl http://100.114.205.53:9502/api/health`. Runs as `boocoder.service` on the host (not Docker). Deploy: `pnpm -C apps/server build && pnpm -C apps/coder build && sudo systemctl restart boocoder`. Health reports tool count: `{"ok":true,"db":true,"tools":33}`.
+BooCoder at port 9502: `curl http://100.114.205.53:9502/api/health`. Runs as `boocoder.service` on the host (not Docker). Deploy: `pnpm -C packages/contracts build && pnpm -C apps/server build && pnpm -C apps/coder build && sudo systemctl restart boocoder`. Health reports tool count: `{"ok":true,"db":true,"tools":33}`.
 
 - `FAST_MODEL` (optional) — cheaper model for titles, summaries, labeling (auto_name.ts, tool-summaries.ts). Falls back to session model or DEFAULT_MODEL. Set to a small llama-swap model (e.g. `nemotron-nano-4b`) to avoid loading the 35B for 20-token calls.
 - Qwen Code dispatch: `OPENAI_BASE_URL=http://100.101.41.16:8401/v1 OPENAI_API_KEY=dummy qwen -p "<task>" --output-format stream-json`. Install: `npm install -g @qwen-code/qwen-code@latest`. Node ≥22 on host (container stays Node 20; BooCoder dispatches via direct spawn on host). No `--yolo` flag — `-p` runs autonomously without prompts. ACP bridge is an HTTP daemon (not stdio); use PTY dispatch.
@@ -113,9 +113,9 @@ Cross-cutting only. Per-app conventions live in the matching `apps/*/CLAUDE.md`.
 - No app-layer auth. Authelia handles auth at the reverse proxy. All `broker.publishUser`/`subscribeUser` calls use `'default'` as the user key.
 - TypeScript strict mode. Both apps share `tsconfig.base.json`. Server + coder use NodeNext module resolution (`.js` extensions in imports).
 - Discriminated unions for type narrowing: `Pane` (by `kind`), `SessionEvent` (by `type`), `InferenceFrame` (by `type`).
-- **Adding a new WS frame type** (cross-app) 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 — missing the web side silently drops the frame at JSON-parse.
+- **Adding a new WS frame type** (cross-app): add it to `WsFrameSchema` in `packages/contracts/src/ws-frames.ts` (single source of truth; rebuild with `pnpm -C packages/contracts build`). The server's `InferenceFrame` loose union (`services/inference/turn.ts`) and the web's strict `WsFrame` discriminated union (`apps/web/src/api/types.ts`) still exist separately and also need updating. Server publish is permissive; the frontend type is the wire-format gate — missing the web side silently drops the frame at JSON-parse.
-- **Sentinels** (cross-app) 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`.
+- **Sentinels** (cross-app) 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. `MessageMetadata` is single-sourced in `@boocode/contracts` (`packages/contracts/src/message-metadata.ts`). A new kind requires updating that file and rebuilding the package, plus a render branch in `apps/web/src/components/MessageBubble.tsx`.
-- **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.
+- **Provider snapshot types** (`ProviderSnapshotEntry`, `ProviderModel`, `ProviderMode`, `ThinkingOption`, `AgentCommand`, `ProviderSnapshotStatus`) are single-sourced in `@boocode/contracts` (`packages/contracts/src/provider-snapshot.ts`); `apps/coder/src/services/provider-types.ts` re-exports them. Edit the package source; there is no hand-synced web copy to update.
 - **JSONB columns**: use `sql.json(value as never)` — NOT `${JSON.stringify(value)}::jsonb` which double-serializes (stores a JSON string instead of an object/array). Pattern in `parts.ts`, `settings.ts`.
 - Skills live in `data/skills/<vendor>/`; Sam's own namespace is `boocode/` (`committing-changes`, `using-worktrees`, `improving-boocode-guidance`, `systematic-debugging`) — `SKILL.md` + optional `eval.yaml` (gerund names; eval = `skill:` + `tasks:` of `prompt`+`grader`, incl. a negative-trigger task). `data/skills/` is canonical; a divergent mirror at `/opt/skills/` exists.
 

CURRENT.md

@@ -1,9 +1,10 @@
 # Current focus
 
-Last updated: 2026-06-02
+Last updated: 2026-05-26
 
-- **Last shipped:** `v2.7.8-ember-coder-tabs-model-chips` (2026-06-01)
+- **Batch:** v2.3-provider-lifecycle (openspec drafted; not started)
-- **Branch:** `codebase-audit-cleanup` (audit + cleanup epic, off main HEAD)
+- **Branch:** `main`
-- **In progress:** Phase 3 — stale comments + docs refresh
+- **Blockers:** none
+- **Last shipped:** `v2.2.2-xml-placeholder-reject`
 
-See `CHANGELOG.md` for the full shipped history. That file is always authoritative; this file is a quick orientation pointer only.
+Update this file when starting or finishing a batch. Agents: read this first for session intent; if stale vs `CHANGELOG.md`, trust CHANGELOG for shipped state.

Dockerfile

@@ -5,11 +5,15 @@ RUN corepack enable
 WORKDIR /build
 
 COPY package.json pnpm-workspace.yaml pnpm-lock.yaml tsconfig.base.json ./
+COPY packages/contracts/package.json ./packages/contracts/
 COPY apps/server/package.json ./apps/server/
 COPY apps/web/package.json ./apps/web/
 
 RUN pnpm install --frozen-lockfile
 
+# @boocode/contracts must be present before `pnpm build`, which builds it FIRST
+# (root build script) so apps/web can resolve its compiled dist via the exports map.
+COPY packages/contracts ./packages/contracts
 COPY apps/server ./apps/server
 COPY apps/web ./apps/web
 

README.md

@@ -58,7 +58,7 @@ upstream and inject `Remote-User`. Postgres binds loopback only.
 BooCoder runs as a **host systemd service** (`boocoder.service`, port `:9502`), not in Docker:
 
 ```bash
-pnpm -C apps/server build && pnpm -C apps/coder build
+pnpm -C packages/contracts build && pnpm -C apps/server build && pnpm -C apps/coder build
 sudo systemctl restart boocoder
 curl http://100.114.205.53:9502/api/health
 ```

apps/booterm/package.json

@@ -15,6 +15,7 @@
     "fastify": "^4.28.1",
     "node-pty": "^1.0.0",
     "pg": "^8.13.0",
+    "tslib": "^2.6.3",
     "zod": "^3.23.8"
   },
   "devDependencies": {

apps/booterm/src/config.ts

@@ -9,7 +9,7 @@ const ConfigSchema = z.object({
   TMUX_CONF_PATH: z.string().default('/etc/booterm/tmux.conf'),
 });
 
-type Config = z.infer<typeof ConfigSchema>;
+export type Config = z.infer<typeof ConfigSchema>;
 
 let cached: Config | null = null;
 

apps/booterm/src/db.ts

@@ -10,7 +10,7 @@ export function getPool(databaseUrl: string): pg.Pool {
   return pool;
 }
 
-interface SessionInfo {
+export interface SessionInfo {
   id: string;
   project_id: string;
   project_path: string;

apps/booterm/src/pty/pty.ts

@@ -1,7 +1,7 @@
 import * as pty from 'node-pty';
 import type { IPty } from 'node-pty';
 
-interface AttachPtyOptions {
+export interface AttachPtyOptions {
   sessionName: string;
   projectRoot: string;
   cols: number;

apps/coder/CLAUDE.md

@@ -13,7 +13,7 @@
 ## Build, deploy, dispatch
 
 - **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`.
+- Build + deploy: `pnpm -C packages/contracts build && 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 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 shape). Restart, don't re-debug.
 - `:9502/api/health` is down ~15–20s after a boocoder restart while the startup agent-probe scan runs — retry; an early connection-refused is not a failed deploy.
 - Agent dispatch spawns binaries directly using `install_path` from `available_agents` — no `spawn('sh', ['-c', ...])` (fails under systemd). Paseo's pattern: `spawn(fullBinaryPath, argsArray, { cwd })`.

apps/coder/package.json

@@ -13,6 +13,7 @@
     "test": "vitest run"
   },
   "dependencies": {
+    "@boocode/contracts": "workspace:*",
     "@agentclientprotocol/sdk": "^0.22.1",
     "@anthropic-ai/claude-agent-sdk": "^0.3.159",
     "@boocode/server": "workspace:*",

apps/coder/src/index.ts

@@ -16,7 +16,7 @@ import { createInferenceRunner } from '@boocode/server/inference';
 import { createBroker } from '@boocode/server/broker';
 import { appendMcpTools, ALL_TOOLS } from '@boocode/server/tools';
 import type { Config as ServerConfig } from '@boocode/server/config';
-import type { WsFrame } from '@boocode/server/ws-frames';
+import type { WsFrame } from '@boocode/contracts/ws-frames';
 // v2.0.0 Phase 2C: write tools + adapter for BooChat ToolDef compatibility.
 import { WRITE_TOOLS } from './services/tools/index.js';
 import { adaptWriteTool } from './services/tools/adapter.js';

apps/coder/src/routes/messages.ts

@@ -2,7 +2,7 @@ import type { FastifyInstance } from 'fastify';
 import { z } from 'zod';
 import type { Sql } from '../db.js';
 import type { Broker } from '@boocode/server/broker';
-import type { WsFrame } from '@boocode/server/ws-frames';
+import type { WsFrame } from '@boocode/contracts/ws-frames';
 import { resolveChatId } from './chat-resolve.js';
 
 const AnswerUserInputBody = z.object({

apps/coder/src/routes/skills.ts

@@ -2,7 +2,7 @@ import type { FastifyInstance } from 'fastify';
 import { z } from 'zod';
 import type { Sql } from '../db.js';
 import type { Broker } from '@boocode/server/broker';
-import type { WsFrame } from '@boocode/server/ws-frames';
+import type { WsFrame } from '@boocode/contracts/ws-frames';
 import { getSkillBody } from '@boocode/server/skills';
 import {
   buildSkillInvokeSyntheticFrames,

apps/coder/src/routes/tasks.ts

@@ -95,7 +95,7 @@ export function registerTaskRoutes(app: FastifyInstance, sql: Sql, inference: In
   // GET /api/tasks/:id — single task detail
   app.get<{ Params: { id: string } }>('/api/tasks/:id', async (req, reply) => {
     const rows = await sql`
-      SELECT id, project_id, parent_task_id, state, input, output_summary, agent, model, execution_path, session_id, cost_tokens, started_at, ended_at, created_at
+      SELECT id, project_id, parent_task_id, state, input, output_summary, agent, model, execution_path, worktree_path, session_id, cost_tokens, started_at, ended_at, created_at
       FROM tasks
       WHERE id = ${req.params.id}
     `;

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

@@ -9,7 +9,7 @@
  */
 import type { FastifyInstance } from 'fastify';
 import type { Sql } from '../db.js';
-import { checkWorktreeWorkAtRisk, stashWorktree } from '../services/worktree-risk.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

apps/coder/src/schema.sql

@@ -25,6 +25,7 @@ CREATE TABLE IF NOT EXISTS tasks (
   agent TEXT,
   model TEXT,
   execution_path TEXT,
+  worktree_path TEXT,
   cost_tokens INTEGER,
   started_at TIMESTAMPTZ,
   ended_at TIMESTAMPTZ,
@@ -38,9 +39,9 @@ CREATE TABLE IF NOT EXISTS available_agents (
   install_path TEXT,
   version TEXT,
   supports_acp BOOLEAN NOT NULL DEFAULT false,
+  supports_mcp_client BOOLEAN NOT NULL DEFAULT false,
   last_probed_at TIMESTAMPTZ
 );
-ALTER TABLE available_agents DROP COLUMN IF EXISTS supports_mcp_client;
 
 -- v2.0.0 Phase 4: link tasks to their inference sessions.
 ALTER TABLE tasks ADD COLUMN IF NOT EXISTS session_id UUID REFERENCES sessions(id);
@@ -73,10 +74,31 @@ ALTER TABLE available_agents ADD COLUMN IF NOT EXISTS commands JSONB DEFAULT '[]
 -- v2.2.0: Paseo-style session config on tasks.
 ALTER TABLE tasks ADD COLUMN IF NOT EXISTS mode_id TEXT;
 ALTER TABLE tasks ADD COLUMN IF NOT EXISTS thinking_option_id TEXT;
--- tasks.feature_values and tasks.worktree_path were never read or written by any
+ALTER TABLE tasks ADD COLUMN IF NOT EXISTS feature_values JSONB;
--- code path; drop them from existing DBs (fresh DBs never had them in the CREATE).
+
-ALTER TABLE tasks DROP COLUMN IF EXISTS feature_values;
+-- v2.6: one shared worktree per session (all agents/panes in the session operate in it).
-ALTER TABLE tasks DROP COLUMN IF EXISTS worktree_path;
+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()
+);
+-- P1.5-b: DEFANG the CASCADE — a session delete must no longer wipe its worktree
+-- row. This table is SUPERSEDED by `worktrees` below; all readers are repointed
+-- this phase, so the row just persists (dead) on session delete until a later
+-- cleanup drops the table. session_id is this table's PRIMARY KEY, so it cannot be
+-- nullable → SET NULL is invalid and NO ACTION/RESTRICT would block deletes; the
+-- only valid defang is to drop the FK with no replacement. Idempotent: only fires
+-- while the FK is still ON DELETE CASCADE ('c').
+DO $$ BEGIN
+  IF EXISTS (
+    SELECT 1 FROM pg_constraint
+    WHERE conname = 'session_worktrees_session_id_fkey'
+      AND confdeltype = 'c'
+  ) THEN
+    ALTER TABLE session_worktrees DROP CONSTRAINT session_worktrees_session_id_fkey;
+  END IF;
+END $$;
 
 -- v2.6: one backend session per (session, agent); resumed on switch-back.
 CREATE TABLE IF NOT EXISTS agent_sessions (
@@ -146,9 +168,12 @@ CREATE TABLE IF NOT EXISTS worktrees (
 );
 CREATE UNIQUE INDEX IF NOT EXISTS worktrees_active_path_uidx ON worktrees(path) WHERE status='active';
 
--- session_worktrees was superseded by worktrees (v2.6/P1.5-b); all rows migrated
+-- Migrate any surviving session_worktrees rows → worktrees (idempotent; 0 rows
--- before P2 cleanup. Drop the dead table; no-op on fresh DBs that never had it.
+-- after the test-session delete, kept for generality / fresh-DB safety).
-DROP TABLE IF EXISTS session_worktrees;
+INSERT INTO worktrees (session_id, path, branch, base_commit, status)
+SELECT sw.session_id, sw.worktree_path, 'session-' || sw.session_id, sw.base_commit, 'active'
+FROM session_worktrees sw
+WHERE NOT EXISTS (SELECT 1 FROM worktrees w WHERE w.session_id = sw.session_id AND w.status='active');
 
 -- Dispatch hint: which chat (tab) a task belongs to. The coder message route and
 -- skills route set it from the frontend tab; session-less creators (arena, MCP,

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

@@ -1,74 +0,0 @@
-import { describe, it, expect, vi } from 'vitest';
-import type { RequestPermissionRequest, CreateElicitationRequest, SessionNotification } from '@agentclientprotocol/sdk';
-import { buildAcpClient, type AcpTurnContext } from '../acp-client.js';
-
-/**
- * buildAcpClient (v2.7 audit reshape): the shared ACP `Client` closures. These
- * tests cover the pure routing decisions that don't require the permission-waiter
- * broker machinery — the auto-select/decline fallbacks and the between-turns drop.
- */
-
-describe('buildAcpClient — sessionUpdate', () => {
-  it('drops the update when no turn is active (resolveTurn → null)', async () => {
-    const client = buildAcpClient('/wt', () => null);
-    // Must resolve without throwing and without an onSessionUpdate to call.
-    await expect(client.sessionUpdate({ sessionId: 's', update: {} } as unknown as SessionNotification)).resolves.toBeUndefined();
-  });
-
-  it('forwards the update to the active turn', async () => {
-    const onSessionUpdate = vi.fn();
-    const turn: AcpTurnContext = { taskId: 't', sessionId: 's', modeId: undefined, agent: 'goose', onSessionUpdate };
-    const client = buildAcpClient('/wt', () => turn);
-    const note = { sessionId: 's', update: {} } as unknown as SessionNotification;
-    await client.sessionUpdate(note);
-    expect(onSessionUpdate).toHaveBeenCalledWith(note);
-  });
-});
-
-describe('buildAcpClient — requestPermission fallback (no UI routing)', () => {
-  function req(options: Array<{ optionId: string }>): RequestPermissionRequest {
-    return { options } as unknown as RequestPermissionRequest;
-  }
-
-  it('auto-selects the first option when there is no turn', async () => {
-    const client = buildAcpClient('/wt', () => null);
-    const res = await client.requestPermission(req([{ optionId: 'allow' }, { optionId: 'deny' }]));
-    expect(res).toEqual({ outcome: { outcome: 'selected', optionId: 'allow' } });
-  });
-
-  it('cancels when there is no turn and no options', async () => {
-    const client = buildAcpClient('/wt', () => null);
-    const res = await client.requestPermission(req([]));
-    expect(res).toEqual({ outcome: { outcome: 'cancelled' } });
-  });
-
-  it('auto-selects when the turn has no taskId (UI routing gated off)', async () => {
-    const turn: AcpTurnContext = { taskId: undefined, sessionId: 's', modeId: undefined, agent: 'goose', onSessionUpdate: () => {} };
-    const client = buildAcpClient('/wt', () => turn);
-    const res = await client.requestPermission(req([{ optionId: 'ok' }]));
-    expect(res).toEqual({ outcome: { outcome: 'selected', optionId: 'ok' } });
-  });
-});
-
-describe('buildAcpClient — elicitation fallback', () => {
-  it('declines when there is no turn', async () => {
-    const client = buildAcpClient('/wt', () => null);
-    const res = await client.unstable_createElicitation!({} as CreateElicitationRequest);
-    expect(res).toEqual({ action: 'decline' });
-  });
-
-  it('declines when the turn has no taskId', async () => {
-    const turn: AcpTurnContext = { taskId: undefined, sessionId: 's', modeId: undefined, agent: 'goose', onSessionUpdate: () => {} };
-    const client = buildAcpClient('/wt', () => turn);
-    const res = await client.unstable_createElicitation!({} as CreateElicitationRequest);
-    expect(res).toEqual({ action: 'decline' });
-  });
-});
-
-describe('buildAcpClient — createTerminal', () => {
-  it('returns the noop terminal id', async () => {
-    const client = buildAcpClient('/wt', () => null);
-    const res = await client.createTerminal!({} as never);
-    expect(res).toEqual({ terminalId: 'noop' });
-  });
-});

apps/coder/src/services/__tests__/frame-emitter.test.ts

@@ -1,102 +0,0 @@
-import { describe, it, expect } from 'vitest';
-import type { Broker } from '@boocode/server/broker';
-import { makeFrameEmitter } from '../frame-emitter.js';
-import { makeDcpStreamStripper } from '../dcp-strip.js';
-import type { AcpToolSnapshot } from '../acp-tool-snapshot.js';
-
-/**
- * makeFrameEmitter (v2.7 audit reshape): the AgentEvent → WS-frame mapping + turn
- * accumulators extracted from AcpStreamContext. Pure-ish over an injected broker.
- */
-
-function fakeBroker(): { broker: Broker; frames: Array<{ sid: string; frame: Record<string, unknown> }> } {
-  const frames: Array<{ sid: string; frame: Record<string, unknown> }> = [];
-  const broker = {
-    publishFrame: (sid: string, frame: unknown) => {
-      frames.push({ sid, frame: frame as Record<string, unknown> });
-    },
-  } as unknown as Broker;
-  return { broker, frames };
-}
-
-const toolSnap: AcpToolSnapshot = { toolCallId: 'c1', title: 'grep', status: 'completed', rawOutput: 'x' };
-
-describe('makeFrameEmitter — streaming frames', () => {
-  it('maps text/reasoning/tool events to delta/reasoning_delta/tool_call frames', () => {
-    const { broker, frames } = fakeBroker();
-    const em = makeFrameEmitter({ broker, sessionId: 's1', chatId: 'ch1', assistantId: 'm1' });
-
-    em.onEvent({ type: 'text', text: 'hello ' });
-    em.onEvent({ type: 'reasoning', text: 'mulling' });
-    em.onEvent({ type: 'tool_call', toolCall: toolSnap });
-
-    expect(frames.map((f) => f.frame.type)).toEqual(['delta', 'reasoning_delta', 'tool_call']);
-    expect(frames[0]!.frame).toMatchObject({ message_id: 'm1', chat_id: 'ch1', content: 'hello ' });
-    expect(frames[2]!.frame).toMatchObject({ message_id: 'm1', chat_id: 'ch1' });
-    expect(em.output).toBe('hello ');
-    expect(em.reasoningText).toBe('mulling');
-    expect(em.snapshots).toHaveLength(1);
-  });
-
-  it('publishes a tool_call frame for BOTH tool_call and tool_update events', () => {
-    const { broker, frames } = fakeBroker();
-    const em = makeFrameEmitter({ broker, sessionId: 's1', chatId: 'ch1', assistantId: 'm1' });
-    em.onEvent({ type: 'tool_update', toolCall: toolSnap });
-    expect(frames).toHaveLength(1);
-    expect(frames[0]!.frame.type).toBe('tool_call');
-  });
-
-  it('publishes an agent_commands frame and merges the command cache', () => {
-    const { broker, frames } = fakeBroker();
-    const taskId = `task-fe-${Math.floor(performance.now())}-${frames.length}`;
-    const em = makeFrameEmitter({ broker, sessionId: 's1', chatId: 'ch1', assistantId: 'm1', taskId });
-    em.onEvent({ type: 'commands', commands: [{ name: 'plan' }] });
-    expect(frames).toHaveLength(1);
-    expect(frames[0]!.frame).toMatchObject({ type: 'agent_commands', task_id: taskId, session_id: 's1' });
-  });
-
-  it('does not publish a commands frame without a taskId', () => {
-    const { broker, frames } = fakeBroker();
-    const em = makeFrameEmitter({ broker, sessionId: 's1', chatId: 'ch1', assistantId: 'm1' });
-    em.onEvent({ type: 'commands', commands: [{ name: 'plan' }] });
-    expect(frames).toHaveLength(0);
-  });
-});
-
-describe('makeFrameEmitter — no broker (one-shot accumulation)', () => {
-  it('accumulates output/reasoning/snapshots but publishes nothing', () => {
-    const em = makeFrameEmitter({ sessionId: 's1', chatId: 'ch1', assistantId: 'm1' });
-    em.onEvent({ type: 'text', text: 'abc' });
-    em.onEvent({ type: 'reasoning', text: 'r' });
-    em.onEvent({ type: 'tool_call', toolCall: toolSnap });
-    expect(em.output).toBe('abc');
-    expect(em.reasoningText).toBe('r');
-    expect(em.snapshots).toHaveLength(1);
-  });
-});
-
-describe('makeFrameEmitter — dcp stripping (opencode path contract)', () => {
-  it('strips a split dcp tag across deltas and flushes the tail on finalize', () => {
-    const { broker, frames } = fakeBroker();
-    const em = makeFrameEmitter({ broker, sessionId: 's1', chatId: 'ch1', assistantId: 'm1', dcp: makeDcpStreamStripper() });
-
-    for (const chunk of ['Answer.', '<dcp', '-message', '-id>m1</dcp', '-message-id>', ' tail']) {
-      em.onEvent({ type: 'text', text: chunk });
-    }
-    em.finalize();
-
-    expect(em.output).toBe('Answer. tail');
-    const published = frames.filter((f) => f.frame.type === 'delta').map((f) => f.frame.content).join('');
-    expect(published).toBe('Answer. tail');
-  });
-
-  it('finalize is a no-op without a dcp stripper', () => {
-    const { broker, frames } = fakeBroker();
-    const em = makeFrameEmitter({ broker, sessionId: 's1', chatId: 'ch1', assistantId: 'm1' });
-    em.onEvent({ type: 'text', text: 'raw <dcp-message-id>m</dcp-message-id>' });
-    em.finalize();
-    // No stripping without a stripper — verbatim text (prior ACP-path behavior).
-    expect(em.output).toBe('raw <dcp-message-id>m</dcp-message-id>');
-    expect(frames).toHaveLength(1);
-  });
-});

apps/coder/src/services/__tests__/normalize-agent-status.test.ts

@@ -0,0 +1,83 @@
+import { describe, it, expect } from 'vitest';
+import { normalizeAgentEvent } from '../normalize-agent-status.js';
+
+describe('normalizeAgentEvent', () => {
+  describe('working bucket', () => {
+    const cases = [
+      'SessionStart',
+      'UserPromptSubmit',
+      'UserPromptSubmitted',
+      'PostToolUse',
+      'PostToolUseFailure',
+      'BeforeAgent',
+      'AfterTool',
+      'task_started',
+    ];
+    for (const name of cases) {
+      it(`maps ${name} → working`, () => {
+        expect(normalizeAgentEvent(name)).toBe('working');
+      });
+    }
+  });
+
+  describe('blocked bucket', () => {
+    const cases = [
+      'PreToolUse',
+      'Notification',
+      'PermissionRequest',
+      'exec_approval_request',
+      'apply_patch_approval_request',
+      'request_user_input',
+    ];
+    for (const name of cases) {
+      it(`maps ${name} → blocked`, () => {
+        expect(normalizeAgentEvent(name)).toBe('blocked');
+      });
+    }
+  });
+
+  describe('done bucket', () => {
+    const cases = [
+      'Stop',
+      'AfterAgent',
+      'SessionEnd',
+      'task_complete',
+      'agent-turn-complete',
+    ];
+    for (const name of cases) {
+      it(`maps ${name} → done`, () => {
+        expect(normalizeAgentEvent(name)).toBe('done');
+      });
+    }
+  });
+
+  describe('unknown / nullish → null', () => {
+    it('returns null for an unrecognized event', () => {
+      expect(normalizeAgentEvent('SomeRandomEvent')).toBeNull();
+    });
+    it('returns null for empty string', () => {
+      expect(normalizeAgentEvent('')).toBeNull();
+    });
+    it('returns null for undefined', () => {
+      expect(normalizeAgentEvent(undefined)).toBeNull();
+    });
+  });
+
+  describe('case- and separator-insensitive matching', () => {
+    it('matches snake_case spelling of a PascalCase event', () => {
+      expect(normalizeAgentEvent('session_start')).toBe('working');
+      expect(normalizeAgentEvent('post_tool_use')).toBe('working');
+      expect(normalizeAgentEvent('pre_tool_use')).toBe('blocked');
+    });
+    it('matches camelCase spelling', () => {
+      expect(normalizeAgentEvent('userPromptSubmitted')).toBe('working');
+      expect(normalizeAgentEvent('postToolUse')).toBe('working');
+      expect(normalizeAgentEvent('preToolUse')).toBe('blocked');
+      expect(normalizeAgentEvent('sessionEnd')).toBe('done');
+    });
+    it('matches arbitrary case', () => {
+      expect(normalizeAgentEvent('STOP')).toBe('done');
+      expect(normalizeAgentEvent('notification')).toBe('blocked');
+    });
+  });
+});

apps/coder/src/services/__tests__/provider-types-parity.test.ts

@@ -1,64 +0,0 @@
-import { describe, it, expect } from 'vitest';
-import { readFileSync } from 'node:fs';
-import { resolve, dirname } from 'node:path';
-import { fileURLToPath } from 'node:url';
-
-/**
- * Parity guard between the two copies of the provider snapshot types:
- *   apps/coder/src/services/provider-types.ts  (backend source of truth)
- *   apps/web/src/api/types.ts                  (web wire copy)
- *
- * APPROACH: text-identity of each shared type block (mirrors the repo's existing
- * ws-frames.test.ts byte-parity convention). A compile-time bidirectional-
- * assignability check was attempted first (a web-side file importing coder's
- * import-free provider-types.ts), but apps/web/tsconfig.app.json is a composite
- * project and rejects out-of-include files with TS6307 — so cross-project type
- * import is structurally blocked. This runtime guard FAILS on any field
- * add/remove/rename/loosen in either copy, including the nested model/mode/
- * command types that ProviderSnapshotEntry references. Single-source-of-truth
- * (shared workspace package) is deferred as a Tier-2 follow-up.
- */
-const here = dirname(fileURLToPath(import.meta.url));
-const coderSrc = readFileSync(resolve(here, '../provider-types.ts'), 'utf8');
-const webSrc = readFileSync(resolve(here, '../../../../web/src/api/types.ts'), 'utf8');
-
-function extractBlock(src: string, name: string): string {
-  const iface = src.match(new RegExp(`export interface ${name} \\{[\\s\\S]*?\\n\\}`));
-  const alias = src.match(new RegExp(`export type ${name} =[^;]*;`));
-  const block = iface?.[0] ?? alias?.[0];
-  if (!block) throw new Error(`type block '${name}' not found`);
-  // Normalize to type structure: drop blank + comment lines (//, /* */, *),
-  // trim each line. Field add/remove/rename/loosen still changes a field line.
-  return block
-    .split('\n')
-    .map((l) => l.trim())
-    .filter(
-      (l) =>
-        l.length > 0 &&
-        !l.startsWith('//') &&
-        !l.startsWith('/*') &&
-        !l.startsWith('*'),
-    )
-    .join('\n');
-}
-
-describe('provider snapshot type parity (coder ↔ web)', () => {
-  // Includes the nested types ProviderSnapshotEntry references, so structural
-  // drift anywhere in the snapshot surface is caught.
-  const names = [
-    'ProviderSnapshotStatus',
-    'ProviderSnapshotEntry',
-    'ProviderModel',
-    'ProviderMode',
-    'ThinkingOption',
-    'AgentCommand',
-  ];
-  for (const name of names) {
-    it(`${name} is identical in both copies`, () => {
-      expect(
-        extractBlock(webSrc, name),
-        `${name} drifted between apps/coder/src/services/provider-types.ts and apps/web/src/api/types.ts`,
-      ).toBe(extractBlock(coderSrc, name));
-    });
-  }
-});

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

@@ -1,88 +0,0 @@
-/**
- * Shared ACP `Client` builder — the callback closures every ACP connection needs
- * (worktree-scoped FS bridge + permission/elicitation routing + session updates).
- *
- * Extracted (v2.7 audit reshape) from the byte-identical `buildClient` closures in
- * `acp-dispatch.ts` (one-shot) and `backends/warm-acp.ts` (warm). The two differed
- * only in WHERE the per-turn context comes from (a fixed dispatch vs. the warm
- * backend's `activeTurn`) and a trivially-equivalent permission gate — both are now
- * supplied via the `resolveTurn` callback, so the FS/permission/elicitation wiring
- * lives once. Behavior is preserved exactly:
- *   - `sessionUpdate` drops when `resolveTurn()` returns null (between turns).
- *   - permission/elicitation route to the UI only when BOTH a taskId AND sessionId
- *     are present (warm always has a sessionId, so this matches its prior
- *     `turn?.taskId` gate); otherwise the same auto-select-first / decline fallback.
- */
-import type {
-  Client,
-  SessionNotification,
-  RequestPermissionRequest,
-  RequestPermissionResponse,
-  ReadTextFileRequest,
-  ReadTextFileResponse,
-  WriteTextFileRequest,
-  WriteTextFileResponse,
-  CreateTerminalRequest,
-  CreateTerminalResponse,
-  CreateElicitationRequest,
-  CreateElicitationResponse,
-} from '@agentclientprotocol/sdk';
-import { readWorktreeTextFile, writeWorktreeTextFile } from './acp-client-fs.js';
-import { waitForPermissionResponse, waitForElicitationResponse } from './permission-waiter.js';
-
-/** The per-turn context an ACP `Client` closure needs, resolved lazily per call. */
-export interface AcpTurnContext {
-  /** Per-turn task id, for routing permission/elicitation prompts back to the UI. */
-  taskId: string | undefined;
-  /** BooCode session id (for permission-waiter's broker frames). */
-  sessionId: string | undefined;
-  /** Per-turn mode id (autonomous-mode gate in permission-waiter). */
-  modeId: string | undefined;
-  /** The agent name (for permission-waiter routing). */
-  agent: string;
-  /** Forward a session/update notification to the turn's event sink. */
-  onSessionUpdate: (params: SessionNotification) => void | Promise<void>;
-}
-
-/**
- * Build the ACP `Client` callbacks once per connection. `resolveTurn` is called at
- * the moment each callback fires and returns the live turn context (or null when no
- * turn is active — `sessionUpdate` then drops, matching the warm backend's
- * between-turns behavior). The FS bridge is scoped to `worktreePath`.
- */
-export function buildAcpClient(worktreePath: string, resolveTurn: () => AcpTurnContext | null): Client {
-  return {
-    sessionUpdate: async (params: SessionNotification): Promise<void> => {
-      const turn = resolveTurn();
-      if (!turn) return; // between turns — drop (no orphan settles a future turn)
-      await turn.onSessionUpdate(params);
-    },
-    requestPermission: async (params: RequestPermissionRequest): Promise<RequestPermissionResponse> => {
-      const turn = resolveTurn();
-      if (turn && turn.taskId && turn.sessionId) {
-        return waitForPermissionResponse(turn.taskId, turn.sessionId, turn.agent, turn.modeId, params);
-      }
-      const firstOption = params.options[0];
-      if (firstOption) return { outcome: { outcome: 'selected', optionId: firstOption.optionId } };
-      return { outcome: { outcome: 'cancelled' } };
-    },
-    readTextFile: async (params: ReadTextFileRequest): Promise<ReadTextFileResponse> => {
-      const content = await readWorktreeTextFile(worktreePath, params.path, params.line, params.limit);
-      return { content };
-    },
-    writeTextFile: async (params: WriteTextFileRequest): Promise<WriteTextFileResponse> => {
-      await writeWorktreeTextFile(worktreePath, params.path, params.content);
-      return {};
-    },
-    createTerminal: async (_params: CreateTerminalRequest): Promise<CreateTerminalResponse> => {
-      return { terminalId: 'noop' };
-    },
-    unstable_createElicitation: async (params: CreateElicitationRequest): Promise<CreateElicitationResponse> => {
-      const turn = resolveTurn();
-      if (turn && turn.taskId && turn.sessionId) {
-        return waitForElicitationResponse(turn.taskId, turn.sessionId, turn.agent, turn.modeId, params);
-      }
-      return { action: 'decline' };
-    },
-  };
-}

apps/coder/src/services/acp-dispatch.ts

@@ -9,20 +9,35 @@ import {
   ClientSideConnection,
   type Client,
   type SessionNotification,
+  type RequestPermissionRequest,
+  type RequestPermissionResponse,
+  type ReadTextFileRequest,
+  type ReadTextFileResponse,
+  type WriteTextFileRequest,
+  type WriteTextFileResponse,
+  type CreateTerminalRequest,
+  type CreateTerminalResponse,
+  type CreateElicitationRequest,
+  type CreateElicitationResponse,
   type SessionConfigOption,
   type ClientSideConnection as ConnectionType,
 } from '@agentclientprotocol/sdk';
 import type { Broker } from '@boocode/server/broker';
+import type { WsFrame } from '@boocode/contracts/ws-frames';
 import { spawn } from 'node:child_process';
 import { findThoughtLevelConfigId } from './acp-derive.js';
 import { resolveLaunchSpec } from './acp-spawn.js';
 import { getResolvedRegistry, type ResolvedProviderDef } from './provider-config-registry.js';
 import { createAcpNdJsonStream } from './acp-stream.js';
-import { cancelPendingPermission } from './permission-waiter.js';
+import { waitForPermissionResponse, waitForElicitationResponse, cancelPendingPermission } from './permission-waiter.js';
+import { mergeTaskCommands, getTaskCommands } from './agent-commands-cache.js';
+import { readWorktreeTextFile, writeWorktreeTextFile } from './acp-client-fs.js';
 import { mapSessionUpdate } from './acp-event-map.js';
-import { type AcpToolSnapshot, synthesizeCanceledSnapshots } from './acp-tool-snapshot.js';
+import {
-import { makeFrameEmitter, type FrameEmitter } from './frame-emitter.js';
+  type AcpToolSnapshot,
-import { buildAcpClient } from './acp-client.js';
+  snapshotToWireToolCall,
+  synthesizeCanceledSnapshots,
+} from './acp-tool-snapshot.js';
 
 export interface AcpDispatchResult {
   exitCode: number;
@@ -96,61 +111,144 @@ async function applySessionOverrides(
 }
 
 class AcpStreamContext {
-  /** AgentEvent → WS-frame mapping + text/reasoning/tool accumulation (shared
+  readonly textChunks: string[] = [];
-   *  `makeFrameEmitter`). The one-shot path passes no `dcp` stripper, so text is
+  readonly reasoningChunks: string[] = [];
-   *  emitted verbatim — byte-identical to the prior inline switch. */
+  readonly toolSnapshots = new Map<string, AcpToolSnapshot>();
-  private readonly emitter: FrameEmitter;
+  private aborted = false;
 
   constructor(
-    opts: Pick<AcpDispatchOpts, 'broker' | 'sessionId' | 'chatId' | 'messageId' | 'taskId'>,
+    private readonly opts: Pick<
+      AcpDispatchOpts,
+      'broker' | 'sessionId' | 'chatId' | 'messageId' | 'taskId'
+    >,
     private readonly worktreePath: string,
-  ) {
+  ) {}
-    this.emitter = makeFrameEmitter({
-      broker: opts.broker,
-      sessionId: opts.sessionId,
-      chatId: opts.chatId,
-      assistantId: opts.messageId,
-      taskId: opts.taskId,
-    });
-  }
 
   get reasoningText(): string {
-    return this.emitter.reasoningText;
+    return this.reasoningChunks.join('');
   }
 
   get output(): string {
-    return this.emitter.output;
+    return this.textChunks.join('');
   }
 
   get snapshots(): AcpToolSnapshot[] {
-    return this.emitter.snapshots;
+    return [...this.toolSnapshots.values()];
   }
 
   markAborted(): void {
-    // Synthesize 'canceled' updates for still-running tool calls so the UI doesn't
+    this.aborted = true;
-    // leave them spinning, then emit them through the same frame path (tool_update
+    for (const snap of synthesizeCanceledSnapshots(this.toolSnapshots.values())) {
-    // → the same `tool_call` wire frame the original published).
+      this.toolSnapshots.set(snap.toolCallId, snap);
-    for (const snap of synthesizeCanceledSnapshots(this.emitter.toolSnapshots.values())) {
+      this.publishToolSnapshot(snap);
-      this.emitter.onEvent({ type: 'tool_update', toolCall: snap });
     }
   }
 
-  handleSessionUpdate(params: SessionNotification): void {
+  private canStream(): boolean {
-    // The merge accumulator (`this.emitter.toolSnapshots`) is the same Map the
+    return !!(this.opts.broker && this.opts.sessionId && this.opts.chatId && this.opts.messageId);
-    // emitter publishes from, so a later tool_call_update merges over its tool_call.
+  }
-    for (const event of mapSessionUpdate(params, this.emitter.toolSnapshots)) {
+
-      this.emitter.onEvent(event);
+  private publishToolSnapshot(snapshot: AcpToolSnapshot): void {
+    if (!this.canStream()) return;
+    const wire = snapshotToWireToolCall(snapshot);
+    this.opts.broker!.publishFrame(this.opts.sessionId!, {
+      type: 'tool_call',
+      message_id: this.opts.messageId!,
+      chat_id: this.opts.chatId!,
+      tool_call: wire,
+    } as WsFrame);
+  }
+
+  async handleSessionUpdate(params: SessionNotification): Promise<void> {
+    // v2.6 Phase 2: the case-by-case mapping now lives in the shared, pure
+    // `mapSessionUpdate` (reused by the warm ACP backend). This method keeps the
+    // identical broker-publishing side effects — it just translates the normalized
+    // AgentEvents back into the same frames it always emitted. `this.toolSnapshots`
+    // is the merge accumulator, so a later tool_call_update merges over its
+    // tool_call (the prior `handleToolUpdate` behavior, byte-for-byte).
+    for (const event of mapSessionUpdate(params, this.toolSnapshots)) {
+      switch (event.type) {
+        case 'text':
+          this.textChunks.push(event.text);
+          if (this.canStream()) {
+            this.opts.broker!.publishFrame(this.opts.sessionId!, {
+              type: 'delta',
+              message_id: this.opts.messageId!,
+              chat_id: this.opts.chatId!,
+              content: event.text,
+            } as WsFrame);
+          }
+          break;
+        case 'reasoning':
+          this.reasoningChunks.push(event.text);
+          if (this.canStream()) {
+            this.opts.broker!.publishFrame(this.opts.sessionId!, {
+              type: 'reasoning_delta',
+              message_id: this.opts.messageId!,
+              chat_id: this.opts.chatId!,
+              content: event.text,
+            } as WsFrame);
+          }
+          break;
+        case 'tool_call':
+        case 'tool_update':
+          // mapSessionUpdate already stored the merged snapshot in this.toolSnapshots.
+          this.publishToolSnapshot(event.toolCall);
+          break;
+        case 'commands':
+          if (this.opts.taskId && event.commands.length > 0) {
+            mergeTaskCommands(this.opts.taskId, event.commands);
+            if (this.canStream() && this.opts.sessionId) {
+              const all = getTaskCommands(this.opts.taskId) ?? event.commands;
+              this.opts.broker!.publishFrame(this.opts.sessionId, {
+                type: 'agent_commands',
+                task_id: this.opts.taskId,
+                session_id: this.opts.sessionId,
+                commands: all,
+              } as WsFrame);
+            }
+          }
+          break;
+      }
     }
   }
 
   buildClient(agent: string, modeId: string | undefined, taskId: string | undefined, sessionId: string | undefined): Client {
-    return buildAcpClient(this.worktreePath, () => ({
+    return {
-      taskId,
+      sessionUpdate: (params) => this.handleSessionUpdate(params),
-      sessionId,
+      requestPermission: async (params: RequestPermissionRequest): Promise<RequestPermissionResponse> => {
-      modeId,
+        if (taskId && sessionId) {
-      agent,
+          return waitForPermissionResponse(taskId, sessionId, agent, modeId, params);
-      onSessionUpdate: (params) => this.handleSessionUpdate(params),
+        }
-    }));
+        const firstOption = params.options[0];
+        if (firstOption) {
+          return { outcome: { outcome: 'selected', optionId: firstOption.optionId } };
+        }
+        return { outcome: { outcome: 'cancelled' } };
+      },
+      readTextFile: async (params: ReadTextFileRequest): Promise<ReadTextFileResponse> => {
+        const content = await readWorktreeTextFile(
+          this.worktreePath,
+          params.path,
+          params.line,
+          params.limit,
+        );
+        return { content };
+      },
+      writeTextFile: async (params: WriteTextFileRequest): Promise<WriteTextFileResponse> => {
+        await writeWorktreeTextFile(this.worktreePath, params.path, params.content);
+        return {};
+      },
+      createTerminal: async (_params: CreateTerminalRequest): Promise<CreateTerminalResponse> => {
+        return { terminalId: 'noop' };
+      },
+      unstable_createElicitation: async (params: CreateElicitationRequest): Promise<CreateElicitationResponse> => {
+        if (taskId && sessionId) {
+          return waitForElicitationResponse(taskId, sessionId, agent, modeId, params);
+        }
+        return { action: 'decline' };
+      },
+    };
   }
 }
 

apps/coder/src/services/acp-stream.ts

@@ -2,7 +2,7 @@ import { Readable, Writable } from 'node:stream';
 import type { ChildProcess } from 'node:child_process';
 import { ndJsonStream } from '@agentclientprotocol/sdk';
 
