docs: roadmap shipping-state update + external code-review v2 findings

Update boocode_roadmap.md's shipped section through v2.6.4 (provider lifecycle,
persistent agent sessions, cursor/copilot retirement) and add
boocode_code_review_v2.md — a point-in-time external-fork lift/cross-check
findings doc (Paseo + opencode + llama.cpp + the second fork sweep), companion
to the standing boocode_code_review.md inventory.

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

CHANGELOG.md

@@ -2,6 +2,22 @@
 
 All notable changes per release tag. Most recent on top, ordered by tag creation date (which matches the git history). Tag names follow `vMAJOR.MINOR.PATCH-slug` — the slug describes what shipped, so the tag name alone is enough to recall the batch.
 
+## v2.6.5-panes-tabs-composer — 2026-05-31
+
+A workspace UX batch across BooChat panes, tabs, and the composer, plus the persistence model that backs them. **Panes & tabs:** a chat can be opened in a fresh pane (the ChatTabBar tab context menu's "Open in new pane", and the fork button — which now lands the fork beside the original via a new `open_chat_in_new_pane` event instead of replacing the active pane); the per-pane "+" became a New BooChat/BooTerm/BooCode menu; closing a chat pane relocates its tabs (in order) into the oldest chat/empty pane instead of discarding them, and reopen strips the restored chatIds from every live pane first so a relocated-then-reopened pane never duplicates a tab (no stack-shape change); each tab carries a stable session-scoped number assigned on open and retired on close (never reused), rendered map-keyed rather than positional. The per-message "Open in pane" artifact button was removed, and the empty/landing pane became a real session history — the session's open chats plus separately-fetched archived chats, click to open or restore-and-open. **Persistence:** `sessions.workspace_panes` was widened from a bare `WorkspacePane[]` to a `WorkspaceState` envelope (`panes` + `tabNumbers`/`nextTabNumber` + `closedPaneStack`) so tab numbers and the reopen stack survive reload; the PATCH validator accepts the legacy array or the envelope (zod union) and migrates on write, and the `session_workspace_updated` WS-frame schema was widened on both web and server (byte-identical, parity test green) — the same schema-drift class as `v2.6.4-agent-sessions-fk`. **Composer:** the send button morphs Send → Stop → Queue with generation state (BooCoder keys on `sending || activeTaskId`, which also corrected its queue gates and added `cancelTask`), the standalone "Stop generating" pill was folded into it, and pasted chips now trail the typed text so a leading slash command stays first. **Tooling:** adds the read-only `read_tab_by_number` tool — resolves a session-scoped tab number to its chat via the persisted `tabNumbers` map and returns that chat's transcript; tools gained an optional `ToolExecCtx` (`{ sql, sessionId }`) on `execute` to support DB-reading tools. Builds on `v2.6.4-agent-sessions-fk`.
+
+## v2.6.4-agent-sessions-fk — 2026-05-31
+
+Follow-up to `v2.6.3-chatkey-and-skills` (P1.5-b): the live `agent_sessions.session_id` foreign key is converged from `ON DELETE CASCADE` to `ON DELETE SET NULL`, matching the schema's stated intent. The P1.5-b re-key block re-adds `session_id_fkey` as `SET NULL`, but the whole block is guarded on `chat_id_fkey`'s absence — so a database already re-keyed to `(chat_id, agent)` while `session_id_fkey` was still `CASCADE` never re-enters it, leaving the live FK at `CASCADE` and diverging from both `worktree_id` (already `SET NULL`) and the `v2.6.3` changelog's own claim that `session_id` is informational `SET NULL`. The fix adds a standalone `confdeltype`-guarded `DO` block (mirroring the `session_worktrees` defang) that flips `session_id_fkey` `CASCADE → SET NULL` independently of the re-key gate; it is idempotent — fires only while the FK is still `'c'`, a no-op on a fresh deploy (already `'n'`) and on every re-run. The live DB was converged by hand with the identical statements, so `applySchema` and the hand-applied state match (`\d agent_sessions` now shows `session_id ... ON DELETE SET NULL`). Also bundles a CLAUDE.md doc-sync (committed separately): per-session SSE (P1.5-a) and the `(chat_id, agent)` re-key reflected in the engineering notes, the stale root `AGENTS.md` navigation pointer dropped, and new conventions for `data/AGENTS.md` parsing and the `data/skills/<vendor>/` layout.
+
+## v2.6.3-chatkey-and-skills — 2026-05-31
+
+Three threads. **agent_sessions re-keyed to `(chat_id, agent)` (P1.5-b):** the tab (a chat) is now the agent-context unit, so two opencode tabs in one BooCode session are two independent contexts that share one worktree. `chat_id` is threaded end-to-end — `tasks.chat_id` added, stamped by the coder message + skills routes from the frontend tab, read by `runOpenCodeServerTask` which falls back to resolve-or-create a chat for session-less creators (arena/MCP/new_task/generic `/api/tasks`) so `ensureSession` never receives a degenerate `(null, agent)` key. A new first-class `worktrees` table (one-per-session, survives session delete via `session_id ON DELETE SET NULL`) supersedes `session_worktrees`, which is defanged (CASCADE dropped, not yet removed); `agent_sessions.chat_id` CASCADEs from `chats` (closing a tab ends its context) while `worktree_id`/`session_id` are informational `SET NULL`. The migration is idempotent with a backfill-verify gate; the live re-key was applied against an empty table after the 35-chat test session `20d28876` was deleted (backed up first). This corrects and supersedes an earlier draft that wrongly keyed on `(worktree_id, agent)`; the delete-guard from `v2.6.2-delete-guard-and-sse` is repointed here from `session_worktrees` to `worktrees` (`worktree_path`→`path`). **dcp-strip cross-chunk fix:** the `<dcp-message-id>` tag streams split across SSE deltas, which the per-chunk strip from `v2.6.1-phase1-opencode` missed — a stateful `makeDcpStreamStripper` at the dispatcher boundary holds back partial-tag tails so neither live frames nor persisted content carry the tag (11 unit tests). **Agent-judgment skills:** `committing-changes` (segment by concern, stage explicitly, present-and-stop, never push) and `using-worktrees` (the when-to-isolate heuristic, autonomous-when-clear vs committing's command-gate) land in `data/skills/boocode/` with eval.yamls, plus a parser-safe `data/AGENTS.md` preamble pointing at both.
+
+## v2.6.2-delete-guard-and-sse — 2026-05-30
+
+Two coder-side batches under one tag. **Session-delete work-loss guard:** deleting a BooChat session CASCADE-wipes its `session_worktrees` row, which would silently orphan uncommitted/unpushed/unmerged work — so the server's `DELETE /api/sessions/:id` now gates before the delete. It reads `session_worktrees` from the shared DB first (no row → chat-only session → delete immediately, zero round-trip), and for worktree-backed sessions calls a new BooCoder endpoint (`/worktree-risk`) that runs git on the host, since the container can't see `/tmp/booworktrees` — only the host systemd service can. `checkWorktreeWorkAtRisk` reports dirty/unpushed/unmerged via the audited `hostExec`+`shellEscape` path, default branch detected from `refs/remotes/origin/HEAD` (never the worktree's own branch, never hardcoded); any at-risk worktree returns 409 with per-worktree `RiskReport[]`, `force=true` bypasses, and the check is fail-closed (BooCoder unreachable also blocks — force still escapes). The sidebar renders a block dialog distinguishing work-at-risk (Commit/Stash/Force; stash uses `-u` and re-blocks on remaining commits) from couldn't-verify (Cancel/Force), and Commit never auto-commits. A follow-up fix gates the `unpushed` arm behind an actual upstream (`atRisk = dirty || unmerged > 0 || (hasUpstream && unpushed > 0)`) so the no-upstream `session-<id>` branches stop flagging every pristine worktree-backed session — no protection lost, since real local work always also surfaces as `unmerged > 0`. **Per-session SSE (P1.5-a):** replaces the single global SSE loop scoped to the most-recent worktree directory — the known limit flagged in `v2.6.1-phase1-opencode` — with one `event.subscribe({directory})` per live opencode session, so sessions in different worktrees stream concurrently instead of the second silently dropping the first's events. Each session owns an `AbortController` wired into `subscribe(…, {signal})`, which also fixes a latent Phase-1 bug where switching directories left the old loop parked forever in its `for await` (zombie loops); a `sessionID` demux guard drops cross-session events so two sessions sharing a worktree (possible after P1.5-b) don't double-process deltas. The opencode SDK was confirmed to open an independent SSE connection per `subscribe()` call, so N concurrent dir-scoped streams are supported.
+
 ## v2.6.1-phase1-opencode — 2026-05-30
 
 v2.6 Phase 1: opencode runs as a warm HTTP server (`apps/coder/src/services/backends/opencode-server.ts`) — one `opencode serve` per BooCoder process, one opencode session per BooCode session resumed across turns via the new `agent_sessions` table, with a single SSE read loop, reasoning dedup ported from Paseo, an inactivity watchdog, and a stale-session guard (crashed-not-resumed + a `config_hash` fingerprint over `opencode_server|<model>`, deliberately excluding the ephemeral server port so cross-restart resume survives). Builds on the `v2.6.0-phase0-foundations` schema/interface scaffold. The batch's hard-won fixes: opencode streams `session.next.*` events (not `message.part.*`), and `event.subscribe()` must pass the session's worktree `directory` or events route to the server CWD and turns come back empty; model strings must be `llama-swap/`-prefixed and present in opencode's own config, with `agent-probe` now populating `available_agents.models` via `mergeLlamaSwap` so the frontend stops sending an empty model; `session_worktrees`/`agent_sessions` FKs are `ON DELETE CASCADE` so session deletion no longer 500s. Also bundled: dcp-message-id tag stripping from opencode text output, a reopen-closed-pane control, the `[+]`/split-pane button separation, auto-name using the session's loaded model, and a `systematic-debugging` slash command. Smoke 1 verified end-to-end (two turns, session reuse, turn 2 ~9x faster). Known Phase 1 limit: one SSE stream scoped to the most-recent session's directory — concurrent opencode sessions in different worktrees collide (warns; per-session SSE is Phase 2).

CLAUDE.md

@@ -2,7 +2,7 @@
 
 This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
 
-**Cursor agents:** start with `AGENTS.md` (navigation) and `docs/ARCHITECTURE.md` (diagram). This file is the deep engineering reference.
+**Cursor agents:** start with `docs/ARCHITECTURE.md` (diagram). This file is the deep engineering reference. (Note: the root navigation `AGENTS.md` was removed in v1.12; `data/AGENTS.md` is the agent *registry*, not navigation.)
 
 ## What is BooCode
 
@@ -90,9 +90,9 @@ Route registration: all routes registered in `index.ts` via `register*Routes(app
 - **Provider snapshot lifecycle** (`apps/coder/src/services/`): `provider-config.ts` (Zod config, never-throws on bad input) → `provider-config-registry.ts` (`buildResolvedRegistry`, singleton) → `provider-snapshot.ts` (two-tier probe: tier-1 fast presence, tier-2 cold ACP probe skipped unless force / stale `PROVIDER_PROBE_TTL_MS` 24h / dbEmpty; cached). Verify live: `curl http://100.114.205.53:9502/api/providers/snapshot` — returns providers + models + commands, the exact shape `AgentComposerBar` renders.
 - `PATCH /api/providers/config` replaces a provider id's override object **wholesale** (per-id shallow merge) — to flip one field send `{...existing, enabled}`, or a custom ACP entry's `command`/`label` is wiped and it drops out of the resolved registry. `data/coder-providers.json` is **gitignored** (it's live runtime config — the coder reads AND writes it on UI toggles); the tracked reference is `data/coder-providers.example.json`. The loader falls back to `{providers:{}}` (built-ins only) when the live file is absent, so a fresh checkout needs no copy.
 - **opencode** runs as a warm HTTP server (v2.6 Phase 1, `services/backends/opencode-server.ts` — `opencode serve` per BooCoder process, one opencode session per BooCode session, resumed via `agent_sessions`). goose/qwen/claude still dispatch **one-shot** ACP/PTY with no ctx/token usage; only native `boocode` (llama-swap engine) tracks ctx. Paseo's per-provider native clients (design §12) deliberately not ported.
-- **opencode SSE** (`opencode-server.ts`): live streaming arrives as `session.next.text.delta` / `session.next.reasoning.delta` / `session.next.tool.{called,success,failed}` — NOT `message.part.*` (those are terminal/post-hoc). `client.event.subscribe({ directory })` MUST pass the session's worktree directory; omit it and opencode scopes events to the server's `process.cwd()` → zero session events (empty turns, 180s watchdog timeout). One SSE stream at a time scoped to the last session's dir — concurrent opencode sessions in different worktrees collide (known Phase 1 limit, warns). Turn completes on `session.idle`; `promptAsync` is fire-and-forget (204).
+- **opencode SSE** (`opencode-server.ts`): live streaming arrives as `session.next.text.delta` / `session.next.reasoning.delta` / `session.next.tool.{called,success,failed}` — NOT `message.part.*` (those are terminal/post-hoc). `client.event.subscribe({ directory })` MUST pass the session's worktree directory; omit it and opencode scopes events to the server's `process.cwd()` → zero session events (empty turns, 180s watchdog timeout). Per-session SSE (P1.5-a): each live session owns its own `event.subscribe({directory})` loop + AbortController, so concurrent sessions in different worktrees stream independently; a `sessionID` demux guard drops cross-session events when two share a dir. Turn completes on `session.idle`; `promptAsync` is fire-and-forget (204).
 - **opencode model strings** must be provider-prefixed (`llama-swap/<model>`) AND exist in `~/.config/opencode/opencode.json` `provider.llama-swap.models` — not merely loadable by llama-swap. `parseModel` infers `llama-swap/` for a bare id; the dispatcher coalesces empty→DEFAULT_MODEL then prefixes. `agent-probe` populates opencode's `available_agents.models` via `mergeLlamaSwap` (fetches `/v1/models`); empty model list → frontend sends `''` → no inference (`input:0`, empty turn).
-- **agent_sessions resume**: `config_hash = sha256('opencode_server|<model>')` — must NOT include the server port (random per boot; including it breaks cross-restart resume). `session_worktrees` + `agent_sessions` FKs to `sessions(id)` are `ON DELETE CASCADE` (else DELETE /api/sessions/:id 500s on FK violation). The `@opencode-ai/sdk` v2 client takes flattened params (`{sessionID, directory, parts, model:{providerID,modelID}}`), imports `createOpencodeClient` from `@opencode-ai/sdk/v2/client`.
+- **agent_sessions resume**: `config_hash = sha256('opencode_server|<model>')` — must NOT include the server port (random per boot; including it breaks cross-restart resume). P1.5-b: `agent_sessions` is keyed `(chat_id, agent)` — the tab/chat is the context unit (two opencode tabs in one session = two contexts sharing one worktree). `chat_id` CASCADEs from `chats`; `session_id`/`worktree_id` are informational `SET NULL`. The `worktrees` table (one-per-session, `session_id` SET NULL so it survives session delete) supersedes the defanged `session_worktrees`. `tasks.chat_id` threads the tab id to the dispatcher; `runOpenCodeServerTask` falls back to resolve-or-create a chat when it's null (arena/MCP/new_task). The `@opencode-ai/sdk` v2 client takes flattened params (`{sessionID, directory, parts, model:{providerID,modelID}}`), imports `createOpencodeClient` from `@opencode-ai/sdk/v2/client`.
 
 ### Frontend (`apps/web/src/`)
 
@@ -192,6 +192,8 @@ BooCoder at port 9502: `curl http://100.114.205.53:9502/api/health`. Runs as `bo
 - **ReadableStream test stubs** use `pull()` (not `start()`) so chunks are produced lazily — `start()` enqueues everything and calls `controller.close()` before the consumer reads, so a subsequent `reader.cancel()` finds the stream already closed and the `cancel()` callback never fires. Also provide MORE chunks than the test will consume so the source stays in 'readable' state when cancel runs (e.g. cap test reads ~6 chunks, stub provides 10).
 - Tool-name whitelists must derive from `ALL_TOOLS` in `services/tools.ts`, never hardcoded. `services/agents.ts` `ALL_TOOL_NAMES` had this drift class until v1.12 — same pattern applies to any future tool-aware code.
 - Agent registry lives at `data/AGENTS.md` (global, bind-mounted at `/data/AGENTS.md`). No per-project `AGENTS.md` in this repo — removed in v1.12 to eliminate the two-files-must-stay-in-sync drift. The `getAgentsForProject` per-project override mechanism remains for *other* projects.
+- `data/AGENTS.md` is PARSED (`agents.ts` `splitSections`/`parseAgentSection`): each `## <Name>` is one agent and must be followed by a `---` frontmatter fence or the block throws; content before the first `## ` is discarded. Do NOT add free-form `## ` rule sections — they break the registry. Cross-cutting agent rules go in CLAUDE.md or a parser-ignored preamble.
+- Skills live in `data/skills/<vendor>/`; Sam's own namespace is `boocode/` (`committing-changes`, `using-worktrees`, `improving-boocode-guidance`) — `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.
 - MCP stdio transport uses newline-delimited JSON (NDJSON), NOT LSP-style `Content-Length` headers. The `codecontext/shim.go` framing implementation is the reference; per the MCP spec (modelcontextprotocol.io/specification/server/transports).
 - **Workspace dependency pattern** (`apps/coder` → `@boocode/server`): the consuming package adds `"@boocode/server": "workspace:*"` in `package.json`. The provider's `package.json` needs `exports` with `types` + `default` conditions per subpath: `"./inference": { "types": "./dist/.../index.d.ts", "default": "./dist/.../index.js" }`. Without the `types` condition, NodeNext resolution can't find `.d.ts` files and tsc fails with "Cannot find module" in the consumer.
 - **JSONB columns**: use `sql.json(value as never)` — NOT `${JSON.stringify(value)}::jsonb` which double-serializes (stores a JSON string instead of a JSON object/array). Pattern established in `parts.ts`, `settings.ts`.

apps/coder/src/index.ts

@@ -30,6 +30,7 @@ import { registerInboxRoutes } from './routes/inbox.js';
 import { registerStatsRoutes } from './routes/stats.js';
 import { registerArenaRoutes } from './routes/arena.js';
 import { registerProviderRoutes } from './routes/providers.js';
+import { registerWorktreeSafetyRoutes } from './routes/worktree-safety.js';
 import { registerWebSocket } from './routes/ws.js';
 // Phase 4: dispatcher + agent probe
 import { createDispatcher } from './services/dispatcher.js';
@@ -195,6 +196,7 @@ async function main() {
   registerStatsRoutes(app, sql);
   registerArenaRoutes(app, sql);
   registerProviderRoutes(app, sql, config);
+  registerWorktreeSafetyRoutes(app, sql);
   registerWebSocket(app, sql, broker);
 
   // Serve static frontend (built web app). In production, the dist/ is

apps/coder/src/routes/messages.ts

@@ -224,8 +224,8 @@ export function registerMessageRoutes(
         // External provider: create a task for the dispatcher
         const projectId = sessionRows[0]!.project_id;
         const [task] = await sql<{ id: string; state: string }[]>`
-          INSERT INTO tasks (project_id, input, agent, model, mode_id, thinking_option_id, session_id)
+          INSERT INTO tasks (project_id, input, agent, model, mode_id, thinking_option_id, session_id, chat_id)
-          VALUES (${projectId}, ${content}, ${provider}, ${model ?? null}, ${mode_id ?? null}, ${thinking_option_id ?? null}, ${sessionId})
+          VALUES (${projectId}, ${content}, ${provider}, ${model ?? null}, ${mode_id ?? null}, ${thinking_option_id ?? null}, ${sessionId}, ${chatId})
           RETURNING id, state
         `;
         reply.code(202);

apps/coder/src/routes/skills.ts

@@ -91,8 +91,8 @@ export function registerSkillRoutes(
 
         const taskInput = `${body}\n\n---\n\n${userText}`;
         const [task] = await sql<{ id: string; state: string }[]>`
-          INSERT INTO tasks (project_id, input, agent, model, mode_id, thinking_option_id, session_id)
+          INSERT INTO tasks (project_id, input, agent, model, mode_id, thinking_option_id, session_id, chat_id)
-          VALUES (${sessionRows[0]!.project_id}, ${taskInput}, ${provider}, ${model ?? null}, ${mode_id ?? null}, ${thinking_option_id ?? null}, ${sessionId})
+          VALUES (${sessionRows[0]!.project_id}, ${taskInput}, ${provider}, ${model ?? null}, ${mode_id ?? null}, ${thinking_option_id ?? null}, ${sessionId}, ${chatId})
           RETURNING id, state
         `;
         await sql`UPDATE chats SET updated_at = clock_timestamp() WHERE id = ${chatId}`;

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

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

apps/coder/src/schema.sql

@@ -83,16 +83,20 @@ CREATE TABLE IF NOT EXISTS session_worktrees (
   base_commit TEXT,
   created_at TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp()
 );
--- Migrate existing FK to CASCADE (idempotent: drops the old constraint if present).
+-- 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 $$ BEGIN
   IF EXISTS (
     SELECT 1 FROM pg_constraint
     WHERE conname = 'session_worktrees_session_id_fkey'
-      AND confdeltype <> 'c'
+      AND confdeltype = 'c'
   ) THEN
     ALTER TABLE session_worktrees DROP CONSTRAINT session_worktrees_session_id_fkey;
-    ALTER TABLE session_worktrees ADD CONSTRAINT session_worktrees_session_id_fkey
-      FOREIGN KEY (session_id) REFERENCES sessions(id) ON DELETE CASCADE;
   END IF;
 END $$;
 
@@ -127,6 +131,101 @@ END $$;
 -- v2.6: config fingerprint for stale-session detection (auto-recover on model change).
 ALTER TABLE agent_sessions ADD COLUMN IF NOT EXISTS config_hash TEXT;
 
+-- ─── P1.5-b (corrected): worktrees entity + re-key agent_sessions to (chat_id, agent) ───
+-- The TAB (a chat) is the context unit: two opencode tabs in one session = two
+-- independent contexts sharing one worktree. So agent_sessions keys on
+-- (chat_id, agent), NOT (worktree_id, agent) or (session_id, agent). The
+-- `worktrees` table is one-per-session (selectable later) and only referenced
+-- informationally by agent_sessions.worktree_id (SET NULL); chat_id is the key.
+--
+-- PREREQUISITE: the unmigratable test session (35 chats, 1 agent_sessions row that
+-- maps to no single chat) is DELETED before this runs, so agent_sessions is empty
+-- and the chat_id backfill is N/A. If a row with NULL chat_id remains, the verify
+-- gate below RAISEs and aborts — delete the offending session first.
+
+-- worktree as a first-class entity; survives session delete (session_id SET NULL).
+CREATE TABLE IF NOT EXISTS worktrees (
+  id          UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+  session_id  UUID REFERENCES sessions(id) ON DELETE SET NULL,
+  project_id  UUID,
+  path        TEXT NOT NULL,
+  branch      TEXT,
+  base_commit TEXT,
+  slug        TEXT,
+  status      TEXT NOT NULL DEFAULT 'active' CHECK (status IN ('active','archived')),
+  created_at  TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp()
+);
+CREATE UNIQUE INDEX IF NOT EXISTS worktrees_active_path_uidx ON worktrees(path) WHERE status='active';
+
+-- Migrate any surviving session_worktrees rows → worktrees (idempotent; 0 rows
+-- after the test-session delete, kept for generality / fresh-DB safety).
+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,
+-- new_task, generic /api/tasks) leave it NULL and the dispatcher creates a chat.
+ALTER TABLE tasks ADD COLUMN IF NOT EXISTS chat_id UUID REFERENCES chats(id) ON DELETE SET NULL;
+
+-- Re-key columns on agent_sessions.
+ALTER TABLE agent_sessions ADD COLUMN IF NOT EXISTS chat_id UUID;
+ALTER TABLE agent_sessions ADD COLUMN IF NOT EXISTS worktree_id UUID;
+
+-- BACKFILL-VERIFY GATE: the new PK is (chat_id, agent), so chat_id must be
+-- non-null on every row before the swap. With the test session deleted this is a
+-- 0-row assertion; if any row has NULL chat_id (an unmigratable pre-existing row),
+-- abort loudly rather than create a degenerate (NULL, agent) key.
+DO $$
+DECLARE n int;
+BEGIN
+  SELECT count(*) INTO n FROM agent_sessions WHERE chat_id IS NULL;
+  IF n > 0 THEN
+    RAISE EXCEPTION 'P1.5-b: % agent_sessions row(s) have NULL chat_id — delete the unmigratable session(s) before applying', n;
+  END IF;
+END $$;
+
+-- Swap PK (session_id,agent) → (chat_id,agent) + FKs (run-once, guarded on the new
+-- FK's absence). chat_id CASCADEs from chats (closing a tab ends its context);
+-- worktree_id is informational SET NULL; session_id defanged to nullable SET NULL.
+DO $$ BEGIN
+  IF NOT EXISTS (SELECT 1 FROM pg_constraint WHERE conname = 'agent_sessions_chat_id_fkey') THEN
+    ALTER TABLE agent_sessions DROP CONSTRAINT IF EXISTS agent_sessions_pkey;
+    ALTER TABLE agent_sessions DROP CONSTRAINT IF EXISTS agent_sessions_session_id_fkey;
+    ALTER TABLE agent_sessions ALTER COLUMN session_id DROP NOT NULL;
+    ALTER TABLE agent_sessions ALTER COLUMN chat_id SET NOT NULL;
+    ALTER TABLE agent_sessions ADD CONSTRAINT agent_sessions_pkey PRIMARY KEY (chat_id, agent);
+    ALTER TABLE agent_sessions ADD CONSTRAINT agent_sessions_chat_id_fkey
+      FOREIGN KEY (chat_id) REFERENCES chats(id) ON DELETE CASCADE;
+    ALTER TABLE agent_sessions ADD CONSTRAINT agent_sessions_session_id_fkey
+      FOREIGN KEY (session_id) REFERENCES sessions(id) ON DELETE SET NULL;
+    ALTER TABLE agent_sessions ADD CONSTRAINT agent_sessions_worktree_id_fkey
+      FOREIGN KEY (worktree_id) REFERENCES worktrees(id) ON DELETE SET NULL;
+  END IF;
+END $$;
+
+-- P1.5-b follow-up: converge agent_sessions.session_id FK CASCADE → SET NULL.
+-- The re-key block above re-adds session_id_fkey as SET NULL, but it is guarded on
+-- chat_id_fkey's ABSENCE — so a DB already re-keyed to (chat_id, agent) while
+-- session_id_fkey was still ON DELETE CASCADE never re-enters that block and stays
+-- 'c'. This standalone guard flips it to SET NULL ('n'), matching worktree_id.
+-- Idempotent (mirrors the session_worktrees defang's confdeltype check): only fires
+-- while the FK is still CASCADE — a no-op on a fresh deploy (already 'n' from the
+-- re-key block) and on every re-run thereafter.
+DO $$ BEGIN
+  IF EXISTS (
+    SELECT 1 FROM pg_constraint
+    WHERE conname = 'agent_sessions_session_id_fkey'
+      AND confdeltype = 'c'
+  ) THEN
+    ALTER TABLE agent_sessions ALTER COLUMN session_id DROP NOT NULL;
+    ALTER TABLE agent_sessions DROP CONSTRAINT agent_sessions_session_id_fkey;
+    ALTER TABLE agent_sessions ADD CONSTRAINT agent_sessions_session_id_fkey
+      FOREIGN KEY (session_id) REFERENCES sessions(id) ON DELETE SET NULL;
+  END IF;
+END $$;
+
 -- v2.6: attribution for DiffPanel badges (Phase 1 UX reads this).
 ALTER TABLE pending_changes ADD COLUMN IF NOT EXISTS agent TEXT;
 