-function nodeReadableToWeb(nodeStream: NodeJS.ReadableStream): ReadableStream<Uint8Array> {
+export function nodeReadableToWeb(nodeStream: NodeJS.ReadableStream): ReadableStream<Uint8Array> {
   return new ReadableStream<Uint8Array>({
     start(controller) {
       nodeStream.on('data', (chunk: Buffer) => controller.enqueue(new Uint8Array(chunk)));
@@ -17,7 +17,7 @@ function nodeReadableToWeb(nodeStream: NodeJS.ReadableStream): ReadableStream<Ui
   });
 }
 
-function nodeWritableToWeb(nodeStream: NodeJS.WritableStream): WritableStream<Uint8Array> {
+export function nodeWritableToWeb(nodeStream: NodeJS.WritableStream): WritableStream<Uint8Array> {
   return new WritableStream<Uint8Array>({
     write(chunk) {
       return new Promise<void>((resolve, reject) => {

apps/coder/src/services/agent-status-publish.ts

@@ -8,7 +8,7 @@
  * (`AgentStatusUpdatedFrame`) and mirrored byte-identical in apps/web.
  */
 import type { Broker } from '@boocode/server/broker';
-import type { WsFrame } from '@boocode/server/ws-frames';
+import type { WsFrame } from '@boocode/contracts/ws-frames';
 import type { AgentStatus } from './normalize-agent-status.js';
 
 // The exact slice of Broker we need — accepting just the bound method keeps call

apps/coder/src/services/backends/__tests__/opencode-concurrency.test.ts

@@ -1,173 +0,0 @@
-import { describe, it, expect, vi } from 'vitest';
-import type { Event, OpencodeClient } from '@opencode-ai/sdk/v2/client';
-import {
-  reconnectDecision,
-  runSessionEventLoop,
-  DEFAULT_RECONNECT_POLICY,
-  type SessionState,
-  type SseLoopDeps,
-} from '../opencode-sse.js';
-import { shouldStartServer } from '../opencode-server-process.js';
-
-/**
- * v2.7 concurrency hardening (Phase 7): the pure decision cores for SSE reconnect
- * backoff + the ensureServer double-spawn guard, plus a deterministic exercise of
- * the loop's breaker (injected sleep, fake client). Happy path is asserted to be
- * unchanged (clean stream end → reset → base-delay reconnect).
- */
-
-function freshState(): SessionState {
-  return {
-    boocodeSessionId: 'boo1',
-    agentSessionId: 'oc1',
-    worktreePath: '/wt',
-    streamedPartKeys: new Set(),
-    partTypeById: new Map(),
-    activeTurn: { onEvent: () => {}, settle: () => {} },
-    watchdog: null,
-    sseAbort: null,
-    swallowNextTerminal: false,
-  };
-}
-
-const silentLog = {
-  warn: () => {},
-  info: () => {},
-  error: () => {},
-  debug: () => {},
-} as unknown as SseLoopDeps['log'];
-
-describe('reconnectDecision (pure backoff + breaker)', () => {
-  it('first failure uses the base delay (matches pre-hardening flat delay)', () => {
-    expect(reconnectDecision(1)).toEqual({ action: 'reconnect', delayMs: DEFAULT_RECONNECT_POLICY.baseMs });
-  });
-
-  it('grows exponentially and caps at maxMs', () => {
-    const policy = { baseMs: 1000, maxMs: 30_000, maxAttempts: 10 };
-    expect(reconnectDecision(2, policy)).toEqual({ action: 'reconnect', delayMs: 2000 });
-    expect(reconnectDecision(3, policy)).toEqual({ action: 'reconnect', delayMs: 4000 });
-    expect(reconnectDecision(6, policy)).toEqual({ action: 'reconnect', delayMs: 30_000 }); // 32000 capped
-    expect(reconnectDecision(9, policy)).toEqual({ action: 'reconnect', delayMs: 30_000 });
-  });
-
-  it('gives up once failures exceed maxAttempts', () => {
-    const policy = { baseMs: 1, maxMs: 8, maxAttempts: 3 };
-    expect(reconnectDecision(3, policy).action).toBe('reconnect');
-    expect(reconnectDecision(4, policy)).toEqual({ action: 'give-up' });
-  });
-});
-
-describe('shouldStartServer (double-spawn guard)', () => {
-  it('does not start when the server is live', () => {
-    expect(shouldStartServer({ up: true, hasClient: true, serverStarting: true, childDead: false, startInFlight: false })).toBe(false);
-  });
-
-  it('starts on a fresh process (no start in flight)', () => {
-    expect(shouldStartServer({ up: false, hasClient: false, serverStarting: false, childDead: false, startInFlight: false })).toBe(true);
-  });
-
-  it('re-spawns after a crash once the prior start finished', () => {
-    expect(shouldStartServer({ up: false, hasClient: false, serverStarting: true, childDead: true, startInFlight: false })).toBe(true);
-  });
-
-  it('does NOT double-spawn while a start is already in flight (the race fix)', () => {
-    expect(shouldStartServer({ up: false, hasClient: false, serverStarting: true, childDead: true, startInFlight: true })).toBe(false);
-  });
-
-  it('does NOT double-spawn when a crash nulled serverStarting mid-start', () => {
-    // The narrow window: a crash during the in-flight start (await freePort) nulls
-    // serverStarting while startInFlight is still true. The startInFlight guard must
-    // win over the !serverStarting branch, else a second server spawns on a new port.
-    expect(shouldStartServer({ up: false, hasClient: false, serverStarting: false, childDead: true, startInFlight: true })).toBe(false);
-  });
-
-  it('waits (no spawn) when a cached start exists and the child is still alive', () => {
-    expect(shouldStartServer({ up: false, hasClient: false, serverStarting: true, childDead: false, startInFlight: false })).toBe(false);
-  });
-});
-
-describe('runSessionEventLoop — happy path (unchanged)', () => {
-  it('dispatches streamed events, reconciles on clean end, reconnects at base delay', async () => {
-    const state = freshState();
-    const abort = new AbortController();
-    const events = [
-      { type: 'session.next.text.delta', properties: { sessionID: 'oc1', delta: 'hi' } },
-      { type: 'session.idle', properties: { sessionID: 'oc1' } },
-    ] as unknown as Event[];
-
-    const client = {
-      event: {
-        subscribe: vi.fn(async () => ({
-          stream: (async function* () {
-            for (const ev of events) yield ev;
-          })(),
-        })),
-      },
-    } as unknown as OpencodeClient;
-
-    const dispatched: Event[] = [];
-    const sleeps: number[] = [];
-    let reconciles = 0;
-
-    const deps: SseLoopDeps = {
-      isUp: () => true,
-      getClient: () => client,
-      dispatchEvent: (ev) => dispatched.push(ev),
-      reconcile: async () => {
-        reconciles += 1;
-        abort.abort(); // stop the loop after the first clean cycle
-        return false;
-      },
-      onReconnectGiveUp: () => {
-        throw new Error('should not give up on the happy path');
-      },
-      log: silentLog,
-      sleep: async (ms) => {
-        sleeps.push(ms);
-      },
-    };
-
-    await runSessionEventLoop(state, abort, deps);
-
-    expect(dispatched).toHaveLength(2);
-    expect(reconciles).toBe(1);
-    expect(sleeps).toEqual([DEFAULT_RECONNECT_POLICY.baseMs]); // base delay, not backed off
-  });
-});
-
-describe('runSessionEventLoop — circuit breaker', () => {
-  it('backs off on repeated throws then gives up + fails the turn', async () => {
-    const state = freshState();
-    const abort = new AbortController();
-    const policy = { baseMs: 1, maxMs: 8, maxAttempts: 3 };
-
-    const subscribe = vi.fn(async () => {
-      throw new Error('connection refused');
-    });
-    const client = { event: { subscribe } } as unknown as OpencodeClient;
-
-    const sleeps: number[] = [];
-    const gaveUp = vi.fn();
-
-    const deps: SseLoopDeps = {
-      isUp: () => true,
-      getClient: () => client,
-      dispatchEvent: () => {},
-      reconcile: async () => false,
-      onReconnectGiveUp: gaveUp,
-      log: silentLog,
-      sleep: async (ms) => {
-        sleeps.push(ms);
-      },
-      policy,
-    };
-
-    await runSessionEventLoop(state, abort, deps);
-
-    // 3 backoff sleeps (1, 2, 4), then the 4th failure trips the breaker.
-    expect(sleeps).toEqual([1, 2, 4]);
-    expect(subscribe).toHaveBeenCalledTimes(4);
-    expect(gaveUp).toHaveBeenCalledTimes(1);
-    expect(gaveUp).toHaveBeenCalledWith(state);
-  });
-});

apps/coder/src/services/backends/__tests__/opencode-event-map.test.ts

@@ -1,226 +0,0 @@
-import { describe, it, expect } from 'vitest';
-import type { Event, Part } from '@opencode-ai/sdk/v2/client';
-import {
-  stripDcpTags,
-  eventSessionId,
-  resolvePartDedupeKey,
-  mapToolStatus,
-  toolPartToSnapshot,
-  toolCalledSnapshot,
-  toolSuccessSnapshot,
-  toolFailedSnapshot,
-  classifyPartDelta,
-  classifyUpdatedPart,
-  errToString,
-  errMsg,
-  type DedupState,
-} from '../opencode-event-map.js';
-
-/**
- * Pure opencode Event → AgentEvent translation + dedup gate (v2.7 audit reshape).
- * Mirrors the original `dispatchEvent` / `handleUpdatedPart` arms verbatim — no
- * I/O, so it's unit-testable. The slimmed backend keeps the routing + side effects.
- */
-
-function freshDedup(): DedupState {
-  return { streamedPartKeys: new Set(), partTypeById: new Map() };
-}
-
-describe('stripDcpTags', () => {
-  it('removes a complete dcp tag', () => {
-    expect(stripDcpTags('hi <dcp-message-id>m1</dcp-message-id> there')).toBe('hi  there');
-  });
-  it('leaves untagged text untouched', () => {
-    expect(stripDcpTags('plain text <div>')).toBe('plain text <div>');
-  });
-});
-
-describe('eventSessionId', () => {
-  it('reads properties.sessionID for a normal event', () => {
-    const ev = { type: 'session.idle', properties: { sessionID: 's1' } } as unknown as Event;
-    expect(eventSessionId(ev)).toBe('s1');
-  });
-  it('reads properties.part.sessionID for message.part.updated', () => {
-    const ev = {
-      type: 'message.part.updated',
-      properties: { part: { sessionID: 's2' } },
-    } as unknown as Event;
-    expect(eventSessionId(ev)).toBe('s2');
-  });
-  it('returns null when there is no session', () => {
-    const ev = { type: 'server.connected', properties: {} } as unknown as Event;
-    expect(eventSessionId(ev)).toBeNull();
-  });
-});
-
-describe('resolvePartDedupeKey', () => {
-  it('prefers the part id', () => {
-    expect(resolvePartDedupeKey({ id: 'p1', messageID: 'm1' }, 'text')).toBe('text:p1');
-  });
-  it('falls back to the message id', () => {
-    expect(resolvePartDedupeKey({ id: '  ', messageID: 'm1' }, 'reasoning')).toBe('reasoning:message:m1');
-  });
-  it('returns null when neither is present', () => {
-    expect(resolvePartDedupeKey({ id: '', messageID: '' }, 'text')).toBeNull();
-  });
-});
-
-describe('mapToolStatus', () => {
-  it('maps the opencode tool states to ACP statuses', () => {
-    expect(mapToolStatus('pending')).toBe('pending');
-    expect(mapToolStatus('running')).toBe('in_progress');
-    expect(mapToolStatus('completed')).toBe('completed');
-    expect(mapToolStatus('error')).toBe('failed');
-    expect(mapToolStatus(undefined)).toBeNull();
-  });
-});
-
-describe('session.next.tool.* snapshot builders', () => {
-  it('toolCalledSnapshot → in_progress with tool title + raw input', () => {
-    expect(toolCalledSnapshot({ callID: 'c1', tool: 'read_file', input: { path: 'a.ts' } })).toEqual({
-      toolCallId: 'c1',
-      title: 'read_file',
-      kind: null,
-      status: 'in_progress',
-      rawInput: { path: 'a.ts' },
-      rawOutput: undefined,
-    });
-  });
-  it('toolSuccessSnapshot → completed with joined text content', () => {
-    const snap = toolSuccessSnapshot({ callID: 'c1', content: [{ text: 'foo' }, { text: 'bar' }, { other: 1 }] });
-    expect(snap.status).toBe('completed');
-    expect(snap.title).toBe('c1');
-    expect(snap.rawOutput).toBe('foobar');
-  });
-  it('toolSuccessSnapshot → empty output when content is missing', () => {
-    expect(toolSuccessSnapshot({ callID: 'c1' }).rawOutput).toBe('');
-  });
-  it('toolFailedSnapshot → failed with stringified error', () => {
-    const snap = toolFailedSnapshot({ callID: 'c1', error: 'boom' });
-    expect(snap.status).toBe('failed');
-    expect(snap.title).toBe('c1');
-    expect(snap.rawOutput).toBe('boom');
-  });
-});
-
-describe('toolPartToSnapshot', () => {
-  it('extracts input/output/title/status from the tool state', () => {
-    const part = {
-      type: 'tool',
-      callID: 'c1',
-      tool: 'grep',
-      state: { status: 'completed', input: { q: 'x' }, output: 'result', title: 'Grep run' },
-    } as unknown as Parameters<typeof toolPartToSnapshot>[0];
-    expect(toolPartToSnapshot(part)).toEqual({
-      toolCallId: 'c1',
-      title: 'Grep run',
-      kind: null,
-      status: 'completed',
-      rawInput: { q: 'x' },
-      rawOutput: 'result',
-    });
-  });
-  it('falls back to the tool name and uses error as output', () => {
-    const part = {
-      type: 'tool',
-      callID: 'c2',
-      tool: 'edit',
-      state: { status: 'error', error: 'nope' },
-    } as unknown as Parameters<typeof toolPartToSnapshot>[0];
-    const snap = toolPartToSnapshot(part);
-    expect(snap.title).toBe('edit');
-    expect(snap.status).toBe('failed');
-    expect(snap.rawOutput).toBe('nope');
-  });
-});
-
-describe('classifyPartDelta (message.part.delta dedup recording)', () => {
-  it('records a reasoning key and emits a reasoning event', () => {
-    const st = freshDedup();
-    const e = classifyPartDelta({ partID: 'p1', field: 'reasoning', delta: 'thinking' }, st);
-    expect(e).toEqual({ type: 'reasoning', text: 'thinking' });
-    expect(st.streamedPartKeys.has('reasoning:p1')).toBe(true);
-  });
-  it('records a text key, strips dcp, and emits text', () => {
-    const st = freshDedup();
-    const e = classifyPartDelta({ partID: 'p2', field: 'text', delta: 'hi <dcp-message-id>m</dcp-message-id>' }, st);
-    expect(e).toEqual({ type: 'text', text: 'hi ' });
-    expect(st.streamedPartKeys.has('text:p2')).toBe(true);
-  });
-  it('still records the text key even when the cleaned delta is empty', () => {
-    const st = freshDedup();
-    const e = classifyPartDelta({ partID: 'p3', field: 'text', delta: '<dcp-message-id>m</dcp-message-id>' }, st);
-    expect(e).toBeNull();
-    expect(st.streamedPartKeys.has('text:p3')).toBe(true);
-  });
-  it('uses the recorded part type when the field is absent', () => {
-    const st = freshDedup();
-    st.partTypeById.set('p4', 'reasoning');
-    const e = classifyPartDelta({ partID: 'p4', delta: 'more' }, st);
-    expect(e).toEqual({ type: 'reasoning', text: 'more' });
-  });
-  it('returns null for an unknown field', () => {
-    expect(classifyPartDelta({ partID: 'p5', field: 'other', delta: 'x' }, freshDedup())).toBeNull();
-  });
-});
-
-describe('classifyUpdatedPart (message.part.updated dedup gate)', () => {
-  function textPart(over: Partial<Part> = {}): Part {
-    return {
-      type: 'text',
-      id: 'p1',
-      messageID: 'm1',
-      sessionID: 's1',
-      text: 'final text',
-      time: { start: 1, end: 2 },
-      ...over,
-    } as unknown as Part;
-  }
-
-  it('drops a terminal part already streamed via deltas', () => {
-    const st = freshDedup();
-    st.streamedPartKeys.add('text:p1');
-    expect(classifyUpdatedPart(textPart(), st)).toBeNull();
-    // the key is consumed
-    expect(st.streamedPartKeys.has('text:p1')).toBe(false);
-  });
-  it('emits a finished (ended) text part not seen via deltas', () => {
-    const st = freshDedup();
-    expect(classifyUpdatedPart(textPart(), st)).toEqual({ type: 'text', text: 'final text' });
-    expect(st.partTypeById.get('p1')).toBe('text');
-  });
-  it('does not emit a part that has not ended yet', () => {
-    const st = freshDedup();
-    expect(classifyUpdatedPart(textPart({ time: { start: 1 } as never }), st)).toBeNull();
-  });
-  it('strips dcp tags from the finished text', () => {
-    const st = freshDedup();
-    const part = textPart({ text: 'a <dcp-message-id>m</dcp-message-id>b' });
-    expect(classifyUpdatedPart(part, st)).toEqual({ type: 'text', text: 'a b' });
-  });
-  it('maps a running tool part to tool_call', () => {
-    const st = freshDedup();
-    const part = { type: 'tool', callID: 'c1', tool: 'grep', state: { status: 'running' } } as unknown as Part;
-    const e = classifyUpdatedPart(part, st);
-    expect(e?.type).toBe('tool_call');
-  });
-  it('maps a completed tool part to tool_update', () => {
-    const st = freshDedup();
-    const part = { type: 'tool', callID: 'c1', tool: 'grep', state: { status: 'completed', output: 'x' } } as unknown as Part;
-    const e = classifyUpdatedPart(part, st);
-    expect(e?.type).toBe('tool_update');
-  });
-});
-
-describe('error formatters', () => {
-  it('errMsg unwraps Error.message', () => {
-    expect(errMsg(new Error('x'))).toBe('x');
-    expect(errMsg('plain')).toBe('plain');
-  });
-  it('errToString handles null/string/Error/object', () => {
-    expect(errToString(null)).toBe('unknown error');
-    expect(errToString('s')).toBe('s');
-    expect(errToString(new Error('e'))).toBe('e');
-    expect(errToString({ a: 1 })).toBe('{"a":1}');
-  });
-});

apps/coder/src/services/backends/opencode-event-map.ts

@@ -1,203 +0,0 @@
-/**
- * Pure opencode `Event` → normalized `AgentEvent` translation.
- *
- * Extracted (v2.7 audit reshape) from `OpenCodeServerBackend.dispatchEvent` /
- * `handleUpdatedPart` and the file-local helpers. NO I/O, no timers, no DB, no
- * `byOpencodeId` — every function here is a deterministic transform over its
- * arguments (the dedup state is caller-owned and mutated in place, mirroring the
- * `acp-event-map.ts` `priorSnapshots` pattern). This is the unit-testable core; the
- * backend keeps the routing + side effects (watchdog, usage persistence, settle).
- *
- * Depends only on SDK TYPES + AcpToolSnapshot — safe to import anywhere.
- */
-import type { Event, Part, ToolPart, ToolState } from '@opencode-ai/sdk/v2/client';
-import type { ToolCallStatus } from '@agentclientprotocol/sdk';
-import type { AcpToolSnapshot } from '../acp-tool-snapshot.js';
-import type { AgentEvent } from '../agent-backend.js';
-
-/** Per-(opencode session) dedup state the part-stream classifiers read + mutate. */
-export interface DedupState {
-  /** dedup gate: `${type}:${id}` added on delta, deleted-and-tested on updated. */
-  streamedPartKeys: Set<string>;
-  /** partID → 'text' | 'reasoning', so a delta with a non-'reasoning' field is still classed right. */
-  partTypeById: Map<string, string>;
-}
-
-/** Strip opencode-dcp plugin tags that render as literal text in the UI. */
-export function stripDcpTags(s: string): string {
-  return s.replace(/<dcp-message-id>[^<]*<\/dcp-message-id>/g, '');
-}
-
-/** 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). */
-export 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;
-}
-
-/** Ported verbatim from Paseo opencode-agent.ts: id → message-id fallback → null. */
-export 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;
-}
-
-export 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;
-  }
-}
-
-/** opencode ToolPart → ACP-shaped snapshot (reuses the existing persist/render path). */
-export 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,
-  };
-}
-
-// ─── session.next.tool.* snapshot builders ───────────────────────────────────
-
-/** `session.next.tool.called` → an in-progress tool_call snapshot. */
-export function toolCalledSnapshot(p: { callID: string; tool: string; input: unknown }): AcpToolSnapshot {
-  return {
-    toolCallId: p.callID,
-    title: p.tool,
-    kind: null,
-    status: 'in_progress',
-    rawInput: p.input,
-    rawOutput: undefined,
-  };
-}
-
-/** `session.next.tool.success` → a completed tool snapshot (text content joined). */
-export function toolSuccessSnapshot(p: { callID: string; content?: ReadonlyArray<unknown> | null }): AcpToolSnapshot {
-  const output = p.content?.map((c) => (c && typeof c === 'object' && 'text' in c ? (c as { text: string }).text : '')).join('') ?? '';
-  return {
-    toolCallId: p.callID,
-    title: p.callID,
-    kind: null,
-    status: 'completed',
-    rawInput: undefined,
-    rawOutput: output,
-  };
-}
-
-/** `session.next.tool.failed` → a failed tool snapshot (error stringified). */
-export function toolFailedSnapshot(p: { callID: string; error: unknown }): AcpToolSnapshot {
-  return {
-    toolCallId: p.callID,
-    title: p.callID,
-    kind: null,
-    status: 'failed',
-    rawInput: undefined,
-    rawOutput: errToString(p.error),
-  };
-}
-
-// ─── message.part.* dedup gate ────────────────────────────────────────────────
-
-/**
- * `message.part.delta`: mark the part as streamed (so a later `message.part.updated`
- * for the same part is deduped) and return the AgentEvent to emit, or null when the
- * field is neither reasoning nor text, or a text delta strips down to empty. Mutates
- * `st.streamedPartKeys` exactly as the original inline arm did (the key is recorded
- * for text even when the cleaned delta is empty).
- */
-export function classifyPartDelta(
-  p: { partID: string; field?: string; delta: string },
-  st: DedupState,
-): AgentEvent | null {
-  const isReasoning = p.field === 'reasoning' || st.partTypeById.get(p.partID) === 'reasoning';
-  if (isReasoning) {
-    st.streamedPartKeys.add(`reasoning:${p.partID}`);
-    return { type: 'reasoning', text: p.delta };
-  }
-  if (p.field === 'text') {
-    st.streamedPartKeys.add(`text:${p.partID}`);
-    const cleaned = stripDcpTags(p.delta);
-    return cleaned ? { type: 'text', text: cleaned } : null;
-  }
-  return null;
-}
-
-/**
- * `message.part.updated` terminal part: the dedup gate for text/reasoning (drop a
- * part already streamed via deltas; otherwise emit the finished text) plus the
- * tool-part → tool_call/tool_update mapping. Returns null when nothing should be
- * emitted. Mutates `st.partTypeById` / `st.streamedPartKeys` like the original.
- */
-export function classifyUpdatedPart(part: Part, st: DedupState): AgentEvent | null {
-  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 null; // already streamed via delta
-    const raw = part.text ?? '';
-    const text = part.type === 'text' ? stripDcpTags(raw) : raw;
-    if (text && part.time?.end != null) {
-      return { type: part.type, text };
-    }
-    return null;
-  }
-
-  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.
-    return status === 'completed' || status === 'error'
-      ? { type: 'tool_update', toolCall: snap }
-      : { type: 'tool_call', toolCall: snap };
-  }
-  // NOTE: opencode's SSE payload union carries no available-commands event, so the
-  // AgentEvent 'commands' arm is intentionally never emitted here.
-  return null;
-}
-
-// ─── shared error formatters (pure) ───────────────────────────────────────────
-
-export function errMsg(e: unknown): string {
-  return e instanceof Error ? e.message : String(e);
-}
-
-export 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);
-  }
-}

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

@@ -1,325 +0,0 @@
-/**
- * OpenCodeServerSupervisor — the opencode `serve` child + HTTP client + port +
- * health-counter lifecycle, extracted (v2.7 audit reshape) from the backend
- * god-class. Owns spawn / ready / crash / proactive-health restart / dispose and
- * exposes `client` / `port` / `health()` / `tickHealth()` to the backend.
- *
- * Session-level recovery (failing in-flight turns, marking agent_sessions crashed,
- * tearing down SSE loops) is NOT a process concern — it's delegated back to the
- * backend through the injected `hooks.onServerDown` callback, keeping this module
- * free of the demux map / SQL / turn state.
- *
- * v2.7 concurrency hardening: `ensureServer` is guarded against the crash-window
- * double-spawn (two concurrent callers each re-spawning on different ports) via a
- * synchronous `startInFlight` flag — see `shouldStartServer`.
- */
-import { spawn, type ChildProcess } from 'node:child_process';
-import { createOpencodeClient, type OpencodeClient } from '@opencode-ai/sdk/v2/client';
-import type { FastifyBaseLogger } from 'fastify';
-import { decideRestart, DEFAULT_HEALTH_FAILURE_THRESHOLD } from './lifecycle-decisions.js';
-import { reclaimPort, waitForPortRelease, freePort } from '../net/port-utils.js';
-
-const READY_TIMEOUT_MS = 30_000;
-
-/** Info handed to the backend when the server goes down (crash or forced restart). */
-export interface ServerDownInfo {
-  code: number | null;
-  signal: NodeJS.Signals | null;
-  port: number;
-}
-
-export interface SupervisorHooks {
-  /** True iff ANY pooled session has an in-flight turn (defers a busy restart). */
-  isBusy: () => boolean;
-  /** Session-level recovery: fail in-flight turns, mark crashed, drop demux state. */
-  onServerDown: (info: ServerDownInfo) => void;
-}
-
-export interface OpenCodeServerSupervisorDeps {
-  /** Absolute path to the opencode binary (resolved from available_agents). */
-  opencodeBinary: string;
-  log: FastifyBaseLogger;
-  hooks: SupervisorHooks;
-}
-
-/**
- * Pure decision for `ensureServer`: should we (re)spawn the server right now?
- *
- * - A live, ready server (`up && client`) → no.
- * - A start already in flight (`startInFlight`) → no, NEVER double-spawn — join the
- *   running start instead. This is checked BEFORE `serverStarting` because the crash
- *   handler can null `serverStarting` mid-start (a crash during `await freePort()`),
- *   and without this guard the `!serverStarting` branch would spawn a second server
- *   on a different port while the first is still coming up.
- * - No start cached/running → yes (fresh start or post-crash re-spawn, since the
- *   crash handler nulls `serverStarting`).
- * - A cached start that already finished, but the child has since died and the crash
- *   handler hasn't reset us yet → yes.
- */
-export function shouldStartServer(s: {
-  up: boolean;
-  hasClient: boolean;
-  serverStarting: boolean;
-  childDead: boolean;
-  startInFlight: boolean;
-}): boolean {
-  if (s.up && s.hasClient) return false;
-  if (s.startInFlight) return false;
-  if (!s.serverStarting) return true;
-  if (!s.up && s.childDead) return true;
-  return false;
-}
-
-export class OpenCodeServerSupervisor {
-  private readonly opencodeBinary: string;
-  private readonly log: FastifyBaseLogger;
-  private readonly hooks: SupervisorHooks;
-
-  private childProc: ChildProcess | null = null;
-  private opencodeClient: OpencodeClient | null = null;
-  private serverPort: number | null = null;
-  private up = false;
-  private serverStarting: Promise<void> | null = null;
-  /** True from the synchronous head of startServer() until it settles — the
-   *  double-spawn guard reads it so a concurrent ensureServer joins instead of
-   *  kicking a second spawn. */
-  private startInFlight = false;
-  // Phase 3 busy-aware health monitor (openchamber lift): consecutive failed
-  // probes + the start of an unhealthy-while-busy window feed `decideRestart`.
-  private consecutiveHealthFailures = 0;
-  private unhealthyBusySince = 0;
-  private restarting: Promise<void> | null = null;
-
-  constructor(deps: OpenCodeServerSupervisorDeps) {
-    this.opencodeBinary = deps.opencodeBinary;
-    this.log = deps.log;
-    this.hooks = deps.hooks;
-  }
-
-  /** The live opencode HTTP client, or null between (re)starts. */
-  get client(): OpencodeClient | null {
-    return this.opencodeClient;
-  }
-
-  /** The current server port, or null before the first start. */
-  get port(): number | null {
-    return this.serverPort;
-  }
-
-  /** §2: liveness for the health endpoint + dispatcher fallback decision. */
-  health(): 'up' | 'down' {
-    return this.up ? 'up' : 'down';
-  }
-
-  isUp(): boolean {
-    return this.up;
-  }
-
-  // ─── lifecycle (spawn once + client + ready; crash-restart) ──────────────────
-
-  /**
-   * Lazy: start the single server on first use; re-spawn after a crash. Idempotent
-   * within one live server — `serverStarting` caches the in-flight start, reset to
-   * null by the crash handler so the NEXT ensureServer re-spawns. A dead-but-not-
-   * yet-reaped child (exit handler raced) is also treated as needing a restart.
-   * Concurrent callers in a crash window are coalesced via `startInFlight`.
-   */
-  ensureServer(): Promise<void> {
-    if (this.up && this.opencodeClient) return Promise.resolve();
-    const childDead =
-      this.childProc != null && (this.childProc.exitCode !== null || this.childProc.signalCode !== null);
-    if (
-      shouldStartServer({
-        up: this.up,
-        hasClient: this.opencodeClient != null,
-        serverStarting: this.serverStarting != null,
-        childDead,
-        startInFlight: this.startInFlight,
-      })
-    ) {
-      this.serverStarting = this.startServer();
-    }
-    return this.serverStarting ?? Promise.resolve();
-  }
-
-  private async startServer(): Promise<void> {
-    // Set synchronously (before the first await) so a concurrent ensureServer sees
-    // the in-flight start and joins `serverStarting` instead of double-spawning.
-    this.startInFlight = true;
-    try {
-      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.
-      const child = spawn(this.opencodeBinary, ['serve', '--hostname', '127.0.0.1', '--port', String(port)], {
-        stdio: ['ignore', 'pipe', 'pipe'],
-        env: { ...process.env },
-      });
-      this.childProc = child;
-      this.serverPort = port;
-
-      // Child lifetime is the backend's (the pool's), NOT a request's. On unexpected
-      // exit we recover: settle in-flight turns, mark sessions crashed (the backend's
-      // onServerDown), reclaim the port, and reset state so the next ensureServer
-      // re-spawns.
-      child.on('exit', (code, signal) => {
-        // Only react to THIS child's exit (a restart may have swapped in a new one).
-        if (this.childProc !== child) return;
-        this.handleCrash(code, signal, port);
-      });
-
-      await waitForReady(child, READY_TIMEOUT_MS);
-
-      this.opencodeClient = createOpencodeClient({ baseUrl: `http://127.0.0.1:${port}` });
-      this.up = true;
-      this.log.info({ port }, 'opencode-server: ready');
-    } finally {
-      this.startInFlight = false;
-    }
-  }
-
-  /**
-   * Server down (crash-exit or forced restart): reset process/port state, delegate
-   * session-level recovery to the backend, and reclaim the port. Mirrors the
-   * original `handleServerCrash` ordering (up=false → session cleanup → client/
-   * serverStarting null → reclaimPort).
-   */
-  private handleCrash(code: number | null, signal: NodeJS.Signals | null, port: number): void {
-    this.up = false;
-    this.hooks.onServerDown({ code, signal, port });
-    this.opencodeClient = null;
-    this.serverStarting = null; // force a re-spawn on the next ensureServer
-    // Reclaim the port so a re-spawn on a fixed/leaked port isn't blocked. Best
-    // effort; the next start uses a fresh ephemeral port anyway.
-    reclaimPort(port);
-  }
-
-  /**
-   * Phase 3 proactive health monitor (openchamber `runHealthCheckCycle` lift,
-   * busy-aware). Probes /global/health; on a sustained failure of a NON-busy server,
-   * force a restart so the next turn isn't blocked by a wedged process. Busy servers
-   * are deferred via the stale-grace in `decideRestart`. No-op when never started or
-   * a restart is already in flight.
-   */
-  async tickHealth(now: number = Date.now()): Promise<void> {
-    if (!this.childProc || this.restarting) return;
-    const childExited = this.childProc.exitCode !== null || this.childProc.signalCode !== null;
-    // An exited child is recovered lazily by ensureServer; don't double-restart it.
-    if (childExited) return;
-
-    const healthy = await this.probeHealth();
-    if (healthy) {
-      this.consecutiveHealthFailures = 0;
-      this.unhealthyBusySince = 0;
-      return;
-    }
-    this.consecutiveHealthFailures += 1;
-    const busy = this.hooks.isBusy();
-    const decision = decideRestart({
-      processExited: false,
-      consecutiveFailures: this.consecutiveHealthFailures,
-      busy,
-      unhealthyBusySince: this.unhealthyBusySince,
-      now,
-      failureThreshold: DEFAULT_HEALTH_FAILURE_THRESHOLD,
-    });
-    // Stamp the start of an unhealthy-while-busy window so the stale-grace can fire.
-    if (busy && this.unhealthyBusySince === 0) this.unhealthyBusySince = now;
-    if (decision.action === 'restart') {
-      this.log.warn(
-        { failures: this.consecutiveHealthFailures, busy, reason: decision.reason },
-        'opencode-server: health monitor forcing restart',
-      );
-      this.consecutiveHealthFailures = 0;
-      this.unhealthyBusySince = 0;
-      await this.restartServer();
-    }
-  }
-
-  private async probeHealth(): Promise<boolean> {
-    if (!this.opencodeClient) return false;
-    try {
-      const res = await this.opencodeClient.global.health();
-      return !res.error;
-    } catch {
-      return false;
-    }
-  }
-
-  /** Force-kill the current server + reclaim its port; the next ensureServer
-   *  re-spawns (lazy). Mirrors handleCrash's state reset but is initiated by the
-   *  health monitor rather than the OS. */
-  private async restartServer(): Promise<void> {
-    if (this.restarting) return this.restarting;
-    this.restarting = (async () => {
-      const child = this.childProc;
-      const port = this.serverPort;
-      this.up = false;
-      // Fail in-flight turns + mark sessions crashed via the same path as a crash.
-      if (child) {
-        this.handleCrash(null, null, port ?? 0);
-        if (!child.killed) child.kill('SIGTERM');
-      }
-      if (port) {
-        reclaimPort(port);
-        await waitForPortRelease(port, 3_000);
-      }
-      this.childProc = null;
-    })().finally(() => {
-      this.restarting = null;
-    });
-    return this.restarting;
-  }
-
-  /** Full teardown of the child + client + port state. */
-  async dispose(): Promise<void> {
-    this.up = false;
-    const child = this.childProc;
-    this.childProc = null;
-    this.opencodeClient = null;
-    if (child && !child.killed) {
-      child.kill('SIGTERM');
-      const t = setTimeout(() => {
-        if (!child.killed) child.kill('SIGKILL');
-      }, 5_000);
-      t.unref();
-    }
-  }
-}
-
-/** 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);
-  });
-}

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

@@ -1,64 +1,91 @@
 /**
- * v2.6 Phase 1 — OpenCodeServerBackend (slimmed, v2.7 audit reshape).
+ * 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.
+ * worktree directory so sessions in different directories stream concurrently
- *
+ * (P1.5-a — replaced the Phase-1 single-stream-last-directory model).
- * This file is now just the `AgentBackend` SURFACE — ensureSession / prompt /
- * accumulateUsage / closeSession + the per-session demux side effects (watchdog,
- * reconcile, usage). It composes three extracted collaborators:
- *   - `OpenCodeServerSupervisor` (opencode-server-process.ts) — child/client/port/
- *     health lifecycle, spawn/crash/restart/dispose.
- *   - the per-session SSE loop (opencode-sse.ts) — subscribe + reconnect/backoff.
- *   - the pure event map (opencode-event-map.ts) — Event → AgentEvent translation,
- *     dedup gate, dcp-strip, tool-snapshot.
  *
  * Implements the Phase 0 `AgentBackend` interface. Emits transport-agnostic
- * `AgentEvent`s; the dispatcher maps them to WS frames.
+ * `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, spawnSync, type ChildProcess } from 'node:child_process';
 import { createHash } from 'node:crypto';
+import { createServer, connect as netConnect } from 'node:net';
 import type { FastifyBaseLogger } from 'fastify';
-import type { Event, AssistantMessage } from '@opencode-ai/sdk/v2/client';
+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 { armAbortGuard, noteTurnActivity, consumeTerminal } from './turn-guard.js';
 import { stepEndedToUsage, type StepUsage } from './opencode-usage.js';
-import { OpenCodeServerSupervisor, type ServerDownInfo } from './opencode-server-process.js';
+import { decideRestart, DEFAULT_HEALTH_FAILURE_THRESHOLD } from './lifecycle-decisions.js';
-import {
-  startSessionEventLoop,
-  type SessionState,
-  type TurnState,
-  type SseLoopDeps,
-} from './opencode-sse.js';
-import {
-  classifyPartDelta,
-  classifyUpdatedPart,
-  toolCalledSnapshot,
-  toolSuccessSnapshot,
-  toolFailedSnapshot,
-  stripDcpTags,
-  errMsg,
-  errToString,
-} from './opencode-event-map.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. Generous so a
+ * is wedged or its terminal event (session.idle) was lost (see the reconnect race
- * legitimately slow turn never trips it.
+ * 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;
+  /** F.1 post-abort orphan-terminal guard: swallow the one session.idle/error
+   *  opencode emits for an aborted turn so it can't settle the next turn. */
+  swallowNextTerminal: boolean;
+}
+
 export interface OpenCodeServerBackendDeps {
   sql: Sql;
   log: FastifyBaseLogger;
@@ -71,32 +98,36 @@ export class OpenCodeServerBackend implements AgentBackend {
 
   private readonly sql: Sql;
   private readonly log: FastifyBaseLogger;
-  private readonly supervisor: OpenCodeServerSupervisor;
+  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;
+  // Phase 3 busy-aware health monitor (openchamber lift): consecutive failed
+  // probes + the start of an unhealthy-while-busy window feed `decideRestart`.
+  private consecutiveHealthFailures = 0;
+  private unhealthyBusySince = 0;
+  private restarting: Promise<void> | null = null;
 
   /** opencode session id → demux state. Maintained by ensureSession; read by the SSE loop. */
   private readonly byOpencodeId = new Map<string, SessionState>();
-  /** Coalesces concurrent ensureSession calls for the same (chat, agent) key. */
-  private readonly ensuring = new Map<string, Promise<AgentSessionHandle>>();
 
   constructor(deps: OpenCodeServerBackendDeps) {
     this.sql = deps.sql;
     this.log = deps.log;
-    this.supervisor = new OpenCodeServerSupervisor({
+    this.opencodeBinary = deps.opencodeBinary;
-      opencodeBinary: deps.opencodeBinary,
-      log: deps.log,
-      hooks: {
-        isBusy: () => this.isBusy(),
-        onServerDown: (info) => this.onServerDown(info),
-      },
-    });
   }
 
   /** §2: liveness for the health endpoint + dispatcher fallback decision. */
   health(): 'up' | 'down' {
-    return this.supervisor.health();
+    return this.up ? 'up' : 'down';
   }
 
-  /** Phase 3: busy iff ANY pooled opencode session has an in-flight turn. */
+  /** Phase 3: busy iff ANY pooled opencode session has an in-flight turn. The
+   *  pool reads this to skip idle/LRU eviction and the health-monitor to defer a
+   *  restart (never tear down a session mid-stream). */
   isBusy(): boolean {
     for (const st of this.byOpencodeId.values()) {
       if (st.activeTurn) return true;
@@ -104,23 +135,72 @@ export class OpenCodeServerBackend implements AgentBackend {
     return false;
   }
 
-  /** Phase 3 proactive health probe + busy-aware self-restart, run by the pool's
+  // ─── Server lifecycle (1.2: spawn once + client + ready; Phase 3 crash-restart) ──
-   *  periodic sweep. Delegates to the supervisor. */
+
-  async tickHealth(now: number = Date.now()): Promise<void> {
+  /**
-    await this.supervisor.tickHealth(now);
+   * Lazy: start the single server on first use; re-spawn after a crash. Idempotent
+   * within one live server — `serverStarting` caches the in-flight start, and is
+   * reset to null by the crash handler so the NEXT ensureServer re-spawns a fresh
+   * server (Phase 3 crash recovery). A dead-but-not-yet-reaped child (exit handler
+   * raced) is also treated as needing a restart.
+   */
+  private ensureServer(): Promise<void> {
+    const childDead = this.child != null && (this.child.exitCode !== null || this.child.signalCode !== null);
+    if (!this.serverStarting || (!this.up && childDead)) {
+      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. Phase 3: on unexpected exit we recover —
+    // settle any in-flight turns as failed, mark their agent_sessions rows crashed,
+    // and reset `serverStarting` so the next ensureServer re-spawns. opencode keeps
+    // sessions on disk, but a fresh server's in-memory state is gone, so the next
+    // turn's ensureSession (rows now 'crashed') creates fresh opencode sessions.
+    child.on('exit', (code, signal) => {
+      // Only react to THIS child's exit (a restart may have swapped in a new one).
+      if (this.child !== child) return;
+      this.handleServerCrash(code, signal, port);
+    });
+
+    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');
   }
 