apps/coder/src/services/__tests__/dcp-strip.test.ts

@@ -0,0 +1,73 @@
+import { describe, it, expect } from 'vitest';
+import { stripDcpTags, makeDcpStreamStripper } from '../dcp-strip.js';
+
+// Feed chunks through a fresh stripper and return the fully reassembled output
+// (everything emitted during streaming + the final flush) — i.e. what the
+// dispatcher would accumulate into the persisted message content.
+function run(chunks: string[]): string {
+  const s = makeDcpStreamStripper();
+  let out = '';
+  for (const c of chunks) out += s.push(c);
+  out += s.flush();
+  return out;
+}
+
+describe('stripDcpTags (one-shot)', () => {
+  it('removes a complete tag', () => {
+    expect(stripDcpTags('Yes — "Test".\n\n<dcp-message-id>m0019</dcp-message-id>')).toBe(
+      'Yes — "Test".\n\n',
+    );
+  });
+  it('leaves text without a tag untouched', () => {
+    expect(stripDcpTags('no tag here')).toBe('no tag here');
+  });
+});
+
+describe('per-chunk strip is INSUFFICIENT (documents the bug)', () => {
+  it('a tag split across chunks survives a naive per-chunk .replace()', () => {
+    const chunks = ['Yes.\n\n<dcp', '-message', '-id>m0019</dcp', '-message-id>'];
+    const naive = chunks.map(stripDcpTags).join('');
+    // The reassembled content still contains the tag — this is the screenshot bug.
+    expect(naive).toContain('<dcp-message-id>m0019</dcp-message-id>');
+  });
+});
+
+describe('makeDcpStreamStripper (cross-chunk fix)', () => {
+  it('strips a tag split across chunks (the real opencode case)', () => {
+    expect(run(['Yes.\n\n<dcp', '-message', '-id>m0019</dcp', '-message-id>'])).toBe('Yes.\n\n');
+  });
+
+  it('strips a tag split at EVERY character boundary', () => {
+    const full = 'Answer.<dcp-message-id>m0019</dcp-message-id>';
+    expect(run([...full])).toBe('Answer.');
+  });
+
+  it('strips a tag delivered whole in one chunk', () => {
+    expect(run(['Answer.<dcp-message-id>m0019</dcp-message-id>'])).toBe('Answer.');
+  });
+
+  it('passes through text with no tag', () => {
+    expect(run(['hello ', 'world'])).toBe('hello world');
+  });
+
+  it('does NOT swallow legitimate < content (code/HTML/generics)', () => {
+    expect(run(['use ', '<div>', ' and ', 'Array<', 'string>'])).toBe('use <div> and Array<string>');
+  });
+
+  it('handles a lone < that is not a dcp tag, split across chunks', () => {
+    expect(run(['a <', 'b c'])).toBe('a <b c');
+  });
+
+  it('emits surrounding text and strips a mid-text tag', () => {
+    expect(run(['before ', '<dcp-message-id>', 'm1', '</dcp-message-id>', ' after'])).toBe(
+      'before  after',
+    );
+  });
+
+  it('flushes a truncated/never-closed partial tag without leaking it as a complete tag', () => {
+    // If the stream ends mid-tag, flush strips complete tags; an incomplete
+    // remnant is returned as-is (no complete tag ever existed to render).
+    const out = run(['done.<dcp-message-id>m00']);
+    expect(out).not.toContain('</dcp-message-id>');
+  });
+});

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

@@ -37,8 +37,15 @@ export interface EnsureSessionOpts {
   agent: string;
   /** Resolved model id. */
   model: string;
+  /** P1.5-b: the chat (tab) this turn belongs to. agent_sessions is keyed
+   *  (chat_id, agent) — the tab/chat is the context unit. Always non-null:
+   *  the dispatcher creates a chat for session-less tasks before calling. */
+  chatId: string;
   /** Shared per-session worktree (one per `sessions.id`, not per pane). */
   worktreePath: string;
+  /** P1.5-b: the `worktrees.id` for this session's worktree — stored on the
+   *  agent_sessions row informationally (NOT the key). */
+  worktreeId: string;
   projectId: string;
 }
 
@@ -47,6 +54,10 @@ export interface AgentSessionHandle {
   sessionId: string;
   agent: string;
   backend: AgentBackendKind;
+  /** P1.5-b: the chat (tab) this session is keyed on (with agent). */
+  chatId: string;
+  /** P1.5-b: the worktree this session's chat runs in (informational link). */
+  worktreeId: string;
   /** Provider's own session id (resume token); null until the backend assigns one. */
   agentSessionId: string | null;
   /** opencode HTTP server port; null for ACP backends. */

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

@@ -3,7 +3,9 @@
  *
  * 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); a single SSE read loop demuxes all sessions' events.
+ * on switch-back); one SSE read loop PER session, each scoped to that session's
+ * worktree directory so sessions in different directories stream concurrently
+ * (P1.5-a — replaced the Phase-1 single-stream-last-directory model).
  *
  * Implements the Phase 0 `AgentBackend` interface. Emits transport-agnostic
  * `AgentEvent`s — the dispatcher (Phase 1.7, NOT wired in this batch) maps them
@@ -73,6 +75,9 @@ interface SessionState {
   activeTurn: TurnState | null;
   /** Inactivity backstop timer for the active turn; null when no turn in flight. */
   watchdog: ReturnType<typeof setTimeout> | null;
+  /** Per-session SSE subscription handle. Non-null while the loop is running;
+   *  aborting it tears down the underlying fetch and exits the loop. */
+  sseAbort: AbortController | null;
 }
 
 export interface OpenCodeServerBackendDeps {
@@ -94,7 +99,6 @@ export class OpenCodeServerBackend implements AgentBackend {
   private port: number | null = null;
   private up = false;
   private serverStarting: Promise<void> | null = null;
-  private sseRunning = false;
 
   /** opencode session id → demux state. Maintained by ensureSession; read by the SSE loop. */
   private readonly byOpencodeId = new Map<string, SessionState>();
@@ -150,37 +154,58 @@ export class OpenCodeServerBackend implements AgentBackend {
 
   // ─── SSE read loop + demux + translate (1.3) + dedup (1.4) ───────────────────
 
-  /** Per-directory SSE subscription. opencode scopes events by directory (defaults
+  /** Per-session SSE subscription, scoped to the session's worktree directory.
-   *  to process.cwd if omitted) — so we must subscribe with the same directory used
+   *  opencode scopes events by the `directory` query param (defaults to the
-   *  to create the session. Called from ensureSession; reconnects while up. */
+   *  server's cwd if omitted), so two sessions in different worktrees each get
-  private startEventLoop(directory: string): void {
+   *  their own dir-scoped stream and never drop each other's events. Idempotent:
-    if (this.sseRunning) return;
+   *  a no-op if this session's loop is already running. Started from ensureSession
-    this.sseRunning = true;
+   *  (and defensively from prompt) once worktreePath is known. */
-    this.sseDirectory = directory;
+  private startSessionEventLoop(state: SessionState): void {
-    void this.runEventLoop(directory);
+    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 sseDirectory: string | null = null;
+  private async runSessionEventLoop(state: SessionState, abort: AbortController): Promise<void> {
-
+    const signal = abort.signal;
-  private async runEventLoop(directory: string): Promise<void> {
+    while (this.up && this.client && !signal.aborted) {
-    while (this.up && this.client) {
       try {
-        const sub = await this.client.event.subscribe({ directory });
+        // 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) {
+        if (this.up && !signal.aborted) {
-          await this.reconcileInFlight();
+          await this.reconcile(state); // recover an idle/error lost during the gap
           await sleep(SSE_RECONNECT_DELAY_MS);
         }
       } catch (err) {
-        if (!this.up) break;
+        if (!this.up || signal.aborted) break;
-        this.log.warn({ err: errMsg(err) }, 'opencode-server: event loop error; reconnecting');
+        this.log.warn(
-        await this.reconcileInFlight();
+          { err: errMsg(err), agentSessionId: state.agentSessionId },
+          'opencode-server: session event loop error; reconnecting',
+        );
+        await this.reconcile(state);
         await sleep(SSE_RECONNECT_DELAY_MS);
       }
     }
-    this.sseRunning = false;
   }
 
   /** Demux one event to the owning session's active turn. Unknown/between-turns → drop. */
@@ -354,13 +379,6 @@ export class OpenCodeServerBackend implements AgentBackend {
     }
   }
 
-  /** Reconcile every in-flight turn against the server (called after an SSE drop). */
-  private async reconcileInFlight(): Promise<void> {
-    const states = [...this.byOpencodeId.values()].filter((s) => s.activeTurn);
-    if (states.length === 0) return;
-    await Promise.allSettled(states.map((s) => this.reconcile(s)));
-  }
-
   /**
    * 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.
@@ -405,9 +423,12 @@ export class OpenCodeServerBackend implements AgentBackend {
     if (!this.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 session_id = ${sessionId} AND agent = ${opts.agent}
+      WHERE chat_id = ${opts.chatId} AND agent = ${opts.agent}
     `;
     let agentSessionId = row?.agent_session_id ?? null;
 
@@ -429,10 +450,12 @@ export class OpenCodeServerBackend implements AgentBackend {
       agentSessionId = created.data.id;
       await this.sql`
         INSERT INTO agent_sessions
-          (session_id, agent, backend, agent_session_id, server_port, status, last_active_at, config_hash)
+          (chat_id, session_id, worktree_id, agent, backend, agent_session_id, server_port, status, last_active_at, config_hash)
         VALUES
-          (${sessionId}, ${opts.agent}, 'opencode_server', ${agentSessionId}, ${this.port}, 'active', clock_timestamp(), ${configHash})
+          (${opts.chatId}, ${sessionId}, ${opts.worktreeId}, ${opts.agent}, 'opencode_server', ${agentSessionId}, ${this.port}, 'active', clock_timestamp(), ${configHash})
-        ON CONFLICT (session_id, agent) DO UPDATE SET
+        ON CONFLICT (chat_id, agent) DO UPDATE SET
+          session_id = EXCLUDED.session_id,
+          worktree_id = EXCLUDED.worktree_id,
           backend = 'opencode_server',
           agent_session_id = EXCLUDED.agent_session_id,
           server_port = EXCLUDED.server_port,
@@ -444,42 +467,21 @@ export class OpenCodeServerBackend implements AgentBackend {
       await this.sql`
         UPDATE agent_sessions
         SET status = 'active', last_active_at = clock_timestamp(), server_port = ${this.port}, config_hash = ${configHash}
-        WHERE session_id = ${sessionId} AND agent = ${opts.agent}
+        WHERE chat_id = ${opts.chatId} AND agent = ${opts.agent}
       `;
     }
 
     // Both branches above guarantee agentSessionId is non-null.
     const ocSessionId = agentSessionId!;
 
-    // Start (or re-start) the SSE event loop scoped to this session's directory.
-    // opencode scopes events by the `directory` query param; without it events
-    // default to the server's CWD which doesn't match our worktree paths.
-    //
-    // KNOWN Phase 1 LIMITATION: one SSE stream at a time, scoped to a single
-    // directory. Under 1.9 concurrency, if two opencode sessions use different
-    // worktree directories simultaneously, re-subscribing for the second drops
-    // the first session's events (the watchdog backstop prevents a full hang,
-    // but streamed content is lost). Phase 2 should move to per-session SSE
-    // subscriptions or a directory-agnostic event path.
-    if (!this.sseRunning || this.sseDirectory !== opts.worktreePath) {
-      if (this.sseRunning && this.sseDirectory && this.sseDirectory !== opts.worktreePath) {
-        this.log.warn(
-          { prev: this.sseDirectory, next: opts.worktreePath },
-          'opencode-server: SSE directory changed — concurrent sessions will lose events from the previous directory',
-        );
-      }
-      this.sseRunning = false;
-      this.startEventLoop(opts.worktreePath);
-    }
-
     // Register / refresh the demux entry the SSE loop keys on. Preserve an existing
     // entry (and any in-flight turn) — just refresh the routing fields.
-    const existing = this.byOpencodeId.get(ocSessionId);
+    let state = this.byOpencodeId.get(ocSessionId);
-    if (existing) {
+    if (state) {
-      existing.boocodeSessionId = sessionId;
+      state.boocodeSessionId = sessionId;
-      existing.worktreePath = opts.worktreePath;
+      state.worktreePath = opts.worktreePath;
     } else {
-      this.byOpencodeId.set(ocSessionId, {
+      state = {
         boocodeSessionId: sessionId,
         agentSessionId: ocSessionId,
         worktreePath: opts.worktreePath,
@@ -487,13 +489,22 @@ export class OpenCodeServerBackend implements AgentBackend {
         partTypeById: new Map(),
         activeTurn: null,
         watchdog: null,
-      });
+        sseAbort: null,
+      };
+      this.byOpencodeId.set(ocSessionId, state);
     }
 
+    // Start this session's own SSE loop, scoped to its worktree directory. Both
+    // fresh-create and resume reach here; idempotent, so a re-ensure (e.g. a
+    // second turn) won't spawn a duplicate loop.
+    this.startSessionEventLoop(state);
+
     return {
       sessionId,
       agent: opts.agent,
       backend: 'opencode_server',
+      chatId: opts.chatId,
+      worktreeId: opts.worktreeId,
       agentSessionId: ocSessionId,
       serverPort: this.port,
     };
@@ -516,12 +527,17 @@ export class OpenCodeServerBackend implements AgentBackend {
         partTypeById: new Map(),
         activeTurn: null,
         watchdog: null,
+        sseAbort: null,
       };
       this.byOpencodeId.set(oc, state);
     }
     const session = state;
     // Authoritative per-turn directory for SDK routing + reconcile.
     session.worktreePath = ctx.worktreePath;
+    // Defensive: ensureSession normally starts the loop, but if prompt is reached
+    // with a freshly-created state (no loop yet), start it so the turn streams.
+    // Idempotent when ensureSession already started one.
+    this.startSessionEventLoop(session);
     const client = this.client;
 
     return await new Promise<TurnResult>((resolve) => {
@@ -577,15 +593,21 @@ export class OpenCodeServerBackend implements AgentBackend {
   // ─── teardown ────────────────────────────────────────────────────────────────
 
   async closeSession(handle: AgentSessionHandle): Promise<void> {
-    if (handle.agentSessionId) this.byOpencodeId.delete(handle.agentSessionId);
+    if (handle.agentSessionId) {
+      // Stop this session's SSE loop before dropping its demux entry.
+      this.byOpencodeId.get(handle.agentSessionId)?.sseAbort?.abort();
+      this.byOpencodeId.delete(handle.agentSessionId);
+    }
     await this.sql`
       UPDATE agent_sessions SET status = 'closed'
-      WHERE session_id = ${handle.sessionId} AND agent = ${handle.agent}
+      WHERE chat_id = ${handle.chatId} AND agent = ${handle.agent}
     `.catch(() => {});
   }
 
   async dispose(): Promise<void> {
     this.up = false;
+    // Abort every per-session SSE loop so none survive the teardown.
+    for (const st of this.byOpencodeId.values()) st.sseAbort?.abort();
     const child = this.child;
     this.child = null;
     this.client = null;
@@ -602,6 +624,20 @@ export class OpenCodeServerBackend implements AgentBackend {
 
 // ─── 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;

apps/coder/src/services/dcp-strip.ts

@@ -0,0 +1,77 @@
+/**
+ * Strip opencode-dcp plugin tags (`<dcp-message-id>mNNNN</dcp-message-id>`) that
+ * the @tarquinen/opencode-dcp plugin appends to assistant text and which
+ * otherwise render as literal text in the UI.
+ *
+ * Why a streaming stripper and not a per-chunk `.replace()`: opencode streams
+ * assistant text token-by-token, so the tag arrives SPLIT across many SSE deltas
+ * (`<dcp`, `-message`, `-id>`, `m0019`, `</dcp`, …). A per-chunk regex never sees
+ * a complete tag in any single fragment, so the fragments pass through and the
+ * dispatcher reassembles the full tag in the persisted/displayed content. The
+ * stripper below buffers across chunks: it emits everything that cannot be part
+ * of a forming tag and holds back only a trailing partial-tag prefix until the
+ * next chunk resolves it — without holding back legitimate `<…>` content.
+ */
+
+const DCP_TAG_RE = /<dcp-message-id>[^<]*<\/dcp-message-id>/g;
+const OPEN = '<dcp-message-id>';
+const CLOSE = '</dcp-message-id>';
+
+/** One-shot strip of COMPLETE tags. Safe for non-streaming / final content. */
+export function stripDcpTags(s: string): string {
+  return s.replace(DCP_TAG_RE, '');
+}
+
+/**
+ * Could `tail` (a substring starting at a `<`) still grow into a complete dcp
+ * tag on a future chunk? If so the caller must hold it back rather than emit it.
+ * Returns false for unrelated `<` content (`<div>`, `<T>`, …) so those stream
+ * normally.
+ */
+function isPartialDcp(tail: string): boolean {
+  // A prefix of the opening marker: '<', '<d', …, '<dcp-message-id'.
+  if (OPEN.startsWith(tail)) return true;
+  // Opening marker fully seen — content (and maybe a forming close) still streaming.
+  if (tail.startsWith(OPEN)) {
+    const rest = tail.slice(OPEN.length);
+    const lt = rest.indexOf('<');
+    if (lt === -1) return true; // still inside the [^<]* content run
+    return CLOSE.startsWith(rest.slice(lt)); // a partial close marker forming
+  }
+  return false;
+}
+
+export interface DcpStreamStripper {
+  /** Feed one text chunk; returns the portion safe to emit now (may be ''). */
+  push(chunk: string): string;
+  /** Stream end: returns whatever was held back, with complete tags stripped. */
+  flush(): string;
+}
+
+/** Stateful, cross-chunk-safe dcp stripper. One instance per turn. */
+export function makeDcpStreamStripper(): DcpStreamStripper {
+  let buf = '';
+  return {
+    push(chunk: string): string {
+      buf += chunk;
+      buf = buf.replace(DCP_TAG_RE, ''); // drop any now-complete tags
+      // Find the earliest `<` whose suffix is a forming dcp tag; hold from there,
+      // emit everything before it (real text, including unrelated `<…>`).
+      for (let i = buf.indexOf('<'); i !== -1; i = buf.indexOf('<', i + 1)) {
+        if (isPartialDcp(buf.slice(i))) {
+          const emit = buf.slice(0, i);
+          buf = buf.slice(i);
+          return emit;
+        }
+      }
+      const emit = buf;
+      buf = '';
+      return emit;
+    },
+    flush(): string {
+      const out = stripDcpTags(buf);
+      buf = '';
+      return out;
+    },
+  };
+}

apps/coder/src/services/dispatcher.ts

@@ -4,6 +4,7 @@ import type { Broker } from '@boocode/server/broker';
 import type { WsFrame } from '@boocode/server/ws-frames';
 import type { Config } from '../config.js';
 import { createWorktree, diffWorktree, cleanupWorktree, ensureSessionWorktree } from './worktrees.js';
+import { makeDcpStreamStripper } from './dcp-strip.js';
 import { dispatchViaAcp } from './acp-dispatch.js';
 import { getResolvedRegistry } from './provider-config-registry.js';
 import { dispatchViaPty } from './pty-dispatch.js';
@@ -77,8 +78,9 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
         mode_id: string | null;
         thinking_option_id: string | null;
         session_id: string | null;
+        chat_id: string | null;
       }[]>`
-        SELECT id, project_id, input, agent, model, mode_id, thinking_option_id, session_id
+        SELECT id, project_id, input, agent, model, mode_id, thinking_option_id, session_id, chat_id
         FROM tasks
         WHERE state = 'pending'
         ORDER BY created_at
@@ -109,6 +111,7 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
     mode_id: string | null;
     thinking_option_id: string | null;
     session_id: string | null;
+    chat_id: string | null;
   }): Promise<void> {
     const taskId = task.id;
 
@@ -510,6 +513,7 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
       mode_id: string | null;
       thinking_option_id: string | null;
       session_id: string | null;
+      chat_id: string | null;
     },
     installPath: string | null,
   ): Promise<void> {
@@ -542,10 +546,18 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
         WHERE id = ${taskId}
       `;
 
-      // Resolve session + chat (mirrors runExternalAgent).
+      // Resolve session + chat. P1.5-b: the chat (tab) is the context key, so the
+      // chat_id MUST be non-null and stable before ensureSession. The coder message
+      // route + skills route stamp task.chat_id with the frontend tab's chat — use
+      // it directly. Session-less creators (arena, MCP, new_task, generic
+      // /api/tasks) leave it null; fall back to resolving/creating a real chat so
+      // ensureSession never receives a degenerate (null, agent) key.
       let sessionId: string;
       let chatId: string;
-      if (task.session_id) {
+      if (task.chat_id && task.session_id) {
+        sessionId = task.session_id;
+        chatId = task.chat_id;
+      } else if (task.session_id) {
         sessionId = task.session_id;
         const chats = await sql<{ id: string }[]>`
           SELECT id FROM chats WHERE session_id = ${sessionId} AND status = 'open' ORDER BY created_at DESC LIMIT 1
@@ -586,7 +598,7 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
 
       // Persistent, session-keyed worktree (shared across turns; NOT torn down
       // per turn — Phase 3 reaps it). Captures base_commit for a stable diff.
-      const { worktreePath, baseCommit } = await ensureSessionWorktree(sql, projectPath, sessionId, {
+      const { worktreeId, worktreePath, baseCommit } = await ensureSessionWorktree(sql, projectPath, sessionId, {
         signal: ac.signal,
       });
       log.info({ taskId, worktreePath }, 'dispatcher: session worktree ready');
@@ -620,21 +632,30 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
       const textChunks: string[] = [];
       const reasoningChunks: string[] = [];
       const toolSnaps = new Map<string, AcpToolSnapshot>();
+      // opencode's dcp plugin appends <dcp-message-id>…</dcp-message-id> to the
+      // text, streamed split across deltas — a per-chunk regex misses it (see
+      // dcp-strip.ts). Buffer text through a cross-chunk stripper so neither the
+      // live `delta` frames nor the persisted content ever carry the tag.
+      const dcp = makeDcpStreamStripper();
 
       // Map transport-agnostic AgentEvents → the SAME WS frames the ACP path emits.
       // This boundary is where message_id/chat_id get attached (the backend never
       // owns them).
       const onEvent = (e: AgentEvent): void => {
         switch (e.type) {
-          case 'text':
+          case 'text': {
-            textChunks.push(e.text);
+            const safe = dcp.push(e.text);
+            if (safe) {
+              textChunks.push(safe);
               broker.publishFrame(sessionId, {
                 type: 'delta',
                 message_id: assistantId,
                 chat_id: chatId,
-              content: e.text,
+                content: safe,
               } as WsFrame);
+            }
             break;
+          }
           case 'reasoning':
             reasoningChunks.push(e.text);
             broker.publishFrame(sessionId, {
@@ -670,7 +691,9 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
       const handle = await backend.ensureSession(sessionId, {
         agent,
         model,
+        chatId,
         worktreePath,
+        worktreeId,
         projectId: task.project_id,
       });
       const result = await backend.prompt(handle, task.input, {
@@ -680,6 +703,18 @@ export function createDispatcher(deps: Deps): { start(): void; stop(): Promise<v
         onEvent,
       });
 
+      // Flush any text held back mid-tag at stream end (complete tags stripped).
+      const dcpTail = dcp.flush();
+      if (dcpTail) {
+        textChunks.push(dcpTail);
+        broker.publishFrame(sessionId, {
+          type: 'delta',
+          message_id: assistantId,
+          chat_id: chatId,
+          content: dcpTail,
+        } as WsFrame);
+      }
+
       const assistantContent = textChunks.join('').slice(0, 50_000);
       const reasoningText = reasoningChunks.join('').slice(0, 200_000);
       const outputSummary = (result.ok ? textChunks.join('') : result.error ?? 'opencode turn failed').slice(0, 500);

apps/coder/src/services/worktrees.ts

@@ -119,16 +119,18 @@ export async function cleanupWorktree(
 // ─── v2.6: session-keyed persistent worktree ────────────────────────────────
 
 export interface SessionWorktree {
+  /** P1.5-b: the `worktrees.id` — stored on agent_sessions informationally. */
+  worktreeId: string;
   worktreePath: string;
   baseCommit: string | null;
 }
 
 /**
- * v2.6: create-or-reuse ONE worktree per BooCode session (shared across all
+ * v2.6 / P1.5-b: create-or-reuse ONE worktree per BooCode session (shared across
- * agents/turns in the session), recorded in `session_worktrees`. Unlike the
+ * all tabs/agents in the session), recorded in `worktrees` (was the superseded
- * per-task `createWorktree`, this persists — it is NOT torn down per turn
+ * `session_worktrees`). Persists — NOT torn down per turn (cleanup is Phase 3) —
- * (cleanup is Phase 3). Captures the project's current HEAD as `base_commit`
+ * and now survives session delete (`worktrees.session_id` is ON DELETE SET NULL).
- * so the accumulating diff has a stable baseline across turns.
+ * Captures the project's current HEAD as `base_commit` for a stable diff baseline.
  *
  * Distinct path namespace (`session-<id>` branch, `/sess-<id>` dir) so it never
  * collides with the per-task worktrees that arena/new_task/MCP still use.
@@ -139,11 +141,13 @@ export async function ensureSessionWorktree(
   sessionId: string,
   opts?: { signal?: AbortSignal },
 ): Promise<SessionWorktree> {
-  const [existing] = await sql<{ worktree_path: string; base_commit: string | null }[]>`
+  const [existing] = await sql<{ id: string; path: string; base_commit: string | null }[]>`
-    SELECT worktree_path, base_commit FROM session_worktrees WHERE session_id = ${sessionId}
+    SELECT id, path, base_commit FROM worktrees
+    WHERE session_id = ${sessionId} AND status = 'active'
+    LIMIT 1
   `;
   if (existing) {
-    return { worktreePath: existing.worktree_path, baseCommit: existing.base_commit };
+    return { worktreeId: existing.id, worktreePath: existing.path, baseCommit: existing.base_commit };
   }
 
   const worktreePath = `${WORKTREE_BASE}/sess-${sessionId}`;
@@ -167,21 +171,191 @@ export async function ensureSessionWorktree(
     throw new Error(`Failed to create session worktree: ${result.stderr.trim() || result.stdout.trim()}`);
   }
 
-  // Persist. ON CONFLICT keeps the first writer's row if two turns race the create.
+  // Insert-or-get: WHERE NOT EXISTS keeps the first writer's row if two turns race
-  await sql`
+  // the create (the partial unique on active path also backstops it).
-    INSERT INTO session_worktrees (session_id, worktree_path, base_commit)
+  const [inserted] = await sql<{ id: string; path: string; base_commit: string | null }[]>`
-    VALUES (${sessionId}, ${worktreePath}, ${baseCommit})
+    INSERT INTO worktrees (session_id, path, branch, base_commit, status)
-    ON CONFLICT (session_id) DO NOTHING
+    SELECT ${sessionId}, ${worktreePath}, ${branchName}, ${baseCommit}, 'active'
+    WHERE NOT EXISTS (
+      SELECT 1 FROM worktrees WHERE session_id = ${sessionId} AND status = 'active'
+    )
+    RETURNING id, path, base_commit
   `;
-  const [row] = await sql<{ worktree_path: string; base_commit: string | null }[]>`
+  if (inserted) {
-    SELECT worktree_path, base_commit FROM session_worktrees WHERE session_id = ${sessionId}
+    return { worktreeId: inserted.id, worktreePath: inserted.path, baseCommit: inserted.base_commit };
+  }
+  // Lost the race — another turn inserted first; read its row.
+  const [row] = await sql<{ id: string; path: string; base_commit: string | null }[]>`
+    SELECT id, path, base_commit FROM worktrees
+    WHERE session_id = ${sessionId} AND status = 'active'
+    LIMIT 1
   `;
   return {
-    worktreePath: row?.worktree_path ?? worktreePath,
+    worktreeId: row!.id,
+    worktreePath: row?.path ?? worktreePath,
     baseCommit: row?.base_commit ?? baseCommit,
   };
 }
 