   /**
-   * Server down (crash-exit or forced restart): fail every in-flight turn so its
+   * Crash handler (Phase 3, lift of openchamber's restart-on-exit path). The
-   * dispatcher unblocks, mark each session crashed so ensureSession won't resume a
+   * server died with N live opencode sessions; we can't restart it here (the next
-   * now-dead native id, and tear down the SSE loops + demux state. Invoked by the
+   * turn does, lazily — avoids a restart storm if the binary is broken). We:
-   * supervisor (it owns the process/port reset). Mirrors the original
+   *   1. fail every in-flight turn so its dispatcher unblocks + publishes an error,
-   * handleServerCrash session-half byte-for-byte.
+   *   2. mark each session's agent_sessions row 'crashed' so ensureSession won't
+   *      resume a now-dead native session id (it creates fresh),
+   *   3. tear down the SSE loops + demux state (stale against the dead server),
+   *   4. reclaim the port + reset state so the next ensureServer re-spawns.
    */
-  private onServerDown(info: ServerDownInfo): void {
+  private handleServerCrash(code: number | null, signal: NodeJS.Signals | null, port: number): void {
+    this.up = false;
     const states = [...this.byOpencodeId.values()];
     this.log.warn(
-      { code: info.code, signal: info.signal, port: info.port, liveSessions: states.length },
+      { code, signal, port, liveSessions: states.length },
       'opencode-server: child exited — recovering (fail in-flight, mark crashed, re-spawn next turn)',
     );
 
@@ -139,6 +219,8 @@ export class OpenCodeServerBackend implements AgentBackend {
     }
     // Drop the demux map: every session id is stale against a fresh server.
     this.byOpencodeId.clear();
+    this.client = null;
+    this.serverStarting = null; // force a re-spawn on the next ensureServer
 
     if (crashedIds.length > 0) {
       this.sql`
@@ -148,20 +230,146 @@ export class OpenCodeServerBackend implements AgentBackend {
         this.log.warn({ err: errMsg(err) }, 'opencode-server: failed to mark crashed sessions (non-fatal)');
       });
     }
+
+    // Reclaim the port so a re-spawn on a fixed/leaked port isn't blocked. Best
+    // effort; the next start uses a fresh ephemeral port anyway.
+    reclaimPort(port);
   }
 
-  // ─── SSE loop wiring ─────────────────────────────────────────────────────────
+  /**
+   * Phase 3 proactive health monitor (openchamber `runHealthCheckCycle` lift,
+   * busy-aware). Probes the server's /global/health; on a sustained failure of a
+   * NON-busy server, force a restart so the next turn isn't blocked by a wedged
+   * (hung-but-not-exited) process. Busy servers are deferred via the stale-grace in
+   * `decideRestart` — never tear down live work. Driven by the pool's periodic
+   * sweep (best-effort; a crash-exit is already handled by `handleServerCrash` +
+   * lazy `ensureServer` re-spawn, so this only catches the hung case). No-op when
+   * the server was never started or a restart is already in flight.
+   */
+  async tickHealth(now: number = Date.now()): Promise<void> {
+    if (!this.child || this.restarting) return;
+    const childExited = this.child.exitCode !== null || this.child.signalCode !== null;
+    // An exited child is recovered lazily by ensureServer; don't double-restart it.
+    if (childExited) return;
 
-  /** The dependency bundle the per-session SSE loop reads. */
+    const healthy = await this.probeHealth();
-  private sseDeps(): SseLoopDeps {
+    if (healthy) {
-    return {
+      this.consecutiveHealthFailures = 0;
-      isUp: () => this.supervisor.isUp(),
+      this.unhealthyBusySince = 0;
-      getClient: () => this.supervisor.client,
+      return;
-      dispatchEvent: (ev) => this.dispatchEvent(ev),
+    }
-      reconcile: (st) => this.reconcile(st),
+    this.consecutiveHealthFailures += 1;
-      onReconnectGiveUp: (st) => this.onReconnectGiveUp(st),
+    const busy = this.isBusy();
-      log: this.log,
+    const decision = decideRestart({
-    };
+      processExited: false,
+      consecutiveFailures: this.consecutiveHealthFailures,
+      busy,
+      unhealthyBusySince: this.unhealthyBusySince,
+      now,
+      failureThreshold: DEFAULT_HEALTH_FAILURE_THRESHOLD,
+    });
+    // Stamp the start of an unhealthy-while-busy window so the stale-grace can fire.
+    if (busy && this.unhealthyBusySince === 0) this.unhealthyBusySince = now;
+    if (decision.action === 'restart') {
+      this.log.warn(
+        { failures: this.consecutiveHealthFailures, busy, reason: decision.reason },
+        'opencode-server: health monitor forcing restart',
+      );
+      this.consecutiveHealthFailures = 0;
+      this.unhealthyBusySince = 0;
+      await this.restartServer();
+    }
+  }
+
+  private async probeHealth(): Promise<boolean> {
+    if (!this.client) return false;
+    try {
+      const res = await this.client.global.health();
+      return !res.error;
+    } catch {
+      return false;
+    }
+  }
+
+  /** Force-kill the current server + reclaim its port; the next ensureServer
+   *  re-spawns (lazy). Mirrors handleServerCrash's state reset but is initiated by
+   *  the health monitor rather than the OS. */
+  private async restartServer(): Promise<void> {
+    if (this.restarting) return this.restarting;
+    this.restarting = (async () => {
+      const child = this.child;
+      const port = this.port;
+      this.up = false;
+      // Fail in-flight turns + mark sessions crashed via the same path as a crash.
+      if (child) {
+        this.handleServerCrash(null, null, port ?? 0);
+        if (!child.killed) child.kill('SIGTERM');
+      }
+      if (port) {
+        reclaimPort(port);
+        await waitForPortRelease(port, 3_000);
+      }
+      this.child = null;
+    })().finally(() => {
+      this.restarting = null;
+    });
+    return this.restarting;
+  }
+
+  // ─── 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. */
@@ -190,7 +398,15 @@ export class OpenCodeServerBackend implements AgentBackend {
         const st = this.byOpencodeId.get(p.sessionID);
         if (!st?.activeTurn) return;
         this.bumpActivity(st);
-        st.activeTurn.onEvent({ type: 'tool_call', toolCall: toolCalledSnapshot(p) });
+        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': {
@@ -198,7 +414,16 @@ export class OpenCodeServerBackend implements AgentBackend {
         const st = this.byOpencodeId.get(p.sessionID);
         if (!st?.activeTurn) return;
         this.bumpActivity(st);
-        st.activeTurn.onEvent({ type: 'tool_update', toolCall: toolSuccessSnapshot(p) });
+        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': {
@@ -206,7 +431,15 @@ export class OpenCodeServerBackend implements AgentBackend {
         const st = this.byOpencodeId.get(p.sessionID);
         if (!st?.activeTurn) return;
         this.bumpActivity(st);
-        st.activeTurn.onEvent({ type: 'tool_update', toolCall: toolFailedSnapshot(p) });
+        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;
       }
       // ─── per-step usage (U.6) — token/cost accounting for opencode sessions ──
@@ -216,7 +449,8 @@ export class OpenCodeServerBackend implements AgentBackend {
         if (!st?.activeTurn) return;
         this.bumpActivity(st);
         // Accumulate this step's normalized usage onto the (chat_id, agent) row.
-        // Fire-and-forget: a DB hiccup must not stall the turn.
+        // Fire-and-forget: a DB hiccup must not stall the turn. opencode emits this
+        // once per LLM step, so a multi-tool turn sums several deltas.
         const usage = stepEndedToUsage(p);
         void this.accumulateUsage(st, usage);
         return;
@@ -227,8 +461,15 @@ export class OpenCodeServerBackend implements AgentBackend {
         const st = this.byOpencodeId.get(p.sessionID);
         if (!st?.activeTurn) return;
         this.bumpActivity(st);
-        const e = classifyPartDelta(p, st);
+        const isReasoning = p.field === 'reasoning' || st.partTypeById.get(p.partID) === 'reasoning';
-        if (e) st.activeTurn.onEvent(e);
+        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': {
@@ -236,8 +477,7 @@ export class OpenCodeServerBackend implements AgentBackend {
         const st = this.byOpencodeId.get(part.sessionID);
         if (!st?.activeTurn) return;
         this.bumpActivity(st);
-        const e = classifyUpdatedPart(part, st);
+        this.handleUpdatedPart(part, st);
-        if (e) st.activeTurn.onEvent(e);
         return;
       }
       // ─── lifecycle ─────────────────────────────────────────────────────────
@@ -262,6 +502,40 @@ export class OpenCodeServerBackend implements AgentBackend {
     }
   }
 
+  /** 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. */
@@ -276,8 +550,8 @@ export class OpenCodeServerBackend implements AgentBackend {
     st.watchdog.unref?.();
   }
 
-  /** Watchdog fired: reconcile once; if still-running we can't tell, so fail closed.
+  /** 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. */
+   *  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) {
@@ -290,27 +564,16 @@ export class OpenCodeServerBackend implements AgentBackend {
     }
   }
 
-  /** SSE circuit-breaker fired (reconnect gave up): fail the active turn + mark the
-   *  session crashed so it isn't resumed. The next turn re-creates a fresh session. */
-  private async onReconnectGiveUp(st: SessionState): Promise<void> {
-    if (!st.activeTurn) return;
-    await this.sql`
-      UPDATE agent_sessions SET status = 'crashed'
-      WHERE agent_session_id = ${st.agentSessionId}
-    `.catch(() => {});
-    st.activeTurn?.settle({ ok: false, error: 'opencode SSE stream lost (reconnect gave up)' });
-  }
-
   /**
    * 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;
-    const client = this.supervisor.client;
+    if (!turn || !this.client) return false;
-    if (!turn || !client) return false;
     try {
-      const res = await client.session.messages({
+      const res = await this.client.session.messages({
         sessionID: st.agentSessionId,
         directory: st.worktreePath,
       });
@@ -342,8 +605,10 @@ export class OpenCodeServerBackend implements AgentBackend {
 
   /**
    * Accumulate one `session.next.step.ended`'s normalized usage onto the session's
-   * agent_sessions row. Running totals for the whole conversation context. Zero-delta
+   * agent_sessions row, keyed by the resumed `agent_session_id` (unique per active
-   * steps are skipped. Errors are swallowed: usage telemetry must never fail a turn.
+   * row — the dispatcher's `(chat_id, agent)` lookup wrote it). Running totals for
+   * the whole conversation context (not last-step). Zero-delta steps are skipped to
+   * avoid a no-op write. Errors are swallowed: usage telemetry must never fail a turn.
    */
   private async accumulateUsage(st: SessionState, u: StepUsage): Promise<void> {
     if (u.input === 0 && u.output === 0 && u.cost === 0) return;
@@ -366,29 +631,13 @@ export class OpenCodeServerBackend implements AgentBackend {
   // ─── ensureSession: create-or-resume against agent_sessions (1.5) ────────────
 
   async ensureSession(sessionId: string, opts: EnsureSessionOpts): Promise<AgentSessionHandle> {
-    // Coalesce concurrent first-turns for the same (chat, agent) so the SELECT…
+    await this.ensureServer();
-    // create…upsert can't race into two opencode sessions (the second orphaning
+    if (!this.client) throw new Error('opencode-server: client not ready after ensureServer');
-    // the first). A single (non-concurrent) call is unaffected — the entry is set
-    // and removed within this call. Defensive: the dispatcher already serializes
-    // turns per (chat, agent) via its inflight map.
-    const key = `${opts.chatId}:${opts.agent}`;
-    const existing = this.ensuring.get(key);
-    if (existing) return existing;
-    const p = this.ensureSessionInner(sessionId, opts).finally(() => {
-      if (this.ensuring.get(key) === p) this.ensuring.delete(key);
-    });
-    this.ensuring.set(key, p);
-    return p;
-  }
-
-  private async ensureSessionInner(sessionId: string, opts: EnsureSessionOpts): Promise<AgentSessionHandle> {
-    await this.supervisor.ensureServer();
-    const client = this.supervisor.client;
-    if (!client) throw new Error('opencode-server: client not ready after ensureServer');
 
     const configHash = sessionConfigHash(opts.model);
     // P1.5-b: agent_sessions is keyed (chat_id, agent) — the tab/chat is the
     // context unit (two tabs in one session = two contexts sharing one worktree).
+    // session_id + worktree_id are retained as informational (SET NULL) columns.
     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 chat_id = ${opts.chatId} AND agent = ${opts.agent}
@@ -406,7 +655,7 @@ export class OpenCodeServerBackend implements AgentBackend {
           'opencode-server: not resuming stale session, creating fresh');
         this.byOpencodeId.delete(agentSessionId);
       }
-      const created = await client.session.create({ directory: opts.worktreePath });
+      const created = await this.client.session.create({ directory: opts.worktreePath });
       if (created.error || !created.data) {
         throw new Error(`opencode-server: session.create failed: ${errToString(created.error)}`);
       }
@@ -415,7 +664,7 @@ export class OpenCodeServerBackend implements AgentBackend {
         INSERT INTO agent_sessions
           (chat_id, session_id, worktree_id, agent, backend, agent_session_id, server_port, status, last_active_at, config_hash)
         VALUES
-          (${opts.chatId}, ${sessionId}, ${opts.worktreeId}, ${opts.agent}, 'opencode_server', ${agentSessionId}, ${this.supervisor.port}, 'active', clock_timestamp(), ${configHash})
+          (${opts.chatId}, ${sessionId}, ${opts.worktreeId}, ${opts.agent}, 'opencode_server', ${agentSessionId}, ${this.port}, 'active', clock_timestamp(), ${configHash})
         ON CONFLICT (chat_id, agent) DO UPDATE SET
           session_id = EXCLUDED.session_id,
           worktree_id = EXCLUDED.worktree_id,
@@ -429,7 +678,7 @@ export class OpenCodeServerBackend implements AgentBackend {
     } else {
       await this.sql`
         UPDATE agent_sessions
-        SET status = 'active', last_active_at = clock_timestamp(), server_port = ${this.supervisor.port}, config_hash = ${configHash}
+        SET status = 'active', last_active_at = clock_timestamp(), server_port = ${this.port}, config_hash = ${configHash}
         WHERE chat_id = ${opts.chatId} AND agent = ${opts.agent}
       `;
     }
@@ -444,13 +693,24 @@ export class OpenCodeServerBackend implements AgentBackend {
       state.boocodeSessionId = sessionId;
       state.worktreePath = opts.worktreePath;
     } else {
-      state = this.makeSessionState(sessionId, ocSessionId, opts.worktreePath);
+      state = {
+        boocodeSessionId: sessionId,
+        agentSessionId: ocSessionId,
+        worktreePath: opts.worktreePath,
+        streamedPartKeys: new Set(),
+        partTypeById: new Map(),
+        activeTurn: null,
+        watchdog: null,
+        sseAbort: null,
+        swallowNextTerminal: false,
+      };
       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.
+    // fresh-create and resume reach here; idempotent, so a re-ensure (e.g. a
-    startSessionEventLoop(state, this.sseDeps());
+    // second turn) won't spawn a duplicate loop.
+    this.startSessionEventLoop(state);
 
     return {
       sessionId,
@@ -459,53 +719,40 @@ export class OpenCodeServerBackend implements AgentBackend {
       chatId: opts.chatId,
       worktreeId: opts.worktreeId,
       agentSessionId: ocSessionId,
-      serverPort: this.supervisor.port,
+      serverPort: this.port,
-    };
-  }
-
-  /** Fresh per-(opencode session) demux state. */
-  private makeSessionState(boocodeSessionId: string, agentSessionId: string, worktreePath: string): SessionState {
-    return {
-      boocodeSessionId,
-      agentSessionId,
-      worktreePath,
-      streamedPartKeys: new Set(),
-      partTypeById: new Map(),
-      activeTurn: null,
-      watchdog: null,
-      sseAbort: null,
-      swallowNextTerminal: false,
     };
   }
 
   // ─── prompt: send one turn (1.6) ─────────────────────────────────────────────
 
   async prompt(handle: AgentSessionHandle, input: string, ctx: PromptCtx): Promise<TurnResult> {
-    const client = this.supervisor.client;
+    if (!this.client) throw new Error('opencode-server: client not ready');
-    if (!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 = this.makeSessionState(handle.sessionId, oc, ctx.worktreePath);
+      state = {
+        boocodeSessionId: handle.sessionId,
+        agentSessionId: oc,
+        worktreePath: ctx.worktreePath,
+        streamedPartKeys: new Set(),
+        partTypeById: new Map(),
+        activeTurn: null,
+        watchdog: null,
+        sseAbort: null,
+        swallowNextTerminal: false,
+      };
       this.byOpencodeId.set(oc, state);
     }
     const session = state;
-
-    // v2.7 busy-assert: one in-flight turn per session. The dispatcher serializes
-    // turns per (chat, agent), so this never fires in normal dispatch — but if a
-    // second prompt arrives while one is live it would silently overwrite the slot
-    // and orphan the first turn, so reject instead.
-    if (session.activeTurn) {
-      return { ok: false, error: 'opencode-server: session already has an in-flight turn' };
-    }
-
     // 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.
-    startSessionEventLoop(session, this.sseDeps());
+    // Idempotent when ensureSession already started one.
+    this.startSessionEventLoop(session);
+    const client = this.client;
 
     return await new Promise<TurnResult>((resolve) => {
       let settled = false;
@@ -534,8 +781,7 @@ export class OpenCodeServerBackend implements AgentBackend {
         settle({ ok: false, error: 'aborted' });
       };
 
-      const turn: TurnState = { onEvent: ctx.onEvent, settle };
+      session.activeTurn = { onEvent: ctx.onEvent, settle };
-      session.activeTurn = turn;
       this.bumpActivity(session); // arm the inactivity backstop
 
       if (ctx.signal.aborted) {
@@ -576,15 +822,39 @@ export class OpenCodeServerBackend implements AgentBackend {
   }
 
   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();
-    await this.supervisor.dispose();
+    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;
@@ -594,14 +864,199 @@ function parseModel(model: string | undefined): { providerID: string; modelID: s
     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;
+  }
+}
+
+/**
+ * Reclaim a loopback port a dead opencode child may still hold (lift of
+ * openchamber `killProcessOnPort`). Best-effort, POSIX-only (`lsof`/`kill`); a
+ * failure is harmless because the next spawn allocates a fresh ephemeral port.
+ * Never kills this process. Synchronous + short-timeout so the crash handler
+ * doesn't block.
+ */
+function reclaimPort(port: number | null): void {
+  if (!port || process.platform === 'win32') return;
+  try {
+    const res = spawnSync('lsof', ['-ti', `:${port}`], { encoding: 'utf8', timeout: 3_000, windowsHide: true });
+    const out = res.stdout || '';
+    const myPid = process.pid;
+    for (const pidStr of out.split(/\s+/)) {
+      const pid = parseInt(pidStr.trim(), 10);
+      if (pid && pid !== myPid) {
+        try {
+          spawnSync('kill', ['-9', String(pid)], { stdio: 'ignore', timeout: 2_000 });
+        } catch {
+          // ignore — best effort
+        }
+      }
+    }
+  } catch {
+    // lsof absent or failed — the fresh-ephemeral-port spawn doesn't need this.
+  }
+}
+
+/**
+ * Resolve true once nothing is listening on `port` (lift of openchamber
+ * `waitForPortRelease`). Used before re-spawning on a fixed port; with ephemeral
+ * ports it's a fast no-op. Probes 127.0.0.1; resolves false at the deadline.
+ */
+function waitForPortRelease(port: number, timeoutMs: number): Promise<boolean> {
+  const deadline = Date.now() + timeoutMs;
+  return new Promise((resolve) => {
+    const attempt = () => {
+      const socket = netConnect({ port, host: '127.0.0.1' });
+      let settled = false;
+      const finish = (released: boolean) => {
+        if (settled) return;
+        settled = true;
+        socket.removeAllListeners();
+        socket.destroy();
+        if (released || Date.now() >= deadline) {
+          resolve(released);
+          return;
+        }
+        setTimeout(attempt, 150);
+      };
+      socket.once('connect', () => finish(false));
+      socket.once('error', (err: NodeJS.ErrnoException) => {
+        if (err && (err.code === 'ECONNREFUSED' || err.code === 'EHOSTUNREACH')) finish(true);
+        else finish(false);
+      });
+      socket.setTimeout(500, () => finish(true));
+    };
+    attempt();
+  });
+}
+
+/** 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: ${stderrBuf.slice(-2000)}`)),
+      timeoutMs,
+    );
+
+    child.stdout?.on('data', onOut);
+    child.stderr?.on('data', onErr);
+    child.on('exit', onExit);
+  });
+}
+
+function sleep(ms: number): Promise<void> {
+  return new Promise((r) => setTimeout(r, ms));
+}
+
+/** Strip opencode-dcp plugin tags that render as literal text in the UI. */
+function stripDcpTags(s: string): string {
+  return s.replace(/<dcp-message-id>[^<]*<\/dcp-message-id>/g, '');
+}
+
+function errMsg(e: unknown): string {
+  return e instanceof Error ? e.message : String(e);
+}
+
+function errToString(e: unknown): string {
+  if (e == null) return 'unknown error';
+  if (typeof e === 'string') return e;
+  if (e instanceof Error) return e.message;
+  try {
+    return JSON.stringify(e);
+  } catch {
+    return String(e);
+  }
+}
+
 /** Hash of stable config — detects model changes across sessions without
- *  invalidating on ephemeral state like the random server port. */
+ *  invalidating on ephemeral state like the random server port (which changes
+ *  every BooCoder restart). */
 function sessionConfigHash(model: string): string {
   return createHash('sha256').update(`opencode_server|${model}`).digest('hex').slice(0, 16);
 }

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

@@ -1,181 +0,0 @@
-/**
- * Per-session SSE subscribe loop + reconnect/backoff + eventSessionId demux.
- *
- * Extracted (v2.7 audit reshape) from `OpenCodeServerBackend.startSessionEventLoop`
- * / `runSessionEventLoop`. opencode scopes events by the `directory` query param, so
- * each session runs its own dir-scoped stream and never drops a sibling's events.
- *
- * The loop is intentionally thin: it owns subscribe + the demux filter + reconnect
- * timing only. Translating an event into turn side effects (watchdog, usage,
- * settle) stays on the backend via the injected `dispatchEvent` / `reconcile`
- * callbacks — `opencode-sse` knows nothing about turns or the DB.
- *
- * v2.7 concurrency hardening: the throw-driven reconnect path now backs off
- * exponentially and trips a circuit-breaker (`onReconnectGiveUp`) after a bounded
- * number of consecutive failures, instead of looping forever at a flat 1s. The
- * HAPPY PATH is unchanged — a clean stream end (server still up) reconnects after
- * `baseMs` (1s, as before) and resets the failure counter, so a long-lived session
- * that re-subscribes normally never backs off.
- */
-import type { FastifyBaseLogger } from 'fastify';
-import type { Event, OpencodeClient } from '@opencode-ai/sdk/v2/client';
-import type { AgentEvent } from '../agent-backend.js';
-import type { TurnResult } from '../agent-backend.js';
-import { eventSessionId, errMsg } from './opencode-event-map.js';
-
-export const SSE_RECONNECT_DELAY_MS = 1_000;
-
-/** One in-flight turn's emitter + completion settler. */
-export interface TurnState {
-  onEvent: (e: AgentEvent) => void;
-  settle: (r: TurnResult) => void;
-}
-
-/** Per-(opencode session) demux state. dedup sets scoped here, cleared per turn. */
-export 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;
-  /** F.1 post-abort orphan-terminal guard: swallow the one session.idle/error
-   *  opencode emits for an aborted turn so it can't settle the next turn. */
-  swallowNextTerminal: boolean;
-}
-
-// ─── reconnect backoff (pure) ────────────────────────────────────────────────
-
-export interface ReconnectPolicy {
-  /** First retry delay (and the steady-state clean-reconnect delay). */
-  baseMs: number;
-  /** Cap on the exponential delay. */
-  maxMs: number;
-  /** Consecutive failures tolerated before the breaker trips (give up). */
-  maxAttempts: number;
-}
-
-export const DEFAULT_RECONNECT_POLICY: ReconnectPolicy = {
-  baseMs: SSE_RECONNECT_DELAY_MS,
-  maxMs: 30_000,
-  maxAttempts: 6,
-};
-
-export type ReconnectDecision =
-  | { action: 'reconnect'; delayMs: number }
-  | { action: 'give-up' };
-
-/**
- * Pure backoff decision after `failures` consecutive throwing reconnect attempts
- * (1-based: the first failure passes `failures=1`). Returns an exponentially
- * growing delay capped at `maxMs`, or `give-up` once the count exceeds
- * `maxAttempts`. `failures=1` yields `baseMs`, so the very first retry matches the
- * pre-hardening flat delay (happy-path-preserving).
- */
-export function reconnectDecision(
-  failures: number,
-  policy: ReconnectPolicy = DEFAULT_RECONNECT_POLICY,
-): ReconnectDecision {
-  if (failures > policy.maxAttempts) return { action: 'give-up' };
-  const exp = policy.baseMs * 2 ** (failures - 1);
-  return { action: 'reconnect', delayMs: Math.min(policy.maxMs, exp) };
-}
-
-// ─── the loop ────────────────────────────────────────────────────────────────
-
-export interface SseLoopDeps {
-  /** Live iff the server is up (read each iteration so a crash stops the loop). */
-  isUp: () => boolean;
-  /** The current opencode client (null between server restarts). */
-  getClient: () => OpencodeClient | null;
-  /** Route one demuxed event to its turn (backend side effects live here). */
-  dispatchEvent: (ev: Event) => void;
-  /** Recover an idle/error lost during an SSE gap. Returns true if it settled. */
-  reconcile: (state: SessionState) => Promise<boolean>;
-  /** Circuit-breaker: called once the backoff gives up; fail the active turn. */
-  onReconnectGiveUp: (state: SessionState) => Promise<void> | void;
-  log: FastifyBaseLogger;
-  /** Injectable for tests; defaults to a real timer sleep. */
-  sleep?: (ms: number) => Promise<void>;
-  policy?: ReconnectPolicy;
-}
-
-function defaultSleep(ms: number): Promise<void> {
-  return new Promise((r) => setTimeout(r, ms));
-}
-
-/** Per-session SSE subscription, scoped to the session's worktree directory.
- *  Idempotent: a no-op if this session's loop is already running. */
-export function startSessionEventLoop(state: SessionState, deps: SseLoopDeps): void {
-  if (state.sseAbort) return; // already running
-  const abort = new AbortController();
-  state.sseAbort = abort;
-  void runSessionEventLoop(state, abort, deps).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;
-  });
-}
-
-export async function runSessionEventLoop(
-  state: SessionState,
-  abort: AbortController,
-  deps: SseLoopDeps,
-): Promise<void> {
-  const signal = abort.signal;
-  const sleep = deps.sleep ?? defaultSleep;
-  const policy = deps.policy ?? DEFAULT_RECONNECT_POLICY;
-  let failures = 0;
-  while (deps.isUp() && deps.getClient() && !signal.aborted) {
-    const client = deps.getClient()!;
-    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 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;
-        deps.dispatchEvent(ev);
-      }
-      // Clean stream end — a healthy reconnect, NOT a failure: recover any lost
-      // terminal then re-subscribe at the base delay (pre-hardening behavior).
-      failures = 0;
-      if (deps.isUp() && !signal.aborted) {
-        await deps.reconcile(state); // recover an idle/error lost during the gap
-        await sleep(policy.baseMs);
-      }
-    } catch (err) {
-      if (!deps.isUp() || signal.aborted) break;
-      failures += 1;
-      const decision = reconnectDecision(failures, policy);
-      deps.log.warn(
-        { err: errMsg(err), agentSessionId: state.agentSessionId, failures, action: decision.action },
-        'opencode-server: session event loop error; reconnecting',
-      );
-      await deps.reconcile(state);
-      if (decision.action === 'give-up') {
-        deps.log.warn(
-          { agentSessionId: state.agentSessionId, failures },
-          'opencode-server: SSE reconnect gave up (circuit breaker) — failing active turn',
-        );
-        await deps.onReconnectGiveUp(state);
-        break;
-      }
-      await sleep(decision.delayMs);
-    }
-  }
-}

apps/coder/src/services/backends/warm-acp.ts

@@ -36,15 +36,29 @@
  */
 import { spawn, type ChildProcess } from 'node:child_process';
 import type { FastifyBaseLogger } from 'fastify';
-import { ClientSideConnection, type Client } from '@agentclientprotocol/sdk';
+import {
+  ClientSideConnection,
+  type Client,
+  type SessionNotification,
+  type RequestPermissionRequest,
+  type RequestPermissionResponse,
+  type ReadTextFileRequest,
+  type ReadTextFileResponse,
+  type WriteTextFileRequest,
+  type WriteTextFileResponse,
+  type CreateTerminalRequest,
+  type CreateTerminalResponse,
+  type CreateElicitationRequest,
+  type CreateElicitationResponse,
+} from '@agentclientprotocol/sdk';
 import type { Sql } from '../../db.js';
 import { resolveLaunchSpec } from '../acp-spawn.js';
 import { isTurnOkForStopReason } from './warm-acp-routing.js';
 import { getResolvedRegistry, type ResolvedProviderDef } from '../provider-config-registry.js';
 import { createAcpNdJsonStream } from '../acp-stream.js';
 import { mapSessionUpdate } from '../acp-event-map.js';
-import { buildAcpClient } from '../acp-client.js';
+import { readWorktreeTextFile, writeWorktreeTextFile } from '../acp-client-fs.js';
-import { cancelPendingPermission } from '../permission-waiter.js';
+import { waitForPermissionResponse, waitForElicitationResponse, cancelPendingPermission } from '../permission-waiter.js';
 import { type AcpToolSnapshot, synthesizeCanceledSnapshots } from '../acp-tool-snapshot.js';
 import type {
   AgentBackend,
@@ -197,25 +211,47 @@ export class WarmAcpBackend implements AgentBackend {
     );
   }
 
-  /** Build the ACP Client callbacks ONCE per connection (shared `buildAcpClient`).
+  /** Build the ACP Client callbacks ONCE per connection. They read `this.activeTurn`
-   *  `resolveTurn` reads `this.activeTurn` at each callback so events/permissions
+   *  so each turn's events/permissions route to the right place — exactly the
-   *  route to the live turn — exactly the prior behavior. The warm session always
+   *  opencode-server `activeTurn` pattern. Worktree-scoped FS like AcpStreamContext. */
-   *  has a non-empty `sessionId`, so the shared `taskId && sessionId` permission
-   *  gate is equivalent to the old `turn?.taskId` gate. */
   private buildClient(worktreePath: string): Client {
-    return buildAcpClient(worktreePath, () => {
+    return {
-      const turn = this.activeTurn;
+      sessionUpdate: async (params: SessionNotification): Promise<void> => {
-      if (!turn) return null;
+        const turn = this.activeTurn;
-      return {
+        if (!turn) return; // between turns — drop (no orphan settles a future turn)
-        taskId: turn.taskId,
+        for (const event of mapSessionUpdate(params, turn.snapshots)) {
-        sessionId: turn.sessionId,
+          turn.onEvent(event);
-        modeId: turn.modeId,
+        }
-        agent: this.agent,
+      },
-        onSessionUpdate: (params) => {
+      requestPermission: async (params: RequestPermissionRequest): Promise<RequestPermissionResponse> => {
-          for (const event of mapSessionUpdate(params, turn.snapshots)) turn.onEvent(event);
+        const turn = this.activeTurn;
-        },
+        if (turn?.taskId) {
-      };
+          // Route to the UI via the per-turn task id (same as the one-shot path).
-    });
+          return waitForPermissionResponse(turn.taskId, turn.sessionId, this.agent, turn.modeId, params);
+        }
+        const firstOption = params.options[0];
+        if (firstOption) return { outcome: { outcome: 'selected', optionId: firstOption.optionId } };
+        return { outcome: { outcome: 'cancelled' } };
+      },
+      readTextFile: async (params: ReadTextFileRequest): Promise<ReadTextFileResponse> => {
+        const content = await readWorktreeTextFile(worktreePath, params.path, params.line, params.limit);
+        return { content };
+      },
+      writeTextFile: async (params: WriteTextFileRequest): Promise<WriteTextFileResponse> => {
+        await writeWorktreeTextFile(worktreePath, params.path, params.content);
+        return {};
+      },
+      createTerminal: async (_params: CreateTerminalRequest): Promise<CreateTerminalResponse> => {
+        return { terminalId: 'noop' };
+      },
+      unstable_createElicitation: async (params: CreateElicitationRequest): Promise<CreateElicitationResponse> => {
+        const turn = this.activeTurn;
+        if (turn?.taskId) {
+          return waitForElicitationResponse(turn.taskId, turn.sessionId, this.agent, turn.modeId, params);
+        }
+        return { action: 'decline' };
+      },
+    };
   }
 
   // ─── ensureSession: create-or-reuse the warm session (2.1) ───────────────────
@@ -267,14 +303,6 @@ export class WarmAcpBackend implements AgentBackend {
       return { ok: false, error: 'warm-acp: no live ACP connection' };
     }
 
-    // v2.7 busy-assert: one in-flight turn per warm session. The dispatcher
-    // serializes turns per (chat, agent), so this never fires in normal dispatch —
-    // but a second concurrent prompt would silently overwrite `activeTurn` and
-    // orphan the first turn, so reject instead.
-    if (this.activeTurn) {
-      return { ok: false, error: 'warm-acp: session already has an in-flight turn' };
-    }
-
     const snapshots = new Map<string, AcpToolSnapshot>();
     // taskId routes permission/elicitation prompts back to the UI. The dispatcher
     // passes it (plus mode) on the per-turn PromptCtx; permission-waiter keys on it.

apps/coder/src/services/dispatcher.ts

@@ -1,7 +1,7 @@
 import type { Sql } from '../db.js';
 import type { FastifyBaseLogger } from 'fastify';
 import type { Broker } from '@boocode/server/broker';
-import type { WsFrame } from '@boocode/server/ws-frames';
+import type { WsFrame } from '@boocode/contracts/ws-frames';
 import type { Config } from '../config.js';
 import { createWorktree, diffWorktree, cleanupWorktree, ensureSessionWorktree } from './worktrees.js';
 import { createCheckpoint } from './checkpoints.js';

apps/coder/src/services/frame-emitter.ts

@@ -1,142 +0,0 @@
-/**
- * AgentEvent → WS-frame emitter + turn accumulators.
- *
- * Extracted (v2.7 audit reshape) from `AcpStreamContext.handleSessionUpdate` in
- * `acp-dispatch.ts` — the `AgentEvent → broker.publishFrame` switch that maps a
- * backend's normalized events onto the wire frames the UI consumes, while
- * accumulating the turn's text / reasoning / tool snapshots for persistence.
- *
- * The same shape backs the dispatcher's 4 inline `onEvent` copies (DEFERRED while
- * dispatcher.ts has uncommitted edits), hence the optional `dcp` stripper + the
- * `finalize()` flush: the opencode dispatch path strips dcp tags from text deltas,
- * the ACP path does not (passes no `dcp`, so text is emitted verbatim — identical
- * to the prior AcpStreamContext behavior).
- *
- * Publishing is gated on `canStream()` (all of broker/sessionId/chatId/assistantId
- * present) exactly as the original — a one-shot dispatch with no broker accumulates
- * but never publishes.
- */
-import type { Broker } from '@boocode/server/broker';
-import type { WsFrame } from '@boocode/server/ws-frames';
-import type { AgentEvent } from './agent-backend.js';
-import { type AcpToolSnapshot, snapshotToWireToolCall } from './acp-tool-snapshot.js';
-import { mergeTaskCommands, getTaskCommands } from './agent-commands-cache.js';
-import type { DcpStreamStripper } from './dcp-strip.js';
-
-export interface FrameEmitterOpts {
-  broker?: Broker;
-  sessionId?: string;
-  chatId?: string;
-  /** The assistant message id — the frames' `message_id`. */
-  assistantId?: string;
-  /** Per-turn task id, for the agent_commands frame + command cache. */
-  taskId?: string;
-  /** Optional cross-chunk dcp stripper for text deltas (opencode path). When
-   *  provided, text is stripped before push/publish and `finalize()` flushes the
-   *  held-back tail. The ACP path passes none → text emitted verbatim. */
-  dcp?: DcpStreamStripper;
-}
-
-export interface FrameEmitter {
-  /** Map one AgentEvent to its WS frame(s) + accumulate it. */
-  onEvent: (e: AgentEvent) => void;
-  /** Flush a dcp stripper's held-back tail at turn end (no-op without `dcp`). */
-  finalize: () => void;
-  /** The merge accumulator for tool snapshots (toolCallId → snapshot). */
-  readonly toolSnapshots: Map<string, AcpToolSnapshot>;
-  /** Accumulated assistant text (post-dcp-strip when a stripper is set). */
-  readonly output: string;
-  /** Accumulated reasoning text. */
-  readonly reasoningText: string;
-  /** Tool snapshots in insertion order. */
-  readonly snapshots: AcpToolSnapshot[];
-}
-
-export function makeFrameEmitter(opts: FrameEmitterOpts): FrameEmitter {
-  const { broker, sessionId, chatId, assistantId, taskId, dcp } = opts;
-  const textChunks: string[] = [];
-  const reasoningChunks: string[] = [];
-  const toolSnapshots = new Map<string, AcpToolSnapshot>();
-
-  const canStream = (): boolean => !!(broker && sessionId && chatId && assistantId);
-
-  const publishText = (content: string): void => {
-    textChunks.push(content);
-    if (canStream()) {
-      broker!.publishFrame(sessionId!, {
-        type: 'delta',
-        message_id: assistantId!,
-        chat_id: chatId!,
-        content,
-      } as WsFrame);
-    }
-  };
-
-  const onEvent = (e: AgentEvent): void => {
-    switch (e.type) {
-      case 'text': {
-        const safe = dcp ? dcp.push(e.text) : e.text;
-        if (safe) publishText(safe);
-        break;
-      }
-      case 'reasoning':
-        reasoningChunks.push(e.text);
-        if (canStream()) {
-          broker!.publishFrame(sessionId!, {
-            type: 'reasoning_delta',
-            message_id: assistantId!,
-            chat_id: chatId!,
-            content: e.text,
-          } as WsFrame);
-        }
-        break;
-      case 'tool_call':
-      case 'tool_update':
-        toolSnapshots.set(e.toolCall.toolCallId, e.toolCall);
-        if (canStream()) {
-          broker!.publishFrame(sessionId!, {
-            type: 'tool_call',
-            message_id: assistantId!,
-            chat_id: chatId!,
-            tool_call: snapshotToWireToolCall(e.toolCall),
-          } as WsFrame);
-        }
-        break;
-      case 'commands':
-        if (taskId && e.commands.length > 0) {
-          mergeTaskCommands(taskId, e.commands);
-          if (canStream() && sessionId) {
-            const all = getTaskCommands(taskId) ?? e.commands;
-            broker!.publishFrame(sessionId, {
-              type: 'agent_commands',
-              task_id: taskId,
-              session_id: sessionId,
-              commands: all,
-            } as WsFrame);
-          }
-        }
-        break;
-    }
-  };
-
-  const finalize = (): void => {
-    if (!dcp) return;
-    const tail = dcp.flush();
-    if (tail) publishText(tail);
-  };
-
-  return {
-    onEvent,
-    finalize,
-    toolSnapshots,
-    get output() {
-      return textChunks.join('');
-    },
-    get reasoningText() {
-      return reasoningChunks.join('');
-    },
-    get snapshots() {
-      return [...toolSnapshots.values()];
-    },
-  };
-}

apps/coder/src/services/mcp-server.ts

@@ -25,6 +25,13 @@ interface PendingRow {
   session_id: string;
 }
 
+interface WorktreeRow {
+  id: string;
+  worktree_path: string;
+  agent: string;
+  started_at: string;
+}
+
 interface ProjectPathRow {
   path: string;
 }
@@ -189,6 +196,28 @@ export async function startMcpServer(sql: Sql): Promise<void> {
     },
   );
 
+  // 6. boocoder.list_worktrees
+  server.tool(
+    'boocoder.list_worktrees',
+    'List active worktrees from running tasks',
+    {},
+    async () => {
+      const rows = await sql<WorktreeRow[]>`
+        SELECT id, worktree_path, agent, started_at
+        FROM tasks
+        WHERE worktree_path IS NOT NULL AND state = 'running'
+        ORDER BY started_at DESC
+      `;
+      const items = rows.map((r) => ({
+        task_id: r.id,
+        worktree_path: r.worktree_path,
+        agent: r.agent,
+        started_at: r.started_at,
+      }));
+      return textResult(items);
+    },
+  );
+
   // Connect via stdio
   const transport = new StdioServerTransport();
   await server.connect(transport);

apps/coder/src/services/net/port-utils.ts

@@ -1,88 +0,0 @@
-/**
- * Generic POSIX loopback-port utilities.
- *
- * Extracted verbatim (v2.7 audit reshape) from `backends/opencode-server.ts`,
- * where they were embedded in the backend god-class. They have nothing to do with
- * opencode semantics — they reclaim/await/allocate a 127.0.0.1 port — so they live
- * here as reusable infra. No behavior change from the original.
- */
-import { createServer, connect as netConnect } from 'node:net';
-import { spawnSync } from 'node:child_process';
-
-/**
- * Reclaim a loopback port a dead child may still hold (lift of openchamber
- * `killProcessOnPort`). Best-effort, POSIX-only (`lsof`/`kill`); a failure is
- * harmless because the next spawn allocates a fresh ephemeral port. Never kills
- * this process. Synchronous + short-timeout so a crash handler doesn't block.
- */
-export function reclaimPort(port: number | null): void {
-  if (!port || process.platform === 'win32') return;
-  try {
-    const res = spawnSync('lsof', ['-ti', `:${port}`], { encoding: 'utf8', timeout: 3_000, windowsHide: true });
-    const out = res.stdout || '';
-    const myPid = process.pid;
-    for (const pidStr of out.split(/\s+/)) {
-      const pid = parseInt(pidStr.trim(), 10);
-      if (pid && pid !== myPid) {
-        try {
-          spawnSync('kill', ['-9', String(pid)], { stdio: 'ignore', timeout: 2_000 });
-        } catch {
-          // ignore — best effort
-        }
-      }
-    }
-  } catch {
-    // lsof absent or failed — the fresh-ephemeral-port spawn doesn't need this.
-  }
-}
-
-/**
- * Resolve true once nothing is listening on `port` (lift of openchamber
- * `waitForPortRelease`). Used before re-spawning on a fixed port; with ephemeral
- * ports it's a fast no-op. Probes 127.0.0.1; resolves false at the deadline.
- */
-export function waitForPortRelease(port: number, timeoutMs: number): Promise<boolean> {
-  const deadline = Date.now() + timeoutMs;
-  return new Promise((resolve) => {
-    const attempt = () => {
-      const socket = netConnect({ port, host: '127.0.0.1' });
-      let settled = false;
-      const finish = (released: boolean) => {
-        if (settled) return;
-        settled = true;
-        socket.removeAllListeners();
-        socket.destroy();
-        if (released || Date.now() >= deadline) {
-          resolve(released);
-          return;
-        }
-        setTimeout(attempt, 150);
-      };
-      socket.once('connect', () => finish(false));
-      socket.once('error', (err: NodeJS.ErrnoException) => {
-        if (err && (err.code === 'ECONNREFUSED' || err.code === 'EHOSTUNREACH')) finish(true);
-        else finish(false);
-      });
-      socket.setTimeout(500, () => finish(true));
-    };
-    attempt();
-  });
-}
-
-/** Bind-probe an ephemeral port on loopback. */
-export 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('port-utils: could not determine a free port')));
-      }
-    });
-  });
-}

apps/coder/src/services/normalize-agent-status.ts

@@ -21,3 +21,72 @@
  */
 
 export type AgentStatus = 'working' | 'blocked' | 'idle' | 'error';
+
+/** The coarse signal a raw vendor event collapses to. */
+export type AgentEventBucket = 'working' | 'blocked' | 'done';
+
+// Each bucket lists the canonical vendor event names. Lookup is
+// case-insensitive AND separator-insensitive (snake_case / camelCase /
+// PascalCase all fold to the same key), so we normalize the raw input the same
+// way before matching rather than enumerating every spelling here.
+const WORKING_EVENTS = [
+  'SessionStart',
+  'UserPromptSubmit',
+  'UserPromptSubmitted',
+  'PostToolUse',
+  'PostToolUseFailure',
+  'BeforeAgent',
+  'AfterTool',
+  'task_started',
+] as const;
+
+const BLOCKED_EVENTS = [
+  'PreToolUse',
+  'Notification',
+  'PermissionRequest',
+  'exec_approval_request',
+  'apply_patch_approval_request',
+  'request_user_input',
+] as const;
+
+const DONE_EVENTS = [
+  'Stop',
+  'AfterAgent',
+  'SessionEnd',
+  'task_complete',
+  'agent-turn-complete',
+] as const;
+
+/**
+ * Fold a raw event name to a separator/case-insensitive key:
+ * strip every non-alphanumeric character and lowercase. So `post_tool_use`,
+ * `postToolUse`, `PostToolUse`, and `POST-TOOL-USE` all map to `posttooluse`.
+ */
+function foldKey(raw: string): string {
+  return raw.replace(/[^a-z0-9]/gi, '').toLowerCase();
+}
+
+function buildLookup(
+  groups: ReadonlyArray<readonly [AgentEventBucket, readonly string[]]>,
+): Map<string, AgentEventBucket> {
+  const map = new Map<string, AgentEventBucket>();
+  for (const [bucket, names] of groups) {
+    for (const name of names) map.set(foldKey(name), bucket);
+  }
+  return map;
+}
+
+const EVENT_LOOKUP = buildLookup([
+  ['working', WORKING_EVENTS],
+  ['blocked', BLOCKED_EVENTS],
+  ['done', DONE_EVENTS],
+]);
+
+/**
+ * Map a raw vendor hook-event name to its normalized bucket, or `null` when the
+ * name is unknown / undefined. Case- and separator-insensitive.
+ */
+export function normalizeAgentEvent(raw: string | undefined): AgentEventBucket | null {
+  if (!raw) return null;
+  return EVENT_LOOKUP.get(foldKey(raw)) ?? null;
+}

apps/coder/src/services/orphan-worktree-reaper.ts

@@ -21,8 +21,7 @@ import { readdir, stat } from 'node:fs/promises';
 import { join } from 'node:path';
 import type { FastifyBaseLogger } from 'fastify';
 import type { Sql } from '../db.js';
-import { WORKTREE_BASE } from './worktrees.js';
+import { WORKTREE_BASE, checkWorktreeWorkAtRisk } from './worktrees.js';
-import { checkWorktreeWorkAtRisk } from './worktree-risk.js';
 import { hostExec } from './host-exec.js';
 import {
   selectOrphanWorktreeTargets,

apps/coder/src/services/pending_changes.ts

@@ -181,6 +181,10 @@ export async function rejectOne(sql: Sql, changeId: string): Promise<void> {
   await sql`UPDATE pending_changes SET status = 'rejected' WHERE id = ${changeId} AND status = 'pending'`;
 }
 
+export async function rejectAll(sql: Sql, sessionId: string): Promise<void> {
+  await sql`UPDATE pending_changes SET status = 'rejected' WHERE session_id = ${sessionId} AND status = 'pending'`;
+}
+
 // --- Rewind functions --------------------------------------------------------
 
 export async function rewindOne(

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

@@ -127,3 +127,7 @@ export function getResolvedRegistry(): Map<string, ResolvedProviderDef> {
   return cachedRegistry ?? buildResolvedRegistry(PROVIDERS, { providers: {} });
 }
 
+/** Resolved provider ids in registry order. */
+export function getResolvedProviderIds(): string[] {
+  return [...getResolvedRegistry().keys()];
+}

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

@@ -5,42 +5,28 @@
  * (see provider-config-registry.ts). Loading NEVER throws at startup (design.md
  * §2.1): a missing file, invalid JSON, or schema mismatch all fall back to
  * `{ providers: {} }` (built-ins only, all enabled).
+ *
+ * Schemas are defined once in @boocode/contracts/provider-config and re-exported
+ * here so existing importers (routes, tests, registry) don't need path changes.
  */
 import { readFileSync, writeFileSync } from 'node:fs';
-import { z } from 'zod';
+import {
+  ProviderOverrideSchema,
+  CoderProvidersFileSchema,
+  ProviderConfigPatchSchema,
+  type ProviderOverride,
+  type CoderProvidersFile,
+  type ProviderConfigPatch,
+} from '@boocode/contracts/provider-config';
 
-// Schemas verbatim from design.md §2.2.
+export {
-export const ProviderOverrideSchema = z.object({
+  ProviderOverrideSchema,
-  extends: z.enum(['acp']).optional(), // v2.3: only 'acp' for custom; built-ins omit extends
+  CoderProvidersFileSchema,
-  label: z.string().min(1).optional(),
+  ProviderConfigPatchSchema,
-  description: z.string().optional(),
+  type ProviderOverride,
-  command: z.array(z.string().min(1)).min(1).optional(), // [binary, ...args]
+  type CoderProvidersFile,
-  env: z.record(z.string()).optional(),
+  type ProviderConfigPatch,
-  enabled: z.boolean().optional(), // default true
+};
-  order: z.number().int().optional(), // UI sort key
-  models: z.array(z.object({ id: z.string(), label: z.string() })).optional(),
-  additionalModels: z.array(z.object({ id: z.string(), label: z.string() })).optional(),
-});
-
-export const CoderProvidersFileSchema = z.object({
-  providers: z.record(ProviderOverrideSchema).default({}),
-});
-
-export type ProviderOverride = z.infer<typeof ProviderOverrideSchema>;
-export type CoderProvidersFile = z.infer<typeof CoderProvidersFileSchema>;
-
-/**
- * PATCH body schema (design.md §6.2). A partial providers map where each value
- * is either a full override object (REPLACES that id's override) or `null`
- * (DELETES the override → revert to the built-in default). Ids absent from the
- * patch are left untouched. The route validates the body against this first
- * (malformed → 422) so a bad shape can never reach the merge/save step.
- */
-export const ProviderConfigPatchSchema = z.object({
-  providers: z.record(ProviderOverrideSchema.nullable()).default({}),
-});
-
-export type ProviderConfigPatch = z.infer<typeof ProviderConfigPatchSchema>;
 
 /**
  * Shallow per-id merge (design.md §6.2 / Paseo `patchConfig`). Each key in

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

@@ -1,61 +1,10 @@
-/** Shared provider / snapshot types (Paseo-shaped, BooCoder-native). */
+/** Provider snapshot types — re-exported from @boocode/contracts for local consumers. */
 
-export interface ProviderMode {
+export type {
-  id: string;
+  ProviderMode,
-  label: string;
+  ThinkingOption,
-  description?: string;
+  ProviderModel,
-  /** Auto-approve tool permissions when this mode is selected. */
+  ProviderSnapshotStatus,
-  isUnattended?: boolean;
+  AgentCommand,
-}
+  ProviderSnapshotEntry,
-
+} from '@boocode/contracts/provider-snapshot';
-export interface ThinkingOption {
-  id: string;
-  label: string;
-  isDefault?: boolean;
-}
-
-export interface ProviderModel {
-  id: string;
-  label: string;
-  description?: string;
-  isDefault?: boolean;
-  thinkingOptions?: ThinkingOption[];
-  defaultThinkingOptionId?: string;
-}
-
-// v2.3 phase 2: 'loading' (cache-miss, probe in flight) + 'unavailable'
-// (disabled or not installed) restored alongside the terminal 'ready' | 'error'.
-export type ProviderSnapshotStatus = 'loading' | 'ready' | 'unavailable' | 'error';
-
-export interface AgentCommand {
-  name: string;
-  description?: string;
-  // v2.5.11: 'skill' (plugin skill) vs 'command' (native/CLI slash command).
-  // Drives the icon split in the coder slash menu. Undefined → command.
-  kind?: 'command' | 'skill';
-}
-
-// KEEP IN SYNC with apps/web/src/api/types.ts ProviderSnapshotEntry — parity is
-// enforced by __tests__/provider-types-parity.test.ts (fails on any field drift).
-export interface ProviderSnapshotEntry {
-  name: string;
-  label: string;
-  description?: string;
-  transport: string;
-  status: ProviderSnapshotStatus;
-  enabled: boolean;
-  installed: boolean;
-  models: ProviderModel[];
-  modes: ProviderMode[];
-  defaultModeId: string | null;
-  commands: AgentCommand[];
-  error?: string;
-  fetchedAt?: string;
-}
-
-export interface AgentSessionConfig {
-  provider: string;
-  model?: string;
-  modeId?: string;
-  thinkingOptionId?: string;
-}

apps/coder/src/services/tools/index.ts

@@ -26,4 +26,9 @@ export const WRITE_TOOLS: readonly ToolDef<any>[] = [
   checkTaskStatusTool,
 ];
 
+// eslint-disable-next-line @typescript-eslint/no-explicit-any
+export const WRITE_TOOLS_BY_NAME: ReadonlyMap<string, ToolDef<any>> = new Map(
+  WRITE_TOOLS.map((t) => [t.name, t]),
+);
+
 export { editFileTool, createFileTool, deleteFileTool, applyPendingTool, rewindTool, newTaskTool, listTasksTool, checkTaskStatusTool };

apps/coder/src/services/worktree-risk.ts

@@ -1,175 +0,0 @@
-/**
- * Worktree work-at-risk assessment (split out of `worktrees.ts`, v2.7 audit
- * reshape). The git-worktree create/diff/remove lifecycle stays in `worktrees.ts`;
- * this module owns the orthogonal "would deleting this worktree lose work?" gate
- * the server consults before a session delete, plus the recoverable stash escape.
- *
- * Session delete itself lives in apps/server (Docker), which CANNOT see the host
- * worktree dirs or run git on them — only BooCoder (host systemd) can — so the
- * server calls the routes that wrap these helpers. Behavior is unchanged from the
- * original worktrees.ts implementation.
- */
-import { hostExec } from './host-exec.js';
-
-/**
- * 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
-  return "'" + s.replace(/'/g, "'\\''") + "'";
-}

apps/coder/src/services/worktrees.ts

@@ -8,7 +8,7 @@
  */
 import type { Sql } from '../db.js';
 import { hostExec } from './host-exec.js';
-import { checkWorktreeWorkAtRisk } from './worktree-risk.js';
+import type { WorktreeRiskReport } from '@boocode/contracts/worktree-risk';
 
 export const WORKTREE_BASE = '/tmp/booworktrees';
 
@@ -379,6 +379,151 @@ export async function rebaselineWorktreeAfterApply(
   return { rebaselined: true, newBaseCommit: newBase };
 }
 
+// ─── Session-delete work-loss guard ─────────────────────────────────────────
+// WorktreeRiskReport single-sourced in @boocode/contracts — edit the package, not here.
+export type { WorktreeRiskReport };
+
+/**
+ * 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<WorktreeRiskReport> {
+  // 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/coder/web/package.json

@@ -10,6 +10,7 @@
     "preview": "vite preview"
   },
   "dependencies": {
+    "@boocode/contracts": "workspace:*",
     "lucide-react": "^1.16.0",
     "react": "^18.3.1",
     "react-dom": "^18.3.1",

apps/coder/web/src/api/types.ts

@@ -1,5 +1,22 @@
 // Minimal types for the BooCoder frontend.
 // Shared DB entities (same schema as BooChat).
+//
+// WS wire contracts are single-sourced from @boocode/contracts (the canonical
+// Zod-backed schema). The DB entity types below (Project/Session/Chat/Message/
+// ToolCall/ToolResult/PendingChange) are an intentional minimal SPA-local subset
+// and are NOT cross-app contracts — they stay defined here.
+
+import type { WsFrame } from '@boocode/contracts/ws-frames';
+
+// Re-export the canonical WebSocket frame union (single source of truth). The
+// coder backend publishes the full frame set; this SPA's reducer handles the
+// subset it renders and ignores the rest.
+export type { WsFrame };
+
+// The error frame's `reason`, single-sourced from the canonical schema's
+// frame-level reason enum (derived from WsFrame so it cannot drift from the
+// wire). Distinct from message-metadata's ErrorReason, which is a different set.
+export type ErrorReason = NonNullable<Extract<WsFrame, { type: 'error' }>['reason']>;
 
 export interface Project {
   id: string;
@@ -39,7 +56,9 @@ export interface ToolResult {
   tool_call_id: string;
   output: unknown;
   truncated?: boolean;
-  error?: boolean;
+  // Canonical wire shape: the failure message string (present only on error),
+  // not a boolean. ToolResultBubble treats it as truthy → renders error styling.
+  error?: string;
 }
 
 // Batch 9.7: ask_user_input shapes. The tool_call.args is { questions: AskUserQuestion[] }
@@ -96,15 +115,3 @@ export interface PendingChange {
   created_at: string;
   applied_at: string | null;
 }
-
-// WebSocket frame types (subset of what the coder backend publishes)
-export type WsFrame =
-  | { type: 'snapshot'; messages: Message[] }
-  | { type: 'message_started'; message_id: string; chat_id: string; role: Message['role'] }
-  | { type: 'delta'; message_id: string; chat_id: string; content: string }
-  | { type: 'tool_call'; message_id: string; chat_id: string; tool_call: ToolCall }
-  | { type: 'tool_result'; tool_message_id: string; chat_id: string; tool_call_id: string; output: string; truncated?: boolean; error?: boolean }
-  | { type: 'message_complete'; message_id: string; chat_id: string; tokens_used?: number; ctx_used?: number; ctx_max?: number; started_at?: string; finished_at?: string; metadata?: unknown }
-  | { type: 'error'; message_id?: string; error: string; reason?: string }
-  | { type: 'pending_change_added'; change: PendingChange }
-  | { type: 'pending_change_updated'; change: PendingChange };

apps/coder/web/src/components/DiffPane.tsx

@@ -5,10 +5,9 @@ import { api } from '@/api/client';
 
 interface Props {
   sessionId: string;
-  onPendingChange: (cb: (change: PendingChange) => void) => () => void;
 }
 
-export function DiffPane({ sessionId, onPendingChange }: Props) {
+export function DiffPane({ sessionId }: Props) {
   const [changes, setChanges] = useState<PendingChange[]>([]);
   const [loading, setLoading] = useState(true);
   const [expandedId, setExpandedId] = useState<string | null>(null);
@@ -24,27 +23,13 @@ export function DiffPane({ sessionId, onPendingChange }: Props) {
     }
   }, [sessionId]);
 
-  // Initial load
+  // Initial load. Pending changes are delivered over HTTP (list + apply/reject/
+  // rewind below); there is no WS pending-change frame, so the list refreshes on
+  // mount, on the Refresh button, and optimistically as the user acts on it.
   useEffect(() => {
     fetchPending();
   }, [fetchPending]);
 
-  // Listen for WS pending change events
-  useEffect(() => {
-    const unsub = onPendingChange((change) => {
-      setChanges((prev) => {
-        const idx = prev.findIndex((c) => c.id === change.id);
-        if (idx >= 0) {
-          const next = [...prev];
-          next[idx] = change;
-          return next;
-        }
-        return [...prev, change];
-      });
-    });
-    return unsub;
-  }, [onPendingChange]);
-
   const pendingChanges = changes.filter((c) => c.status === 'pending');
   const resolvedChanges = changes.filter((c) => c.status !== 'pending');
 

apps/coder/web/src/hooks/useSessionStream.ts

@@ -1,5 +1,5 @@
-import { useEffect, useRef, useState, useCallback } from 'react';
+import { useEffect, useRef, useState } from 'react';
-import type { Message, WsFrame, PendingChange } from '@/api/types';
+import type { Message, WsFrame } from '@/api/types';
 
 interface State {
   messages: Message[];
@@ -10,7 +10,9 @@ interface State {
 function applyFrame(state: State, frame: WsFrame): State {
   switch (frame.type) {
     case 'snapshot': {
-      return { ...state, messages: frame.messages };
+      // Canonical SnapshotFrame.messages is opaque (z.array(z.unknown())); the
+      // coder backend sends Message-shaped rows, so cast to the SPA's local type.
+      return { ...state, messages: frame.messages as Message[] };
     }
     case 'message_started': {
       const exists = state.messages.some((m) => m.id === frame.message_id);
@@ -18,7 +20,7 @@ function applyFrame(state: State, frame: WsFrame): State {
       const newMsg: Message = {
         id: frame.message_id,
         session_id: '',
-        chat_id: frame.chat_id,
+        chat_id: frame.chat_id ?? '',
         role: frame.role,
         content: '',
         kind: 'message',
@@ -72,7 +74,7 @@ function applyFrame(state: State, frame: WsFrame): State {
       const newMsg: Message = {
         id: frame.tool_message_id,
         session_id: '',
-        chat_id: frame.chat_id,
+        chat_id: frame.chat_id ?? '',
         role: 'tool',
         content: '',
         kind: 'message',
@@ -119,9 +121,12 @@ function applyFrame(state: State, frame: WsFrame): State {
         : state.messages;
       return { ...state, messages: next, error: frame.error };
     }
-    case 'pending_change_added':
+    default:
-    case 'pending_change_updated':
+      // The canonical WsFrame carries the full set of frames the coder backend
-      // These are handled by the pending changes listener, not the message state
+      // can publish; this SPA only renders the subset handled above and safely
+      // ignores the rest (reasoning_delta, usage, permission_*, agent_*, and the
+      // per-user sidebar frames). pending_change_* frames have no publisher —
+      // pending changes are delivered over HTTP, so there is nothing to handle.
       return state;
   }
 }
@@ -134,14 +139,11 @@ interface SessionStreamResult {
   connected: boolean;
   error: string | null;
   isStreaming: boolean;
-  /** Listeners for pending change frames */
-  onPendingChange: (cb: (change: PendingChange) => void) => () => void;
 }
 
 export function useSessionStream(sessionId: string | undefined): SessionStreamResult {
   const [state, setState] = useState<State>({ messages: [], connected: false, error: null });
   const wsRef = useRef<WebSocket | null>(null);
-  const pendingListenersRef = useRef<Set<(change: PendingChange) => void>>(new Set());
 
   useEffect(() => {
     if (!sessionId) return;
@@ -172,13 +174,6 @@ export function useSessionStream(sessionId: string | undefined): SessionStreamRe
           return;
         }
 
-        // Notify pending change listeners
-        if (frame.type === 'pending_change_added' || frame.type === 'pending_change_updated') {
-          for (const cb of pendingListenersRef.current) {
-            cb(frame.change);
-          }
-        }
-
         setState((s) => applyFrame(s, frame));
       };
 
@@ -213,18 +208,10 @@ export function useSessionStream(sessionId: string | undefined): SessionStreamRe
 
   const isStreaming = state.messages.some((m) => m.status === 'streaming');
 
-  const onPendingChange = useCallback((cb: (change: PendingChange) => void) => {
-    pendingListenersRef.current.add(cb);
-    return () => {
-      pendingListenersRef.current.delete(cb);
-    };
-  }, []);
-
   return {
     messages: state.messages,
     connected: state.connected,
     error: state.error,
     isStreaming,
-    onPendingChange,
   };
 }

apps/coder/web/src/pages/Session.tsx

@@ -14,8 +14,7 @@ export function Session() {
   const [chat, setChat] = useState<Chat | null>(null);
   const [loading, setLoading] = useState(true);
 
-  const { messages, connected, isStreaming, onPendingChange } =
+  const { messages, connected, isStreaming } = useSessionStream(sessionId);
-    useSessionStream(sessionId);
 
   // Get or create a chat for this session
   useEffect(() => {
@@ -78,9 +77,7 @@ export function Session() {
           connected={connected}
         />
       }
-      diffPane={
+      diffPane={<DiffPane sessionId={sessionId} />}
-        <DiffPane sessionId={sessionId} onPendingChange={onPendingChange} />
-      }
     />
   );
 }

apps/coder/web/vite.config.d.ts

@@ -0,0 +1,2 @@
+declare const _default: import("vite").UserConfig;
+export default _default;

apps/coder/web/vite.config.js

@@ -0,0 +1,25 @@
+import { defineConfig } from 'vite';
+import react from '@vitejs/plugin-react';
+import path from 'node:path';
+export default defineConfig({
+    plugins: [react()],
+    resolve: {
+        alias: {
+            '@': path.resolve(__dirname, './src'),
+        },
+    },
+    server: {
+        port: 5174,
+        proxy: {
+            '/api': {
+                target: 'http://127.0.0.1:3000',
+                changeOrigin: true,
+                ws: true,
+            },
+        },
+    },
+    build: {
+        outDir: 'dist',
+        emptyOutDir: true,
+    },
+});

apps/server/CLAUDE.md

@@ -21,7 +21,7 @@
 - **`experimental_repairToolCall`** wired into `streamText` to keep the stream alive when qwen3.6 emits malformed tool args. Pass-through: logs the bad call, returns it unmodified; `executeToolPhase`'s zod-reject path routes it back to the model next turn.
 - **`chat_status` frame** (via `broker.publishUser`) — `status: 'streaming' | 'tool_running' | 'waiting_for_input' | 'idle' | 'error'`. Frontend `useChatStatus` derives `idle_warm` (<30s since idle) vs `idle_cold`. `ChatThroughput` renders beside `StatusDot` only when streaming/tool_running, fed by 500ms-throttled `'usage'` frames (`completion_tokens` + `ctx_used` + `ctx_max`). `POST /api/chats/:id/discard_stale` marks a stuck-streaming row `failed` when the frontend's 60s no-token timer gives up.
 - **Stale-streaming sweeps** (`apps/server/src/index.ts`): a boot-time pass after `applySchema()` and a periodic 60s `setInterval` both flip `messages.status='streaming'` older than 5 min to `failed` (publishing `chat_status='idle'`); the interval also runs `cleanupTruncations` (TTL + orphan reap of tmpfs truncation files). `onClose` hook clears the timer. Recovers from a container restart mid-stream.
-- **`services/broker.ts`** — In-memory pub/sub, two channel types: per-session (message streaming) and per-user (sidebar). No persistence; clients reconnect on restart. Every WS publish goes through `broker.publishFrame(sessionId, frame)` / `publishUserFrame(user, frame)` — both Zod-validate against `WsFrameSchema` (`types/ws-frames.ts`) and fail-closed (log + drop). Schema duplicated byte-identical at `apps/web/src/api/ws-frames.ts`; `ws-frames.test.ts` enforces parity. Don't add raw `broker.publish()`/`publishUser()` calls.
+- **`services/broker.ts`** — In-memory pub/sub, two channel types: per-session (message streaming) and per-user (sidebar). No persistence; clients reconnect on restart. Every WS publish goes through `broker.publishFrame(sessionId, frame)` / `publishUserFrame(user, frame)` — both Zod-validate against `WsFrameSchema` (`types/ws-frames.ts`) and fail-closed (log + drop). Schema single-sourced in `@boocode/contracts` (`packages/contracts/src/ws-frames.ts`); the package's `ws-frames.test.ts` enforces schema correctness. Don't add raw `broker.publish()`/`publishUser()` calls.
 - **`services/tools.ts`** — Tool registry (`ALL_TOOLS`, `READ_ONLY_TOOL_NAMES`, `TOOLS_BY_NAME`). Filesystem tools (view_file/list_dir/grep/find_files) pass three guards: `path_guard.ts` (workspace scope), `secret_guard.ts` (filename deny list), `url_guard.ts` (SSRF/private-IP block for web_fetch). Web tools (`web_search`, `web_fetch`) are opt-in per chat via `session.web_search_enabled` (falls back to `project.default_web_search_enabled`) and filtered out of the LLM tool schema when false. Truncation: when a tool slice cuts content, `services/truncate.ts` stashes the full text on tmpfs (`BOOCODE_TRUNCATION_DIR`, default `/tmp/boocode-truncations`, 0o700) keyed by `tr_<12 base32>`; `view_truncated_output(id)` retrieves it. 5MB cap, 7-day TTL, reaped by the sweeper. Container restart loses retrieval — acceptable.
 - **`services/compaction.ts`** + **`services/model-context.ts`** — Anchored rolling summary (single `summary=true` assistant row per chat, supersedes itself each compaction). Triggered when `chats.needs_compaction` is set after a turn exceeds `usable(ctx_max) = floor(0.85 × ctx_max)`. **`ctx_max` comes from `model-context.getModelContext()` fetching `${LLAMA_SWAP_URL}/upstream/<model>/props`** — NOT from `parsed.timings.n_ctx`. First inferences after boot may have `ctx_max=NULL` if llama-swap hasn't loaded the model; negative cache TTL 60s, recovers next turn. `buildHeadPayload` embeds `reasoning_parts` as a `<reasoning>...</reasoning>` prose prefix on assistant `content` (OpenAI wire shape has no structured reasoning field); standalone tag when content is empty. `buildHeadPayload` + `OpenAiMessage` exported for tests — keep them exported.
 - **`services/system-prompt.ts`** — `buildSystemPrompt` is the string shim; `buildSystemPromptWithFingerprint` is the canonical impl returning `{prompt, fingerprint, drift}`. SHA-256 of the assembled prefix is logged per `buildMessagesPayload` (`prefix-fingerprint`, info); a `Map<sessionId, lastHash>` fires `prefix-drift` (warn) on change with a `changed_inputs` diff. The prefix is byte-stable in steady-state, so prefix caching is left to the input-layer mtime caches (BOOCHAT.md + AGENTS.md global/per-project in `agents.ts:safeStat`).

apps/server/package.json

@@ -53,10 +53,6 @@
       "types": "./dist/types/api.d.ts",
       "default": "./dist/types/api.js"
     },
-    "./ws-frames": {
-      "types": "./dist/types/ws-frames.d.ts",
-      "default": "./dist/types/ws-frames.js"
-    },
     "./db": {
       "types": "./dist/db.d.ts",
       "default": "./dist/db.js"
@@ -81,6 +77,7 @@
     "test": "vitest run"
   },
   "dependencies": {
+    "@boocode/contracts": "workspace:*",
     "@ai-sdk/openai-compatible": "^2.0.47",
     "@fastify/static": "^7.0.4",
     "@fastify/websocket": "^10.0.1",

apps/server/src/config.ts

@@ -18,6 +18,7 @@ const ConfigSchema = z.object({
   GITEA_BASE_URL: z.string().url().default('https://git.indifferentketchup.com'),
   GITEA_USER: z.string().default('indifferentketchup'),
   GITEA_TOKEN: z.string().optional(),
+  GITEA_SSH_HOST: z.string().default('100.114.205.53:2222'),
   // v1.15.0-mcp-multi: path to the MCP config JSON file. Default /data/mcp.json
   // (bind-mounted alongside AGENTS.md). File missing = no MCP (opt-in).
   MCP_CONFIG_PATH: z.string().optional(),

apps/server/src/index.ts

@@ -140,7 +140,7 @@ async function main() {
       publish: (sessionId, frame) => {
         // v1.13.11-b: route through the typed publishFrame so the broker's
         // Zod gate validates every inference frame before delivery.
-        broker.publishFrame(sessionId, frame as unknown as import('./types/ws-frames.js').WsFrame);
+        broker.publishFrame(sessionId, frame as unknown as import('@boocode/contracts/ws-frames').WsFrame);
       },
       // v1.11: broker handle for compaction.process to publish 'compacted'
       // frames on the per-session channel. Inference's regular publish path
@@ -149,7 +149,7 @@ async function main() {
       broker,
     },
     (user, frame) => {
-      broker.publishUserFrame(user, frame as unknown as import('./types/ws-frames.js').WsFrame);
+      broker.publishUserFrame(user, frame as unknown as import('@boocode/contracts/ws-frames').WsFrame);
     }
   );
   registerMessageRoutes(app, sql, config, broker, {
@@ -194,7 +194,7 @@ async function main() {
       });
     },
     publishSessionFrame: (sessionId, frame) => {
-      broker.publishFrame(sessionId, frame as import('./types/ws-frames.js').WsFrame);
+      broker.publishFrame(sessionId, frame as import('@boocode/contracts/ws-frames').WsFrame);
     },
   });
   registerArtifactRoutes(app, sql);
@@ -222,7 +222,7 @@ async function main() {
       });
     },
     publishSessionFrame: (sessionId, frame) => {
-      broker.publishFrame(sessionId, frame as import('./types/ws-frames.js').WsFrame);
+      broker.publishFrame(sessionId, frame as import('@boocode/contracts/ws-frames').WsFrame);
     },
   });
   registerWebSocket(app, sql, broker);

apps/server/src/routes/chats.ts

@@ -5,7 +5,6 @@ import type { Broker } from '../services/broker.js';
 import type { Chat, Message } from '../types/api.js';
 import { getModelContext } from '../services/model-context.js';
 import { notifyCoderClose } from '../services/coder-notify.js';
-import { MESSAGE_COLUMNS } from '../services/message-columns.js';
 
 const CreateBody = z.object({
   name: z.string().min(1).max(200).optional(),
@@ -440,7 +439,9 @@ export function registerChatRoutes(
       }
       // v1.13.1-B: reads tool_calls/tool_results via the parts-merged view.
       const rows = await sql<Message[]>`
-        SELECT ${sql.unsafe(MESSAGE_COLUMNS)}
+        SELECT id, session_id, chat_id, role, content, kind, tool_calls, tool_results, status, last_seq,
+               tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at, metadata,
+               summary, tail_start_id, compacted_at, model
         FROM messages_with_parts
         WHERE chat_id = ${req.params.id}
         ORDER BY created_at ASC, id ASC

apps/server/src/routes/messages.ts

@@ -8,81 +8,6 @@ import type { Chat, Message, Session, ToolCall } from '../types/api.js';
 // decision time (not at request time) so concurrent project changes don't
 // stale-bind the resolution.
 import { resolveGrantRoot } from '../services/grant_resolver.js';
-import { MESSAGE_COLUMNS } from '../services/message-columns.js';
-
-// Shared lookup for the answer_user_input + grant_read_access pause-resume
-// endpoints. Finds the originating assistant tool_call by id in message_parts,
-// validates the tool name, finds the pending tool_result part, and checks the
-// already-answered guard. Returns ok:true+context on success, ok:false+HTTP
-// status+body on any error (caller does reply.code(ctx.code); return ctx.body).
-type PendingToolLookupResult =
-  | {
-      ok: true;
-      foundCall: ToolCall;
-      toolMessageId: string;
-      toolRow: { message_id: string; payload: { tool_call_id: string; output: unknown } };
-    }
-  | { ok: false; code: number; body: Record<string, unknown> };
-
-async function lookupPendingToolCall(
-  sql: Sql,
-  chatId: string,
-  tool_call_id: string,
-  expectedToolName: string,
-  wrongToolError: string,
-): Promise<PendingToolLookupResult> {
-  // Find the assistant's tool_call by id via message_parts.
-  const callerRows = await sql<{
-    message_id: string;
-    payload: { id: string; name: string; args: Record<string, unknown> };
-  }[]>`
-    SELECT p.message_id, p.payload
-    FROM message_parts p
-    JOIN messages m ON m.id = p.message_id
-    WHERE m.chat_id = ${chatId}
-      AND m.role = 'assistant'
-      AND p.kind = 'tool_call'
-      AND p.payload->>'id' = ${tool_call_id}
-    ORDER BY m.created_at DESC
-    LIMIT 1
-  `;
-  const callerRow = callerRows[0];
-  if (!callerRow) return { ok: false, code: 404, body: { error: 'unknown_tool_call_id' } };
-
-  const foundCall: ToolCall = {
-    id: callerRow.payload.id,
-    name: callerRow.payload.name,
-    args: callerRow.payload.args,
-  };
-  if (foundCall.name !== expectedToolName) {
-    return { ok: false, code: 400, body: { error: wrongToolError } };
-  }
-
-  // Find the pending tool_result part by tool_call_id.
-  const toolRows = await sql<{
-    message_id: string;
-    payload: { tool_call_id: string; output: unknown };
-  }[]>`
-    SELECT p.message_id, p.payload
-    FROM message_parts p
-    JOIN messages m ON m.id = p.message_id
-    WHERE m.chat_id = ${chatId}
-      AND m.role = 'tool'
-      AND p.kind = 'tool_result'
-      AND p.payload->>'tool_call_id' = ${tool_call_id}
-    ORDER BY m.created_at DESC
-    LIMIT 1
-  `;
-  const toolRow = toolRows[0];
-  if (!toolRow) {
-    return { ok: false, code: 404, body: { error: 'unknown_tool_call_id', detail: 'tool message not found' } };
-  }
-  if (toolRow.payload && toolRow.payload.output !== null) {
-    return { ok: false, code: 409, body: { error: 'tool_call_already_answered' } };
-  }
-
-  return { ok: true, foundCall, toolMessageId: toolRow.message_id, toolRow };
-}
 
 const SendBody = z.object({
   content: z.string().min(1).max(64_000),
@@ -191,7 +116,9 @@ export function registerMessageRoutes(
       // see services/inference.ts loadContext + services/compaction.ts.
       // v1.13.1-B: reads tool_calls/tool_results via the parts-merged view.
       const rows = await sql<Message[]>`
-        SELECT ${sql.unsafe(MESSAGE_COLUMNS)}
+        SELECT id, session_id, chat_id, role, content, kind, tool_calls, tool_results, status, last_seq,
+               tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at, metadata,
+               summary, tail_start_id, compacted_at, model
         FROM messages_with_parts
         WHERE session_id = ${req.params.id}
         ORDER BY created_at ASC, id ASC
@@ -566,16 +493,40 @@ export function registerMessageRoutes(
       const chat = chatRows[0]!;
       const sessionId = chat.session_id;
 
-      // v1.13.1-C: resolve the originating tool_call + pending tool row.
+      // v1.13.1-C: find the assistant's tool_call by indexing message_parts
-      // Pre-v1.13.0 history has no parts rows — those become unreachable (404).
+      // directly on payload->>'id'. Scoped by chat_id + role via the JOIN.
-      const ctx = await lookupPendingToolCall(
+      // Pre-v1.13.0 history has no parts rows — those tool_calls become
-        sql, chat.id, tool_call_id, 'ask_user_input', 'tool_call_not_ask_user_input',
+      // unreachable here (404). Acceptable per the dispatch decision: any
-      );
+      // pending elicitation from before v1.13.0 is long timed out by now;
-      if (!ctx.ok) {
+      // promote to a hotfix with a JSON-column fallback if it ever surfaces.
-        reply.code(ctx.code);
+      const callerRows = await sql<{
-        return ctx.body;
+        message_id: string;
+        payload: { id: string; name: string; args: Record<string, unknown> };
+      }[]>`
+        SELECT p.message_id, p.payload
+        FROM message_parts p
+        JOIN messages m ON m.id = p.message_id
+        WHERE m.chat_id = ${chat.id}
+          AND m.role = 'assistant'
+          AND p.kind = 'tool_call'
+          AND p.payload->>'id' = ${tool_call_id}
+        ORDER BY m.created_at DESC
+        LIMIT 1
+      `;
+      const callerRow = callerRows[0];
+      if (!callerRow) {
+        reply.code(404);
+        return { error: 'unknown_tool_call_id' };
+      }
+      const foundCall: ToolCall = {
+        id: callerRow.payload.id,
+        name: callerRow.payload.name,
+        args: callerRow.payload.args,
+      };
+      if (foundCall.name !== 'ask_user_input') {
+        reply.code(400);
+        return { error: 'tool_call_not_ask_user_input' };
       }
-      const { foundCall, toolMessageId } = ctx;
 
       // Validate the args themselves — the LLM could have emitted bad JSON.
       const argsParsed = AskUserInputArgs.safeParse(foundCall.args);
@@ -618,6 +569,33 @@ export function registerMessageRoutes(
         }
       }
 
+      // v1.13.1-C: find the pending tool row via message_parts on
+      // payload->>'tool_call_id'. Same fallback caveat as the caller lookup
+      // above — pre-v1.13.0 rows are unreachable here.
+      const toolRows = await sql<{
+        message_id: string;
+        payload: { tool_call_id: string; output: unknown };
+      }[]>`
+        SELECT p.message_id, p.payload
+        FROM message_parts p
+        JOIN messages m ON m.id = p.message_id
+        WHERE m.chat_id = ${chat.id}
+          AND m.role = 'tool'
+          AND p.kind = 'tool_result'
+          AND p.payload->>'tool_call_id' = ${tool_call_id}
+        ORDER BY m.created_at DESC
+        LIMIT 1
+      `;
+      const toolRow = toolRows[0];
+      if (!toolRow) {
+        reply.code(404);
+        return { error: 'unknown_tool_call_id', detail: 'tool message not found' };
+      }
+      if (toolRow.payload && toolRow.payload.output !== null) {
+        reply.code(409);
+        return { error: 'tool_call_already_answered' };
+      }
+
       const answerSet = { answers };
       const newToolResults = {
         tool_call_id,
@@ -625,6 +603,7 @@ export function registerMessageRoutes(
         truncated: false,
       };
 
+      const toolMessageId = toolRow.message_id;
       const result = await sql.begin(async (tx) => {
         // v1.13.20: parts-only. Replace the pending tool_result part inserted
         // at message creation (tool-phase.ts) with the answered one. Delete-
@@ -702,15 +681,35 @@ export function registerMessageRoutes(
       const chat = chatRows[0]!;
       const sessionId = chat.session_id;
 
-      const grantCtx = await lookupPendingToolCall(
+      // Mirror the /answer lookup: assistant tool_call by id via message_parts.
-        sql, chat.id, tool_call_id, 'request_read_access', 'tool_call_not_request_read_access',
+      const callerRows = await sql<{
-      );
+        message_id: string;
-      if (!grantCtx.ok) {
+        payload: { id: string; name: string; args: Record<string, unknown> };
-        reply.code(grantCtx.code);
+      }[]>`
-        return grantCtx.body;
+        SELECT p.message_id, p.payload
+        FROM message_parts p
+        JOIN messages m ON m.id = p.message_id
+        WHERE m.chat_id = ${chat.id}
+          AND m.role = 'assistant'
+          AND p.kind = 'tool_call'
+          AND p.payload->>'id' = ${tool_call_id}
+        ORDER BY m.created_at DESC
+        LIMIT 1
+      `;
+      const callerRow = callerRows[0];
+      if (!callerRow) {
+        reply.code(404);
+        return { error: 'unknown_tool_call_id' };
+      }
+      const foundCall: ToolCall = {
+        id: callerRow.payload.id,
+        name: callerRow.payload.name,
+        args: callerRow.payload.args,
+      };
+      if (foundCall.name !== 'request_read_access') {
+        reply.code(400);
+        return { error: 'tool_call_not_request_read_access' };
       }
-      const { foundCall, toolMessageId } = grantCtx;
-
       const argsParsed = RequestReadAccessArgs.safeParse(foundCall.args);
       if (!argsParsed.success) {
         reply.code(400);
@@ -718,6 +717,31 @@ export function registerMessageRoutes(
       }
       const requestedPath = argsParsed.data.path;
 
+      // Find the pending tool row.
+      const toolRows = await sql<{
+        message_id: string;
+        payload: { tool_call_id: string; output: unknown };
+      }[]>`
+        SELECT p.message_id, p.payload
+        FROM message_parts p
+        JOIN messages m ON m.id = p.message_id
+        WHERE m.chat_id = ${chat.id}
+          AND m.role = 'tool'
+          AND p.kind = 'tool_result'
+          AND p.payload->>'tool_call_id' = ${tool_call_id}
+        ORDER BY m.created_at DESC
+        LIMIT 1
+      `;
+      const toolRow = toolRows[0];
+      if (!toolRow) {
+        reply.code(404);
+        return { error: 'unknown_tool_call_id', detail: 'tool message not found' };
+      }
+      if (toolRow.payload && toolRow.payload.output !== null) {
+        reply.code(409);
+        return { error: 'tool_call_already_answered' };
+      }
+
       // Look up session + project so we can re-resolve the grant root and
       // append to allowed_read_paths atomically. We don't need agent or
       // history here — just the project path for the resolver.
@@ -766,6 +790,7 @@ export function registerMessageRoutes(
         output: resultOutput,
         truncated: false,
       };
+      const toolMessageId = toolRow.message_id;
       const dbResult = await sql.begin(async (tx) => {
         // v1.13.20: parts-only. Same delete+insert dance as /answer —
         // UNIQUE (message_id, sequence) blocks plain UPDATE on append-style

apps/server/src/routes/projects.ts

@@ -67,20 +67,6 @@ export async function resolveProjectPath(
   return { real, name: basename(real) };
 }
 