+// ─── Session-delete work-loss guard ─────────────────────────────────────────
+
+/**
+ * Risk report for a single worktree, returned by checkWorktreeWorkAtRisk.
+ * `atRisk` is the gate the server reads before allowing a session delete.
+ * A git error never silently passes — it forces `atRisk` true and surfaces
+ * the message in `error` (fail-closed).
+ */
+export interface RiskReport {
+  worktreePath: string;
+  branch: string;
+  dirty: boolean;   // uncommitted working-tree changes (incl. untracked)
+  unpushed: number; // commits ahead of upstream, or -1 if no upstream is set
+  unmerged: number; // commits on this branch not in the project default branch
+  atRisk: boolean;  // dirty || unmerged > 0 || (upstream && unpushed > 0) || git error
+  error?: string;   // populated on a git failure; presence forces atRisk
+}
+
+/**
+ * Resolve the project's default branch as a git-usable ref (e.g. "origin/main").
+ *
+ * `refs/remotes/origin/HEAD` lives in the repo's COMMON git dir and is shared
+ * across every linked worktree, so reading it from the session worktree returns
+ * the REMOTE's default branch — never this worktree's own `session-<id>` branch
+ * (that would be `symbolic-ref HEAD`, a different ref). Falls back to probing
+ * common defaults by verified existence when origin/HEAD isn't set (e.g. a repo
+ * that never ran `git remote set-head`). Returns null if none resolve, in which
+ * case the unmerged check is skipped (dirty + unpushed still protect the work).
+ */
+async function detectDefaultBranchRef(
+  worktreePath: string,
+  opts?: { signal?: AbortSignal },
+): Promise<string | null> {
+  const head = await hostExec(
+    `git -C ${shellEscape(worktreePath)} symbolic-ref --short refs/remotes/origin/HEAD`,
+    { signal: opts?.signal, timeoutMs: 10_000 },
+  );
+  if (head.exitCode === 0) {
+    const ref = head.stdout.trim(); // e.g. "origin/main"
+    if (ref) {
+      const verify = await hostExec(
+        `git -C ${shellEscape(worktreePath)} rev-parse --verify --quiet ${shellEscape(ref + '^{commit}')}`,
+        { signal: opts?.signal, timeoutMs: 10_000 },
+      );
+      if (verify.exitCode === 0 && verify.stdout.trim()) return ref;
+    }
+  }
+  // origin/HEAD unset or unresolvable — probe common defaults. Prefer the
+  // remote-tracking ref (always resolvable in a fresh worktree) over the local
+  // head, which may not exist if the default branch lives only in the main tree.
+  for (const cand of ['origin/main', 'origin/master', 'main', 'master']) {
+    const verify = await hostExec(
+      `git -C ${shellEscape(worktreePath)} rev-parse --verify --quiet ${shellEscape(cand + '^{commit}')}`,
+      { signal: opts?.signal, timeoutMs: 10_000 },
+    );
+    if (verify.exitCode === 0 && verify.stdout.trim()) return cand;
+  }
+  return null;
+}
+
+/**
+ * Inspect a worktree for work that would be lost if its session were deleted.
+ * Three checks, all via the audited hostExec + shellEscape path (every
+ * interpolated value — paths, refs — is single-quote-escaped; no bare
+ * interpolation). Any unexpected git failure is treated as at-risk, never a
+ * silent pass.
+ */
+export async function checkWorktreeWorkAtRisk(
+  worktreePath: string,
+  opts?: { signal?: AbortSignal },
+): Promise<RiskReport> {
+  // Branch name — also doubles as the "is this still a git worktree?" probe.
+  const br = await hostExec(
+    `git -C ${shellEscape(worktreePath)} rev-parse --abbrev-ref HEAD`,
+    { signal: opts?.signal, timeoutMs: 10_000 },
+  );
+  if (br.exitCode !== 0) {
+    return {
+      worktreePath,
+      branch: '',
+      dirty: false,
+      unpushed: 0,
+      unmerged: 0,
+      atRisk: true,
+      error: `git rev-parse failed: ${br.stderr.trim() || 'not a git worktree'}`,
+    };
+  }
+  const branch = br.stdout.trim();
+
+  // (a) Uncommitted (dirty working tree, including untracked files).
+  const st = await hostExec(
+    `git -C ${shellEscape(worktreePath)} status --porcelain`,
+    { signal: opts?.signal, timeoutMs: 15_000 },
+  );
+  if (st.exitCode !== 0) {
+    return {
+      worktreePath,
+      branch,
+      dirty: false,
+      unpushed: 0,
+      unmerged: 0,
+      atRisk: true,
+      error: `git status failed: ${st.stderr.trim()}`,
+    };
+  }
+  const dirty = st.stdout.trim().length > 0;
+
+  // (b) Unpushed commits. No upstream configured => work exists only locally;
+  // treat as unpushed-by-definition (-1) rather than an error.
+  const up = await hostExec(
+    `git -C ${shellEscape(worktreePath)} rev-list --count ${shellEscape('@{u}..HEAD')}`,
+    { signal: opts?.signal, timeoutMs: 15_000 },
+  );
+  const unpushed = up.exitCode === 0 ? (parseInt(up.stdout.trim() || '0', 10) || 0) : -1;
+
+  // (c) Unmerged commits — on this branch but not in the project default branch.
+  const defaultRef = await detectDefaultBranchRef(worktreePath, opts);
+  let unmerged = 0;
+  if (defaultRef) {
+    const rl = await hostExec(
+      `git -C ${shellEscape(worktreePath)} rev-list --count ${shellEscape(defaultRef + '..HEAD')}`,
+      { signal: opts?.signal, timeoutMs: 15_000 },
+    );
+    if (rl.exitCode === 0) unmerged = parseInt(rl.stdout.trim() || '0', 10) || 0;
+  }
+
+  // unpushed only contributes when an upstream actually exists. Session branches
+  // (session-<id>) never have one (unpushed === -1), and any real local-only work
+  // there already surfaces as unmerged > 0 — so the no-upstream case adds no
+  // protection, only friction (it flagged every pristine worktree-backed session).
+  // The unpushed > 0 arm stays forward-compatible with P1.5 pushable branches.
+  const hasUpstream = unpushed !== -1;
+  const atRisk = dirty || unmerged > 0 || (hasUpstream && unpushed > 0);
+  return { worktreePath, branch, dirty, unpushed, unmerged, atRisk };
+}
+
+/**
+ * Stash a worktree's uncommitted changes (including untracked, via -u) so the
+ * working tree is clean. Stash entries live in the repo's common git dir, so
+ * they survive worktree-dir removal — this is the recoverable, safe-by-default
+ * escape. Note it only clears the *dirty* risk; unpushed/unmerged commits
+ * remain on the branch, so a re-attempted delete may still block on those.
+ */
+export async function stashWorktree(
+  worktreePath: string,
+  opts?: { signal?: AbortSignal },
+): Promise<{ stashed: boolean; error?: string }> {
+  const r = await hostExec(
+    `git -C ${shellEscape(worktreePath)} stash push -u -m ${shellEscape('boocode: pre-delete stash')}`,
+    { signal: opts?.signal, timeoutMs: 30_000 },
+  );
+  if (r.exitCode !== 0) {
+    return { stashed: false, error: r.stderr.trim() || r.stdout.trim() };
+  }
+  // "No local changes to save" => exit 0, nothing stashed — not an error.
+  const stashed = !/no local changes to save/i.test(r.stdout);
+  return { stashed };
+}
+
 /** Minimal shell escape for paths (single-quote wrapping). */
 function shellEscape(s: string): string {
   // Replace single quotes with escaped version, wrap in single quotes

apps/server/src/routes/sessions.ts

@@ -3,7 +3,7 @@ import { z } from 'zod';
 import type { Sql } from '../db.js';
 import type { Config } from '../config.js';
 import type { Broker } from '../services/broker.js';
-import type { Session } from '../types/api.js';
+import type { Session, WorktreeRiskReport } from '../types/api.js';
 import { getSetting } from './settings.js';
 
 const CreateBody = z.object({
@@ -28,9 +28,7 @@ const HtmlArtifactStateZ = z.object({
   title: z.string().max(500),
 });
 
-const WorkspacePaneZ = z.object({
+const PaneKindZ = z.enum([
-  id: z.string().min(1).max(200),
-  kind: z.enum([
   'chat',
   'terminal',
   'coder',
@@ -39,7 +37,11 @@ const WorkspacePaneZ = z.object({
   'settings',
   'markdown_artifact',
   'html_artifact',
-  ]),
+]);
+
+const WorkspacePaneZ = z.object({
+  id: z.string().min(1).max(200),
+  kind: PaneKindZ,
   chatId: z.string().min(1).max(200).optional(),
   chatIds: z.array(z.string().min(1).max(200)).max(50),
   activeChatIdx: z.number().int(),
@@ -47,8 +49,27 @@ const WorkspacePaneZ = z.object({
   html_artifact_state: HtmlArtifactStateZ.optional(),
 });
 
+// v2.6.x: workspace_panes column widened from a bare WorkspacePane[] to a
+// WorkspaceState envelope (panes + stable session-scoped tab numbering +
+// reopen stack). closedPaneStack entries are lighter than full panes — just
+// the kind + chat ids needed to recreate a closed pane on reopen.
+const ClosedPaneEntryZ = z.object({
+  kind: PaneKindZ,
+  chatIds: z.array(z.string().min(1).max(200)).max(50),
+  activeChatIdx: z.number().int(),
+});
+
+const WorkspaceStateZ = z.object({
+  panes: z.array(WorkspacePaneZ).max(10),
+  tabNumbers: z.record(z.string(), z.number().int()).default({}),
+  nextTabNumber: z.number().int().default(1),
+  closedPaneStack: z.array(ClosedPaneEntryZ).max(10).default([]),
+});
+
+// Accept either the legacy bare array OR the envelope. The handler normalizes
+// to a full envelope before storing (see MIGRATION rule in the PATCH handler).
 const WorkspacePanesBody = z.object({
-  workspace_panes: z.array(WorkspacePaneZ).max(10),
+  workspace_panes: z.union([z.array(WorkspacePaneZ).max(10), WorkspaceStateZ]),
 });
 
 const PatchBody = z.object({
@@ -308,12 +329,20 @@ export function registerSessionRoutes(
         reply.code(400);
         return { error: 'invalid body', details: parsed.error.flatten() };
       }
-      const workspacePanes = parsed.data.workspace_panes.map((pane) =>
+      // v2.6.x MIGRATION: the body is either a legacy bare WorkspacePane[] or
+      // the WorkspaceState envelope. Normalize to a full envelope so the column
+      // always stores the envelope shape going forward.
+      const body = parsed.data.workspace_panes;
+      const envelope = Array.isArray(body)
+        ? { panes: body, tabNumbers: {}, nextTabNumber: 1, closedPaneStack: [] }
+        : body;
+      // agent → coder normalization on the panes array (unchanged write rule).
+      envelope.panes = envelope.panes.map((pane) =>
         pane.kind === 'agent' ? { ...pane, kind: 'coder' as const } : pane,
       );
       const rows = await sql<Session[]>`
         UPDATE sessions
-        SET workspace_panes = ${sql.json(workspacePanes as never)},
+        SET workspace_panes = ${sql.json(envelope as never)},
             updated_at = clock_timestamp()
         WHERE id = ${req.params.id}
         RETURNING id, project_id, name, model, system_prompt, status, created_at, updated_at,
@@ -426,10 +455,55 @@ export function registerSessionRoutes(
     }
   );
 
-  app.delete<{ Params: { id: string } }>(
+  app.delete<{ Params: { id: string }; Querystring: { force?: string } }>(
     '/api/sessions/:id',
     async (req, reply) => {
       const id = req.params.id;
+      const force = req.query.force === 'true' || req.query.force === '1';
+
+      // Session-delete work-loss guard. The check MUST run BEFORE the DELETE:
+      // worktrees.session_id is ON DELETE SET NULL (P1.5-b), so once the session
+      // is gone the worktree rows no longer point back to it — read them while
+      // the link still exists.
+      //
+      // Optimization: read worktrees (P1.5-b — was session_worktrees) from our
+      // own (shared) DB first. No row => chat-only session => nothing on disk =>
+      // delete immediately, zero round-trip. Only worktree-backed sessions pay
+      // the host git check.
+      if (!force) {
+        const worktrees = await sql<{ path: string }[]>`
+          SELECT path FROM worktrees WHERE session_id = ${id}
+        `;
+        if (worktrees.length > 0) {
+          // Worktree dirs live on the host; only BooCoder can run git on them.
+          const origin = process.env.BOOCODER_URL ?? 'http://boocoder:3000';
+          let reports: WorktreeRiskReport[];
+          try {
+            const res = await fetch(`${origin}/api/sessions/${id}/worktree-risk`);
+            if (!res.ok) {
+              // Fail-closed: can't verify => don't risk silent loss. Force escapes.
+              reply.code(409);
+              return {
+                error: 'could not verify worktree safety (BooCoder check failed). Use force to delete anyway.',
+                reports: [] as WorktreeRiskReport[],
+              };
+            }
+            reports = ((await res.json()) as { reports?: WorktreeRiskReport[] }).reports ?? [];
+          } catch {
+            // Fail-closed: BooCoder unreachable. Force bypasses this path entirely.
+            reply.code(409);
+            return {
+              error: 'BooCoder unreachable; cannot verify worktree safety. Use force to delete anyway.',
+              reports: [] as WorktreeRiskReport[],
+            };
+          }
+          if (reports.some((r) => r.atRisk)) {
+            reply.code(409);
+            return { error: 'This session has work at risk in its worktree.', reports };
+          }
+        }
+      }
+
       const deleted = await sql<{ project_id: string }[]>`
         DELETE FROM sessions WHERE id = ${id} RETURNING project_id
       `;

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

@@ -2,6 +2,7 @@ import type { Agent, Session, ToolCall } from '../../types/api.js';
 import * as modelContext from '../model-context.js';
 import { PathScopeError } from '../path_guard.js';
 import { TOOLS_BY_NAME } from '../tools.js';
+import type { ToolExecCtx } from '../tools.js';
 import { matchToolGlob } from '../agents.js';
 import { maybeFlagForCompaction } from './payload.js';
 import { insertParts, partsFromAssistantMessage, partsFromToolMessage } from './parts.js';
@@ -31,6 +32,7 @@ async function executeToolCall(
   projectRoot: string,
   toolCall: ToolCall,
   extraRoots: readonly string[],
+  toolCtx?: ToolExecCtx,
 ): Promise<{ output: unknown; truncated: boolean; error?: string }> {
   const tool = TOOLS_BY_NAME[toolCall.name];
   if (!tool) {
@@ -65,7 +67,7 @@ async function executeToolCall(
     };
   }
   try {
-    const output = await tool.execute(parsed.data, projectRoot, extraRoots);
+    const output = await tool.execute(parsed.data, projectRoot, extraRoots, toolCtx);
     const truncated =
       typeof output === 'object' && output !== null && 'truncated' in output
         ? Boolean((output as { truncated: unknown }).truncated)
@@ -289,7 +291,10 @@ export async function executeToolPhase(
         });
         return;
       }
-      const tres = await executeToolCall(projectRoot, tc, session.allowed_read_paths);
+      const tres = await executeToolCall(projectRoot, tc, session.allowed_read_paths, {
+        sql: ctx.sql,
+        sessionId,
+      });
       if (SYNTHESIS_TOOLS.has(tc.name)) {
         synthEntries.push({ tc, output: tres.output, ...(tres.error ? { error: tres.error } : {}) });
       }

apps/server/src/services/read_tab_by_number.ts

@@ -0,0 +1,142 @@
+// v2.6.x: read_tab_by_number tool. Reads the conversation transcript of the
+// chat that occupies a given session-scoped tab number. Stable tab numbers are
+// 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 + READ_ONLY_TOOL_NAMES.
+
+import { z } from 'zod';
+import type { Sql } from '../db.js';
+// type-only import to dodge the runtime cycle (tools.ts re-exports this tool
+// via ALL_TOOLS; importing ToolDef/ToolExecCtx at type level keeps the dep
+// one-way).
+import type { ToolDef, ToolExecCtx } from './tools.js';
+
+const ReadTabByNumberInput = z.object({
+  number: z.number().int().positive(),
+});
+export type ReadTabByNumberInputT = z.infer<typeof ReadTabByNumberInput>;
+
+// Cap total transcript size so a long conversation can't blow the context
+// window. The model gets a clear truncation marker when the cap is hit.
+const MAX_TRANSCRIPT_CHARS = 20_000;
+
+// WorkspaceState envelope shape (panes omitted — we only need tabNumbers here).
+interface WorkspaceStateLike {
+  panes?: unknown;
+  tabNumbers?: Record<string, number>;
+  nextTabNumber?: number;
+  closedPaneStack?: unknown[];
+}
+
+// MIGRATION: the stored workspace_panes value may be the legacy bare
+// WorkspacePane[] OR the WorkspaceState envelope. Normalize to an envelope so
+// tabNumbers is always available (empty for the legacy shape — no tab numbers
+// were tracked before the envelope landed).
+function normalizeWorkspaceState(v: unknown): {
+  tabNumbers: Record<string, number>;
+} {
+  if (Array.isArray(v)) {
+    return { tabNumbers: {} };
+  }
+  if (v && typeof v === 'object' && Array.isArray((v as WorkspaceStateLike).panes)) {
+    const env = v as WorkspaceStateLike;
+    return { tabNumbers: env.tabNumbers ?? {} };
+  }
+  return { tabNumbers: {} };
+}
+
+// Pure executor split out from the ToolDef wrapper so tests can call it with a
+// mocked Sql. Returns a transcript string (read-only — never writes).
+export async function executeReadTabByNumber(
+  input: ReadTabByNumberInputT,
+  sql: Sql,
+  sessionId: string,
+): Promise<string> {
+  const sessionRows = await sql<{ workspace_panes: unknown }[]>`
+    SELECT workspace_panes FROM sessions WHERE id = ${sessionId}
+  `;
+  if (sessionRows.length === 0) {
+    return `Session not found.`;
+  }
+  const { tabNumbers } = normalizeWorkspaceState(sessionRows[0]!.workspace_panes);
+
+  // Reverse-lookup: find the chat id whose stable tab number equals the input.
+  let chatId: string | null = null;
+  for (const [cid, num] of Object.entries(tabNumbers)) {
+    if (num === input.number) {
+      chatId = cid;
+      break;
+    }
+  }
+  if (chatId === null) {
+    return `No tab is numbered ${input.number} in this session.`;
+  }
+
+  // Read the conversation: skip system sentinels (role='system') and empty
+  // content rows. Oldest first.
+  const messages = await sql<{ role: string; content: string }[]>`
+    SELECT role, content
+      FROM messages
+     WHERE chat_id = ${chatId}
+       AND role <> 'system'
+       AND content <> ''
+     ORDER BY created_at ASC
+  `;
+  if (messages.length === 0) {
+    return `Tab ${input.number} (chat ${chatId}) has no messages yet.`;
+  }
+
+  // Format a compact transcript, capping total output size.
+  const parts: string[] = [];
+  let total = 0;
+  let truncated = false;
+  for (const m of messages) {
+    const block = `### ${m.role}\n${m.content}`;
+    // +2 accounts for the "\n\n" joiner between blocks.
+    if (total + block.length + 2 > MAX_TRANSCRIPT_CHARS) {
+      truncated = true;
+      break;
+    }
+    parts.push(block);
+    total += block.length + 2;
+  }
+
+  let out = parts.join('\n\n');
+  if (truncated) {
+    out += `\n\n[transcript truncated at ${MAX_TRANSCRIPT_CHARS} chars]`;
+  }
+  return out;
+}
+
+export const readTabByNumber: ToolDef<ReadTabByNumberInputT> = {
+  name: 'read_tab_by_number',
+  description:
+    'Read the conversation transcript of the tab with the given session-scoped tab number. Tab numbers are stable per session (shown in the workspace tab strip). Returns the messages of that tab oldest-first as a compact transcript. Read-only.',
+  inputSchema: ReadTabByNumberInput,
+  jsonSchema: {
+    type: 'function',
+    function: {
+      name: 'read_tab_by_number',
+      description:
+        'Read the conversation transcript of the tab with the given session-scoped tab number. Read-only.',
+      parameters: {
+        type: 'object',
+        properties: {
+          number: {
+            type: 'integer',
+            description: 'The session-scoped tab number (positive integer).',
+          },
+        },
+        required: ['number'],
+        additionalProperties: false,
+      },
+    },
+  },
+  async execute(input, _projectRoot, _extraRoots, toolCtx?: ToolExecCtx) {
+    if (!toolCtx) {
+      return 'read_tab_by_number unavailable: no session context';
+    }
+    return await executeReadTabByNumber(input, toolCtx.sql, toolCtx.sessionId);
+  },
+};

apps/server/src/services/tools.ts

@@ -1,6 +1,7 @@
 import { readFile, readdir, stat } from 'node:fs/promises';
 import { resolve, basename, relative } from 'node:path';
 import { z } from 'zod';
+import type { Sql } from '../db.js';
 import { pathGuard, PathScopeError } from './path_guard.js';
 import { isSecretPath, SecretBlockedError, filterSecretEntries } from './secret_guard.js';
 import { grep as fileOpsGrep, findFiles as fileOpsFindFiles } from './file_ops.js';
@@ -30,6 +31,9 @@ import {
 // with the pause-on-pending-grant branch in inference/tool-phase.ts and the
 // POST /api/chats/:id/grant_read_access endpoint in routes/messages.ts.
 import { requestReadAccess } from './request_read_access.js';
+// v2.6.x: read-only tool that reads a tab's transcript by its session-scoped
+// tab number. Needs DB/session context (ToolExecCtx 4th arg).
+import { readTabByNumber } from './read_tab_by_number.js';
 
 const MAX_FILE_BYTES = 5 * 1024 * 1024;
 const DEFAULT_VIEW_LINES = 200;
@@ -48,6 +52,16 @@ export interface ToolJsonSchema {
   };
 }
 
+// v2.6.x: optional DB/session context threaded into a tool's execute(). Only
+// tools that need to read session-scoped DB state (e.g. read_tab_by_number)
+// use it; every other tool ignores the 4th arg. Kept optional so existing
+// 3-arg execute() implementations stay assignable (apps/coder consumes this
+// type from the compiled dist — the optional param keeps it backward-compatible).
+export interface ToolExecCtx {
+  sql: Sql;
+  sessionId: string;
+}
+
 export interface ToolDef<TInput> {
   name: string;
   description: string;
@@ -59,7 +73,15 @@ export interface ToolDef<TInput> {
   // view_truncated_output) forward it to pathGuard; other tools accept the
   // arg and ignore it. The execute signature stays compatible with
   // pre-v1.13.17 callsites because the parameter is optional.
-  execute(input: TInput, projectRoot: string, extraRoots?: readonly string[]): Promise<unknown>;
+  // v2.6.x: optional 4th param toolCtx carries DB/session context for tools
+  // that read session-scoped state (read_tab_by_number). Optional so 3-arg
+  // implementations remain assignable.
+  execute(
+    input: TInput,
+    projectRoot: string,
+    extraRoots?: readonly string[],
+    toolCtx?: ToolExecCtx,
+  ): Promise<unknown>;
 }
 
 const ViewFileInput = z.object({
@@ -694,6 +716,9 @@ export let ALL_TOOLS: ToolDef<unknown>[] = [
   // state change is appending to sessions.allowed_read_paths via the
   // grant endpoint, gated by user consent.
   requestReadAccess as ToolDef<unknown>,
+  // v2.6.x: read a tab's transcript by its session-scoped tab number.
+  // Read-only; uses the ToolExecCtx 4th arg for DB/session access.
+  readTabByNumber as ToolDef<unknown>,
 ].sort((a, b) => a.name.localeCompare(b.name));
 
 // v1.8.2: forward-compatible read-only whitelist. An agent whose `tools` is
@@ -734,6 +759,9 @@ export const READ_ONLY_TOOL_NAMES = [
   // state directly (the grant endpoint appends to sessions.allowed_read_paths
   // only with user consent). Belongs in the read-only budget tier.
   'request_read_access',
+  // v2.6.x: reads a tab's transcript from session-scoped DB state; never
+  // writes. Belongs in the read-only budget tier.
+  'read_tab_by_number',
 ] as const;
 
 export let TOOLS_BY_NAME: Record<string, ToolDef<unknown>> = Object.fromEntries(

apps/server/src/types/api.ts

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

apps/server/src/types/ws-frames.ts

@@ -203,7 +203,12 @@ export const SessionDeletedFrame = z.object({
 export const SessionWorkspaceUpdatedFrame = z.object({
   type: z.literal('session_workspace_updated'),
   session_id: Uuid,
-  workspace_panes: z.array(OpaqueObject),
+  // v2.6.x: widened from z.array — the payload is now either the legacy bare
+  // WorkspacePane[] OR the WorkspaceState envelope object (panes + tabNumbers +
+  // nextTabNumber + closedPaneStack). z.array alone would fail-closed and drop
+  // every envelope frame at validation. MUST be mirrored in the server's
+  // byte-identical copy (parity test).
+  workspace_panes: z.union([z.array(OpaqueObject), z.record(z.unknown())]),
 });
 
 export const ChatCreatedFrame = z.object({

apps/web/src/api/client.ts

@@ -22,6 +22,7 @@ import type {
   CoderTaskDetail,
   PermissionPrompt,
   AgentCommand,
+  WorkspaceState,
 } from './types';
 
 export class ApiError extends Error {
@@ -151,8 +152,17 @@ export const api = {
         method: 'PATCH',
         body: JSON.stringify(body),
       }),
-    remove: (id: string) =>
+    // force=true bypasses the server-side worktree work-loss guard. A blocked
-      request<void>(`/api/sessions/${id}`, { method: 'DELETE' }),
+    // delete throws ApiError(409) whose body carries { error, reports }.
+    remove: (id: string, force = false) =>
+      request<void>(`/api/sessions/${id}${force ? '?force=true' : ''}`, { method: 'DELETE' }),
+    // Stash the session's worktree (uncommitted changes) on the host, via the
+    // BooCoder proxy. Recoverable escape from the work-at-risk dialog.
+    worktreeStash: (id: string) =>
+      request<{ results: { worktreePath: string; stashed: boolean; error?: string }[] }>(
+        `/api/coder/sessions/${id}/worktree-stash`,
+        { method: 'POST' },
+      ),
     archive: (id: string) =>
       request<void>(`/api/sessions/${id}/archive`, { method: 'POST' }),
     unarchive: (id: string) =>
@@ -166,10 +176,10 @@ export const api = {
       ),
     openChatsCount: (id: string) =>
       request<{ count: number }>(`/api/sessions/${id}/chats/open-count`),
-    updateWorkspacePanes: (id: string, panes: Session['workspace_panes']) =>
+    updateWorkspacePanes: (id: string, state: WorkspaceState) =>
       request<Session>(`/api/sessions/${id}/workspace`, {
         method: 'PATCH',
-        body: JSON.stringify({ workspace_panes: panes }),
+        body: JSON.stringify({ workspace_panes: state }),
       }),
   },
 
@@ -345,6 +355,10 @@ export const api = {
       request<{ taskId: string; commands: AgentCommand[] }>(`/api/coder/tasks/${taskId}/commands`),
     getTask: (taskId: string) =>
       request<CoderTaskDetail>(`/api/coder/tasks/${taskId}`),
+    // Cancel a pending/running coder task (cancels permission wait + inference;
+    // server sets state='cancelled'). Used by CoderPane's stop button.
+    cancelTask: (taskId: string) =>
+      request<{ cancelled: boolean }>(`/api/coder/tasks/${taskId}/cancel`, { method: 'POST' }),
     listMessages: (sessionId: string, chatId?: string) =>
       request<CoderMessageWire[]>(
         `/api/coder/sessions/${sessionId}/messages${chatId ? `?chat_id=${encodeURIComponent(chatId)}` : ''}`,

apps/web/src/api/types.ts

@@ -34,6 +34,19 @@ export interface AvailableProject {
 
 export type SessionStatus = 'open' | 'archived';
 