-async function selectProject(sql: Sql, id: string): Promise<Project | null> {
-  const rows = await sql<Project[]>`
-    SELECT id, name, path, added_at, last_session_id, status, gitea_remote,
-           default_system_prompt, default_web_search_enabled
-    FROM projects WHERE id = ${id}
-  `;
-  return rows[0] ?? null;
-}
-
-async function selectProjectPath(sql: Sql, id: string): Promise<string | null> {
-  const rows = await sql<{ path: string }[]>`SELECT path FROM projects WHERE id = ${id}`;
-  return rows[0]?.path ?? null;
-}
-
 export function registerProjectRoutes(
   app: FastifyInstance,
   sql: Sql,
@@ -213,12 +199,16 @@ export function registerProjectRoutes(
   // v1.9: single-project fetch so the settings pane can refetch on
   // project_updated without pulling the whole project list.
   app.get<{ Params: { id: string } }>('/api/projects/:id', async (req, reply) => {
-    const project = await selectProject(sql, req.params.id);
+    const rows = await sql<Project[]>`
-    if (!project) {
+      SELECT id, name, path, added_at, last_session_id, status, gitea_remote,
+             default_system_prompt, default_web_search_enabled
+      FROM projects WHERE id = ${req.params.id}
+    `;
+    if (rows.length === 0) {
       reply.code(404);
       return { error: 'not found' };
     }
-    return project;
+    return rows[0];
   });
 
   app.patch<{ Params: { id: string } }>('/api/projects/:id', async (req, reply) => {
@@ -350,14 +340,18 @@ export function registerProjectRoutes(
       const { id } = req.params;
       const relPath = req.query.path ?? '.';
 
-      const projectPath = await selectProjectPath(sql, id);
+      const rows = await sql<Project[]>`
-      if (projectPath === null) {
+        SELECT id, name, path, added_at, last_session_id, status, gitea_remote
+        FROM projects WHERE id = ${id}
+      `;
+      if (rows.length === 0) {
         reply.code(404);
         return { error: 'not found' };
       }
+      const project = rows[0]!;
       let projectRoot: string;
       try {
-        projectRoot = await resolveProjectRoot(projectPath);
+        projectRoot = await resolveProjectRoot(project.path);
       } catch (err) {
         if (err instanceof PathScopeError) {
           reply.code(404);
@@ -391,14 +385,18 @@ export function registerProjectRoutes(
         return { error: 'path is required' };
       }
 
-      const projectPath = await selectProjectPath(sql, id);
+      const rows = await sql<Project[]>`
-      if (projectPath === null) {
+        SELECT id, name, path, added_at, last_session_id, status, gitea_remote
+        FROM projects WHERE id = ${id}
+      `;
+      if (rows.length === 0) {
         reply.code(404);
         return { error: 'not found' };
       }
+      const project = rows[0]!;
       let projectRoot: string;
       try {
-        projectRoot = await resolveProjectRoot(projectPath);
+        projectRoot = await resolveProjectRoot(project.path);
       } catch (err) {
         if (err instanceof PathScopeError) {
           reply.code(404);
@@ -433,14 +431,18 @@ export function registerProjectRoutes(
     '/api/projects/:id/git',
     async (req, reply) => {
       const { id } = req.params;
-      const projectPath = await selectProjectPath(sql, id);
+      const rows = await sql<Project[]>`
-      if (projectPath === null) {
+        SELECT id, name, path, added_at, last_session_id, status, gitea_remote
+        FROM projects WHERE id = ${id}
+      `;
+      if (rows.length === 0) {
         reply.code(404);
         return { error: 'not found' };
       }
+      const project = rows[0]!;
       let projectRoot: string;
       try {
-        projectRoot = await resolveProjectRoot(projectPath);
+        projectRoot = await resolveProjectRoot(project.path);
       } catch (err) {
         if (err instanceof PathScopeError) {
           reply.code(404);
@@ -459,14 +461,18 @@ export function registerProjectRoutes(
     async (req, reply) => {
       const { id } = req.params;
 
-      const projectPath = await selectProjectPath(sql, id);
+      const rows = await sql<Project[]>`
-      if (projectPath === null) {
+        SELECT id, name, path, added_at, last_session_id, status, gitea_remote
+        FROM projects WHERE id = ${id}
+      `;
+      if (rows.length === 0) {
         reply.code(404);
         return { error: 'not found' };
       }
+      const project = rows[0]!;
       let projectRoot: string;
       try {
-        projectRoot = await resolveProjectRoot(projectPath);
+        projectRoot = await resolveProjectRoot(project.path);
       } catch (err) {
         if (err instanceof PathScopeError) {
           reply.code(404);

apps/server/src/routes/ws.ts

@@ -2,7 +2,6 @@ import type { FastifyInstance } from 'fastify';
 import type { Sql } from '../db.js';
 import type { Broker } from '../services/broker.js';
 import type { Message } from '../types/api.js';
-import { MESSAGE_COLUMNS } from '../services/message-columns.js';
 
 export function registerWebSocket(
   app: FastifyInstance,
@@ -26,7 +25,9 @@ export function registerWebSocket(
       // render the SummaryCard for summary=true rows on first connect.
       // v1.13.1-B: reads tool_calls/tool_results via the parts-merged view.
       const messages = await sql<Message[]>`
-        SELECT ${sql.unsafe(MESSAGE_COLUMNS)}
+        SELECT id, session_id, chat_id, role, content, kind, tool_calls, tool_results, status, last_seq,
+               tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at, metadata,
+               summary, tail_start_id, compacted_at, model
         FROM messages_with_parts
         WHERE session_id = ${sessionId}
         ORDER BY created_at ASC, id ASC

apps/server/src/schema.sql

@@ -1,5 +1,5 @@
 -- v1.13.3: statement_timeout is set at database level via:
---   ALTER DATABASE boochat SET statement_timeout = '30s';
+--   ALTER DATABASE boocode SET statement_timeout = '30s';
 -- ALTER DATABASE can't run inside a DO block, so this is an operational
 -- step rather than schema. Re-apply after a volume reset (the setting
 -- lives in pg_db which survives `docker compose up --build` but NOT a
@@ -30,6 +30,8 @@ CREATE TABLE IF NOT EXISTS messages (
   session_id UUID NOT NULL REFERENCES sessions(id) ON DELETE CASCADE,
   role TEXT NOT NULL,
   content TEXT NOT NULL DEFAULT '',
+  tool_calls JSONB,
+  tool_results JSONB,
   status TEXT NOT NULL DEFAULT 'complete',
   last_seq INT NOT NULL DEFAULT 0,
   created_at TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp()
@@ -37,10 +39,11 @@ CREATE TABLE IF NOT EXISTS messages (
 
 CREATE INDEX IF NOT EXISTS idx_messages_session ON messages(session_id, created_at);
 
--- v1.13.0: granular message parts table. v1.13.20: legacy tool_calls/
+-- v1.13.0: granular message parts table for AI SDK migration. Old
--- tool_results columns dropped; message_parts is now the sole source of
+-- messages.content / tool_calls / tool_results columns stay authoritative
--- truth for tool calls, tool results, and reasoning. ON DELETE CASCADE
+-- for reads in v1.13.0; this table is dual-written so the swap can happen
--- means removing a message removes its parts in one go.
+-- in a later dispatch without a backfill window. ON DELETE CASCADE means
+-- removing a message removes its parts in one go.
 CREATE TABLE IF NOT EXISTS message_parts (
   id uuid PRIMARY KEY DEFAULT gen_random_uuid(),
   message_id uuid NOT NULL REFERENCES messages(id) ON DELETE CASCADE,
@@ -139,9 +142,10 @@ ALTER TABLE messages DROP COLUMN IF EXISTS tool_calls;
 ALTER TABLE messages DROP COLUMN IF EXISTS tool_results;
 
 -- v1.13.10: per-tool token cost rolling window. Derives from
--- messages_with_parts (the v1.13.1-B view; v1.13.20 removed the legacy
+-- messages_with_parts (the v1.13.1-B view that COALESCEs message_parts over
--- JSON-column COALESCE fallback — parts are sole source). No new write
+-- the legacy JSON column) so this works whether the chat predates v1.13.0
--- site — all source data already lands via tool-phase.ts:94-95 UPDATE.
+-- or postdates v1.13.2 (column drop). No new write site — all source data
+-- already lands via the existing tool-phase.ts:94-95 UPDATE.
 --
 -- Attribution model: equal split. A turn emitting N tool calls divides its
 -- prompt/completion tokens by N before attribution. See v1.13.10 dispatch
@@ -348,7 +352,7 @@ INSERT INTO settings (key, value) VALUES ('theme_mode', '"dark"') ON CONFLICT (k
 ALTER TABLE projects ADD COLUMN IF NOT EXISTS default_system_prompt TEXT NOT NULL DEFAULT '';
 ALTER TABLE projects ADD COLUMN IF NOT EXISTS default_web_search_enabled BOOLEAN NOT NULL DEFAULT false;
 ALTER TABLE sessions ADD COLUMN IF NOT EXISTS web_search_enabled BOOLEAN;
-ALTER TABLE sessions DROP COLUMN IF EXISTS tags;
+ALTER TABLE sessions ADD COLUMN IF NOT EXISTS tags TEXT[] DEFAULT '{}';
 
 -- v1.11: anchored rolling compaction.
 --   compacted_at  — marks rows that are "behind the curtain" of the latest
@@ -387,7 +391,9 @@ CREATE TABLE IF NOT EXISTS tasks (
   model             TEXT,
   mode_id           TEXT,
   thinking_option_id TEXT,
+  feature_values    JSONB,
   execution_path    TEXT CHECK (execution_path IS NULL OR execution_path IN ('native','acp','pty','qwen')),
+  worktree_path     TEXT,
   cost_tokens       INTEGER,
   started_at        TIMESTAMPTZ,
   ended_at          TIMESTAMPTZ,

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

@@ -1,46 +0,0 @@
-import { describe, expect, it } from 'vitest';
-import { resolveToolBudget } from '../inference/budget.js';
-import type { Agent } from '../../types/api.js';
-
-const BASE_AGENT: Agent = {
-  id: 'test-agent',
-  name: 'Test',
-  description: 'test',
-  system_prompt: '',
-  temperature: 0.7,
-  top_p: null,
-  top_k: null,
-  min_p: null,
-  presence_penalty: null,
-  top_n_sigma: null,
-  dry_multiplier: null,
-  dry_base: null,
-  dry_allowed_length: null,
-  dry_penalty_last_n: null,
-  tools: ['view_file'],
-  model: null,
-  source: 'global',
-  max_tool_calls: null,
-  steps: null,
-  llama_extra_args: null,
-};
-
-describe('resolveToolBudget', () => {
-  it('returns 100 when agent is null (no-agent raw chat)', () => {
-    expect(resolveToolBudget(null)).toBe(100);
-  });
-
-  it('returns 100 when agent has no max_tool_calls override', () => {
-    expect(resolveToolBudget(BASE_AGENT)).toBe(100);
-  });
-
-  it('returns max_tool_calls when agent overrides the default', () => {
-    const agent: Agent = { ...BASE_AGENT, max_tool_calls: 25 };
-    expect(resolveToolBudget(agent)).toBe(25);
-  });
-
-  it('returns 0 when max_tool_calls is explicitly 0 (text-only mode)', () => {
-    const agent: Agent = { ...BASE_AGENT, max_tool_calls: 0 };
-    expect(resolveToolBudget(agent)).toBe(0);
-  });
-});

apps/server/src/services/__tests__/inference-helpers.test.ts

@@ -1,149 +0,0 @@
-import { describe, expect, it, vi, afterEach } from 'vitest';
-import { samplerOptsFromAgent } from '../inference/stream-phase.js';
-import { createContentFlusher } from '../inference/content-flusher.js';
-import type { Sql } from '../../db.js';
-import type { Agent } from '../../types/api.js';
-
-const BASE_AGENT: Agent = {
-  id: 'test-agent',
-  name: 'Test',
-  description: 'test',
-  system_prompt: '',
-  temperature: 0.7,
-  top_p: null,
-  top_k: null,
-  min_p: null,
-  presence_penalty: null,
-  top_n_sigma: null,
-  dry_multiplier: null,
-  dry_base: null,
-  dry_allowed_length: null,
-  dry_penalty_last_n: null,
-  tools: ['view_file'],
-  model: null,
-  source: 'global',
-  max_tool_calls: null,
-  steps: null,
-  llama_extra_args: null,
-};
-
-describe('samplerOptsFromAgent', () => {
-  it('maps every nullable sampler field to undefined when agent is null', () => {
-    expect(samplerOptsFromAgent(null)).toEqual({
-      temperature: undefined,
-      top_p: undefined,
-      top_k: undefined,
-      min_p: undefined,
-      presence_penalty: undefined,
-      top_n_sigma: undefined,
-      dry_multiplier: undefined,
-      dry_base: undefined,
-      dry_allowed_length: undefined,
-      dry_penalty_last_n: undefined,
-    });
-  });
-
-  it('strips null sampler fields to undefined but keeps numeric values', () => {
-    const agent: Agent = {
-      ...BASE_AGENT,
-      temperature: 0.5,
-      top_p: 0.9,
-      top_k: null,
-      min_p: 0.05,
-      presence_penalty: null,
-      top_n_sigma: 1,
-      dry_multiplier: null,
-      dry_base: 1.75,
-      dry_allowed_length: null,
-      dry_penalty_last_n: 256,
-    };
-    expect(samplerOptsFromAgent(agent)).toEqual({
-      temperature: 0.5,
-      top_p: 0.9,
-      top_k: undefined,
-      min_p: 0.05,
-      presence_penalty: undefined,
-      top_n_sigma: 1,
-      dry_multiplier: undefined,
-      dry_base: 1.75,
-      dry_allowed_length: undefined,
-      dry_penalty_last_n: 256,
-    });
-  });
-
-  it('never includes a tools field (callers add it)', () => {
-    expect('tools' in samplerOptsFromAgent(BASE_AGENT)).toBe(false);
-  });
-});
-
-describe('createContentFlusher', () => {
-  afterEach(() => {
-    vi.useRealTimers();
-  });
-
-  // A tagged-template stub matching postgres' sql`...` shape. Records the
-  // interpolated content snapshot (values[0]) of each UPDATE.
-  function makeSqlSpy() {
-    const writes: string[] = [];
-    const sql = ((_strings: TemplateStringsArray, ...values: unknown[]) => {
-      writes.push(values[0] as string);
-      return Promise.resolve([]);
-    }) as unknown as Sql;
-    return { sql, writes };
-  }
-
-  it('debounces: many scheduleFlush calls in one window produce one write', async () => {
-    vi.useFakeTimers();
-    const { sql, writes } = makeSqlSpy();
-    let content = '';
-    const flusher = createContentFlusher(sql, 'msg-1', () => content, 500);
-
-    content = 'a';
-    flusher.scheduleFlush();
-    content = 'ab';
-    flusher.scheduleFlush();
-    content = 'abc';
-    flusher.scheduleFlush();
-
-    expect(writes).toHaveLength(0); // nothing before the interval elapses
-    vi.advanceTimersByTime(500);
-    await flusher.drain();
-
-    expect(writes).toHaveLength(1);
-    // snapshot is read at fire time → latest content, not the value at schedule time
-    expect(writes[0]).toBe('abc');
-  });
-
-  it('arms a fresh timer after a flush fires', async () => {
-    vi.useFakeTimers();
-    const { sql, writes } = makeSqlSpy();
-    let content = 'one';
-    const flusher = createContentFlusher(sql, 'msg-1', () => content, 500);
-
-    flusher.scheduleFlush();
-    vi.advanceTimersByTime(500);
-    await Promise.resolve();
-
-    content = 'two';
-    flusher.scheduleFlush();
-    vi.advanceTimersByTime(500);
-    await flusher.drain();
-
-    expect(writes).toEqual(['one', 'two']);
-  });
-
-  it('drain cancels a pending timer without performing a final flush', async () => {
-    vi.useFakeTimers();
-    const { sql, writes } = makeSqlSpy();
-    let content = 'pending';
-    const flusher = createContentFlusher(sql, 'msg-1', () => content, 500);
-
-    flusher.scheduleFlush();
-    // Drain before the timer fires — the pending flush is cancelled, not forced.
-    await flusher.drain();
-    vi.advanceTimersByTime(500);
-    await Promise.resolve();
-
-    expect(writes).toHaveLength(0);
-  });
-});

apps/server/src/services/__tests__/model-context.test.ts

@@ -9,9 +9,12 @@ import {
 
 const TEST_URL = 'http://llama-swap.test:8401';
 
-function mockOkProps(n_ctx: number) {
+function mockOkProps(n_ctx: number, total_slots = 1) {
   return new Response(
-    JSON.stringify({ default_generation_settings: { n_ctx } }),
+    JSON.stringify({
+      default_generation_settings: { n_ctx },
+      total_slots,
+    }),
     { status: 200, headers: { 'Content-Type': 'application/json' } },
   );
 }
@@ -30,10 +33,12 @@ afterEach(() => {
 
 describe('getModelContext — positive cache', () => {
   it('returns the parsed body on a 200 with valid shape', async () => {
-    const fetchSpy = vi.spyOn(globalThis, 'fetch').mockResolvedValueOnce(mockOkProps(262_144));
+    const fetchSpy = vi.spyOn(globalThis, 'fetch').mockResolvedValueOnce(mockOkProps(262_144, 1));
     const result = await getModelContext('qwen3.6');
     expect(result).not.toBeNull();
     expect(result!.n_ctx).toBe(262_144);
+    expect(result!.total_slots).toBe(1);
+    expect(typeof result!.fetched_at).toBe('number');
     // Verify the URL was constructed correctly — encodes the model name in
     // case it contains characters that would break the path.
     expect(fetchSpy).toHaveBeenCalledExactlyOnceWith(
@@ -52,6 +57,19 @@ describe('getModelContext — positive cache', () => {
     expect(fetchSpy).toHaveBeenCalledTimes(1);
   });
 
+  it('defaults total_slots to 1 when the server omits it', async () => {
+    // Mirror the docstring claim — total_slots is informational and we don't
+    // reject the response just because it's missing.
+    vi.spyOn(globalThis, 'fetch').mockResolvedValueOnce(
+      new Response(JSON.stringify({ default_generation_settings: { n_ctx: 8192 } }), {
+        status: 200,
+      }),
+    );
+    const result = await getModelContext('partial-model');
+    expect(result).not.toBeNull();
+    expect(result!.n_ctx).toBe(8192);
+    expect(result!.total_slots).toBe(1);
+  });
 });
 
 // ---- negative cache (single-shot) ------------------------------------------

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

@@ -1,87 +0,0 @@
-import { describe, it, expect } from 'vitest';
-import { SENTINEL_KINDS, isAnySentinel, isCapHitSentinel, isDoomLoopSentinel, isMistakeRecoverySentinel } from '../inference/sentinels.js';
-import type { Message } from '../../types/api.js';
-
-function makeSentinel(kind: string): Message {
-  return {
-    id: 'msg-1',
-    session_id: 's',
-    chat_id: 'c',
-    role: 'system',
-    content: '',
-    kind: 'message',
-    tool_calls: null,
-    tool_results: null,
-    status: 'complete',
-    last_seq: 0,
-    tokens_used: null,
-    ctx_used: null,
-    ctx_max: null,
-    started_at: null,
-    finished_at: null,
-    created_at: new Date().toISOString(),
-    metadata: { kind } as unknown as import('../../types/api.js').MessageMetadata,
-    summary: false,
-    tail_start_id: null,
-    compacted_at: null,
-  };
-}
-
-describe('SENTINEL_KINDS — single source of truth', () => {
-  it('contains the three known sentinel kinds', () => {
-    expect(SENTINEL_KINDS.has('cap_hit')).toBe(true);
-    expect(SENTINEL_KINDS.has('doom_loop')).toBe(true);
-    expect(SENTINEL_KINDS.has('mistake_recovery')).toBe(true);
-  });
-
-  it('does not contain arbitrary strings', () => {
-    expect(SENTINEL_KINDS.has('user')).toBe(false);
-    expect(SENTINEL_KINDS.has('assistant')).toBe(false);
-    expect(SENTINEL_KINDS.has('')).toBe(false);
-  });
-});
-
-describe('isAnySentinel', () => {
-  it('returns true for cap_hit', () => {
-    expect(isAnySentinel(makeSentinel('cap_hit'))).toBe(true);
-  });
-
-  it('returns true for doom_loop', () => {
-    expect(isAnySentinel(makeSentinel('doom_loop'))).toBe(true);
-  });
-
-  it('returns true for mistake_recovery', () => {
-    expect(isAnySentinel(makeSentinel('mistake_recovery'))).toBe(true);
-  });
-
-  it('returns false for non-system role', () => {
-    const m = { ...makeSentinel('cap_hit'), role: 'user' as const };
-    expect(isAnySentinel(m)).toBe(false);
-  });
-
-  it('returns false for null metadata', () => {
-    const m = { ...makeSentinel('cap_hit'), metadata: null };
-    expect(isAnySentinel(m)).toBe(false);
-  });
-
-  it('returns false for unknown kind', () => {
-    expect(isAnySentinel(makeSentinel('unknown_kind'))).toBe(false);
-  });
-});
-
-describe('individual sentinel predicates still work', () => {
-  it('isCapHitSentinel matches cap_hit only', () => {
-    expect(isCapHitSentinel(makeSentinel('cap_hit'))).toBe(true);
-    expect(isCapHitSentinel(makeSentinel('doom_loop'))).toBe(false);
-  });
-
-  it('isDoomLoopSentinel matches doom_loop only', () => {
-    expect(isDoomLoopSentinel(makeSentinel('doom_loop'))).toBe(true);
-    expect(isDoomLoopSentinel(makeSentinel('cap_hit'))).toBe(false);
-  });
-
-  it('isMistakeRecoverySentinel matches mistake_recovery only', () => {
-    expect(isMistakeRecoverySentinel(makeSentinel('mistake_recovery'))).toBe(true);
-    expect(isMistakeRecoverySentinel(makeSentinel('cap_hit'))).toBe(false);
-  });
-});

apps/server/src/services/__tests__/step-decision.test.ts

@@ -1,111 +0,0 @@
-import { describe, expect, it } from 'vitest';
-import { resolveTurnConfig, MAX_STEPS } from '../inference/turn-config.js';
-import { decideStep, decidePostToolAction } from '../inference/step-decision.js';
-import { DOOM_LOOP_THRESHOLD } from '../inference/sentinels.js';
-import type { MistakeState } from '../inference/mistake-tracker.js';
-import type { Agent, ToolCall } from '../../types/api.js';
-
-const BASE_AGENT: Agent = {
-  id: 'test-agent',
-  name: 'Test',
-  description: 'test',
-  system_prompt: '',
-  temperature: 0.7,
-  top_p: null,
-  top_k: null,
-  min_p: null,
-  presence_penalty: null,
-  top_n_sigma: null,
-  dry_multiplier: null,
-  dry_base: null,
-  dry_allowed_length: null,
-  dry_penalty_last_n: null,
-  tools: ['view_file'],
-  model: null,
-  source: 'global',
-  max_tool_calls: null,
-  steps: null,
-  llama_extra_args: null,
-};
-
-function call(name: string, args: Record<string, unknown> = {}): ToolCall {
-  return { id: `tc-${name}-${JSON.stringify(args)}`, name, args };
-}
-
-describe('resolveTurnConfig', () => {
-  it('no agent → budget 100, cap MAX_STEPS, not text-only', () => {
-    expect(resolveTurnConfig(null)).toEqual({
-      effectiveCap: MAX_STEPS,
-      budget: 100,
-      isTextOnly: false,
-    });
-  });
-
-  it('steps: 0 → effectiveCap 0 and isTextOnly true', () => {
-    expect(resolveTurnConfig({ ...BASE_AGENT, steps: 0 })).toEqual({
-      effectiveCap: 0,
-      budget: 100,
-      isTextOnly: true,
-    });
-  });
-
-  it('steps below MAX_STEPS → effectiveCap is the agent value', () => {
-    expect(resolveTurnConfig({ ...BASE_AGENT, steps: 5 }).effectiveCap).toBe(5);
-  });
-
-  it('steps above MAX_STEPS → effectiveCap clamps to MAX_STEPS', () => {
-    expect(resolveTurnConfig({ ...BASE_AGENT, steps: 9999 }).effectiveCap).toBe(MAX_STEPS);
-  });
-
-  it('max_tool_calls overrides the budget', () => {
-    expect(resolveTurnConfig({ ...BASE_AGENT, max_tool_calls: 12 }).budget).toBe(12);
-  });
-});
-
-describe('decideStep (top-of-loop gate)', () => {
-  it('returns stream when no doom loop and under budget', () => {
-    expect(decideStep({ recentToolCalls: [], toolsUsed: 0, budget: 30 })).toEqual({ kind: 'stream' });
-  });
-
-  it('returns budget when toolsUsed has reached the budget', () => {
-    expect(decideStep({ recentToolCalls: [], toolsUsed: 30, budget: 30 })).toEqual({ kind: 'budget' });
-  });
-
-  it('returns doom (with the looping call) on identical-repeat tail', () => {
-    const recent = Array.from({ length: DOOM_LOOP_THRESHOLD }, () => call('view_file', { path: '/a' }));
-    const d = decideStep({ recentToolCalls: recent, toolsUsed: 1, budget: 30 });
-    expect(d.kind).toBe('doom');
-    if (d.kind === 'doom') {
-      expect(d.loop.name).toBe('view_file');
-      expect(d.loop.args).toEqual({ path: '/a' });
-    }
-  });
-
-  it('doom takes precedence over budget when both would trip', () => {
-    const recent = Array.from({ length: DOOM_LOOP_THRESHOLD }, () => call('grep', { q: 'x' }));
-    expect(decideStep({ recentToolCalls: recent, toolsUsed: 30, budget: 30 }).kind).toBe('doom');
-  });
-});
-
-describe('decidePostToolAction (post-tool decision)', () => {
-  const clean: MistakeState = { run: [], nudges: 0 };
-
-  it('non-continue actions stop the loop without consulting the tracker', () => {
-    expect(decidePostToolAction('paused', { run: ['exec_error', 'exec_error', 'exec_error'], nudges: 0 })).toBe('stop');
-    expect(decidePostToolAction('synthesis_done', clean)).toBe('stop');
-  });
-
-  it('continue with a clean tracker → continue', () => {
-    expect(decidePostToolAction('continue', clean)).toBe('continue');
-  });
-
-  it('continue with a threshold streak and no prior nudge → nudge', () => {
-    const tracker: MistakeState = { run: ['zod_reject', 'tool_not_found', 'exec_error'], nudges: 0 };
-    expect(decidePostToolAction('continue', tracker)).toBe('nudge');
-  });
-
-  it('continue with a threshold streak after a nudge already fired → escalate', () => {
-    const tracker: MistakeState = { run: ['zod_reject', 'tool_not_found', 'exec_error'], nudges: 1 };
-    expect(decidePostToolAction('continue', tracker)).toBe('escalate');
-  });
-});

apps/server/src/services/__tests__/tools-registry.test.ts

@@ -1,68 +0,0 @@
-import { describe, it, expect } from 'vitest';
-import { z } from 'zod';
-import {
-  ALL_TOOLS,
-  TOOLS_BY_NAME,
-  appendMcpTools,
-  toolJsonSchemas,
-  type ToolDef,
-} from '../tools.js';
-
-// Parity test for the register-through MCP-discovery contract (Phase 6 split).
-// `ALL_TOOLS` / `TOOLS_BY_NAME` are `let`-bound in tools/registry.ts and
-// reassigned by appendMcpTools() at startup; this barrel re-exports them.
-// apps/coder relies on this exact behavior: it imports `appendMcpTools` + the
-// live `ALL_TOOLS` binding from @boocode/server/tools, calls appendMcpTools()
-// once, then reads ALL_TOOLS. ESM live bindings must carry the mutation
-// through the barrel re-export — if the split ever snapshots the array instead
-// of re-exporting the live binding, these assertions fail. Each test file gets
-// an isolated module instance (vitest default), so mutating the registry here
-// does not leak into tools.test.ts.
-function makeFakeMcpTool(name: string): ToolDef<unknown> {
-  return {
-    name,
-    description: `fake mcp tool ${name}`,
-    inputSchema: z.object({}) as z.ZodType<unknown>,
-    jsonSchema: {
-      type: 'function',
-      function: {
-        name,
-        description: `fake mcp tool ${name}`,
-        parameters: { type: 'object', properties: {}, additionalProperties: false },
-      },
-    },
-    async execute() {
-      return { ok: true };
-    },
-  };
-}
-
-describe('appendMcpTools register-through contract', () => {
-  it('is a no-op for an empty array', () => {
-    const before = ALL_TOOLS.length;
-    appendMcpTools([]);
-    expect(ALL_TOOLS.length).toBe(before);
-  });
-
-  it('mutates the live ALL_TOOLS / TOOLS_BY_NAME bindings observable through the barrel', () => {
-    const before = ALL_TOOLS.length;
-    // Names chosen so insertion lands away from the array ends, proving the
-    // re-sort runs (a naive concat would leave them at the tail).
-    const a = makeFakeMcpTool('mcp__alpha__probe');
-    const z2 = makeFakeMcpTool('mcp__zeta__probe');
-    appendMcpTools([z2, a]);
-
-    expect(ALL_TOOLS.length).toBe(before + 2);
-    expect(TOOLS_BY_NAME['mcp__alpha__probe']).toBe(a);
-    expect(TOOLS_BY_NAME['mcp__zeta__probe']).toBe(z2);
-
-    // Still alpha-sorted after the append (prompt-cache stability invariant).
-    const names = ALL_TOOLS.map((t) => t.name);
-    expect(names).toEqual([...names].sort((x, y) => x.localeCompare(y)));
-
-    // toolJsonSchemas() reads through the same live binding.
-    const schemaNames = toolJsonSchemas().map((s) => s.function.name);
-    expect(schemaNames).toContain('mcp__alpha__probe');
-    expect(schemaNames).toContain('mcp__zeta__probe');
-  });
-});

apps/server/src/services/__tests__/ws-frames.test.ts

@@ -1,159 +1,13 @@
 import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
-import { readFileSync } from 'node:fs';
-import { resolve } from 'node:path';
-import { fileURLToPath } from 'node:url';
 import {
-  WsFrameSchema,
-  KNOWN_FRAME_TYPES,
   type WsFrame,
-} from '../../types/ws-frames.js';
+} from '@boocode/contracts/ws-frames';
 import { createBroker } from '../broker.js';
 
 const VALID_UUID_A = '00000000-0000-0000-0000-000000000001';
 const VALID_UUID_B = '00000000-0000-0000-0000-000000000002';
-const VALID_UUID_C = '00000000-0000-0000-0000-000000000003';
 const VALID_TIMESTAMP = '2026-05-22T14:30:00.000Z';
 
-describe('WsFrameSchema (v1.13.11-a)', () => {
-  it('accepts a well-formed chat_status frame', () => {
-    const result = WsFrameSchema.safeParse({
-      type: 'chat_status',
-      chat_id: VALID_UUID_A,
-      status: 'streaming',
-      at: VALID_TIMESTAMP,
-    });
-    expect(result.success).toBe(true);
-  });
-
-  it('rejects an unknown frame type', () => {
-    const result = WsFrameSchema.safeParse({
-      type: 'cosmic_ray_strike',
-      chat_id: VALID_UUID_A,
-    });
-    expect(result.success).toBe(false);
-  });
-
-  it('rejects a chat_status frame with invalid status enum', () => {
-    // v1.12.1 dropped the legacy 'working' status. Any frame still emitting it
-    // should fail validation — that's a drift catcher.
-    const result = WsFrameSchema.safeParse({
-      type: 'chat_status',
-      chat_id: VALID_UUID_A,
-      status: 'working',
-      at: VALID_TIMESTAMP,
-    });
-    expect(result.success).toBe(false);
-  });
-
-  it('rejects a UUID field with a non-UUID string', () => {
-    const result = WsFrameSchema.safeParse({
-      type: 'chat_status',
-      chat_id: 'not-a-uuid',
-      status: 'idle',
-      at: VALID_TIMESTAMP,
-    });
-    expect(result.success).toBe(false);
-  });
-
-  it('rejects negative token counts in usage frame', () => {
-    const result = WsFrameSchema.safeParse({
-      type: 'usage',
-      message_id: VALID_UUID_A,
-      chat_id: VALID_UUID_B,
-      completion_tokens: -1,
-      ctx_used: 100,
-      ctx_max: 1000,
-    });
-    expect(result.success).toBe(false);
-  });
-
-  it('accepts a usage frame with nullable token counts (pre-v1.13.7 history)', () => {
-    const result = WsFrameSchema.safeParse({
-      type: 'usage',
-      message_id: VALID_UUID_A,
-      chat_id: VALID_UUID_B,
-      completion_tokens: null,
-      ctx_used: null,
-      ctx_max: null,
-    });
-    expect(result.success).toBe(true);
-  });
-
-  it('accepts a tool_result frame with non-UUID tool_call_id (model-emitted)', () => {
-    // Model-emitted tool_call_ids look like "call_abc123", not UUIDs.
-    const result = WsFrameSchema.safeParse({
-      type: 'tool_result',
-      tool_message_id: VALID_UUID_A,
-      chat_id: VALID_UUID_B,
-      tool_call_id: 'call_abc123',
-      output: { whatever: true },
-      truncated: false,
-    });
-    expect(result.success).toBe(true);
-  });
-
-  it('accepts a compacted frame', () => {
-    const result = WsFrameSchema.safeParse({
-      type: 'compacted',
-      session_id: VALID_UUID_A,
-      chat_id: VALID_UUID_B,
-      summary_message_id: VALID_UUID_C,
-    });
-    expect(result.success).toBe(true);
-  });
-
-  it('accepts a session_workspace_updated frame', () => {
-    const result = WsFrameSchema.safeParse({
-      type: 'session_workspace_updated',
-      session_id: VALID_UUID_A,
-      workspace_panes: [{ id: 'p1', kind: 'chat', chatIds: [], activeChatIdx: 0 }],
-    });
-    expect(result.success).toBe(true);
-  });
-
-  it('accepts a message_complete frame with a null model (external coder, no model selected)', () => {
-    // Regression guard: the dispatcher publishes `model: task.model` (string |
-    // null). When null, this MUST validate or publishFrame fail-closes and drops
-    // the whole frame, incl. the status:'complete' transition.
-    const result = WsFrameSchema.safeParse({
-      type: 'message_complete',
-      message_id: VALID_UUID_A,
-      chat_id: VALID_UUID_B,
-      model: null,
-    });
-    expect(result.success).toBe(true);
-  });
-
-  it('every KNOWN_FRAME_TYPES entry has a discriminated branch', () => {
-    // Probe each known type by attempting a minimal valid construction.
-    // Failure here means the union and the KNOWN_FRAME_TYPES list drifted.
-    for (const type of KNOWN_FRAME_TYPES) {
-      const probe = WsFrameSchema.safeParse({ type, __dummy__: true });
-      // We expect FAILURE on every type because we're missing required fields,
-      // but the failure must be ABOUT the missing fields, not about an unknown
-      // type. A "Invalid discriminator value" error means the type isn't in
-      // the union — that's a drift.
-      if (probe.success) continue;
-      const issues = probe.error.issues;
-      const hasInvalidDiscriminator = issues.some(
-        (i) => i.code === 'invalid_union_discriminator',
-      );
-      expect(hasInvalidDiscriminator, `frame type '${type}' is missing from the discriminated union`).toBe(false);
-    }
-  });
-});
-
-describe('ws-frames.ts file mirror parity', () => {
-  it('apps/server and apps/web copies are byte-identical', () => {
-    const here = fileURLToPath(import.meta.url);
-    const serverPath = resolve(here, '../../../types/ws-frames.ts');
-    const webPath = resolve(here, '../../../../../web/src/api/ws-frames.ts');
-    const serverContent = readFileSync(serverPath, 'utf8');
-    const webContent = readFileSync(webPath, 'utf8');
-    expect(webContent, 'apps/web/src/api/ws-frames.ts must be byte-identical to apps/server/src/types/ws-frames.ts').toBe(serverContent);
-  });
-});
-
 describe('broker.publishFrame / publishUserFrame fail-closed behavior', () => {
   let logErrors: Array<{ obj: unknown; msg: string }>;
   let mockLog: Parameters<typeof createBroker>[0];

apps/server/src/services/agents.ts

@@ -3,7 +3,6 @@ import { join } from 'node:path';
 import type { Agent, AgentsResponse, AgentParseError } from '../types/api.js';
 import { ALL_TOOLS, resolveToolTier } from './tools.js';
 import { validateExtraArgs } from './inference/llama-args-validator.js';
-import { stripQuotes } from '../utils/string-utils.js';
 
 // v1.8.1: global agents live at /data/AGENTS.md inside the container
 // (./data:/data:ro mount on the host). Per-project AGENTS.md at the project
@@ -108,50 +107,17 @@ interface ParsedFrontmatter {
   llama_extra_args?: string[];
 }
 
-// P5: table-driven validation for the "soft-range" numeric frontmatter fields.
+function stripQuotes(s: string): string {
-// Each was a near-identical Number() + finite/integer + range-warn + push-error
+  if (
-// block. "Soft-range" = the value is STORED whenever the type checks out; an
+    s.length >= 2 &&
-// out-of-range value only emits a console.warn (it is NOT skipped). A type
+    (s[0] === '"' || s[0] === "'") &&
-// mismatch hard-fails the block. The range descriptor in the warn message is
+    s[0] === s[s.length - 1]
-// `min-max` when both bounds exist, else `(≥min)` — matching the original
+  ) {
-// hand-written strings byte-for-byte.
+    return s.slice(1, -1);
-//
+  }
-// max_tool_calls and steps are deliberately NOT in this table: they are
+  return s;
-// "hard-range" (store ONLY if in range; an in-type-but-out-of-range value is
-// warned AND skipped) with bespoke messages, so they stay explicit below.
-type NumericFieldKey =
-  | 'temperature'
-  | 'top_p'
-  | 'top_k'
-  | 'min_p'
-  | 'presence_penalty'
-  | 'top_n_sigma'
-  | 'dry_multiplier'
-  | 'dry_base'
-  | 'dry_allowed_length'
-  | 'dry_penalty_last_n';
-
-interface NumericFieldSpec {
-  key: NumericFieldKey;
-  isInt: boolean;
-  min?: number;
-  max?: number;
 }
 
-const NUMERIC_FIELDS: readonly NumericFieldSpec[] = [
-  { key: 'temperature', isInt: false },
-  { key: 'top_p', isInt: false, min: 0, max: 1 },
-  { key: 'top_k', isInt: true, min: 0, max: 200 },
-  { key: 'min_p', isInt: false, min: 0, max: 1 },
-  { key: 'presence_penalty', isInt: false, min: -2, max: 2 },
-  // v2.6 sampling-streamjson-tokens (#11): llama.cpp sampler extensions.
-  { key: 'top_n_sigma', isInt: false, min: 0 },
-  { key: 'dry_multiplier', isInt: false, min: 0 },
-  { key: 'dry_base', isInt: false, min: 0 },
-  { key: 'dry_allowed_length', isInt: true, min: 0 },
-  { key: 'dry_penalty_last_n', isInt: true, min: -1 },
-];
-
 function parseFrontmatter(yaml: string): { data: ParsedFrontmatter; errors: string[] } {
   const data: ParsedFrontmatter = {};
   const errors: string[] = [];
@@ -174,33 +140,108 @@ function parseFrontmatter(yaml: string): { data: ParsedFrontmatter; errors: stri
     const key = line.slice(0, colonIdx).trim();
     const valueRaw = line.slice(colonIdx + 1).trim();
 