+// Session-delete work-loss guard. Mirror of WorktreeRiskReport in
+// apps/server/src/types/api.ts — edit both copies together. Arrives as the
+// `reports` field of the 409 body when a delete is blocked.
+export interface WorktreeRiskReport {
+  worktreePath: string;
+  branch: string;
+  dirty: boolean;
+  unpushed: number; // commits ahead of upstream, or -1 if no upstream
+  unmerged: number; // commits not in the project default branch
+  atRisk: boolean;
+  error?: string;
+}
+
 export interface Session {
   id: string;
   project_id: string;
@@ -47,7 +60,10 @@ export interface Session {
   // v1.9: null = inherit from project.default_web_search_enabled.
   web_search_enabled: boolean | null;
   // v1.12.1: server-authoritative pane layout, replaces localStorage.
-  workspace_panes: WorkspacePane[];
+  // A value may be the legacy bare WorkspacePane[] (older rows) OR the new
+  // WorkspaceState envelope (panes + tab numbering + reopen stack). Normalize
+  // on read via useWorkspacePanes' toWorkspaceState.
+  workspace_panes: WorkspacePane[] | WorkspaceState;
   // v1.13.17: paths the agent has been granted read access to via the
   // request_read_access tool. Empty by default. Settings UI surfaces the
   // list with per-row revoke; the grant flow itself appends through the
@@ -498,6 +514,30 @@ export interface WorkspacePane {
   html_artifact_state?: HtmlArtifactState;
 }
 
+// Reopen LIFO stack entry. Shape unchanged from the prior module-level stack;
+// now persisted inside the WorkspaceState envelope so the reopen-pane stack
+// survives a reload / cross-device sync.
+export interface ClosedPaneEntry {
+  kind: WorkspacePane['kind'];
+  chatIds: string[];
+  activeChatIdx: number;
+}
+
+// Envelope persisted to sessions.workspace_panes. Supersedes the bare
+// WorkspacePane[] shape (still accepted on read for legacy rows — see the
+// migration in useWorkspacePanes.toWorkspaceState). The server accepts either
+// shape; the frontend always emits this envelope going forward.
+export interface WorkspaceState {
+  panes: WorkspacePane[];
+  // Stable, session-scoped tab number per chat id. Numbers only ever increase
+  // and are never reused (retired entries are pruned on tab close).
+  tabNumbers: { [chatId: string]: number };
+  // Next number to hand out; starts at 1; ONLY increments.
+  nextTabNumber: number;
+  // Reopen LIFO stack, max 10, most-recent last.
+  closedPaneStack: ClosedPaneEntry[];
+}
+
 export type WsFrame =
   | { type: 'snapshot'; messages: Message[] }
   | { type: 'message_started'; message_id: string; chat_id?: string; role: MessageRole }

apps/web/src/api/ws-frames.ts

@@ -203,7 +203,12 @@ export const SessionDeletedFrame = z.object({
 export const SessionWorkspaceUpdatedFrame = z.object({
   type: z.literal('session_workspace_updated'),
   session_id: Uuid,
-  workspace_panes: z.array(OpaqueObject),
+  // v2.6.x: widened from z.array — the payload is now either the legacy bare
+  // WorkspacePane[] OR the WorkspaceState envelope object (panes + tabNumbers +
+  // nextTabNumber + closedPaneStack). z.array alone would fail-closed and drop
+  // every envelope frame at validation. MUST be mirrored in the server's
+  // byte-identical copy (parity test).
+  workspace_panes: z.union([z.array(OpaqueObject), z.record(z.unknown())]),
 });
 
 export const ChatCreatedFrame = z.object({

apps/web/src/components/ChatInput.tsx

@@ -1,5 +1,5 @@
 import { useCallback, useEffect, useMemo, useRef, useState, type DragEvent, type KeyboardEvent } from 'react';
-import { Check, Plus, Send } from 'lucide-react';
+import { Check, ListPlus, Plus, Send, Square } from 'lucide-react';
 import { toast } from 'sonner';
 import { Textarea } from '@/components/ui/textarea';
 import { Button } from '@/components/ui/button';
@@ -51,6 +51,11 @@ interface Props {
   webSearchEnabled?: boolean | null;
   onSend: (content: string) => void | Promise<void>;
   onForceSend?: (content: string) => void | Promise<void>;
+  // When the assistant/agent is generating, the send button morphs: empty draft
+  // → Stop (calls onStop); non-empty draft → Queue (submits, which the caller
+  // queues while busy). Omitting onStop falls back to a (disabled) Send button.
+  generating?: boolean;
+  onStop?: () => void | Promise<void>;
   // Batch 9.6: slash-command dispatch. When the input parses to a known skill,
   // ChatInput calls this with the skill name + the post-name args (possibly
   // empty). Callers wire this to api.chats.skillInvoke. Omitting the prop
@@ -78,7 +83,7 @@ interface Props {
   modelContextLimit?: number | null;
 }
 
-export function ChatInput({ disabled, projectId, agentId, onAgentChange, sessionId, webSearchEnabled, onSend, onForceSend, onSlashCommand, slashGroups, chatId, chatLabel, messages, modelContextLimit }: Props) {
+export function ChatInput({ disabled, projectId, agentId, onAgentChange, sessionId, webSearchEnabled, onSend, onForceSend, generating, onStop, onSlashCommand, slashGroups, chatId, chatLabel, messages, modelContextLimit }: Props) {
   const { isMobile } = useViewport();
   const [value, setValue] = useState('');
   const [busy, setBusy] = useState(false);
@@ -651,14 +656,38 @@ export function ChatInput({ disabled, projectId, agentId, onAgentChange, session
           rows={3}
           className="resize-none min-h-[68px] max-h-[240px]"
         />
+        {(() => {
+          const hasContent = value.trim().length > 0 || attachments.length > 0;
+          // While generating with an empty draft, the button stops generation.
+          if (generating && onStop && !hasContent) {
+            return (
+              <Button
+                onClick={() => void onStop()}
+                size="icon-lg"
+                variant="outline"
+                aria-label="Stop generating"
+                title="Stop generating"
+              >
+                <Square className="fill-current size-3.5" />
+              </Button>
+            );
+          }
+          // With a draft, submit. While generating the caller queues it, so the
+          // button reads as Queue; otherwise it's a normal Send.
+          const queueing = !!generating && hasContent;
+          return (
             <Button
               onClick={() => void submit()}
-          disabled={disabled || busy || (!value.trim() && attachments.length === 0)}
+              disabled={disabled || busy || !hasContent}
               size="icon-lg"
-          aria-label="Send"
+              variant={queueing ? 'secondary' : 'default'}
+              aria-label={queueing ? 'Queue message' : 'Send'}
+              title={queueing ? 'Queue message' : 'Send'}
             >
-          <Send />
+              {queueing ? <ListPlus /> : <Send />}
             </Button>
+          );
+        })()}
       </div>
       </div>
       <AttachmentPreviewModal

apps/web/src/components/ChatTabBar.tsx

@@ -16,11 +16,15 @@ import {
   DropdownMenuTrigger,
 } from '@/components/ui/dropdown-menu';
 import { useLongPress } from '@/hooks/useLongPress';
+import { sessionEvents } from '@/hooks/sessionEvents';
 import { cn } from '@/lib/utils';
 
 interface Props {
   pane: WorkspacePane;
   tabs: Chat[];
+  // v2.6.x (Batch 3a): stable session-scoped tab number per chat id. Keyed by
+  // chat.id, NEVER by tab position.
+  tabNumbers: Record<string, number>;
   onSwitchTab: (tabIdx: number) => void;
   onRemoveTab: (chatId: string) => void;
   onCloseOthers: (chatId: string) => void;
@@ -37,6 +41,7 @@ interface Props {
 export function ChatTabBar({
   pane,
   tabs,
+  tabNumbers,
   onSwitchTab,
   onRemoveTab,
   onCloseOthers,
@@ -83,6 +88,9 @@ export function ChatTabBar({
         const isLast = tabIdx === tabs.length - 1;
         const onlyTab = tabs.length === 1;
         const label = chat.name ?? 'New chat';
+        // v2.6.x: stable tab number keyed by chat.id (NOT tab position).
+        // Omit gracefully when not yet assigned.
+        const tabNumber = tabNumbers[chat.id];
         return (
           <ContextMenu key={chat.id}>
             <ContextMenuTrigger asChild>
@@ -117,8 +125,11 @@ export function ChatTabBar({
                     className="bg-transparent border-b border-border text-xs outline-none w-28"
                   />
                 ) : (
-                  <span className="truncate max-w-[140px]" title={label}>
+                  <span
-                    {label}
+                    className="truncate max-w-[140px]"
+                    title={tabNumber !== undefined ? `${tabNumber} · ${label}` : label}
+                  >
+                    {tabNumber !== undefined ? `${tabNumber} · ${label}` : label}
                   </span>
                 )}
                 <button
@@ -138,6 +149,13 @@ export function ChatTabBar({
               <ContextMenuItem onSelect={onNewTab}>
                 New chat
               </ContextMenuItem>
+              <ContextMenuItem
+                onSelect={() =>
+                  sessionEvents.emit({ type: 'open_chat_in_new_pane', chat_id: chat.id })
+                }
+              >
+                Open in new pane
+              </ContextMenuItem>
               <ContextMenuSeparator />
               <ContextMenuItem onSelect={() => startRename(chat.id, chat.name)}>
                 Rename
@@ -174,15 +192,31 @@ export function ChatTabBar({
       )}
 
       <div className="flex items-center ml-auto gap-0.5 px-1 shrink-0">
+        <DropdownMenu>
+          <DropdownMenuTrigger asChild>
             <button
               type="button"
-          onClick={onNewTab}
               className="inline-flex items-center justify-center p-1 rounded text-muted-foreground hover:bg-muted hover:text-foreground max-md:min-h-[44px] max-md:min-w-[44px]"
-          aria-label="New tab"
+              aria-label="New chat, terminal, or coder"
-          title="New tab"
+              title="New chat / terminal / coder"
             >
               <Plus size={12} />
             </button>
+          </DropdownMenuTrigger>
+          <DropdownMenuContent align="end" className="w-fit">
+            {/* New BooChat opens a tab in THIS pane; terminal/coder can't be
+                tabs, so they split into a new pane (matches the Split menu). */}
+            <DropdownMenuItem onSelect={onNewTab}>
+              <MessageSquare size={14} /> New BooChat
+            </DropdownMenuItem>
+            <DropdownMenuItem onSelect={() => onSplitPane('terminal')}>
+              <Terminal size={14} /> New BooTerm
+            </DropdownMenuItem>
+            <DropdownMenuItem onSelect={() => onSplitPane('coder')}>
+              <Code size={14} /> New BooCode
+            </DropdownMenuItem>
+          </DropdownMenuContent>
+        </DropdownMenu>
         <DropdownMenu>
           <DropdownMenuTrigger asChild>
             <button

apps/web/src/components/MessageBubble.tsx

@@ -1,9 +1,9 @@
 import { useEffect, useState } from 'react';
 import type { ReactNode } from 'react';
-import { ChevronDown, ChevronRight, Copy, RefreshCw, Check, Share2, RotateCw, GitFork, Trash2, PanelRightOpen, Brain } from 'lucide-react';
+import { ChevronDown, ChevronRight, Copy, RefreshCw, Check, Share2, RotateCw, GitFork, Trash2, Brain } from 'lucide-react';
 import { toast } from 'sonner';
 import type { Chat, ErrorReason, Message } from '@/api/types';
-import { api, ApiError } from '@/api/client';
+import { api } from '@/api/client';
 import { sessionEvents } from '@/hooks/sessionEvents';
 import { sendToTerminal, terminalsRegistry, type TerminalRegistration } from '@/lib/events';
 import { CapHitSentinel } from './CapHitSentinel';
@@ -105,18 +105,6 @@ const ERROR_REASON_LABELS: Record<ErrorReason, string> = {
 // moved to apps/web/src/components/MarkdownRenderer.tsx so the new artifact
 // panes can render assistant content with the same Shiki + remark-gfm setup.
 
-// Pane-header title derivation for a markdown artifact. Order matches the
-// server slug logic in services/artifacts.ts: first `# ` heading → first 6
-// words of the body → 'Markdown artifact'. Truncated to keep the pane header
-// readable.
-function deriveMarkdownTitle(content: string): string {
-  const headingMatch = content.match(/^\s*#\s+(.+?)\s*$/m);
-  if (headingMatch && headingMatch[1]) return headingMatch[1].slice(0, 80);
-  const words = content.trim().split(/\s+/).slice(0, 6).join(' ');
-  if (words) return words.slice(0, 80);
-  return 'Markdown artifact';
-}
-
 export interface MessageActions {
   onRegenerate?: (chatId: string, messageId: string) => Promise<void>;
   onResend?: (chatId: string, content: string) => Promise<void>;
@@ -129,8 +117,8 @@ interface Props {
   sessionChats?: Chat[];
   capHitInfo?: { position: number; isLatest: boolean };
   actions?: MessageActions;
-  /** Hide actions that don't apply (fork, delete, open-in-pane). */
+  /** Hide actions that don't apply (fork, delete). */
-  hideActions?: ('fork' | 'delete' | 'openInPane')[];
+  hideActions?: ('fork' | 'delete')[];
 }
 
 function StatsLine({ message }: { message: Message }) {
@@ -226,7 +214,7 @@ function ActionRow({
       } else {
         const chat = await api.chats.fork(message.chat_id, { messageId: message.id });
         sessionEvents.emit({ type: 'refetch_messages' });
-        sessionEvents.emit({ type: 'open_chat_in_active_pane', chat_id: chat.id });
+        sessionEvents.emit({ type: 'open_chat_in_new_pane', chat_id: chat.id });
       }
     } catch (err) {
       toast.error(err instanceof Error ? err.message : 'fork failed');
@@ -258,54 +246,6 @@ function ActionRow({
   const canResend = isUser && message.status === 'complete' && !!message.content?.trim();
   const canFork = message.status === 'complete';
   const canDelete = message.status !== 'streaming';
-  const [openingPane, setOpeningPane] = useState(false);
-
-  // v1.14.x-html-artifact-panes: probe for an html_artifact part. If present,
-  // open the HTML pane variant; otherwise fall back to the markdown variant.
-  // Title derivation for markdown: first `# ` heading → first 6 words of the
-  // body → 'Markdown artifact' (mirrors the slug logic in
-  // services/artifacts.ts).
-  async function openInPane() {
-    if (openingPane || message.status === 'streaming') return;
-    setOpeningPane(true);
-    try {
-      try {
-        const payload = await api.messages.getHtmlArtifact(
-          message.chat_id,
-          message.id,
-        );
-        sessionEvents.emit({
-          type: 'open_html_artifact_pane',
-          state: {
-            chat_id: message.chat_id,
-            message_id: message.id,
-            title: payload.title,
-          },
-        });
-        return;
-      } catch (err) {
-        // 404 (no html_artifact part) is the expected fall-through path —
-        // markdown variant opens below. Any other error (network, 500) is
-        // a real failure; toast and bail rather than masquerading as markdown.
-        const status = err instanceof ApiError ? err.status : null;
-        if (status !== 404) {
-          toast.error(err instanceof Error ? err.message : 'open in pane failed');
-          return;
-        }
-      }
-      const title = deriveMarkdownTitle(message.content);
-      sessionEvents.emit({
-        type: 'open_markdown_artifact_pane',
-        state: {
-          chat_id: message.chat_id,
-          message_id: message.id,
-          title,
-        },
-      });
-    } finally {
-      setOpeningPane(false);
-    }
-  }
 