-    const numericSpec = NUMERIC_FIELDS.find((f) => f.key === key);
+    if (key === 'temperature') {
-    if (numericSpec) {
       const n = Number(valueRaw);
-      const typeOk = numericSpec.isInt ? Number.isInteger(n) : Number.isFinite(n);
+      if (Number.isFinite(n)) data.temperature = n;
-      if (typeOk) {
+      else errors.push(`temperature must be a number (got "${valueRaw}")`);
-        // Soft-range: store regardless of range; out-of-range only warns.
+    } else if (key === 'top_p') {
-        data[numericSpec.key] = n;
+      const n = Number(valueRaw);
-        const below = numericSpec.min !== undefined && n < numericSpec.min;
+      if (Number.isFinite(n)) {
-        const above = numericSpec.max !== undefined && n > numericSpec.max;
+        data.top_p = n;
-        if (below || above) {
+        if (n < 0 || n > 1) {
-          const range =
+          console.warn(`agents: top_p ${n} out of range 0-1, ignoring (falling back to default)`);
-            numericSpec.max !== undefined
-              ? `${numericSpec.min}-${numericSpec.max}`
-              : `(≥${numericSpec.min})`;
-          console.warn(
-            `agents: ${numericSpec.key} ${n} out of range ${range}, ignoring (falling back to default)`,
-          );
         }
       } else {
-        errors.push(
+        errors.push(`top_p must be a number (got "${valueRaw}")`);
-          `${numericSpec.key} must be ${numericSpec.isInt ? 'an integer' : 'a number'} (got "${valueRaw}")`,
-        );
       }
-      continue;
+    } else if (key === 'top_k') {
-    }
+      const n = Number(valueRaw);
-
+      if (Number.isInteger(n)) {
-    if (key === 'tools') {
+        data.top_k = n;
+        if (n < 0 || n > 200) {
+          console.warn(`agents: top_k ${n} out of range 0-200, ignoring (falling back to default)`);
+        }
+      } else {
+        errors.push(`top_k must be an integer (got "${valueRaw}")`);
+      }
+    } else if (key === 'min_p') {
+      const n = Number(valueRaw);
+      if (Number.isFinite(n)) {
+        data.min_p = n;
+        if (n < 0 || n > 1) {
+          console.warn(`agents: min_p ${n} out of range 0-1, ignoring (falling back to default)`);
+        }
+      } else {
+        errors.push(`min_p must be a number (got "${valueRaw}")`);
+      }
+    } else if (key === 'presence_penalty') {
+      const n = Number(valueRaw);
+      if (Number.isFinite(n)) {
+        data.presence_penalty = n;
+        if (n < -2 || n > 2) {
+          console.warn(`agents: presence_penalty ${n} out of range -2-2, ignoring (falling back to default)`);
+        }
+      } else {
+        errors.push(`presence_penalty must be a number (got "${valueRaw}")`);
+      }
+    } else if (key === 'top_n_sigma') {
+      // v2.6 #11: llama.cpp top-n-sigma sampler. Float ≥ 0 (typical 0-3).
+      // Mirrors top_p/min_p: store then warn on out-of-range (non-numeric
+      // hard-fails the block).
+      const n = Number(valueRaw);
+      if (Number.isFinite(n)) {
+        data.top_n_sigma = n;
+        if (n < 0) {
+          console.warn(`agents: top_n_sigma ${n} out of range (≥0), ignoring (falling back to default)`);
+        }
+      } else {
+        errors.push(`top_n_sigma must be a number (got "${valueRaw}")`);
+      }
+    } else if (key === 'dry_multiplier') {
+      // v2.6 #11: DRY repetition-penalty multiplier. Float ≥ 0 (0 disables DRY).
+      const n = Number(valueRaw);
+      if (Number.isFinite(n)) {
+        data.dry_multiplier = n;
+        if (n < 0) {
+          console.warn(`agents: dry_multiplier ${n} out of range (≥0), ignoring (falling back to default)`);
+        }
+      } else {
+        errors.push(`dry_multiplier must be a number (got "${valueRaw}")`);
+      }
+    } else if (key === 'dry_base') {
+      // v2.6 #11: DRY penalty growth base. Float ≥ 0.
+      const n = Number(valueRaw);
+      if (Number.isFinite(n)) {
+        data.dry_base = n;
+        if (n < 0) {
+          console.warn(`agents: dry_base ${n} out of range (≥0), ignoring (falling back to default)`);
+        }
+      } else {
+        errors.push(`dry_base must be a number (got "${valueRaw}")`);
+      }
+    } else if (key === 'dry_allowed_length') {
+      // v2.6 #11: DRY max sequence length not penalized. Integer ≥ 0.
+      const n = Number(valueRaw);
+      if (Number.isInteger(n)) {
+        data.dry_allowed_length = n;
+        if (n < 0) {
+          console.warn(`agents: dry_allowed_length ${n} out of range (≥0), ignoring (falling back to default)`);
+        }
+      } else {
+        errors.push(`dry_allowed_length must be an integer (got "${valueRaw}")`);
+      }
+    } else if (key === 'dry_penalty_last_n') {
+      // v2.6 #11: DRY lookback window. Integer ≥ -1 (-1 = whole context, 0 = off).
+      const n = Number(valueRaw);
+      if (Number.isInteger(n)) {
+        data.dry_penalty_last_n = n;
+        if (n < -1) {
+          console.warn(`agents: dry_penalty_last_n ${n} out of range (≥-1), ignoring (falling back to default)`);
+        }
+      } else {
+        errors.push(`dry_penalty_last_n must be an integer (got "${valueRaw}")`);
+      }
+    } else if (key === 'tools') {
       if (valueRaw === '') {
         data.tools = [];
         arrayKey = 'tools';
@@ -437,6 +478,14 @@ interface CacheEntry {
 // corresponding mtime so the next read sees a miss without a watcher.
 const cache = new Map<string, CacheEntry>();
 
+export function invalidateAgentsCache(projectPath?: string): void {
+  if (projectPath === undefined) {
+    cache.clear();
+  } else {
+    cache.delete(projectPath);
+  }
+}
+
 // v1.13.8: cache-read accessor for the system-prompt prefix-fingerprint log.
 // Returns the AGENTS.md mtimes that getAgentsForProject() observed on its
 // last cache fill for this projectPath. Both fields are null when the cache

apps/server/src/services/auto_name.ts

@@ -19,6 +19,8 @@ function cleanTitle(raw: string): string {
   return name;
 }
 
+// TODO: wire suggestTags after task model validation
+
 export async function maybeAutoNameChat(
   ctx: InferenceContext,
   chatId: string,

apps/server/src/services/broker.ts

@@ -1,5 +1,5 @@
 import type { FastifyBaseLogger } from 'fastify';
-import { WsFrameSchema, type WsFrame } from '../types/ws-frames.js';
+import { WsFrameSchema, type WsFrame } from '@boocode/contracts/ws-frames';
 
 export type Frame = Record<string, unknown> & { type: string };
 export type Listener = (frame: Frame) => void;

apps/server/src/services/codecontext_client.ts

@@ -113,7 +113,7 @@ export async function callCodecontext(
   fetcher: typeof fetch = fetch,
 ): Promise<CodecontextResponse> {
   // Step 1: realpath the project root, then realpath the requested target_dir
-  // (defaulting to projectPath when the caller didn't pass one — the 12 wrappers
+  // (defaulting to projectPath when the caller didn't pass one — the 8 wrappers
   // never pass target_dir; tests can override). A non-existent target_dir
   // throws before we hit the network so the model gets a sharp error.
   const resolvedProject = await realpath(req.projectPath);

apps/server/src/services/compaction.ts

@@ -22,8 +22,6 @@ import type { Config } from '../config.js';
 import type { Broker } from './broker.js';
 import { SUMMARY_TEMPLATE } from './compaction-prompt.js';
 import * as modelContextLookup from './model-context.js';
-import { SENTINEL_KINDS } from './inference/sentinels.js';
-import type { OpenAiMessage } from './inference/payload.js';
 
 // v1.13.9: ratio-only overflow trigger. Fires compaction at 85% of ctx_max
 // (opencode session/overflow.ts pattern). Replaces the v1.11.0-era
@@ -258,9 +256,24 @@ export function buildPrompt(
 // would silently drop pre-legacy-compact history before the LLM sees it.
 // Compaction wants to send the entire head, full stop.) ===
 
-// #12: SENTINEL_KINDS imported from inference/sentinels.ts (single source).
+// v1.13.6: exported for unit-test access (reasoning render coverage).
-// OpenAiMessage imported from inference/payload.ts (structurally compatible —
+export interface OpenAiMessage {
-// compaction's head payload doesn't need the optional reasoning? field).
+  role: 'system' | 'user' | 'assistant' | 'tool';
+  content: string | null;
+  tool_calls?: Array<{
+    id: string;
+    type: 'function';
+    function: { name: string; arguments: string };
+  }>;
+  tool_call_id?: string;
+}
+
+// #12: mirror inference/sentinels.ts:isAnySentinel over the CompactionMessage
+// shape (which carries metadata as { kind?: string } | null, not the full
+// Message type isAnySentinel expects). All UI-only sentinels are stripped from
+// the head payload — they never go to the summarizer LLM. Keep the kind list in
+// sync with isAnySentinel in sentinels.ts.
+const SENTINEL_KINDS = new Set(['cap_hit', 'doom_loop', 'mistake_recovery']);
 function isAnySentinel(m: CompactionMessage): boolean {
   return (
     m.role === 'system' &&

apps/server/src/services/file_ops.ts

@@ -200,7 +200,7 @@ export async function grep(
 export async function findFiles(
   projectRoot: string,
   pattern?: string,
-  opts?: { max_results?: number; path?: string; extra_roots?: readonly string[] }
+  opts?: { type?: 'file' | 'dir'; max_results?: number; path?: string; extra_roots?: readonly string[] }
 ): Promise<FindFilesResult> {
   const limit = Math.min(
     Math.max(opts?.max_results ?? DEFAULT_FIND_RESULTS, 1),

apps/server/src/services/git_meta.ts

@@ -83,3 +83,10 @@ export async function getGitMeta(rootPath: string): Promise<GitMeta | null> {
   return value;
 }
 
+export function invalidateGitMetaCache(rootPath?: string): void {
+  if (rootPath) {
+    cache.delete(rootPath);
+  } else {
+    cache.clear();
+  }
+}

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

@@ -1,10 +1,32 @@
 import type { Agent } from '../../types/api.js';
+import { READ_ONLY_TOOL_NAMES } from '../tools.js';
+
+// v1.8.2: tool-call budget defaults. Resolved per-turn by resolveToolBudget.
+//   - Agent with explicit max_tool_calls: that value.
+//   - Agent with read-only-only tools:    BUDGET_READ_ONLY (50).
+//   - Agent with any non-read-only tool:  BUDGET_NON_READ_ONLY (10).
+//   - No agent (raw chat):                BUDGET_NO_AGENT (50).
+// v1.13.7: bumped BUDGET_NO_AGENT 15→30 to match BUDGET_READ_ONLY. Every tool
+// in ALL_TOOLS today is read-only (see services/tools.ts comment at
+// READ_ONLY_TOOL_NAMES); the cautious 15-cap was a forward-looking guard for
+// write tools that haven't landed yet. No-agent mode gets the same toolset as
+// an all-read-only agent at runtime, so they should share the same budget.
+// v1.13.12: bumped read-only caps 30→50. Real recon sessions were hitting 30
+// with ~3 turns wasted on codecontext parse failures (empty node_modules
+// files); legitimate need was ~27, and Architect-class system overviews want
+// deeper recon than a 30-cap permits. Headroom of 20 absorbs failure-retry
+// turns + deeper exploration without changing the safety floor materially —
+// the doom-loop guard (3 identical calls → abort) catches the actual failure
+// mode this cap was guarding against.
+export const BUDGET_READ_ONLY = 100;
+export const BUDGET_NON_READ_ONLY = 100;
+export const BUDGET_NO_AGENT = 100;
+
+const READ_ONLY_SET: ReadonlySet<string> = new Set(READ_ONLY_TOOL_NAMES);
 
-// Tool-call budget. All three historical tiers (read-only, non-read-only,
-// no-agent) converged to 100 as of v1.13.12, collapsing the tier logic.
-// The only remaining override is per-agent max_tool_calls from AGENTS.md
-// frontmatter. Flat default of 100; doom-loop guard in sentinels.ts catches
-// pathological cases well before the cap is reached.
 export function resolveToolBudget(agent: Agent | null): number {
-  return agent?.max_tool_calls ?? 100;
+  if (agent?.max_tool_calls != null) return agent.max_tool_calls;
+  if (!agent) return BUDGET_NO_AGENT;
+  const allReadOnly = agent.tools.every((t) => READ_ONLY_SET.has(t));
+  return allReadOnly ? BUDGET_READ_ONLY : BUDGET_NON_READ_ONLY;
 }

apps/server/src/services/inference/content-flusher.ts

@@ -1,64 +0,0 @@
-// P5: the debounced DB content-flush timer, extracted from the verbatim copy
-// that lived in executeStreamPhase + the three sentinel summaries (4 sites).
-// Each site streamed deltas into a local `accumulated`/`state.accumulated`
-// string and threw an UPDATE at the row at most once per DB_FLUSH_INTERVAL_MS
-// to bound write rate under heavy streaming.
-//
-// The accumulated string stays owned by the caller (stream-phase keeps it on
-// the shared StreamPhaseState; the summaries keep a local) — the flusher reads
-// it through a `getContent` thunk at fire time, snapshotting the latest value
-// exactly as the inline `const snapshot = accumulated` did. No final flush is
-// performed on drain (matches the originals): every caller writes the full
-// content itself in its terminal UPDATE, so drain only cancels the pending
-// timer and awaits whatever write is already chained.
-
-import type { Sql } from '../../db.js';
-import { DB_FLUSH_INTERVAL_MS } from './types.js';
-
-export interface ContentFlusher {
-  // Arm a debounced flush. No-op if one is already pending (the in-flight timer
-  // will pick up the latest content via getContent when it fires).
-  scheduleFlush: () => void;
-  // Cancel any pending timer and await the in-flight write chain. Does NOT
-  // perform a final flush — the caller's terminal UPDATE owns the final write.
-  drain: () => Promise<void>;
-}
-
-export function createContentFlusher(
-  sql: Sql,
-  messageId: string,
-  getContent: () => string,
-  intervalMs: number = DB_FLUSH_INTERVAL_MS,
-): ContentFlusher {
-  let pendingFlushTimer: NodeJS.Timeout | null = null;
-  let flushPromise: Promise<unknown> = Promise.resolve();
-
-  const flushNow = () => {
-    if (pendingFlushTimer) {
-      clearTimeout(pendingFlushTimer);
-      pendingFlushTimer = null;
-    }
-    const snapshot = getContent();
-    flushPromise = flushPromise.then(() =>
-      sql`UPDATE messages SET content = ${snapshot} WHERE id = ${messageId}`
-    );
-  };
-
-  const scheduleFlush = () => {
-    if (pendingFlushTimer) return;
-    pendingFlushTimer = setTimeout(() => {
-      pendingFlushTimer = null;
-      flushNow();
-    }, intervalMs);
-  };
-
-  const drain = async () => {
-    if (pendingFlushTimer) {
-      clearTimeout(pendingFlushTimer);
-      pendingFlushTimer = null;
-    }
-    await flushPromise;
-  };
-
-  return { scheduleFlush, drain };
-}

apps/server/src/services/inference/error-handler.ts

@@ -10,7 +10,7 @@ import { maybeFlagForCompaction } from './payload.js';
 import { insertParts, partsFromAssistantMessage } from './parts.js';
 import type { PartInsert } from './parts.js';
 import { stripToolMarkup } from './tool-call-parser.js';
-import type { InferenceContext, StreamResult, TurnArgs } from './types.js';
+import type { InferenceContext, StreamResult, TurnArgs } from './turn.js';
 
 export async function handleAbortOrError(
   ctx: InferenceContext,
@@ -95,90 +95,6 @@ export async function handleAbortOrError(
   }
 }
 
-// P5: the success-finalize atom shared by the wrap-up summaries
-// (sentinel-summaries.ts) and the synthesis pass (synthesisPipeline.ts). Both
-// previously hand-rolled this exact ceremony — n_ctx lookup, the complete
-// UPDATE (content/status/tokens/ctx/ctx_max/finished_at; NO model column), and
-// the message_complete frame with the full token fields. Single-sourcing it
-// means a message_complete frame-contract change lands in one place instead of
-// silently skipping the summary/synthesis paths.
-//
-// `beforeComplete` runs AFTER the UPDATE and BEFORE the message_complete frame
-// — synthesis uses it to write its kind='synthesis' part in the original order
-// (UPDATE → insertParts → message_complete), preserving timing exactly.
-//
-// NOTE: finalizeCompletion does NOT use this — it additionally writes the
-// `model` column, the text/reasoning/html_artifact parts, the compaction flag,
-// and the session_updated bump, which this atom deliberately omits (the summary
-// and synthesis paths handle those — or not — themselves).
-export async function finalizeStreamedRow(
-  ctx: InferenceContext,
-  opts: {
-    sessionId: string;
-    chatId: string;
-    messageId: string;
-    model: string;
-    content: string;
-    completionTokens: number | null;
-    promptTokens: number | null;
-    startedAt: string | null;
-    beforeComplete?: () => Promise<void>;
-  },
-): Promise<void> {
-  // v1.11.3: see executeToolPhase for the rationale.
-  const mctx = await modelContext.getModelContext(opts.model);
-  const nCtx = mctx?.n_ctx ?? null;
-  const [updated] = await ctx.sql<
-    { tokens_used: number | null; ctx_used: number | null; ctx_max: number | null; finished_at: string | null }[]
-  >`
-    UPDATE messages
-    SET content = ${opts.content},
-        status = 'complete',
-        tokens_used = ${opts.completionTokens},
-        ctx_used = ${opts.promptTokens},
-        ctx_max = ${nCtx},
-        finished_at = clock_timestamp()
-    WHERE id = ${opts.messageId}
-    RETURNING tokens_used, ctx_used, ctx_max, finished_at
-  `;
-  if (opts.beforeComplete) await opts.beforeComplete();
-  ctx.publish(opts.sessionId, {
-    type: 'message_complete',
-    message_id: opts.messageId,
-    chat_id: opts.chatId,
-    tokens_used: updated?.tokens_used ?? null,
-    ctx_used: updated?.ctx_used ?? null,
-    ctx_max: updated?.ctx_max ?? null,
-    started_at: opts.startedAt,
-    finished_at: updated?.finished_at ?? null,
-    model: opts.model,
-  });
-}
-
-// P5: minimal empty-finalize for the mistake-escalate path. The escalate
-// branch in runAssistantTurn stops the turn cap-hit-style; the next assistant
-// row is still 'streaming', so it's finalized as an empty complete row (no
-// tokens, no parts, no session bump — the escalate branch handles the sentinel
-// + chat_status itself). Centralizing the status-column write + message_complete
-// frame here keeps it next to the other finalize paths so a status-column
-// change is found in one place.
-export async function finalizeEmpty(
-  ctx: InferenceContext,
-  args: TurnArgs,
-): Promise<void> {
-  const { sessionId, chatId, assistantMessageId } = args;
-  await ctx.sql`
-    UPDATE messages
-    SET content = '', status = 'complete', finished_at = clock_timestamp()
-    WHERE id = ${assistantMessageId}
-  `;
-  ctx.publish(sessionId, {
-    type: 'message_complete',
-    message_id: assistantMessageId,
-    chat_id: chatId,
-  });
-}
-
 export async function finalizeCompletion(
   ctx: InferenceContext,
   args: TurnArgs,

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

@@ -7,17 +7,26 @@
 export {
   createInferenceRunner,
   MAX_STEPS,
+  runAssistantTurn,
   runInference,
 } from './turn.js';
-// P5: the shared pipeline types moved from turn.ts to types.ts (breaking the
-// hub-and-leaf near-cycle). Re-exported here so the public surface is unchanged.
 export type {
   FramePublisher,
   InferenceContext,
   InferenceFrame,
   StreamResult,
   TurnArgs,
-} from './types.js';
+} from './turn.js';
 export type { ToolPhaseResult } from './tool-phase.js';
 export { detectDoomLoop, DOOM_LOOP_THRESHOLD } from './sentinels.js';
+export {
+  detectMistakePattern,
+  freshMistakeState,
+  recordStep,
+  MISTAKE_THRESHOLD,
+  MISTAKE_RECOVERY_NOTE,
+} from './mistake-tracker.js';
+export type { FailureKind, MistakeState } from './mistake-tracker.js';
 export { buildMessagesPayload } from './payload.js';
+export { generateToolUseSummary } from './tool-summaries.js';
+export type { ToolInfo } from './tool-summaries.js';

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

@@ -1,10 +1,11 @@
 import type { Sql } from '../../db.js';
 import type { ToolCall, ToolResult } from '../../types/api.js';
 
-// v1.13.0: message_parts write helpers. v1.13.20: legacy tool_calls/
+// v1.13.0: dual-write helper. Every site that writes the legacy
-// tool_results JSON columns dropped; message_parts is the sole source of
+// messages.tool_calls / messages.tool_results JSON columns calls into here
-// truth. All writes go through insertParts / partsFromAssistantMessage /
+// to mirror the same data into message_parts rows. Reads still go to the
-// partsFromToolMessage. Reads use the messages_with_parts view.
+// JSON columns; the swap to parts-as-source-of-truth happens in a later
+// v1.13 dispatch alongside the AI SDK streamText migration.
 
 // v1.13.13: 'synthesis' added. Schema CHECK constraint is updated in lockstep
 // (schema.sql adds 'synthesis' to message_parts_kind_chk on startup). The

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

@@ -10,8 +10,7 @@ import * as compaction from '../compaction.js';
 import { buildSystemPromptWithFingerprint } from '../system-prompt.js';
 import { isAnySentinel } from './sentinels.js';
 import { PRUNE_TRIGGER_TOKENS, prune } from './prune.js';
-import type { InferenceContext } from './types.js';
+import type { InferenceContext } from './turn.js';
-import { INFERENCE_MESSAGE_COLUMNS } from '../message-columns.js';
 
 export interface OpenAiMessage {
   role: 'system' | 'user' | 'assistant' | 'tool';
@@ -206,7 +205,9 @@ export async function loadContext(
   // v1.13.1-C: also pull reasoning_parts so assistant messages from
   // reasoning models can be replayed with their reasoning context preserved.
   const history = await sql<Message[]>`
-    SELECT ${sql.unsafe(INFERENCE_MESSAGE_COLUMNS)}
+    SELECT id, session_id, chat_id, role, content, kind, tool_calls, tool_results, status, last_seq,
+           tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at, metadata,
+           reasoning_parts
     FROM messages_with_parts
     WHERE chat_id = ${chatId} AND compacted_at IS NULL
     ORDER BY created_at ASC, id ASC

apps/server/src/services/inference/sentinel-summaries.ts

@@ -5,16 +5,16 @@ import type {
   Project,
   Session,
 } from '../../types/api.js';
+import * as modelContext from '../model-context.js';
 import { buildMessagesPayload } from './payload.js';
 import { DOOM_LOOP_THRESHOLD } from './sentinels.js';
-import { streamCompletion, samplerOptsFromAgent } from './stream-phase.js';
+import { streamCompletion } from './stream-phase.js';
-import { createContentFlusher } from './content-flusher.js';
+import { DB_FLUSH_INTERVAL_MS } from './types.js';
-import { finalizeStreamedRow } from './error-handler.js';
 import type {
   InferenceContext,
   StreamResult,
   TurnArgs,
-} from './types.js';
+} from './turn.js';
 
 // Synthetic system note appended to the cap-hit summary call. Verbatim from
 // the v1.8.2 spec — do not paraphrase: the model is more reliable when the
@@ -25,50 +25,21 @@ const CAP_HIT_SUMMARY_NOTE = (limit: number) =>
 const DOOM_LOOP_NOTE = (name: string) =>
   `You called ${name} with the same arguments ${DOOM_LOOP_THRESHOLD} times in a row. Stop calling it. Produce the best answer you can with what you have.`;
 
-// v1.14.0: step-cap wrap-up note. Names the step limit rather than the tool
+export async function runCapHitSummary(
-// budget. The sentinel reuses metadata.kind = 'cap_hit' so the frontend
-// CapHitSentinel component renders it without changes.
-const STEP_CAP_NOTE = (steps: number, cap: number) =>
-  `You've reached the step limit (${steps}/${cap} steps). Produce the best answer you can with what you have. Do not call more tools.`;
-
-// P5: the ONE generic wrap-up flow shared by the three sentinel summaries
-// (cap-hit, doom-loop, step-cap). Each reuses the in-flight assistant slot to
-// stream a short tools-disabled summary, finalizes via the same 3-outcome
-// branch (complete / cancelled / failed), bumps the session, then drops a
-// sentinel and the chat_status. The three differ only in:
-//   - `note`: the synthetic system instruction appended to the summary call.
-//   - `errorText`: the fallback used in the failed-status metadata + error frame.
-//   - sentinel timing: cap-hit inserts BEFORE the stream (`beforeStream`);
-//     doom-loop + step-cap insert AFTER the session bump (`afterSession`).
-//   - `logMsg` / `logFields`: per-kind log line + extra fields.
-// All three use error_reason / chat_status reason = 'summary_after_cap_failed'
-// (doom-loop reuses it deliberately — the user-visible failure mode is the
-// same "model gave up mid-summary"; the ErrorReason union is shared and the UI
-// surfaces a generic "summary failed" line for every sentinel path).
-interface WrapUpOpts {
-  note: string;
-  errorText: string;
-  logMsg: string;
-  logFields: Record<string, unknown>;
-  beforeStream?: () => Promise<void>;
-  afterSession?: () => Promise<void>;
-}
-
-async function runWrapUpSummary(
   ctx: InferenceContext,
   args: TurnArgs,
   session: Session,
   project: Project,
   history: Message[],
   agent: Agent | null,
-  opts: WrapUpOpts,
+  budget: number,
 ): Promise<void> {
   const { sessionId, chatId, assistantMessageId, signal } = args;
 
-  if (opts.beforeStream) await opts.beforeStream();
+  await insertCapHitSentinel(ctx, sessionId, chatId, agent, budget);
 
   const messages = await buildMessagesPayload(session, project, history, agent, ctx.log);
-  messages.push({ role: 'system', content: opts.note });
+  messages.push({ role: 'system', content: CAP_HIT_SUMMARY_NOTE(budget) });
 
   const startedRow = await ctx.sql<{ started_at: string }[]>`
     UPDATE messages
@@ -86,7 +57,25 @@ async function runWrapUpSummary(
   });
 
   let accumulated = '';
-  const flusher = createContentFlusher(ctx.sql, assistantMessageId, () => accumulated);
+  let pendingFlushTimer: NodeJS.Timeout | null = null;
+  let flushPromise: Promise<unknown> = Promise.resolve();
+  const flushNow = () => {
+    if (pendingFlushTimer) {
+      clearTimeout(pendingFlushTimer);
+      pendingFlushTimer = null;
+    }
+    const snapshot = accumulated;
+    flushPromise = flushPromise.then(() =>
+      ctx.sql`UPDATE messages SET content = ${snapshot} WHERE id = ${assistantMessageId}`
+    );
+  };
+  const scheduleFlush = () => {
+    if (pendingFlushTimer) return;
+    pendingFlushTimer = setTimeout(() => {
+      pendingFlushTimer = null;
+      flushNow();
+    }, DB_FLUSH_INTERVAL_MS);
+  };
 
   let summaryOk = false;
   let summarySoftCancelled = false;
@@ -97,7 +86,7 @@ async function runWrapUpSummary(
       ctx,
       session.model,
       messages,
-      { tools: null, ...samplerOptsFromAgent(agent) },
+      { tools: null, temperature: agent?.temperature, top_p: agent?.top_p ?? undefined, top_k: agent?.top_k ?? undefined, min_p: agent?.min_p ?? undefined, presence_penalty: agent?.presence_penalty ?? undefined, top_n_sigma: agent?.top_n_sigma ?? undefined, dry_multiplier: agent?.dry_multiplier ?? undefined, dry_base: agent?.dry_base ?? undefined, dry_allowed_length: agent?.dry_allowed_length ?? undefined, dry_penalty_last_n: agent?.dry_penalty_last_n ?? undefined },
       (delta) => {
         accumulated += delta;
         ctx.publish(sessionId, {
@@ -106,7 +95,7 @@ async function runWrapUpSummary(
           chat_id: chatId,
           content: delta,
         });
-        flusher.scheduleFlush();
+        scheduleFlush();
       },
       undefined,
       signal,
@@ -119,23 +108,44 @@ async function runWrapUpSummary(
       summaryError = err instanceof Error ? err.message : String(err);
     }
   } finally {
-    await flusher.drain();
+    if (pendingFlushTimer) {
+      clearTimeout(pendingFlushTimer);
+      pendingFlushTimer = null;
+    }
+    await flushPromise;
   }
 
-  // Finalize the summary message based on the three outcomes. The sentinel is
+  // Finalize the summary message based on the three outcomes. The sentinel
-  // inserted regardless (before or after, per opts) so the user always has the
+  // is inserted regardless so the user always has the Continue affordance —
-  // appropriate affordance — even on a partial / failed summary the chat
+  // even on a partial / failed summary the chat history shows where the
-  // history shows where the loop stopped.
+  // budget was hit.
   if (summaryOk && result) {
-    await finalizeStreamedRow(ctx, {
+    // v1.11.3: see executeToolPhase for the rationale.
-      sessionId,
+    const mctx = await modelContext.getModelContext(session.model);
-      chatId,
+    const nCtx = mctx?.n_ctx ?? null;
-      messageId: assistantMessageId,
+    const [updated] = await ctx.sql<
+      { tokens_used: number | null; ctx_used: number | null; ctx_max: number | null; finished_at: string | null }[]
+    >`
+      UPDATE messages
+      SET content = ${result.content},
+          status = 'complete',
+          tokens_used = ${result.completionTokens},
+          ctx_used = ${result.promptTokens},
+          ctx_max = ${nCtx},
+          finished_at = clock_timestamp()
+      WHERE id = ${assistantMessageId}
+      RETURNING tokens_used, ctx_used, ctx_max, finished_at
+    `;
+    ctx.publish(sessionId, {
+      type: 'message_complete',
+      message_id: assistantMessageId,
+      chat_id: chatId,
+      tokens_used: updated?.tokens_used ?? null,
+      ctx_used: updated?.ctx_used ?? null,
+      ctx_max: updated?.ctx_max ?? null,
+      started_at: startedAt,
+      finished_at: updated?.finished_at ?? null,
       model: session.model,
-      content: result.content,
-      completionTokens: result.completionTokens,
-      promptTokens: result.promptTokens,
-      startedAt,
     });
   } else if (summarySoftCancelled) {
     await ctx.sql`
@@ -154,7 +164,7 @@ async function runWrapUpSummary(
     const errMeta: MessageMetadata = {
       kind: 'error',
       error_reason: 'summary_after_cap_failed',
-      error_text: summaryError ?? opts.errorText,
+      error_text: summaryError ?? 'summary failed',
     };
     await ctx.sql`
       UPDATE messages
@@ -168,7 +178,7 @@ async function runWrapUpSummary(
       type: 'error',
       message_id: assistantMessageId,
       chat_id: chatId,
-      error: summaryError ?? opts.errorText,
+      error: summaryError ?? 'summary failed',
       reason: 'summary_after_cap_failed',
     });
   }
@@ -187,11 +197,11 @@ async function runWrapUpSummary(
     updated_at: sessRow!.updated_at,
   });
 
-  if (opts.afterSession) await opts.afterSession();
-
   // Status frame fires last so the dot color reflects the terminal state.
   // Success → idle, abort → idle (user-driven stop), error → error+reason.
-  if (summaryOk || summarySoftCancelled) {
+  if (summaryOk) {
+    ctx.publishUser({ type: 'chat_status', chat_id: chatId, status: 'idle', at: new Date().toISOString() });
+  } else if (summarySoftCancelled) {
     ctx.publishUser({ type: 'chat_status', chat_id: chatId, status: 'idle', at: new Date().toISOString() });
   } else {
     ctx.publishUser({
@@ -204,113 +214,11 @@ async function runWrapUpSummary(
   }
 
   ctx.log.info(
-    { sessionId, chatId, assistantMessageId, ...opts.logFields, summaryOk, summaryCancelled: summarySoftCancelled },
+    { sessionId, chatId, assistantMessageId, budget, summaryOk, summaryCancelled: summarySoftCancelled },
-    opts.logMsg,
+    'inference cap-hit summary finished',
   );
 }
 
-// v1.8.2: cap-hit summary flow. Called instead of erroring when the loop hits
-// its budget. The cap-hit sentinel is inserted FIRST (before the summary
-// stream) so the UI shows the Continue affordance regardless of summary
-// outcome.
-export async function runCapHitSummary(
-  ctx: InferenceContext,
-  args: TurnArgs,
-  session: Session,
-  project: Project,
-  history: Message[],
-  agent: Agent | null,
-  budget: number,
-): Promise<void> {
-  await runWrapUpSummary(ctx, args, session, project, history, agent, {
-    note: CAP_HIT_SUMMARY_NOTE(budget),
-    errorText: 'summary failed',
-    logMsg: 'inference cap-hit summary finished',
-    logFields: { budget },
-    beforeStream: () => insertCapHitSentinel(ctx, args.sessionId, args.chatId, agent, budget),
-  });
-}
-
-// v1.11.6: doom-loop wrap-up. The doom-loop sentinel is inserted AFTER the
-// session bump (no Continue affordance — continuing would re-trigger the loop
-// with the same tools available; the user needs to restate or switch agents).
-export async function runDoomLoopSummary(
-  ctx: InferenceContext,
-  args: TurnArgs,
-  session: Session,
-  project: Project,
-  history: Message[],
-  agent: Agent | null,
-  loop: { name: string; args: Record<string, unknown> },
-): Promise<void> {
-  await runWrapUpSummary(ctx, args, session, project, history, agent, {
-    note: DOOM_LOOP_NOTE(loop.name),
-    errorText: 'doom-loop summary failed',
-    logMsg: 'inference doom-loop summary finished',
-    logFields: { loopedTool: loop.name },
-    afterSession: () => insertDoomLoopSentinel(ctx, args.sessionId, args.chatId, loop),
-  });
-}
-
-// v1.14.0: step-cap wrap-up. Reuses the cap_hit sentinel (inserted AFTER the
-// session bump) so the frontend CapHitSentinel component renders it without
-// changes; the content text distinguishes step cap from budget.
-export async function runStepCapSummary(
-  ctx: InferenceContext,
-  args: TurnArgs,
-  session: Session,
-  project: Project,
-  history: Message[],
-  agent: Agent | null,
-  steps: number,
-  cap: number,
-): Promise<void> {
-  await runWrapUpSummary(ctx, args, session, project, history, agent, {
-    note: STEP_CAP_NOTE(steps, cap),
-    errorText: 'step-cap summary failed',
-    logMsg: 'inference step-cap summary finished',
-    logFields: { steps, cap },
-    afterSession: () => insertCapHitSentinel(ctx, args.sessionId, args.chatId, agent, cap),
-  });
-}
-
-// P5: the ONE INSERT + message_started → delta → message_complete frame
-// sequence shared by every sentinel inserter. The sentinel row is a
-// role='system', status='complete' message; the static content rides the same
-// streaming-frame path useSessionStream's reducer uses for assistant messages
-// (the delta carries the full text in one chunk).
-async function insertSentinel(
-  ctx: InferenceContext,
-  sessionId: string,
-  chatId: string,
-  metadata: MessageMetadata,
-  content: string,
-): Promise<void> {
-  const [row] = await ctx.sql<{ id: string }[]>`
-    INSERT INTO messages (session_id, chat_id, role, content, status, created_at, metadata)
-    VALUES (${sessionId}, ${chatId}, 'system', ${content}, 'complete', clock_timestamp(), ${ctx.sql.json(metadata as never)})
-    RETURNING id
-  `;
-  ctx.publish(sessionId, {
-    type: 'message_started',
-    message_id: row!.id,
-    chat_id: chatId,
-    role: 'system',
-  });
-  ctx.publish(sessionId, {
-    type: 'delta',
-    message_id: row!.id,
-    chat_id: chatId,
-    content,
-  });
-  ctx.publish(sessionId, {
-    type: 'message_complete',
-    message_id: row!.id,
-    chat_id: chatId,
-    metadata,
-  });
-}
-
 async function insertCapHitSentinel(
   ctx: InferenceContext,
   sessionId: string,
@@ -338,7 +246,430 @@ async function insertCapHitSentinel(
     can_continue: canContinue,
   };
   const content = `Reached tool budget (${budget}/${budget}). Continue to extend.`;
-  await insertSentinel(ctx, sessionId, chatId, metadata, content);
+
+  const [row] = await ctx.sql<{ id: string }[]>`
+    INSERT INTO messages (session_id, chat_id, role, content, status, created_at, metadata)
+    VALUES (${sessionId}, ${chatId}, 'system', ${content}, 'complete', clock_timestamp(), ${ctx.sql.json(metadata as never)})
+    RETURNING id
+  `;
+
+  // The sentinel content is static, but we still walk the standard frame
+  // sequence (started → delta → complete) so useSessionStream's reducer
+  // appends it via the same path it uses for streaming assistant messages.
+  // The delta carries the full text in one chunk.
+  ctx.publish(sessionId, {
+    type: 'message_started',
+    message_id: row!.id,
+    chat_id: chatId,
+    role: 'system',
+  });
+  ctx.publish(sessionId, {
+    type: 'delta',
+    message_id: row!.id,
+    chat_id: chatId,
+    content,
+  });
+  ctx.publish(sessionId, {
+    type: 'message_complete',
+    message_id: row!.id,
+    chat_id: chatId,
+    metadata,
+  });
+}
+
+// v1.11.6: doom-loop wrap-up. Mirrors runCapHitSummary structurally — same
+// in-flight-slot reuse, same tools-disabled streaming-summary call, same
+// post-finalize sentinel insert + chat_status drop. Differences:
+//   - synthetic note text comes from DOOM_LOOP_NOTE (names the looping tool)
+//   - sentinel metadata is { kind: 'doom_loop', tool_name, args, threshold }
+//     and has no Continue affordance (manual retry would just re-loop)
+//   - chat_status error path uses reason: 'doom_loop_summary_failed'
+// Kept as a clone rather than refactored into a shared helper because the
+// two summary paths still differ in error reason + sentinel shape; a third
+// sentinel would justify factoring out runWrapUpSummary(opts).
+export async function runDoomLoopSummary(
+  ctx: InferenceContext,
+  args: TurnArgs,
+  session: Session,
+  project: Project,
+  history: Message[],
+  agent: Agent | null,
+  loop: { name: string; args: Record<string, unknown> },
+): Promise<void> {
+  const { sessionId, chatId, assistantMessageId, signal } = args;
+
+  const messages = await buildMessagesPayload(session, project, history, agent, ctx.log);
+  messages.push({ role: 'system', content: DOOM_LOOP_NOTE(loop.name) });
+
+  const startedRow = await ctx.sql<{ started_at: string }[]>`
+    UPDATE messages
+    SET started_at = clock_timestamp()
+    WHERE id = ${assistantMessageId}
+    RETURNING started_at
+  `;
+  const startedAt = startedRow[0]?.started_at ?? null;
+
+  ctx.publish(sessionId, {
+    type: 'message_started',
+    message_id: assistantMessageId,
+    chat_id: chatId,
+    role: 'assistant',
+  });
+
+  let accumulated = '';
+  let pendingFlushTimer: NodeJS.Timeout | null = null;
+  let flushPromise: Promise<unknown> = Promise.resolve();
+  const flushNow = () => {
+    if (pendingFlushTimer) {
+      clearTimeout(pendingFlushTimer);
+      pendingFlushTimer = null;
+    }
+    const snapshot = accumulated;
+    flushPromise = flushPromise.then(() =>
+      ctx.sql`UPDATE messages SET content = ${snapshot} WHERE id = ${assistantMessageId}`
+    );
+  };
+  const scheduleFlush = () => {
+    if (pendingFlushTimer) return;
+    pendingFlushTimer = setTimeout(() => {
+      pendingFlushTimer = null;
+      flushNow();
+    }, DB_FLUSH_INTERVAL_MS);
+  };
+
+  let summaryOk = false;
+  let summarySoftCancelled = false;
+  let summaryError: string | null = null;
+  let result: StreamResult | null = null;
+  try {
+    result = await streamCompletion(
+      ctx,
+      session.model,
+      messages,
+      { tools: null, temperature: agent?.temperature, top_p: agent?.top_p ?? undefined, top_k: agent?.top_k ?? undefined, min_p: agent?.min_p ?? undefined, presence_penalty: agent?.presence_penalty ?? undefined, top_n_sigma: agent?.top_n_sigma ?? undefined, dry_multiplier: agent?.dry_multiplier ?? undefined, dry_base: agent?.dry_base ?? undefined, dry_allowed_length: agent?.dry_allowed_length ?? undefined, dry_penalty_last_n: agent?.dry_penalty_last_n ?? undefined },
+      (delta) => {
+        accumulated += delta;
+        ctx.publish(sessionId, {
+          type: 'delta',
+          message_id: assistantMessageId,
+          chat_id: chatId,
+          content: delta,
+        });
+        scheduleFlush();
+      },
+      undefined,
+      signal,
+    );
+    summaryOk = true;
+  } catch (err) {
+    if (err instanceof Error && err.name === 'AbortError') {
+      summarySoftCancelled = true;
+    } else {
+      summaryError = err instanceof Error ? err.message : String(err);
+    }
+  } finally {
+    if (pendingFlushTimer) {
+      clearTimeout(pendingFlushTimer);
+      pendingFlushTimer = null;
+    }
+    await flushPromise;
+  }
+
+  if (summaryOk && result) {
+    const mctx = await modelContext.getModelContext(session.model);
+    const nCtx = mctx?.n_ctx ?? null;
+    const [updated] = await ctx.sql<
+      { tokens_used: number | null; ctx_used: number | null; ctx_max: number | null; finished_at: string | null }[]
+    >`
+      UPDATE messages
+      SET content = ${result.content},
+          status = 'complete',
+          tokens_used = ${result.completionTokens},
+          ctx_used = ${result.promptTokens},
+          ctx_max = ${nCtx},
+          finished_at = clock_timestamp()
+      WHERE id = ${assistantMessageId}
+      RETURNING tokens_used, ctx_used, ctx_max, finished_at
+    `;
+    ctx.publish(sessionId, {
+      type: 'message_complete',
+      message_id: assistantMessageId,
+      chat_id: chatId,
+      tokens_used: updated?.tokens_used ?? null,
+      ctx_used: updated?.ctx_used ?? null,
+      ctx_max: updated?.ctx_max ?? null,
+      started_at: startedAt,
+      finished_at: updated?.finished_at ?? null,
+      model: session.model,
+    });
+  } else if (summarySoftCancelled) {
+    await ctx.sql`
+      UPDATE messages
+      SET content = ${accumulated},
+          status = 'cancelled',
+          finished_at = clock_timestamp()
+      WHERE id = ${assistantMessageId}
+    `;
+    ctx.publish(sessionId, {
+      type: 'message_complete',
+      message_id: assistantMessageId,
+      chat_id: chatId,
+    });
+  } else {
+    // Doom-loop summary failure reuses the existing summary_after_cap_failed
+    // error reason — the ErrorReason union is shared between sentinel paths
+    // and the UI surfaces a generic "summary failed" line for both. We don't
+    // add a new reason code because the user-visible failure mode is the
+    // same (model gave up mid-summary). Sentinel below still fires.
+    const errMeta: MessageMetadata = {
+      kind: 'error',
+      error_reason: 'summary_after_cap_failed',
+      error_text: summaryError ?? 'doom-loop summary failed',
+    };
+    await ctx.sql`
+      UPDATE messages
+      SET content = ${accumulated},
+          status = 'failed',
+          finished_at = clock_timestamp(),
+          metadata = ${ctx.sql.json(errMeta as never)}
+      WHERE id = ${assistantMessageId}
+    `;
+    ctx.publish(sessionId, {
+      type: 'error',
+      message_id: assistantMessageId,
+      chat_id: chatId,
+      error: summaryError ?? 'doom-loop summary failed',
+      reason: 'summary_after_cap_failed',
+    });
+  }
+
+  const [sessRow] = await ctx.sql<{ project_id: string; name: string; updated_at: string }[]>`
+    UPDATE sessions SET updated_at = clock_timestamp()
+    WHERE id = ${sessionId}
+    RETURNING project_id, name, updated_at
+  `;
+  ctx.publishUser({
+    type: 'session_updated',
+    session_id: sessionId,
+    project_id: sessRow!.project_id,
+    name: sessRow!.name,
+    updated_at: sessRow!.updated_at,
+  });
+
+  await insertDoomLoopSentinel(ctx, sessionId, chatId, loop);
+
+  if (summaryOk || summarySoftCancelled) {
+    ctx.publishUser({ type: 'chat_status', chat_id: chatId, status: 'idle', at: new Date().toISOString() });
+  } else {
+    ctx.publishUser({
+      type: 'chat_status',
+      chat_id: chatId,
+      status: 'error',
+      at: new Date().toISOString(),
+      reason: 'summary_after_cap_failed',
+    });
+  }
+
+  ctx.log.info(
+    { sessionId, chatId, assistantMessageId, loopedTool: loop.name, summaryOk, summaryCancelled: summarySoftCancelled },
+    'inference doom-loop summary finished',
+  );
+}
+
+// v1.14.0: step-cap wrap-up. Mirrors runCapHitSummary structurally — same
+// in-flight-slot reuse, same tools-disabled streaming-summary call, same
+// post-finalize sentinel insert + chat_status drop. Difference: the note
+// text names the step limit rather than the tool budget. Sentinel reuses
+// metadata.kind = 'cap_hit' so the frontend CapHitSentinel component
+// renders it without changes.
+const STEP_CAP_NOTE = (steps: number, cap: number) =>
+  `You've reached the step limit (${steps}/${cap} steps). Produce the best answer you can with what you have. Do not call more tools.`;
+
+export async function runStepCapSummary(
+  ctx: InferenceContext,
+  args: TurnArgs,
+  session: Session,
+  project: Project,
+  history: Message[],
+  agent: Agent | null,
+  steps: number,
+  cap: number,
+): Promise<void> {
+  const { sessionId, chatId, assistantMessageId, signal } = args;
+
+  const messages = await buildMessagesPayload(session, project, history, agent, ctx.log);
+  messages.push({ role: 'system', content: STEP_CAP_NOTE(steps, cap) });
+
+  const startedRow = await ctx.sql<{ started_at: string }[]>`
+    UPDATE messages
+    SET started_at = clock_timestamp()
+    WHERE id = ${assistantMessageId}
+    RETURNING started_at
+  `;
+  const startedAt = startedRow[0]?.started_at ?? null;
+
+  ctx.publish(sessionId, {
+    type: 'message_started',
+    message_id: assistantMessageId,
+    chat_id: chatId,
+    role: 'assistant',
+  });
+
+  let accumulated = '';
+  let pendingFlushTimer: NodeJS.Timeout | null = null;
+  let flushPromise: Promise<unknown> = Promise.resolve();
+  const flushNow = () => {
+    if (pendingFlushTimer) {
+      clearTimeout(pendingFlushTimer);
+      pendingFlushTimer = null;
+    }
+    const snapshot = accumulated;
+    flushPromise = flushPromise.then(() =>
+      ctx.sql`UPDATE messages SET content = ${snapshot} WHERE id = ${assistantMessageId}`
+    );
+  };
+  const scheduleFlush = () => {
+    if (pendingFlushTimer) return;
+    pendingFlushTimer = setTimeout(() => {
+      pendingFlushTimer = null;
+      flushNow();
+    }, DB_FLUSH_INTERVAL_MS);
+  };
+
+  let summaryOk = false;
+  let summarySoftCancelled = false;
+  let summaryError: string | null = null;
+  let result: StreamResult | null = null;
+  try {
+    result = await streamCompletion(
+      ctx,
+      session.model,
+      messages,
+      { tools: null, temperature: agent?.temperature, top_p: agent?.top_p ?? undefined, top_k: agent?.top_k ?? undefined, min_p: agent?.min_p ?? undefined, presence_penalty: agent?.presence_penalty ?? undefined, top_n_sigma: agent?.top_n_sigma ?? undefined, dry_multiplier: agent?.dry_multiplier ?? undefined, dry_base: agent?.dry_base ?? undefined, dry_allowed_length: agent?.dry_allowed_length ?? undefined, dry_penalty_last_n: agent?.dry_penalty_last_n ?? undefined },
+      (delta) => {
+        accumulated += delta;
+        ctx.publish(sessionId, {
+          type: 'delta',
+          message_id: assistantMessageId,
+          chat_id: chatId,
+          content: delta,
+        });
+        scheduleFlush();
+      },
+      undefined,
+      signal,
+    );
+    summaryOk = true;
+  } catch (err) {
+    if (err instanceof Error && err.name === 'AbortError') {
+      summarySoftCancelled = true;
+    } else {
+      summaryError = err instanceof Error ? err.message : String(err);
+    }
+  } finally {
+    if (pendingFlushTimer) {
+      clearTimeout(pendingFlushTimer);
+      pendingFlushTimer = null;
+    }
+    await flushPromise;
+  }
+
+  if (summaryOk && result) {
+    const mctx = await modelContext.getModelContext(session.model);
+    const nCtx = mctx?.n_ctx ?? null;
+    const [updated] = await ctx.sql<
+      { tokens_used: number | null; ctx_used: number | null; ctx_max: number | null; finished_at: string | null }[]
+    >`
+      UPDATE messages
+      SET content = ${result.content},
+          status = 'complete',
+          tokens_used = ${result.completionTokens},
+          ctx_used = ${result.promptTokens},
+          ctx_max = ${nCtx},
+          finished_at = clock_timestamp()
+      WHERE id = ${assistantMessageId}
+      RETURNING tokens_used, ctx_used, ctx_max, finished_at
+    `;
+    ctx.publish(sessionId, {
+      type: 'message_complete',
+      message_id: assistantMessageId,
+      chat_id: chatId,
+      tokens_used: updated?.tokens_used ?? null,
+      ctx_used: updated?.ctx_used ?? null,
+      ctx_max: updated?.ctx_max ?? null,
+      started_at: startedAt,
+      finished_at: updated?.finished_at ?? null,
+      model: session.model,
+    });
+  } else if (summarySoftCancelled) {
+    await ctx.sql`
+      UPDATE messages
+      SET content = ${accumulated},
+          status = 'cancelled',
+          finished_at = clock_timestamp()
+      WHERE id = ${assistantMessageId}
+    `;
+    ctx.publish(sessionId, {
+      type: 'message_complete',
+      message_id: assistantMessageId,
+      chat_id: chatId,
+    });
+  } else {
+    const errMeta: MessageMetadata = {
+      kind: 'error',
+      error_reason: 'summary_after_cap_failed',
+      error_text: summaryError ?? 'step-cap summary failed',
+    };
+    await ctx.sql`
+      UPDATE messages
+      SET content = ${accumulated},
+          status = 'failed',
+          finished_at = clock_timestamp(),
+          metadata = ${ctx.sql.json(errMeta as never)}
+      WHERE id = ${assistantMessageId}
+    `;
+    ctx.publish(sessionId, {
+      type: 'error',
+      message_id: assistantMessageId,
+      chat_id: chatId,
+      error: summaryError ?? 'step-cap summary failed',
+      reason: 'summary_after_cap_failed',
+    });
+  }
+
+  const [sessRow] = await ctx.sql<{ project_id: string; name: string; updated_at: string }[]>`
+    UPDATE sessions SET updated_at = clock_timestamp()
+    WHERE id = ${sessionId}
+    RETURNING project_id, name, updated_at
+  `;
+  ctx.publishUser({
+    type: 'session_updated',
+    session_id: sessionId,
+    project_id: sessRow!.project_id,
+    name: sessRow!.name,
+    updated_at: sessRow!.updated_at,
+  });
+
+  // Reuse cap_hit sentinel so the frontend CapHitSentinel component renders
+  // it without changes. The content text distinguishes step cap from budget.
+  await insertCapHitSentinel(ctx, sessionId, chatId, agent, cap);
+
+  if (summaryOk || summarySoftCancelled) {
+    ctx.publishUser({ type: 'chat_status', chat_id: chatId, status: 'idle', at: new Date().toISOString() });
+  } else {
+    ctx.publishUser({
+      type: 'chat_status',
+      chat_id: chatId,
+      status: 'error',
+      at: new Date().toISOString(),
+      reason: 'summary_after_cap_failed',
+    });
+  }
+
+  ctx.log.info(
+    { sessionId, chatId, assistantMessageId, steps, cap, summaryOk, summaryCancelled: summarySoftCancelled },
+    'inference step-cap summary finished',
+  );
 }
 
 async function insertDoomLoopSentinel(
@@ -358,12 +689,39 @@ async function insertDoomLoopSentinel(
     threshold: DOOM_LOOP_THRESHOLD,
   };
   const content = `Detected ${DOOM_LOOP_THRESHOLD} identical calls to ${loop.name}. Stopping the tool-call loop. Produce the best answer you can with what you have.`;
-  await insertSentinel(ctx, sessionId, chatId, metadata, content);
+
+  const [row] = await ctx.sql<{ id: string }[]>`
+    INSERT INTO messages (session_id, chat_id, role, content, status, created_at, metadata)
+    VALUES (${sessionId}, ${chatId}, 'system', ${content}, 'complete', clock_timestamp(), ${ctx.sql.json(metadata as never)})
+    RETURNING id
+  `;
+
+  // Standard frame sequence — same as cap-hit sentinel — so
+  // useSessionStream's reducer appends the row via the existing path.
+  ctx.publish(sessionId, {
+    type: 'message_started',
+    message_id: row!.id,
+    chat_id: chatId,
+    role: 'system',
+  });
+  ctx.publish(sessionId, {
+    type: 'delta',
+    message_id: row!.id,
+    chat_id: chatId,
+    content,
+  });
+  ctx.publish(sessionId, {
+    type: 'message_complete',
+    message_id: row!.id,
+    chat_id: chatId,
+    metadata,
+  });
 }
 
-// #12 MistakeTracker: heterogeneous-failure recovery sentinel. A role='system',
+// #12 MistakeTracker: heterogeneous-failure recovery sentinel. Mirrors
-// status='complete' row firing the standard sentinel frame sequence. Two
+// insertDoomLoopSentinel structurally — a role='system', status='complete' row
-// variants distinguished by `escalated`:
+// firing the standard message_started → delta → message_complete frame
+// sequence. Two variants distinguished by `escalated`:
 //   - escalated:false → a nudge fired; recovery guidance was injected into the
 //     model's next step and the loop continued. can_continue is true (the turn
 //     is still live).
@@ -386,5 +744,30 @@ export async function insertMistakeRecoverySentinel(
   const content = opts.escalated
     ? `Repeated different errors persisted after a recovery nudge (${opts.count} in a row). Stopping the tool-call loop.`
     : `Hit ${opts.count} different errors in a row. Injected recovery guidance and continuing.`;
-  await insertSentinel(ctx, sessionId, chatId, metadata, content);
+
+  const [row] = await ctx.sql<{ id: string }[]>`
+    INSERT INTO messages (session_id, chat_id, role, content, status, created_at, metadata)
+    VALUES (${sessionId}, ${chatId}, 'system', ${content}, 'complete', clock_timestamp(), ${ctx.sql.json(metadata as never)})
+    RETURNING id
+  `;
+
+  // Standard frame sequence — same as cap-hit / doom-loop sentinels.
+  ctx.publish(sessionId, {
+    type: 'message_started',
+    message_id: row!.id,
+    chat_id: chatId,
+    role: 'system',
+  });
+  ctx.publish(sessionId, {
+    type: 'delta',
+    message_id: row!.id,
+    chat_id: chatId,
+    content,
+  });
+  ctx.publish(sessionId, {
+    type: 'message_complete',
+    message_id: row!.id,
+    chat_id: chatId,
+    metadata,
+  });
 }

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

@@ -27,10 +27,6 @@ export function detectDoomLoop(
   return { name: ref.name, args: ref.args };
 }
 
-// All sentinel kinds. isAnySentinel and compaction.ts's local predicate both
-// consume this set — single source so a new kind can't be missed in one.
-export const SENTINEL_KINDS = new Set(['cap_hit', 'doom_loop', 'mistake_recovery']);
-
 export function isCapHitSentinel(m: Message): boolean {
   return (
     m.role === 'system' &&
@@ -65,10 +61,5 @@ export function isMistakeRecoverySentinel(m: Message): boolean {
 }
 
 export function isAnySentinel(m: Message): boolean {
-  return (
+  return isCapHitSentinel(m) || isDoomLoopSentinel(m) || isMistakeRecoverySentinel(m);
-    m.role === 'system' &&
-    m.metadata !== null &&
-    typeof m.metadata === 'object' &&
-    SENTINEL_KINDS.has((m.metadata as { kind?: unknown }).kind as string)
-  );
 }

apps/server/src/services/inference/step-decision.ts

@@ -1,47 +0,0 @@
-// P5 (SPLIT SKETCH 5): pure step-decision helpers for the runAssistantTurn
-// loop. These COMPOSE the existing decision predicates (detectDoomLoop,
-// detectMistakePattern) — they do not reimplement them — so the loop body in
-// turn.ts becomes a thin driver and the branch logic is unit-testable without
-// a DB, broker, or stream.
-
-import type { ToolCall } from '../../types/api.js';
-import { detectDoomLoop } from './sentinels.js';
-import { detectMistakePattern, type MistakeState } from './mistake-tracker.js';
-import type { ToolPhaseResult } from './tool-phase.js';
-
-// Top-of-loop gate, evaluated before the stream phase. Order matters and
-// matches the original inline checks exactly: doom-loop first (identical-repeat
-// guard), then the cumulative tool-call budget, otherwise proceed to stream.
-export type PreStepDecision =
-  | { kind: 'doom'; loop: { name: string; args: Record<string, unknown> } }
-  | { kind: 'budget' }
-  | { kind: 'stream' };
-
-export function decideStep(input: {
-  recentToolCalls: ToolCall[];
-  toolsUsed: number;
-  budget: number;
-}): PreStepDecision {
-  const loop = detectDoomLoop(input.recentToolCalls);
-  if (loop) return { kind: 'doom', loop };
-  if (input.toolsUsed >= input.budget) return { kind: 'budget' };
-  return { kind: 'stream' };
-}
-
-// Post-tool-phase decision, evaluated after the tool phase returns. 'stop'
-// covers the tool-phase's own non-'continue' actions ('paused' for user input,
-// 'synthesis_done'); on 'continue' the mistake-tracker pattern gates the
-// nudge/escalate/continue choice (detectMistakePattern is only consulted on the
-// 'continue' path, exactly as the original loop did).
-export type PostToolDecision = 'continue' | 'nudge' | 'escalate' | 'stop';
-
-export function decidePostToolAction(
-  action: ToolPhaseResult['action'],
-  mistakeTracker: MistakeState,
-): PostToolDecision {
-  if (action !== 'continue') return 'stop';
-  const mistake = detectMistakePattern(mistakeTracker);
-  if (mistake === 'nudge') return 'nudge';
-  if (mistake === 'escalate') return 'escalate';
-  return 'continue';
-}

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

@@ -1,405 +0,0 @@
-// P5 (SPLIT SKETCH): the generic AI-SDK adapter, split out of stream-phase.ts.
-// This module is the v1.13.1-A streamText adapter and nothing else — it has NO
-// SQL, broker, or BooCode persistence dependencies (its only `ctx` access is
-// config + log), so it can be unit-tested without standing up a DB or broker.
-// stream-phase.ts (the I/O layer) re-exports the public names below so existing
-// importers (`./stream-phase.js`) are unchanged.
-
-import type { FastifyBaseLogger } from 'fastify';
-import type { Config } from '../../config.js';
-import type { Agent, ToolCall } from '../../types/api.js';
-import type { ToolJsonSchema } from '../tools.js';
-import type { OpenAiMessage } from './payload.js';
-import { extractToolCallBlocks } from './tool-call-parser.js';
-import type { StreamResult } from './types.js';
-import { upstreamModel } from './provider.js';
-import {
-  jsonSchema,
-  streamText,
-  tool,
-  type JSONValue,
-  type ModelMessage,
-  type ToolCallRepairFunction,
-} from 'ai';
-
-// The slice of InferenceContext the adapter actually needs. Narrowing it here
-// (instead of taking the full InferenceContext) keeps the adapter free of the
-// SQL/broker/publish surface. InferenceContext structurally satisfies this, so
-// callers pass their ctx unchanged.
-export interface StreamAdapterContext {
-  config: Config;
-  log: FastifyBaseLogger;
-}
-
-export interface StreamOptions {
-  // null = omit tools entirely (compact phase); [] = caller stripped all tools
-  // (rare; we still omit from the request body to avoid OpenAI 400).
-  tools: ToolJsonSchema[] | null;
-  temperature?: number;
-  top_p?: number | null;
-  top_k?: number | null;
-  min_p?: number | null;
-  presence_penalty?: number | null;
-  // v2.6 sampling-streamjson-tokens (#11): llama.cpp sampler extensions. These
-  // are NOT standard AI-SDK streamText options and are NOT serialized by the
-  // openai-compatible provider's standardized-settings path (topK is even
-  // explicitly dropped with an "unsupported feature: topK" warning). They reach
-  // llama-server only via providerOptions.openaiCompatible (see buildSamplerProviderOptions).
-  top_n_sigma?: number | null;
-  dry_multiplier?: number | null;
-  dry_base?: number | null;
-  dry_allowed_length?: number | null;
-  dry_penalty_last_n?: number | null;
-}
-
-// P5: the 10-field sampler-options literal that was copy-pasted at 4 sites
-// (the three sentinel summaries + executeStreamPhase). Builds the StreamOptions
-// sampler subset from an agent's frontmatter knobs. `temperature` is
-// `agent?.temperature` (already number|undefined); the nullable fields strip
-// null → undefined so they're omitted from the request body when unset. Keep
-// this in lockstep with the StreamOptions sampler fields — a new sampler knob
-// (the v2.7.3 dry_* family did this) is added here once instead of at 4 sites.
-export type SamplerOpts = Omit<StreamOptions, 'tools'>;
-
-export function samplerOptsFromAgent(agent: Agent | null): SamplerOpts {
-  return {
-    temperature: agent?.temperature,
-    top_p: agent?.top_p ?? undefined,
-    top_k: agent?.top_k ?? undefined,
-    min_p: agent?.min_p ?? undefined,
-    presence_penalty: agent?.presence_penalty ?? undefined,
-    top_n_sigma: agent?.top_n_sigma ?? undefined,
-    dry_multiplier: agent?.dry_multiplier ?? undefined,
-    dry_base: agent?.dry_base ?? undefined,
-    dry_allowed_length: agent?.dry_allowed_length ?? undefined,
-    dry_penalty_last_n: agent?.dry_penalty_last_n ?? undefined,
-  };
-}
-
-// v2.6 #11: build the providerOptions.openaiCompatible extraBody object for the
-// llama.cpp sampler extensions. @ai-sdk/openai-compatible (2.0.47) merges every
-// non-reserved key under providerOptions.openaiCompatible straight into the
-// chat-completion request body (see its getArgs: the Object.fromEntries spread
-// filtered against openaiCompatibleLanguageModelChatOptions.shape). This is the
-// ONLY working passthrough for these params:
-//   - top_k / min_p were latently dropped before this: top_k was passed as the
-//     AI-SDK `topK` setting which the openai-compatible provider rejects as
-//     unsupported; min_p was never passed to streamText at all.
-//   - top_n_sigma + the dry_* family have no AI-SDK equivalent.
-// Keys use llama-server's snake_case body names so they land verbatim.
-function buildSamplerProviderOptions(opts: StreamOptions): Record<string, number> | undefined {
-  const body: Record<string, number> = {};
-  if (typeof opts.top_k === 'number') body.top_k = opts.top_k;
-  if (typeof opts.min_p === 'number') body.min_p = opts.min_p;
-  if (typeof opts.top_n_sigma === 'number') body.top_n_sigma = opts.top_n_sigma;
-  if (typeof opts.dry_multiplier === 'number') body.dry_multiplier = opts.dry_multiplier;
-  if (typeof opts.dry_base === 'number') body.dry_base = opts.dry_base;
-  if (typeof opts.dry_allowed_length === 'number') body.dry_allowed_length = opts.dry_allowed_length;
-  if (typeof opts.dry_penalty_last_n === 'number') body.dry_penalty_last_n = opts.dry_penalty_last_n;
-  return Object.keys(body).length > 0 ? body : undefined;
-}
-
-// v1.13.1-A: convert BooCode's OpenAI-shaped history into AI SDK
-// ModelMessage[]. Tool result messages need a `toolName` field that the
-// OpenAI shape doesn't carry; we look it up by scanning earlier assistant
-// `tool_calls` entries for a matching id.
-function toModelMessages(messages: OpenAiMessage[]): ModelMessage[] {
-  const toolNameById = new Map<string, string>();
-  for (const m of messages) {
-    if (m.role === 'assistant' && m.tool_calls) {
-      for (const tc of m.tool_calls) {
-        toolNameById.set(tc.id, tc.function.name);
-      }
-    }
-  }
-  const out: ModelMessage[] = [];
-  for (const m of messages) {
-    if (m.role === 'system' || m.role === 'user') {
-      out.push({ role: m.role, content: m.content ?? '' });
-      continue;
-    }
-    if (m.role === 'assistant') {
-      const hasTools = m.tool_calls && m.tool_calls.length > 0;
-      const hasReasoning = typeof m.reasoning === 'string' && m.reasoning.length > 0;
-      if (!hasTools && !hasReasoning) {
-        // Bare text assistant (string content). null content + no tool_calls
-        // is degenerate but harmless to forward.
-        out.push({ role: 'assistant', content: m.content ?? '' });
-        continue;
-      }
-      // v1.13.1-C: AI SDK ReasoningPart precedes text + tool-calls in the
-      // assistant content array. Reasoning models (qwen3.6) consume their
-      // prior reasoning context to resume mid-thought across tool boundaries.
-      const parts: Array<
-        | { type: 'reasoning'; text: string }
-        | { type: 'text'; text: string }
-        | { type: 'tool-call'; toolCallId: string; toolName: string; input: unknown }
-      > = [];
-      if (hasReasoning) {
-        parts.push({ type: 'reasoning', text: m.reasoning! });
-      }
-      if (m.content && m.content.length > 0) {
-        parts.push({ type: 'text', text: m.content });
-      }
-      for (const tc of m.tool_calls ?? []) {
-        let input: unknown = {};
-        try {
-          input = tc.function.arguments.length > 0 ? JSON.parse(tc.function.arguments) : {};
-        } catch {
-          // Malformed args from a prior turn: pass through as a raw blob so
-          // the model sees the same shape it emitted. Wraps the string under
-          // _raw to match the buildMessagesPayload upstream convention.
-          input = { _raw: tc.function.arguments };
-        }
-        parts.push({ type: 'tool-call', toolCallId: tc.id, toolName: tc.function.name, input });
-      }
-      out.push({ role: 'assistant', content: parts });
-      continue;
-    }
-    if (m.role === 'tool') {
-      const toolCallId = m.tool_call_id ?? '';
-      const toolName = toolNameById.get(toolCallId) ?? 'unknown';
-      const raw = m.content ?? '';
-      let output: { type: 'text'; value: string } | { type: 'json'; value: JSONValue };
-      try {
-        // JSON.parse returns `any`; cast to JSONValue since the upstream
-        // tool_results column is already JSON-serializable by construction.
-        output = { type: 'json', value: JSON.parse(raw) as JSONValue };
-      } catch {
-        output = { type: 'text', value: raw };
-      }
-      out.push({
-        role: 'tool',
-        content: [{ type: 'tool-result', toolCallId, toolName, output }],
-      });
-      continue;
-    }
-  }
-  return out;
-}
-
-// Build the AI SDK tools record from BooCode's JSON-schema tool definitions.
-// No `execute` field: BooCode runs tools itself in tool-phase.ts; streamText
-// surfaces the tool-call parts via fullStream and we capture them for the
-// outer loop to dispatch.
-function buildAiTools(schemas: ToolJsonSchema[]): Record<string, ReturnType<typeof tool>> {
-  const out: Record<string, ReturnType<typeof tool>> = {};
-  for (const s of schemas) {
-    out[s.function.name] = tool({
-      description: s.function.description,
-      inputSchema: jsonSchema(s.function.parameters),
-    });
-  }
-  return out;
-}
-
-// v1.10.5 Qwen-coder XML fallback. Some local models (notably qwen3-coder via
-// llama-swap) emit tool calls as inline XML inside delta.content rather than
-// the structured tool_calls field. We extract them out of the streamed text
-// before flushing it to the client.
-//
-// Qwen shape:
-//   <tool_call>
-//   <function=NAME>
-//   <parameter=KEY>VALUE</parameter>
-//   ...
-//   </function>
-//   </tool_call>
-//
-// v1.13.16: also recognize Anthropic <invoke> markup that qwen3.6-35b-a3b-mxfp4
-// drifts to (training-data residue from Claude Code documentation):
-//   <invoke name="NAME">
-//   <parameter name="KEY">VALUE</parameter>
-//   </invoke>
-// Both formats share the synthetic xml_call_${idx} ID space; the counter
-// increments across whichever opener appears first. Multiple blocks may
-// appear back-to-back in either format and they never nest.
-export async function streamCompletion(
-  ctx: StreamAdapterContext,
-  model: string,
-  messages: OpenAiMessage[],
-  opts: StreamOptions,
-  onDelta: (content: string) => void,
-  onUsage: ((prompt: number | null, completion: number | null) => void) | undefined,
-  signal?: AbortSignal,
-  agent?: Agent | null,
-): Promise<StreamResult> {
-  const aiMessages = toModelMessages(messages);
-  const hasTools = opts.tools !== null && opts.tools.length > 0;
-  const aiTools = hasTools ? buildAiTools(opts.tools!) : undefined;
-
-  const startedAt = Date.now();
-  // v1.13.1-C: accumulate reasoning text across reasoning-delta parts.
-  // qwen3.6 emits these on a separate channel from text content; we capture
-  // them per stream so finalizeCompletion can dual-write a 'reasoning' part.
-  // Replaces the v1.13.1-A counter-only diagnostic.
-  let reasoningAccumulated = '';
-
-  // v1.13.3: experimental_repairToolCall keeps the stream alive when the
-  // model emits a malformed tool call (bad JSON args, unknown name, etc.).
-  // Without a repair function streamText throws and the WHOLE stream dies;
-  // with one, the SDK invokes us and we route the bad call through normally.
-  // Strategy: pass through unmodified. executeToolPhase's existing error
-  // path (unknown tool name → "unknown tool: X" result; zod-reject → tool
-  // 'X' rejected — fieldname: required) already gives the model a clean
-  // recovery surface on the next turn. Logging gives us visibility into
-  // how often qwen3.6 actually emits broken calls.
-  const repairToolCall: ToolCallRepairFunction<NonNullable<typeof aiTools>> = async ({
-    toolCall,
-    error,
-  }) => {
-    ctx.log.warn(
-      {
-        toolCallId: toolCall.toolCallId,
-        toolName: toolCall.toolName,
-        error: error.message,
-      },
-      'malformed tool call surfaced via repairToolCall',
-    );
-    return toolCall;
-  };
-
-  // v2.6 #11: llama.cpp sampler extensions (top_k, min_p, top_n_sigma, dry_*)
-  // ride providerOptions.openaiCompatible — they are NOT standardized streamText
-  // settings. NB: top_k used to be passed below as the AI-SDK `topK` setting;
-  // the openai-compatible provider dropped it with an "unsupported feature: topK"
-  // warning and min_p was never wired at all, so both were dead on the wire
-  // before this. They now go through the same extraBody path as the new params.
-  const samplerBody = buildSamplerProviderOptions(opts);
-
-  const result = streamText({
-    model: upstreamModel(ctx.config, model, agent ?? null),
-    messages: aiMessages,
-    ...(aiTools
-      ? { tools: aiTools, toolChoice: 'auto' as const, experimental_repairToolCall: repairToolCall }
-      : {}),
-    ...(typeof opts.temperature === 'number' ? { temperature: opts.temperature } : {}),
-    ...(typeof opts.top_p === 'number' ? { topP: opts.top_p } : {}),
-    ...(typeof opts.presence_penalty === 'number' ? { presencePenalty: opts.presence_penalty } : {}),
-    ...(samplerBody ? { providerOptions: { openaiCompatible: samplerBody } } : {}),
-    abortSignal: signal,
-  });
-
-  let content = '';
-  let pendingBuffer = '';
-  let finishReason: string | null = null;
-  // v1.13.1-A: AI SDK emits one `tool-call` part per fully-aggregated call,
-  // so we no longer need the OpenAI-index reassembly map the manual SSE
-  // parser used. XML tool calls extracted from text content go into the
-  // same flat list and keep the v1.10.5 synthetic id convention.
-  const toolCalls: ToolCall[] = [];
-
-  for await (const part of result.fullStream) {
-    switch (part.type) {
-      case 'text-delta': {
-        pendingBuffer += part.text;
-        // v1.13.16: unified extraction. The helper finds the earliest-opening
-        // complete <tool_call> or <invoke> block, flushes prose between/around
-        // them, holds any partial opener for the next chunk, and silently
-        // drops blocks that fail to parse (matches pre-v1.13.16 behavior).
-        const extracted = extractToolCallBlocks(pendingBuffer);
-        if (extracted.flushed.length > 0) {
-          content += extracted.flushed;
-          onDelta(extracted.flushed);
-        }
-        for (const call of extracted.calls) {
-          const synthIdx = toolCalls.length;
-          toolCalls.push({
-            id: `xml_call_${synthIdx}`,
-            name: call.name,
-            args: call.args,
-          });
-        }
-        pendingBuffer = extracted.remaining;
-        break;
-      }
-      case 'tool-call': {
-        // AI SDK has already parsed the input into an object. Match the
-        // ToolCall shape BooCode passes around in toolCallsBuffer downstream.
-        toolCalls.push({
-          id: part.toolCallId,
-          name: part.toolName,
-          args: (part.input ?? {}) as Record<string, unknown>,
-        });
-        break;
-      }
-      case 'reasoning-delta': {
-        // v1.13.1-C: accumulate; finalizeCompletion / executeToolPhase
-        // dual-write the resulting text as a kind='reasoning' part.
-        if (typeof part.text === 'string') {
-          reasoningAccumulated += part.text;
-        }
-        break;
-      }
-      case 'finish': {
-        if (typeof part.finishReason === 'string') {
-          finishReason = part.finishReason;
-        }
-        break;
-      }
-      case 'error': {
-        const err = part.error;
-        throw err instanceof Error ? err : new Error(String(err));
-      }
-      // Intentional no-op: start, start-step, text-start, text-end,
-      // reasoning-start, reasoning-end, source, file, tool-input-start,
-      // tool-input-delta, tool-input-end, tool-result, tool-error,
-      // finish-step, raw. We only care about the aggregated tool-call and
-      // text-delta paths above; the rest are AI SDK lifecycle/streaming
-      // breadcrumbs that don't change BooCode's persistence or WS contract.
-      default:
-        break;
-    }
-  }
-
-  // v1.13.1-A: drain any buffered partial XML opener as plain text. The
-  // pre-AI-SDK path did this on stream end too — better to leak `<tool_c`
-  // than vanish the text.
-  if (pendingBuffer.length > 0) {
-    content += pendingBuffer;
-    onDelta(pendingBuffer);
-    pendingBuffer = '';
-  }
-
-  // AI SDK v6 fullStream returns normally on abort; check signal explicitly.
-  // Without this throw the row would land as status='complete' with partial
-  // content instead of going through handleAbortOrError → status='cancelled'.
-  // Smoke D caught this in v1.13.1-A — don't refactor it away.
-  if (signal?.aborted) {
-    const abortErr = new Error('aborted');
-    abortErr.name = 'AbortError';
-    throw abortErr;
-  }
-
-  // Usage lands as a promise on the result; awaiting after fullStream is
-  // drained is safe. AI SDK v6 names: `inputTokens` / `outputTokens`.
-  let promptTokens: number | null = null;
-  let completionTokens: number | null = null;
-  try {
-    const usage = await result.usage;
-    if (typeof usage.inputTokens === 'number') promptTokens = usage.inputTokens;
-    if (typeof usage.outputTokens === 'number') completionTokens = usage.outputTokens;
-  } catch {
-    // Some providers omit usage on partial streams; leave both null.
-  }
-
-  if (onUsage && (promptTokens !== null || completionTokens !== null)) {
-    onUsage(promptTokens, completionTokens);
-  }
-
-  if (reasoningAccumulated.length > 0) {
-    ctx.log.debug(
-      { reasoningChars: reasoningAccumulated.length, model, elapsed_ms: Date.now() - startedAt },
-      'streamCompletion: captured reasoning',
-    );
-  }
-
-  return {
-    finishReason,
-    content,
-    toolCalls,
-    promptTokens,
-    completionTokens,
-    reasoning: reasoningAccumulated,
-  };
-}

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

@@ -1,34 +1,377 @@
-// P5 (SPLIT SKETCH): stream-phase.ts is now the BooCode I/O layer for the
+import type {
-// stream phase — `executeStreamPhase` owns the row UPDATE, message_started
+  Agent,
-// frame, debounced content flush, throttled usage publish, model-context
+  Session,
-// lookup, and tool-whitelist filter. The generic AI-SDK adapter
+  ToolCall,
-// (streamCompletion / toModelMessages / buildAiTools / sampler helpers) moved
+} from '../../types/api.js';
-// to ./stream-phase-adapter.ts, which has no SQL/broker/publish deps and is
-// unit-testable on its own. The adapter's public names are re-exported below so
-// existing importers of './stream-phase.js' (sentinel-summaries, synthesis
-// pipeline, the helper tests) keep working unchanged.
-
-import type { Agent, Session } from '../../types/api.js';
 import * as modelContext from '../model-context.js';
 import { toolJsonSchemas, type ToolJsonSchema } from '../tools.js';
 import { matchToolGlob } from '../agents.js';
 import type { OpenAiMessage } from './payload.js';
-import { createContentFlusher } from './content-flusher.js';
+import { extractToolCallBlocks } from './tool-call-parser.js';
+import { DB_FLUSH_INTERVAL_MS, type StreamPhaseState } from './types.js';
 import type {
-  StreamPhaseState,
   InferenceContext,
   StreamResult,
   TurnArgs,
-} from './types.js';
+} from './turn.js';
-import { streamCompletion, samplerOptsFromAgent } from './stream-phase-adapter.js';
+import { upstreamModel } from './provider.js';
+import {
+  jsonSchema,
+  streamText,
+  tool,
+  type JSONValue,
+  type ModelMessage,
+  type ToolCallRepairFunction,
+} from 'ai';
 
-export {
+interface StreamOptions {
-  streamCompletion,
+  // null = omit tools entirely (compact phase); [] = caller stripped all tools
-  samplerOptsFromAgent,
+  // (rare; we still omit from the request body to avoid OpenAI 400).
-  type StreamOptions,
+  tools: ToolJsonSchema[] | null;
-  type SamplerOpts,
+  temperature?: number;
-  type StreamAdapterContext,
+  top_p?: number | null;
-} from './stream-phase-adapter.js';
+  top_k?: number | null;
+  min_p?: number | null;
+  presence_penalty?: number | null;
+  // v2.6 sampling-streamjson-tokens (#11): llama.cpp sampler extensions. These
+  // are NOT standard AI-SDK streamText options and are NOT serialized by the
+  // openai-compatible provider's standardized-settings path (topK is even
+  // explicitly dropped with an "unsupported feature: topK" warning). They reach
+  // llama-server only via providerOptions.openaiCompatible (see buildSamplerProviderOptions).
+  top_n_sigma?: number | null;
+  dry_multiplier?: number | null;
+  dry_base?: number | null;
+  dry_allowed_length?: number | null;
+  dry_penalty_last_n?: number | null;
+}
+
+// v2.6 #11: build the providerOptions.openaiCompatible extraBody object for the
+// llama.cpp sampler extensions. @ai-sdk/openai-compatible (2.0.47) merges every
+// non-reserved key under providerOptions.openaiCompatible straight into the
+// chat-completion request body (see its getArgs: the Object.fromEntries spread
+// filtered against openaiCompatibleLanguageModelChatOptions.shape). This is the
+// ONLY working passthrough for these params:
+//   - top_k / min_p were latently dropped before this: top_k was passed as the
+//     AI-SDK `topK` setting which the openai-compatible provider rejects as
+//     unsupported; min_p was never passed to streamText at all.
+//   - top_n_sigma + the dry_* family have no AI-SDK equivalent.
+// Keys use llama-server's snake_case body names so they land verbatim.
+function buildSamplerProviderOptions(opts: StreamOptions): Record<string, number> | undefined {
+  const body: Record<string, number> = {};
+  if (typeof opts.top_k === 'number') body.top_k = opts.top_k;
+  if (typeof opts.min_p === 'number') body.min_p = opts.min_p;
+  if (typeof opts.top_n_sigma === 'number') body.top_n_sigma = opts.top_n_sigma;
+  if (typeof opts.dry_multiplier === 'number') body.dry_multiplier = opts.dry_multiplier;
+  if (typeof opts.dry_base === 'number') body.dry_base = opts.dry_base;
+  if (typeof opts.dry_allowed_length === 'number') body.dry_allowed_length = opts.dry_allowed_length;
+  if (typeof opts.dry_penalty_last_n === 'number') body.dry_penalty_last_n = opts.dry_penalty_last_n;
+  return Object.keys(body).length > 0 ? body : undefined;
+}
+
+// v1.13.1-A: convert BooCode's OpenAI-shaped history into AI SDK
+// ModelMessage[]. Tool result messages need a `toolName` field that the
+// OpenAI shape doesn't carry; we look it up by scanning earlier assistant
+// `tool_calls` entries for a matching id.
+function toModelMessages(messages: OpenAiMessage[]): ModelMessage[] {
+  const toolNameById = new Map<string, string>();
+  for (const m of messages) {
+    if (m.role === 'assistant' && m.tool_calls) {
+      for (const tc of m.tool_calls) {
+        toolNameById.set(tc.id, tc.function.name);
+      }
+    }
+  }
+  const out: ModelMessage[] = [];
+  for (const m of messages) {
+    if (m.role === 'system' || m.role === 'user') {
+      out.push({ role: m.role, content: m.content ?? '' });
+      continue;
+    }
+    if (m.role === 'assistant') {
+      const hasTools = m.tool_calls && m.tool_calls.length > 0;
+      const hasReasoning = typeof m.reasoning === 'string' && m.reasoning.length > 0;
+      if (!hasTools && !hasReasoning) {
+        // Bare text assistant (string content). null content + no tool_calls
+        // is degenerate but harmless to forward.
+        out.push({ role: 'assistant', content: m.content ?? '' });
+        continue;
+      }
+      // v1.13.1-C: AI SDK ReasoningPart precedes text + tool-calls in the
+      // assistant content array. Reasoning models (qwen3.6) consume their
+      // prior reasoning context to resume mid-thought across tool boundaries.
+      const parts: Array<
+        | { type: 'reasoning'; text: string }
+        | { type: 'text'; text: string }
+        | { type: 'tool-call'; toolCallId: string; toolName: string; input: unknown }
+      > = [];
+      if (hasReasoning) {
+        parts.push({ type: 'reasoning', text: m.reasoning! });
+      }
+      if (m.content && m.content.length > 0) {
+        parts.push({ type: 'text', text: m.content });
+      }
+      for (const tc of m.tool_calls ?? []) {
+        let input: unknown = {};
+        try {
+          input = tc.function.arguments.length > 0 ? JSON.parse(tc.function.arguments) : {};
+        } catch {
+          // Malformed args from a prior turn: pass through as a raw blob so
+          // the model sees the same shape it emitted. Wraps the string under
+          // _raw to match the buildMessagesPayload upstream convention.
+          input = { _raw: tc.function.arguments };
+        }
+        parts.push({ type: 'tool-call', toolCallId: tc.id, toolName: tc.function.name, input });
+      }
+      out.push({ role: 'assistant', content: parts });
+      continue;
+    }
+    if (m.role === 'tool') {
+      const toolCallId = m.tool_call_id ?? '';
+      const toolName = toolNameById.get(toolCallId) ?? 'unknown';
+      const raw = m.content ?? '';
+      let output: { type: 'text'; value: string } | { type: 'json'; value: JSONValue };
+      try {
+        // JSON.parse returns `any`; cast to JSONValue since the upstream
+        // tool_results column is already JSON-serializable by construction.
+        output = { type: 'json', value: JSON.parse(raw) as JSONValue };
+      } catch {
+        output = { type: 'text', value: raw };
+      }
+      out.push({
+        role: 'tool',
+        content: [{ type: 'tool-result', toolCallId, toolName, output }],
+      });
+      continue;
+    }
+  }
+  return out;
+}
+
+// Build the AI SDK tools record from BooCode's JSON-schema tool definitions.
+// No `execute` field: BooCode runs tools itself in tool-phase.ts; streamText
+// surfaces the tool-call parts via fullStream and we capture them for the
+// outer loop to dispatch.
+function buildAiTools(schemas: ToolJsonSchema[]): Record<string, ReturnType<typeof tool>> {
+  const out: Record<string, ReturnType<typeof tool>> = {};
+  for (const s of schemas) {
+    out[s.function.name] = tool({
+      description: s.function.description,
+      inputSchema: jsonSchema(s.function.parameters),
+    });
+  }
+  return out;
+}
+
+// v1.10.5 Qwen-coder XML fallback. Some local models (notably qwen3-coder via
+// llama-swap) emit tool calls as inline XML inside delta.content rather than
+// the structured tool_calls field. We extract them out of the streamed text
+// before flushing it to the client.
+//
+// Qwen shape:
+//   <tool_call>
+//   <function=NAME>
+//   <parameter=KEY>VALUE</parameter>
+//   ...
+//   </function>
+//   </tool_call>
+//
+// v1.13.16: also recognize Anthropic <invoke> markup that qwen3.6-35b-a3b-mxfp4
+// drifts to (training-data residue from Claude Code documentation):
+//   <invoke name="NAME">
+//   <parameter name="KEY">VALUE</parameter>
+//   </invoke>
+// Both formats share the synthetic xml_call_${idx} ID space; the counter
+// increments across whichever opener appears first. Multiple blocks may
+// appear back-to-back in either format and they never nest.
+export async function streamCompletion(
+  ctx: InferenceContext,
+  model: string,
+  messages: OpenAiMessage[],
+  opts: StreamOptions,
+  onDelta: (content: string) => void,
+  onUsage: ((prompt: number | null, completion: number | null) => void) | undefined,
+  signal?: AbortSignal,
+  agent?: Agent | null,
+): Promise<StreamResult> {
+  const aiMessages = toModelMessages(messages);
+  const hasTools = opts.tools !== null && opts.tools.length > 0;
+  const aiTools = hasTools ? buildAiTools(opts.tools!) : undefined;
+
+  const startedAt = Date.now();
+  // v1.13.1-C: accumulate reasoning text across reasoning-delta parts.
+  // qwen3.6 emits these on a separate channel from text content; we capture
+  // them per stream so finalizeCompletion can dual-write a 'reasoning' part.
+  // Replaces the v1.13.1-A counter-only diagnostic.
+  let reasoningAccumulated = '';
+
+  // v1.13.3: experimental_repairToolCall keeps the stream alive when the
+  // model emits a malformed tool call (bad JSON args, unknown name, etc.).
+  // Without a repair function streamText throws and the WHOLE stream dies;
+  // with one, the SDK invokes us and we route the bad call through normally.
+  // Strategy: pass through unmodified. executeToolPhase's existing error
+  // path (unknown tool name → "unknown tool: X" result; zod-reject → tool
+  // 'X' rejected — fieldname: required) already gives the model a clean
+  // recovery surface on the next turn. Logging gives us visibility into
+  // how often qwen3.6 actually emits broken calls.
+  const repairToolCall: ToolCallRepairFunction<NonNullable<typeof aiTools>> = async ({
+    toolCall,
+    error,
+  }) => {
+    ctx.log.warn(
+      {
+        toolCallId: toolCall.toolCallId,
+        toolName: toolCall.toolName,
+        error: error.message,
+      },
+      'malformed tool call surfaced via repairToolCall',
+    );
+    return toolCall;
+  };
+
+  // v2.6 #11: llama.cpp sampler extensions (top_k, min_p, top_n_sigma, dry_*)
+  // ride providerOptions.openaiCompatible — they are NOT standardized streamText
+  // settings. NB: top_k used to be passed below as the AI-SDK `topK` setting;
+  // the openai-compatible provider dropped it with an "unsupported feature: topK"
+  // warning and min_p was never wired at all, so both were dead on the wire
+  // before this. They now go through the same extraBody path as the new params.
+  const samplerBody = buildSamplerProviderOptions(opts);
+
+  const result = streamText({
+    model: upstreamModel(ctx.config, model, agent ?? null),
+    messages: aiMessages,
+    ...(aiTools
+      ? { tools: aiTools, toolChoice: 'auto' as const, experimental_repairToolCall: repairToolCall }
+      : {}),
+    ...(typeof opts.temperature === 'number' ? { temperature: opts.temperature } : {}),
+    ...(typeof opts.top_p === 'number' ? { topP: opts.top_p } : {}),
+    ...(typeof opts.presence_penalty === 'number' ? { presencePenalty: opts.presence_penalty } : {}),
+    ...(samplerBody ? { providerOptions: { openaiCompatible: samplerBody } } : {}),
+    abortSignal: signal,
+  });
+
+  let content = '';
+  let pendingBuffer = '';
+  let finishReason: string | null = null;
+  // v1.13.1-A: AI SDK emits one `tool-call` part per fully-aggregated call,
+  // so we no longer need the OpenAI-index reassembly map the manual SSE
+  // parser used. XML tool calls extracted from text content go into the
+  // same flat list and keep the v1.10.5 synthetic id convention.
+  const toolCalls: ToolCall[] = [];
+
+  for await (const part of result.fullStream) {
+    switch (part.type) {
+      case 'text-delta': {
+        pendingBuffer += part.text;
+        // v1.13.16: unified extraction. The helper finds the earliest-opening
+        // complete <tool_call> or <invoke> block, flushes prose between/around
+        // them, holds any partial opener for the next chunk, and silently
+        // drops blocks that fail to parse (matches pre-v1.13.16 behavior).
+        const extracted = extractToolCallBlocks(pendingBuffer);
+        if (extracted.flushed.length > 0) {
+          content += extracted.flushed;
+          onDelta(extracted.flushed);
+        }
+        for (const call of extracted.calls) {
+          const synthIdx = toolCalls.length;
+          toolCalls.push({
+            id: `xml_call_${synthIdx}`,
+            name: call.name,
+            args: call.args,
+          });
+        }
+        pendingBuffer = extracted.remaining;
+        break;
+      }
+      case 'tool-call': {
+        // AI SDK has already parsed the input into an object. Match the
+        // ToolCall shape BooCode passes around in toolCallsBuffer downstream.
+        toolCalls.push({
+          id: part.toolCallId,
+          name: part.toolName,
+          args: (part.input ?? {}) as Record<string, unknown>,
+        });
+        break;
+      }
+      case 'reasoning-delta': {
+        // v1.13.1-C: accumulate; finalizeCompletion / executeToolPhase
+        // dual-write the resulting text as a kind='reasoning' part.
+        if (typeof part.text === 'string') {
+          reasoningAccumulated += part.text;
+        }
+        break;
+      }
+      case 'finish': {
+        if (typeof part.finishReason === 'string') {
+          finishReason = part.finishReason;
+        }
+        break;
+      }
+      case 'error': {
+        const err = part.error;
+        throw err instanceof Error ? err : new Error(String(err));
+      }
+      // Intentional no-op: start, start-step, text-start, text-end,
+      // reasoning-start, reasoning-end, source, file, tool-input-start,
+      // tool-input-delta, tool-input-end, tool-result, tool-error,
+      // finish-step, raw. We only care about the aggregated tool-call and
+      // text-delta paths above; the rest are AI SDK lifecycle/streaming
+      // breadcrumbs that don't change BooCode's persistence or WS contract.
+      default:
+        break;
+    }
+  }
+
+  // v1.13.1-A: drain any buffered partial XML opener as plain text. The
+  // pre-AI-SDK path did this on stream end too — better to leak `<tool_c`
+  // than vanish the text.
+  if (pendingBuffer.length > 0) {
+    content += pendingBuffer;
+    onDelta(pendingBuffer);
+    pendingBuffer = '';
+  }
+
+  // AI SDK v6 fullStream returns normally on abort; check signal explicitly.
+  // Without this throw the row would land as status='complete' with partial
+  // content instead of going through handleAbortOrError → status='cancelled'.
+  // Smoke D caught this in v1.13.1-A — don't refactor it away.
+  if (signal?.aborted) {
+    const abortErr = new Error('aborted');
+    abortErr.name = 'AbortError';
+    throw abortErr;
+  }
+
+  // Usage lands as a promise on the result; awaiting after fullStream is
+  // drained is safe. AI SDK v6 names: `inputTokens` / `outputTokens`.
+  let promptTokens: number | null = null;
+  let completionTokens: number | null = null;
+  try {
+    const usage = await result.usage;
+    if (typeof usage.inputTokens === 'number') promptTokens = usage.inputTokens;
+    if (typeof usage.outputTokens === 'number') completionTokens = usage.outputTokens;
+  } catch {
+    // Some providers omit usage on partial streams; leave both null.
+  }
+
+  if (onUsage && (promptTokens !== null || completionTokens !== null)) {
+    onUsage(promptTokens, completionTokens);
+  }
+
+  if (reasoningAccumulated.length > 0) {
+    ctx.log.debug(
+      { reasoningChars: reasoningAccumulated.length, model, elapsed_ms: Date.now() - startedAt },
+      'streamCompletion: captured reasoning',
+    );
+  }
+
+  return {
+    finishReason,
+    content,
+    toolCalls,
+    promptTokens,
+    completionTokens,
+    reasoning: reasoningAccumulated,
+  };
+}
 
 export async function executeStreamPhase(
   ctx: InferenceContext,
@@ -58,7 +401,27 @@ export async function executeStreamPhase(
     role: 'assistant',
   });
 
-  const flusher = createContentFlusher(ctx.sql, assistantMessageId, () => state.accumulated);
+  let pendingFlushTimer: NodeJS.Timeout | null = null;
+  let flushPromise: Promise<unknown> = Promise.resolve();
+
+  const flushNow = () => {
+    if (pendingFlushTimer) {
+      clearTimeout(pendingFlushTimer);
+      pendingFlushTimer = null;
+    }
+    const snapshot = state.accumulated;
+    flushPromise = flushPromise.then(() =>
+      ctx.sql`UPDATE messages SET content = ${snapshot} WHERE id = ${assistantMessageId}`
+    );
+  };
+
+  const scheduleFlush = () => {
+    if (pendingFlushTimer) return;
+    pendingFlushTimer = setTimeout(() => {
+      pendingFlushTimer = null;
+      flushNow();
+    }, DB_FLUSH_INTERVAL_MS);
+  };
 
   // Tool whitelist: if an agent is set, filter the global tool list to only the
   // tool names it allows. v1.15.0-mcp-multi: uses matchToolGlob for glob
@@ -71,6 +434,17 @@ export async function executeStreamPhase(
     ? toolJsonSchemas().filter((t) => matchToolGlob(t.function.name, agent.tools))
     : toolJsonSchemas()
   ).filter((t) => webToolsEnabled || !WEB_TOOL_NAMES.has(t.function.name));
+  const effectiveTemperature = agent?.temperature;
+  const effectiveTopP = agent?.top_p ?? undefined;
+  const effectiveTopK = agent?.top_k ?? undefined;
+  const effectiveMinP = agent?.min_p ?? undefined;
+  const effectivePresencePenalty = agent?.presence_penalty ?? undefined;
+  // v2.6 #11: llama.cpp sampler extensions, threaded the same way as top_k/min_p.
+  const effectiveTopNSigma = agent?.top_n_sigma ?? undefined;
+  const effectiveDryMultiplier = agent?.dry_multiplier ?? undefined;
+  const effectiveDryBase = agent?.dry_base ?? undefined;
+  const effectiveDryAllowedLength = agent?.dry_allowed_length ?? undefined;
+  const effectiveDryPenaltyLastN = agent?.dry_penalty_last_n ?? undefined;
 
   // v1.12.2: ctx_max lookup is cached after the first hit per model, so this
   // is a Map probe in steady state. We capture nCtx once at the top of the
@@ -110,7 +484,16 @@ export async function executeStreamPhase(
       messages,
       {
         tools: effectiveTools,
-        ...samplerOptsFromAgent(agent),
+        temperature: effectiveTemperature,
+        top_p: effectiveTopP,
+        top_k: effectiveTopK,
+        min_p: effectiveMinP,
+        presence_penalty: effectivePresencePenalty,
+        top_n_sigma: effectiveTopNSigma,
+        dry_multiplier: effectiveDryMultiplier,
+        dry_base: effectiveDryBase,
+        dry_allowed_length: effectiveDryAllowedLength,
+        dry_penalty_last_n: effectiveDryPenaltyLastN,
       },
       (delta) => {
         state.accumulated += delta;
@@ -121,7 +504,7 @@ export async function executeStreamPhase(
           content: delta,
         });
         ctx.log.debug({ sessionId, delta }, 'inference delta');
-        flusher.scheduleFlush();
+        scheduleFlush();
       },
       (prompt, completion) => {
         pendingUsage = { p: prompt, c: completion };
@@ -139,10 +522,14 @@ export async function executeStreamPhase(
       agent,
     );
   } finally {
+    if (pendingFlushTimer) {
+      clearTimeout(pendingFlushTimer);
+      pendingFlushTimer = null;
+    }
     if (usageTimer) {
       clearTimeout(usageTimer);
       usageTimer = null;
     }
-    await flusher.drain();
+    await flushPromise;
   }
 }

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

@@ -22,7 +22,7 @@ import type {
   InferenceContext,
   StreamResult,
   TurnArgs,
-} from './types.js';
+} from './turn.js';
 // v1.13.13: synthesis pipeline — replaces the immediate recursive turn when
 // any of this batch's tool calls is in SYNTHESIS_TOOLS. Falls through to
 // recursion on synthesis failure (timeout / model error). See module header

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

@@ -0,0 +1,81 @@
+/**
+ * v2.0.5: Tool-use summary generation.
+ *
+ * After a batch of tool calls completes, fire a cheap LLM call to generate
+ * a "git-commit-subject-style" one-liner label describing what the tools
+ * accomplished. Ported from the Qwen Code source recon.
+ */
+import type { FastifyBaseLogger } from 'fastify';
+
+const TOOL_SUMMARY_SYSTEM_PROMPT = `Write a short summary label describing what these tool calls accomplished. Think git-commit-subject, not sentence. Past tense, most distinctive noun. Max 30 characters. Output ONLY the label.
+
+Examples:
+- Searched in auth/
+- Fixed NPE in UserService
+- Created signup endpoint
+- Read config.json
+- Ran failing tests`;
+
+const INPUT_TRUNCATE = 300;
+const MAX_SUMMARY_LENGTH = 100;
+
+export interface ToolInfo {
+  name: string;
+  input: string;
+  output: string;
+}
+
+export async function generateToolUseSummary(opts: {
+  tools: ToolInfo[];
+  llamaSwapUrl: string;
+  model: string;
+  log: FastifyBaseLogger;
+  signal?: AbortSignal;
+}): Promise<string | null> {
+  const { tools, llamaSwapUrl, model, log, signal } = opts;
+  if (tools.length === 0) return null;
+  if (signal?.aborted) return null;
+
+  const toolText = tools
+    .map(t => `Tool: ${t.name}\nInput: ${t.input.slice(0, INPUT_TRUNCATE)}\nOutput: ${t.output.slice(0, INPUT_TRUNCATE)}`)
+    .join('\n\n');
+
+  try {
+    const res = await fetch(`${llamaSwapUrl}/v1/chat/completions`, {
+      method: 'POST',
+      headers: { 'Content-Type': 'application/json' },
+      body: JSON.stringify({
+        model,
+        messages: [
+          { role: 'system', content: TOOL_SUMMARY_SYSTEM_PROMPT },
+          { role: 'user', content: toolText },
+        ],
+        max_tokens: 30,
+        temperature: 0.2,
+        stream: false,
+        chat_template_kwargs: { enable_thinking: false },
+      }),
+      signal,
+    });
+    if (!res.ok) {
+      log.debug({ status: res.status }, 'tool-summary: LLM request failed');
+      return null;
+    }
+    const data = await res.json() as { choices?: Array<{ message?: { content?: string } }> };
+    const raw = data.choices?.[0]?.message?.content?.trim() ?? '';
+    if (!raw) return null;
+    // Clean: strip quotes, "Label:" prefix, cap length
+    let cleaned = raw.split('\n')[0]?.trim() ?? '';
+    cleaned = cleaned
+      .replace(/^[-*•]\s+/, '')
+      .replace(/^["'`‘’“”]|["'`‘’“”]$/g, '')
+      .replace(/^(label|summary)\s*:\s*/i, '')
+      .trim();
+    return cleaned.length > MAX_SUMMARY_LENGTH
+      ? cleaned.slice(0, MAX_SUMMARY_LENGTH).trim()
+      : cleaned || null;
+  } catch (err) {
+    log.debug({ err: err instanceof Error ? err.message : String(err) }, 'tool-summary: error');
+    return null;
+  }
+}

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

@@ -1,33 +0,0 @@
-// P5 (SPLIT SKETCH 5): pure per-turn configuration resolved once at the top of
-// runAssistantTurn. No I/O — just the cap math + budget lookup so it can be
-// unit-tested without a DB or broker.
-
-import type { Agent } from '../../types/api.js';
-import { resolveToolBudget } from './budget.js';
-
-// v1.14.0: hard ceiling on the number of stream-and-tool iterations per
-// user-message turn. Per-agent cap via agent.steps is the primary knob;
-// MAX_STEPS is the safety ceiling. 200 is 4x the effective budget ceiling
-// (50 tool calls) — in practice budget fires first unless the model makes
-// many 0-tool-call iterations (which exit the loop via the non-tool finish
-// path anyway).
-export const MAX_STEPS = 200;
-
-export interface TurnConfig {
-  // min(agent.steps ?? Infinity, MAX_STEPS). The while loop runs while
-  // stepNumber < effectiveCap.
-  effectiveCap: number;
-  // cumulative tool-call budget for the turn (resolveToolBudget).
-  budget: number;
-  // effectiveCap === 0 → the model responds text-only (no tool execution).
-  isTextOnly: boolean;
-}
-
-export function resolveTurnConfig(agent: Agent | null): TurnConfig {
-  const budget = resolveToolBudget(agent);
-  // v1.14.0: effectiveCap = min(agent.steps ?? Infinity, MAX_STEPS).
-  // steps: 0 means "no tool calls allowed" — the first stream phase runs but
-  // any tool calls it emits are not executed (finalize as text-only).
-  const effectiveCap = Math.min(agent?.steps ?? Infinity, MAX_STEPS);
-  return { effectiveCap, budget, isTextOnly: effectiveCap === 0 };
-}

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

@@ -1,21 +1,33 @@
+import type { FastifyBaseLogger } from 'fastify';
+import type { Sql } from '../../db.js';
+import type { Config } from '../../config.js';
 import type {
   Agent,
+  ErrorReason,
   Message,
+  MessageMetadata,
   Project,
   Session,
+  ToolCall,
   UserStreamFrame,
 } from '../../types/api.js';
+import { ALL_TOOLS } from '../tools.js';
 import { resolveProjectRoot } from '../path_guard.js';
 import { maybeAutoNameChat } from '../auto_name.js';
 import { rewriteSearchQuery } from '../task-search-rewrite.js';
 import { getAgentById } from '../agents.js';
 import * as compaction from '../compaction.js';
-import { resolveTurnConfig } from './turn-config.js';
+import type { Broker } from '../broker.js';
-import { decideStep, decidePostToolAction } from './step-decision.js';
+import { resolveToolBudget } from './budget.js';
 import {
+  detectDoomLoop,
+} from './sentinels.js';
+import {
+  detectMistakePattern,
   freshMistakeState,
   recordStep,
   MISTAKE_RECOVERY_NOTE,
+  type MistakeState,
 } from './mistake-tracker.js';
 import {
   buildMessagesPayload,
@@ -23,19 +35,13 @@ import {
 } from './payload.js';
 import {
   finalizeCompletion,
-  finalizeEmpty,
   handleAbortOrError,
 } from './error-handler.js';
 import {
   executeStreamPhase,
 } from './stream-phase.js';
 import { executeToolPhase, type ToolPhaseResult } from './tool-phase.js';
-import type {
+import type { StreamPhaseState } from './types.js';
-  InferenceContext,
-  StreamPhaseState,
-  StreamResult,
-  TurnArgs,
-} from './types.js';
 import {
   runCapHitSummary,
   runDoomLoopSummary,
@@ -43,24 +49,121 @@ import {
   insertMistakeRecoverySentinel,
 } from './sentinel-summaries.js';
 
-// P5: MAX_STEPS moved to ./turn-config.ts (with resolveTurnConfig). Re-exported
+// v1.14.0: hard ceiling on the number of stream-and-tool iterations per
-// here so the public surface (index.ts → './turn.js') is unchanged.
+// user-message turn. Per-agent cap via agent.steps is the primary knob;
-export { MAX_STEPS } from './turn-config.js';
+// MAX_STEPS is the safety ceiling. 200 is 4x the effective budget ceiling
+// (50 tool calls) — in practice budget fires first unless the model makes
+// many 0-tool-call iterations (which exit the loop via the non-tool finish
+// path anyway).
+export const MAX_STEPS = 200;
 
 // v1.12.4: re-exported so external callers (tests, future consumers) keep
 // importing from services/inference.js as the public surface.
 export { detectDoomLoop, DOOM_LOOP_THRESHOLD } from './sentinels.js';
 export { buildMessagesPayload } from './payload.js';
 
+export interface InferenceFrame {
+  type:
+    | 'message_started'
+    | 'delta'
+    | 'tool_call'
+    | 'tool_result'
+    | 'message_complete'
+    | 'usage'
+    | 'messages_deleted'
+    | 'session_renamed'
+    | 'chat_renamed'
+    | 'error';
+  message_id?: string;
+  message_ids?: string[];
+  chat_id?: string;
+  tool_message_id?: string;
+  tool_call_id?: string;
+  // v1.8.2: 'system' added so cap-hit sentinel messages can announce themselves
+  // through the normal message_started → delta → message_complete sequence.
+  role?: 'assistant' | 'tool' | 'user' | 'system';
+  content?: string;
+  tool_call?: ToolCall;
+  output?: unknown;
+  truncated?: boolean;
+  error?: string;
+  // v1.8.2: structured error reason. Set on `type: 'error'` so the UI can
+  // surface a specific message; `error` stays the human-readable text.
+  reason?: ErrorReason;
+  // v1.8.2: piggybacks on `message_complete` so static or terminally-resolved
+  // messages can carry their persisted metadata to the live stream without a
+  // refetch (sentinels carry { kind: 'cap_hit', ... }; failed messages carry
+  // { kind: 'error', ... }).
+  metadata?: MessageMetadata | null;
+  tokens_used?: number | null;
+  ctx_used?: number | null;
+  ctx_max?: number | null;
+  completion_tokens?: number | null;
+  started_at?: string | null;
+  finished_at?: string | null;
+  model?: string;
+  session_id?: string;
+  name?: string;
+}
+
+export type FramePublisher = (sessionId: string, frame: InferenceFrame) => void;
+
+export interface InferenceContext {
+  sql: Sql;
+  config: Config;
+  log: FastifyBaseLogger;
+  publish: FramePublisher;
+  publishUser: (frame: UserStreamFrame) => void;
+  // v1.11: passed through so compaction.process can publish 'compacted'
+  // frames on the same session WS channel useSessionStream subscribes to.
+  // Compaction is the only path that needs the raw broker handle (regular
+  // inference goes through `publish`); keeping a separate field avoids
+  // tempting other code paths into bypassing the session-id binding.
+  broker: Broker;
+}
+
 // v1.12.4: payload assembly extracted to ./inference/payload.ts (tests
 // import buildMessagesPayload from this module, so a re-export below
 // preserves the public surface). Stream + tool phases extracted to
 // ./inference/stream-phase.ts and ./inference/tool-phase.ts.
-//
+
-// P5: the shared pipeline types (InferenceFrame / FramePublisher /
+export interface StreamResult {
-// InferenceContext / StreamResult / TurnArgs) moved to ./types.js to break the
+  finishReason: string | null;
-// turn.ts type-hub-and-leaf near-cycle. They are re-exported from there via
+  content: string;
-// inference/index.ts for the public surface.
+  toolCalls: ToolCall[];
+  promptTokens: number | null;
+  completionTokens: number | null;
+  // v1.13.1-C: reasoning text accumulated across reasoning-delta parts.
+  // Empty string when the model doesn't emit reasoning (most cases).
+  reasoning: string;
+}
+
+
+export interface TurnArgs {
+  sessionId: string;
+  chatId: string;
+  assistantMessageId: string;
+  // v1.8.2: cumulative tool calls executed this run. Compared against the
+  // resolved budget at the top of each turn. Replaces the older `depth`
+  // counter (which counted iterations, not invocations).
+  toolsUsed: number;
+  // v1.11.6: ordered tool calls executed in this user-message turn (across
+  // recursive runAssistantTurn invocations). Reset to [] at user-message
+  // boundaries by runInference, same as toolsUsed. Doom-loop check at the
+  // top of runAssistantTurn slices the last DOOM_LOOP_THRESHOLD entries.
+  recentToolCalls: ToolCall[];
+  // v#12 MistakeTracker: heterogeneous-failure recovery state. Loop-local,
+  // reset per runInference (user-message boundary) like recentToolCalls. Folds
+  // tool-phase outcomes via recordStep each iteration; detectMistakePattern
+  // gates the nudge/escalate decision.
+  mistakeTracker: MistakeState;
+  // v#12: transient model-facing recovery note set when a nudge fires. Consumed
+  // (appended as a role:'system' message + cleared) on the NEXT payload build.
+  // Never persisted — mirrors how the cap-hit/doom-loop notes live only inside
+  // the summary call's messages array.
+  pendingRecoveryNote?: string;
+  signal: AbortSignal | undefined;
+}
 
 
 export async function runAssistantTurn(
@@ -81,13 +184,17 @@ export async function runAssistantTurn(
   const agent = session.agent_id
     ? await getAgentById(project.path, session.agent_id)
     : null;
-  // P5: pure per-turn config (budget + cap math + text-only flag).
+  const budget = resolveToolBudget(agent);
-  const { effectiveCap, budget, isTextOnly } = resolveTurnConfig(agent);
+
+  // v1.14.0: effectiveCap = min(agent.steps ?? Infinity, MAX_STEPS).
+  // steps: 0 means "no tool calls allowed" — the first stream phase runs
+  // but if it emits tool calls they are not executed (finalize as text-only).
+  const effectiveCap = Math.min(agent?.steps ?? Infinity, MAX_STEPS);
 
   // steps: 0 special case — model responds text-only. The while loop would
   // never enter (effectiveCap === 0), so we handle it explicitly before the
   // loop. The model always gets at least one chance to respond with text.
-  if (isTextOnly) {
+  if (effectiveCap === 0) {
     const loaded = await loadContext(ctx.sql, sessionId, chatId);
     if (loaded) {
       await runTextOnlyTurn(ctx, args, loaded.session, loaded.project, loaded.history, agent);
@@ -107,18 +214,20 @@ export async function runAssistantTurn(
   let pendingRecoveryNote: string | undefined = args.pendingRecoveryNote;
 
   while (stepNumber < effectiveCap) {
-    // ---- top-of-loop gate: doom-loop, then budget (pure decision) ----
+    // ---- doom-loop check (moved from top-of-function) ----
-    const decision = decideStep({ recentToolCalls, toolsUsed, budget });
+    const loop = detectDoomLoop(recentToolCalls);
-    if (decision.kind === 'doom') {
+    if (loop) {
       // Need fresh history for the summary.
       const loaded = await loadContext(ctx.sql, sessionId, chatId);
       if (loaded) {
         const iterArgs: TurnArgs = { sessionId, chatId, assistantMessageId, toolsUsed, recentToolCalls, mistakeTracker, signal };
-        await runDoomLoopSummary(ctx, iterArgs, loaded.session, loaded.project, loaded.history, agent, decision.loop);
+        await runDoomLoopSummary(ctx, iterArgs, loaded.session, loaded.project, loaded.history, agent, loop);
       }
       break;
     }
-    if (decision.kind === 'budget') {
+
+    // ---- budget check (moved from top-of-function) ----
+    if (toolsUsed >= budget) {
       const loaded = await loadContext(ctx.sql, sessionId, chatId);
       if (loaded) {
         const iterArgs: TurnArgs = { sessionId, chatId, assistantMessageId, toolsUsed, recentToolCalls, mistakeTracker, signal };
@@ -126,7 +235,6 @@ export async function runAssistantTurn(
       }
       break;
     }
-    // decision.kind === 'stream' → proceed with compaction + stream + tools.
 
     // ---- compaction check ----
     // v1.11: if the prior turn flagged this chat for compaction, run it
@@ -237,17 +345,19 @@ export async function runAssistantTurn(
       recordStep(mistakeTracker, o);
     }
 
-    // v#12 MistakeTracker: post-tool decision (pure). 'stop' = the tool phase
+    if (toolPhaseResult.action !== 'continue') {
-    // returned a non-'continue' action ('paused' for user input, or
+      // 'paused' (user input) or 'synthesis_done' — stop the loop. The turn is
-    // 'synthesis_done') — neither a nudge nor an escalate would change the
+      // already ending, so neither a nudge nor an escalate would change the
-    // control flow, so the mistake check is skipped. On 'continue' the
+      // control flow; we skip the mistake decision here.
-    // heterogeneous-failure pattern gates nudge/escalate/continue. Complements
-    // the doom-loop gate above, which only catches *identical* repeats.
-    const post = decidePostToolAction(toolPhaseResult.action, mistakeTracker);
-    if (post === 'stop') {
       break;
     }
-    if (post === 'nudge') {
+
+    // v#12 MistakeTracker: heterogeneous-failure decision. Only evaluated on
+    // the 'continue' path (the only case where the loop would otherwise
+    // proceed to another step). Complements the doom-loop check above, which
+    // only catches *identical* repeats.
+    const mistake = detectMistakePattern(mistakeTracker);
+    if (mistake === 'nudge') {
       // Soft intervention: inject model-facing recovery guidance into the NEXT
       // step's payload, drop a UI sentinel, bump nudges, reset the streak, and
       // continue. The note is consumed (and cleared) at the top of the next
@@ -269,16 +379,23 @@ export async function runAssistantTurn(
       assistantMessageId = toolPhaseResult.nextAssistantId!;
       continue;
     }
-    if (post === 'escalate') {
+    if (mistake === 'escalate') {
       // The nudge didn't break the failure run — stop the turn (cap-hit-style)
       // to avoid burning the whole step budget on heterogeneous failures. The
-      // next assistant row is still 'streaming'; finalize it as an empty
+      // next assistant row is still 'streaming'; finalize it as a short note so
-      // complete row so the slot doesn't dangle, then drop the escalate
+      // the slot doesn't dangle, then drop the escalate sentinel.
-      // sentinel.
       const failureKinds = [...mistakeTracker.run];
       assistantMessageId = toolPhaseResult.nextAssistantId!;
-      const escalateArgs: TurnArgs = { sessionId, chatId, assistantMessageId, toolsUsed, recentToolCalls, mistakeTracker, signal };
+      await ctx.sql`
-      await finalizeEmpty(ctx, escalateArgs);
+        UPDATE messages
+        SET content = '', status = 'complete', finished_at = clock_timestamp()
+        WHERE id = ${assistantMessageId}
+      `;
+      ctx.publish(sessionId, {
+        type: 'message_complete',
+        message_id: assistantMessageId,
+        chat_id: chatId,
+      });
       await insertMistakeRecoverySentinel(ctx, sessionId, chatId, {
         failureKinds,
         count: failureKinds.length,
@@ -445,3 +562,4 @@ export function createInferenceRunner(
   };
 }
 
+export const _toolNames = ALL_TOOLS.map((t) => t.name);

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

@@ -1,25 +1,6 @@
 // v1.12.4: shared inter-phase types/constants for the extracted phase files.
 // Lives here so stream-phase, tool-phase, and the summary functions still in
 // inference.ts can all reference the same definitions without circular imports.
-//
-// P5: the shared pipeline types (InferenceContext / TurnArgs / StreamResult /
-// InferenceFrame / FramePublisher) moved here from turn.ts. turn.ts was both the
-// type hub (every phase imported these from './turn.js') AND the orchestration
-// leaf (it imports functions back from payload/stream-phase/tool-phase/
-// error-handler/sentinel-summaries) — a hub-and-leaf near-cycle. Hosting the
-// shared types here (this module imports no inference functions) breaks it.
-
-import type { FastifyBaseLogger } from 'fastify';
-import type { Sql } from '../../db.js';
-import type { Config } from '../../config.js';
-import type {
-  ErrorReason,
-  MessageMetadata,
-  ToolCall,
-  UserStreamFrame,
-} from '../../types/api.js';
-import type { Broker } from '../broker.js';
-import type { MistakeState } from './mistake-tracker.js';
 
 export interface StreamPhaseState {
   accumulated: string;
@@ -30,100 +11,3 @@ export interface StreamPhaseState {
 // executeStreamPhase, runCapHitSummary, and runDoomLoopSummary — every site
 // that does a debounced content flush during streaming.
 export const DB_FLUSH_INTERVAL_MS = 500;
-
-export interface InferenceFrame {
-  type:
-    | 'message_started'
-    | 'delta'
-    | 'tool_call'
-    | 'tool_result'
-    | 'message_complete'
-    | 'usage'
-    | 'messages_deleted'
-    | 'session_renamed'
-    | 'chat_renamed'
-    | 'error';
-  message_id?: string;
-  message_ids?: string[];
-  chat_id?: string;
-  tool_message_id?: string;
-  tool_call_id?: string;
-  // v1.8.2: 'system' added so cap-hit sentinel messages can announce themselves
-  // through the normal message_started → delta → message_complete sequence.
-  role?: 'assistant' | 'tool' | 'user' | 'system';
-  content?: string;
-  tool_call?: ToolCall;
-  output?: unknown;
-  truncated?: boolean;
-  error?: string;
-  // v1.8.2: structured error reason. Set on `type: 'error'` so the UI can
-  // surface a specific message; `error` stays the human-readable text.
-  reason?: ErrorReason;
-  // v1.8.2: piggybacks on `message_complete` so static or terminally-resolved
-  // messages can carry their persisted metadata to the live stream without a
-  // refetch (sentinels carry { kind: 'cap_hit', ... }; failed messages carry
-  // { kind: 'error', ... }).
-  metadata?: MessageMetadata | null;
-  tokens_used?: number | null;
-  ctx_used?: number | null;
-  ctx_max?: number | null;
-  completion_tokens?: number | null;
-  started_at?: string | null;
-  finished_at?: string | null;
-  model?: string;
-  session_id?: string;
-  name?: string;
-}
-
-export type FramePublisher = (sessionId: string, frame: InferenceFrame) => void;
-
-export interface InferenceContext {
-  sql: Sql;
-  config: Config;
-  log: FastifyBaseLogger;
-  publish: FramePublisher;
-  publishUser: (frame: UserStreamFrame) => void;
-  // v1.11: passed through so compaction.process can publish 'compacted'
-  // frames on the same session WS channel useSessionStream subscribes to.
-  // Compaction is the only path that needs the raw broker handle (regular
-  // inference goes through `publish`); keeping a separate field avoids
-  // tempting other code paths into bypassing the session-id binding.
-  broker: Broker;
-}
-
-export interface StreamResult {
-  finishReason: string | null;
-  content: string;
-  toolCalls: ToolCall[];
-  promptTokens: number | null;
-  completionTokens: number | null;
-  // v1.13.1-C: reasoning text accumulated across reasoning-delta parts.
-  // Empty string when the model doesn't emit reasoning (most cases).
-  reasoning: string;
-}
-
-export interface TurnArgs {
-  sessionId: string;
-  chatId: string;
-  assistantMessageId: string;
-  // v1.8.2: cumulative tool calls executed this run. Compared against the
-  // resolved budget at the top of each turn. Replaces the older `depth`
-  // counter (which counted iterations, not invocations).
-  toolsUsed: number;
-  // v1.11.6: ordered tool calls executed in this user-message turn (across
-  // recursive runAssistantTurn invocations). Reset to [] at user-message
-  // boundaries by runInference, same as toolsUsed. Doom-loop check at the
-  // top of runAssistantTurn slices the last DOOM_LOOP_THRESHOLD entries.
-  recentToolCalls: ToolCall[];
-  // v#12 MistakeTracker: heterogeneous-failure recovery state. Loop-local,
-  // reset per runInference (user-message boundary) like recentToolCalls. Folds
-  // tool-phase outcomes via recordStep each iteration; detectMistakePattern
-  // gates the nudge/escalate decision.
-  mistakeTracker: MistakeState;
-  // v#12: transient model-facing recovery note set when a nudge fires. Consumed
-  // (appended as a role:'system' message + cleared) on the NEXT payload build.
-  // Never persisted — mirrors how the cap-hit/doom-loop notes live only inside
-  // the summary call's messages array.
-  pendingRecoveryNote?: string;
-  signal: AbortSignal | undefined;
-}

apps/server/src/services/message-columns.ts

@@ -1,15 +0,0 @@
-// Shared column projections for queries against the messages_with_parts view.
-// All sites that read the full Message wire shape for route responses use
-// MESSAGE_COLUMNS. The inference load path uses INFERENCE_MESSAGE_COLUMNS —
-// it adds reasoning_parts but omits the compaction-display fields
-// (summary, tail_start_id, compacted_at, model) that only the UI needs.
-
-export const MESSAGE_COLUMNS =
-  'id, session_id, chat_id, role, content, kind, tool_calls, tool_results, status, last_seq, ' +
-  'tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at, metadata, ' +
-  'summary, tail_start_id, compacted_at, model';
-
-export const INFERENCE_MESSAGE_COLUMNS =
-  'id, session_id, chat_id, role, content, kind, tool_calls, tool_results, status, last_seq, ' +
-  'tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at, metadata, ' +
-  'reasoning_parts';

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

@@ -18,6 +18,8 @@
 
 export interface ModelContext {
   n_ctx: number;
+  total_slots: number;
+  fetched_at: number;
 }
 
 const NEGATIVE_TTL_MS = 60_000;
@@ -75,13 +77,19 @@ export async function getModelContext(model: string): Promise<ModelContext | nul
     }
     const body = (await res.json()) as {
       default_generation_settings?: { n_ctx?: number };
+      total_slots?: number;
     };
     const n_ctx = body?.default_generation_settings?.n_ctx;
     if (typeof n_ctx !== 'number' || n_ctx <= 0) {
       negativeCache.set(model, Date.now());
       return null;
     }
-    const entry: ModelContext = { n_ctx };
+    // total_slots is informational; default to 1 if missing rather than
+    // reject the whole response. Most local llama-swap setups run a
+    // single slot anyway.
+    const total_slots =
+      typeof body?.total_slots === 'number' && body.total_slots > 0 ? body.total_slots : 1;
+    const entry: ModelContext = { n_ctx, total_slots, fetched_at: Date.now() };
     positiveCache.set(model, entry);
     // Clear any stale negative entry so a future query sees the positive
     // hit cleanly (otherwise the negative TTL never expires from the map).

apps/server/src/services/read_tab_by_number.ts

@@ -3,7 +3,7 @@
 // stored in the session's workspace_panes envelope (WorkspaceState.tabNumbers),
 // keyed by chat id. Lives in its own file (not appended to tools.ts) so tests
 // can import the executor directly without dragging in the whole tool registry.
-// Registered in tools.ts ALL_TOOLS.
+// Registered in tools.ts ALL_TOOLS + READ_ONLY_TOOL_NAMES.
 
 import { z } from 'zod';
 import type { Sql } from '../db.js';

apps/server/src/services/skills.ts

@@ -1,7 +1,6 @@
 import { promises as fs } from 'node:fs';
 import { join, isAbsolute, basename } from 'node:path';
 import { pathGuard, PathScopeError } from './path_guard.js';
-import { stripQuotes } from '../utils/string-utils.js';
 
 // Batch 9.6: read-only skill library. Folders under /data/skills/<group>/<skill>/
 // contain a SKILL.md with YAML frontmatter (name + description) and a markdown
@@ -45,6 +44,13 @@ interface Frontmatter {
   description?: string;
 }
 
+function stripQuotes(s: string): string {
+  if (s.length >= 2 && (s[0] === '"' || s[0] === "'") && s[0] === s[s.length - 1]) {
+    return s.slice(1, -1);
+  }
+  return s;
+}
+
 function parseFrontmatter(yaml: string): Frontmatter {
   const fm: Frontmatter = {};
   for (const raw of yaml.split('\n')) {

apps/server/src/services/synthesisPipeline.ts

@@ -24,12 +24,12 @@ import { TOOLS_BY_NAME } from './tools.js';
 import { streamCompletion } from './inference/stream-phase.js';
 import { SYNTHESIS_SYSTEM_PROMPT } from './synthesisPrompt.js';
 import { insertParts } from './inference/parts.js';
-import { finalizeStreamedRow } from './inference/error-handler.js';
+import * as modelContext from './model-context.js';
 import { readTruncation } from './truncate.js';
 
 import type { Session } from '../types/api.js';
 import type { OpenAiMessage } from './inference/payload.js';
-import type { InferenceContext, TurnArgs } from './inference/types.js';
+import type { InferenceContext, TurnArgs } from './inference/turn.js';
 
 export const SYNTHESIS_TOOLS: ReadonlySet<string> = new Set([
   'get_codebase_overview',
@@ -192,28 +192,44 @@ export async function runSynthesisPass(p: SynthesisParams): Promise<boolean> {
       combinedSignal,
     );
 
-    // P5: the n_ctx lookup + complete UPDATE + message_complete frame are the
+    const mctx = await modelContext.getModelContext(p.session.model);
-    // shared success-finalize atom (finalizeStreamedRow). beforeComplete writes
+    const nCtx = mctx?.n_ctx ?? null;
-    // the kind='synthesis' part in the original order (UPDATE → insertParts →
+    const [updated] = await p.ctx.sql<
-    // message_complete), preserving timing exactly.
+      {
-    await finalizeStreamedRow(p.ctx, {
+        tokens_used: number | null;
-      sessionId: p.args.sessionId,
+        ctx_used: number | null;
-      chatId: p.args.chatId,
+        ctx_max: number | null;
-      messageId: synthMessageId,
+        finished_at: string | null;
+      }[]
+    >`
+      UPDATE messages
+      SET content = ${streamResult.content},
+          status = 'complete',
+          tokens_used = ${streamResult.completionTokens},
+          ctx_used = ${streamResult.promptTokens},
+          ctx_max = ${nCtx},
+          finished_at = clock_timestamp()
+      WHERE id = ${synthMessageId}
+      RETURNING tokens_used, ctx_used, ctx_max, finished_at
+    `;
+    await insertParts(p.ctx.sql, [
+      {
+        message_id: synthMessageId,
+        sequence: 0,
+        kind: 'synthesis',
+        payload: { text: streamResult.content },
+      },
+    ]);
+    p.ctx.publish(p.args.sessionId, {
+      type: 'message_complete',
+      message_id: synthMessageId,
+      chat_id: p.args.chatId,
+      tokens_used: updated?.tokens_used ?? null,
+      ctx_used: updated?.ctx_used ?? null,
+      ctx_max: updated?.ctx_max ?? null,
+      started_at: startedAt,
+      finished_at: updated?.finished_at ?? null,
       model: p.session.model,
-      content: streamResult.content,
-      completionTokens: streamResult.completionTokens,
-      promptTokens: streamResult.promptTokens,
-      startedAt,
-      beforeComplete: () =>
-        insertParts(p.ctx.sql, [
-          {
-            message_id: synthMessageId!,
-            sequence: 0,
-            kind: 'synthesis',
-            payload: { text: streamResult.content },
-          },
-        ]),
     });
     p.ctx.publishUser({
       type: 'chat_status',

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

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

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

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