   return (
     <>
@@ -330,18 +270,6 @@ function ActionRow({
             <RefreshCw className="size-3" />
           </button>
         )}
-        {isAssistant && !hiddenSet.has('openInPane') && (
-          <button
-            type="button"
-            onClick={() => void openInPane()}
-            disabled={openingPane || message.status === 'streaming'}
-            className="inline-flex items-center justify-center size-6 rounded text-muted-foreground hover:bg-muted hover:text-foreground disabled:opacity-40 disabled:cursor-not-allowed max-md:min-h-[44px] max-md:min-w-[44px]"
-            aria-label="Open in pane"
-            title="Open in pane"
-          >
-            <PanelRightOpen className="size-3" />
-          </button>
-        )}
         {isAssistant && (
           <button
             type="button"

apps/web/src/components/ProjectSidebar.tsx

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

apps/web/src/components/SessionLandingPage.tsx

@@ -1,6 +1,9 @@
-import { useCallback, useState } from 'react';
+import { useCallback, useEffect, useState } from 'react';
+import { Archive, MessageSquare, RotateCcw } from 'lucide-react';
 import { toast } from 'sonner';
 import { ChatInput } from '@/components/ChatInput';
+import { api } from '@/api/client';
+import type { Chat } from '@/api/types';
 
 interface Props {
   projectId: string;
@@ -13,6 +16,30 @@ interface Props {
   // the skill — same transition the text send uses. See useSessionChats.
   onSkillInvoke: (skillName: string, userMessage: string | null) => void;
   createChat: () => Promise<{ id: string }>;
+  // Session history: the session's open chats (live), and callbacks to open one
+  // in THIS pane / restore an archived one. Archived chats are fetched here
+  // (the default open-only list excludes them).
+  chats: Chat[];
+  onOpenChat: (chatId: string) => void;
+  onUnarchiveChat: (chatId: string) => Promise<void>;
+}
+
+function formatRelative(iso: string): string {
+  const then = new Date(iso).getTime();
+  if (Number.isNaN(then)) return '';
+  const s = Math.max(0, Math.round((Date.now() - then) / 1000));
+  if (s < 60) return 'just now';
+  const m = Math.round(s / 60);
+  if (m < 60) return `${m}m ago`;
+  const h = Math.round(m / 60);
+  if (h < 24) return `${h}h ago`;
+  const d = Math.round(h / 24);
+  if (d < 7) return `${d}d ago`;
+  return new Date(iso).toLocaleDateString();
+}
+
+function byRecent(a: Chat, b: Chat): number {
+  return (b.updated_at ?? '').localeCompare(a.updated_at ?? '');
 }
 
 export function SessionLandingPage({
@@ -23,8 +50,24 @@ export function SessionLandingPage({
   onSend,
   onSkillInvoke,
   createChat,
+  chats,
+  onOpenChat,
+  onUnarchiveChat,
 }: Props) {
   const [chatId, setChatId] = useState<string | null>(null);
+  const [archived, setArchived] = useState<Chat[]>([]);
+
+  // Archived chats aren't in the default (open-only) list, so fetch them. One
+  // shot on session change — the history view is transient (pick a chat and
+  // it's gone), so slight staleness is fine; reopening the pane refetches.
+  useEffect(() => {
+    let cancelled = false;
+    api.chats
+      .listForSession(sessionId, { status: 'archived' })
+      .then((list) => { if (!cancelled) setArchived(list); })
+      .catch(() => {});
+    return () => { cancelled = true; };
+  }, [sessionId]);
 
   const ensureChat = useCallback(async (): Promise<string> => {
     if (chatId) return chatId;
@@ -57,12 +100,87 @@ export function SessionLandingPage({
     onSkillInvoke(skillName, userMessage.length > 0 ? userMessage : null);
   }, [onSkillInvoke]);
 
+  const restoreAndOpen = useCallback(async (id: string) => {
+    try {
+      await onUnarchiveChat(id);
+      onOpenChat(id);
+    } catch {
+      // onUnarchiveChat surfaces its own toast.
+    }
+  }, [onUnarchiveChat, onOpenChat]);
+
+  const openChats = [...chats.filter((c) => c.status === 'open')].sort(byRecent);
+  const openIds = new Set(openChats.map((c) => c.id));
+  const archivedChats = archived.filter((c) => !openIds.has(c.id)).sort(byRecent);
+  const isEmpty = openChats.length === 0 && archivedChats.length === 0;
+
   return (
     <div className="flex flex-col h-full min-h-0">
-      <div className="flex-1 flex items-center justify-center px-6">
+      <div className="flex-1 min-h-0 overflow-y-auto">
-        <p className="text-sm text-muted-foreground">
+        <div className="max-w-[760px] mx-auto w-full px-4 py-4">
-          Send a message to start.
+          {isEmpty ? (
+            <p className="text-sm text-muted-foreground text-center py-8">
+              No conversations yet. Send a message to start.
             </p>
+          ) : (
+            <>
+              {openChats.length > 0 && (
+                <>
+                  <h3 className="text-xs font-medium uppercase tracking-wide text-muted-foreground px-1 mb-1.5">
+                    Conversations
+                  </h3>
+                  <div className="space-y-0.5 mb-4">
+                    {openChats.map((c) => (
+                      <button
+                        key={c.id}
+                        type="button"
+                        onClick={() => onOpenChat(c.id)}
+                        className="w-full flex items-center gap-2 text-left px-2 py-1.5 rounded hover:bg-muted text-sm max-md:min-h-[44px]"
+                      >
+                        <MessageSquare size={14} className="shrink-0 text-muted-foreground" />
+                        <span className="truncate shrink-0 max-w-[45%]">{c.name ?? 'New chat'}</span>
+                        {c.last_message_preview && (
+                          <span className="truncate flex-1 text-xs text-muted-foreground hidden sm:block">
+                            {c.last_message_preview}
+                          </span>
+                        )}
+                        <span className="shrink-0 ml-auto text-xs text-muted-foreground">
+                          {formatRelative(c.updated_at)}
+                        </span>
+                      </button>
+                    ))}
+                  </div>
+                </>
+              )}
+              {archivedChats.length > 0 && (
+                <>
+                  <h3 className="text-xs font-medium uppercase tracking-wide text-muted-foreground px-1 mb-1.5">
+                    Archived
+                  </h3>
+                  <div className="space-y-0.5">
+                    {archivedChats.map((c) => (
+                      <button
+                        key={c.id}
+                        type="button"
+                        onClick={() => void restoreAndOpen(c.id)}
+                        title="Restore and open"
+                        className="group/arch w-full flex items-center gap-2 text-left px-2 py-1.5 rounded hover:bg-muted text-sm text-muted-foreground max-md:min-h-[44px]"
+                      >
+                        <Archive size={14} className="shrink-0" />
+                        <span className="truncate flex-1">{c.name ?? 'New chat'}</span>
+                        <span className="shrink-0 text-xs">{formatRelative(c.updated_at)}</span>
+                        <RotateCcw
+                          size={13}
+                          className="shrink-0 opacity-0 group-hover/arch:opacity-100"
+                        />
+                      </button>
+                    ))}
+                  </div>
+                </>
+              )}
+            </>
+          )}
+        </div>
       </div>
       <ChatInput
         disabled={false}

apps/web/src/components/Workspace.tsx

@@ -54,6 +54,7 @@ export function Workspace({
 }: Props) {
   const {
     panes,
+    tabNumbers,
     activePaneIdx,
     setActivePaneIdx,
     openChatInPane,
@@ -204,6 +205,7 @@ export function Workspace({
                 <ChatTabBar
                   pane={pane}
                   tabs={chatsForPane(pane)}
+                  tabNumbers={tabNumbers}
                   onSwitchTab={(tabIdx) => switchTab(idx, tabIdx)}
                   onRemoveTab={(chatId) => removeTab(idx, chatId)}
                   onCloseOthers={(chatId) => closeOtherTabs(idx, chatId)}
@@ -390,6 +392,9 @@ export function Workspace({
                   createChat={() => api.chats.create(sessionId)}
                   onSend={(content) => void handleLandingSend(idx, content)}
                   onSkillInvoke={(skillName, userMessage) => void handleLandingSkill(idx, skillName, userMessage)}
+                  chats={chats}
+                  onOpenChat={(chatId) => openChatInPane(idx, chatId)}
+                  onUnarchiveChat={unarchiveChat}
                 />
               )}
             </div>

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

@@ -1,5 +1,5 @@
 import { useCallback, useEffect, useRef, useState } from 'react';
-import { Pencil, Send, Square, X } from 'lucide-react';
+import { Pencil, Send, X } from 'lucide-react';
 import { toast } from 'sonner';
 import { api } from '@/api/client';
 import { useSessionStream } from '@/hooks/useSessionStream';
@@ -248,22 +248,6 @@ export function ChatPane({ sessionId, chatId, projectId, agentId, onAgentChange,
         </div>
       )}
 
-      {/* Stop button when streaming */}
-      {streaming && (
-        <div className="border-t py-1">
-          <div className="max-w-[1000px] mx-auto w-full flex justify-center">
-          <button
-            type="button"
-            onClick={() => void handleStop()}
-            className="flex items-center gap-1.5 text-xs px-3 py-1 rounded-full border hover:bg-muted text-muted-foreground hover:text-foreground max-md:min-h-[44px] max-md:px-5"
-          >
-            <Square size={10} className="fill-current" />
-            Stop generating
-          </button>
-          </div>
-        </div>
-      )}
-
       {stale && streamingId && (
         <StaleStreamBanner
           onRetry={() => void handleRetryStale()}
@@ -280,6 +264,8 @@ export function ChatPane({ sessionId, chatId, projectId, agentId, onAgentChange,
         webSearchEnabled={webSearchEnabled}
         onSend={handleSend}
         onForceSend={streaming ? handleForceSend : undefined}
+        generating={streaming}
+        onStop={handleStop}
         onSlashCommand={handleSlashCommand}
         chatId={chatId}
         chatLabel={sessionChats?.find((c) => c.id === chatId)?.name ?? 'Chat'}

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

@@ -149,7 +149,7 @@ interface Props {
   actions?: MessageActions;
 }
 
-const CODER_HIDDEN_ACTIONS: ('fork' | 'delete' | 'openInPane')[] = ['fork', 'openInPane'];
+const CODER_HIDDEN_ACTIONS: ('fork' | 'delete')[] = ['fork'];
 
 export function CoderMessageList({ messages, chatId, footer, actions }: Props) {
   const endRef = useRef<HTMLDivElement>(null);

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

@@ -581,6 +581,10 @@ export function CoderPane({
   const [queue, setQueue] = useState<string[]>([]);
   const queueProcessing = useRef(false);
   const inputRef = useRef<HTMLTextAreaElement>(null);
+  // The agent is "generating" during the dispatch POST (sending) AND while its
+  // task runs (activeTaskId). sending alone is too brief — it clears the moment
+  // dispatch returns — so queueing/stop must key on this combined signal.
+  const generating = sending || activeTaskId !== null;
 
   // Refresh pending changes when a message_complete arrives
   useEffect(() => {
@@ -760,24 +764,35 @@ export function CoderPane({
     }
   }, [sessionId, paneId, chatId, agentConfig, setMessages]);
 
-  // Drain queue when not busy
+  // Drain queue once the agent is idle (not just past the dispatch POST).
   useEffect(() => {
-    if (sending || queue.length === 0 || queueProcessing.current) return;
+    if (generating || queue.length === 0 || queueProcessing.current) return;
     queueProcessing.current = true;
     const next = queue[0]!;
     setQueue((prev) => prev.slice(1));
     sendOneMessage(next).finally(() => { queueProcessing.current = false; });
-  }, [sending, queue, sendOneMessage]);
+  }, [generating, queue, sendOneMessage]);
 
   const handleChatInputSend = useCallback(async (content: string) => {
     const text = content.trim();
     if (!text || !chatId) return;
-    if (sending) {
+    if (generating) {
       setQueue((prev) => [...prev, text]);
       return;
     }
     await sendOneMessage(text);
-  }, [sending, chatId, sendOneMessage]);
+  }, [generating, chatId, sendOneMessage]);
+
+  const handleStop = useCallback(async () => {
+    const taskId = activeTaskId;
+    if (!taskId) return;
+    try {
+      await api.coder.cancelTask(taskId);
+      setActiveTaskId(null); // optimistic; WS/poll terminal-state also clears it
+    } catch (err) {
+      toast.error(err instanceof Error ? err.message : 'stop failed');
+    }
+  }, [activeTaskId]);
 
   const handleChatInputSlash = useCallback(async (skillName: string, userMessage: string) => {
     if (!chatId) return;
@@ -867,9 +882,11 @@ export function CoderPane({
       {/* Composer + input */}
       <div className="shrink-0 border-t border-border">
         <ChatInput
-          disabled={sending || !chatId || chatPending}
+          disabled={!chatId || chatPending}
           projectId={projectPath ?? ''}
           onSend={handleChatInputSend}
+          generating={generating}
+          onStop={handleStop}
           onSlashCommand={handleChatInputSlash}
           slashGroups={slashGroups}
           chatId={chatId ?? undefined}

apps/web/src/hooks/sessionEvents.ts

@@ -51,7 +51,11 @@ export interface SessionUpdatedEvent {
 export interface SessionWorkspaceUpdatedEvent {
   type: 'session_workspace_updated';
   session_id: string;
-  workspace_panes: import('@/api/types').WorkspacePane[];
+  // Legacy bare array OR the new envelope — useWorkspacePanes normalizes both
+  // via toWorkspaceState.
+  workspace_panes:
+    | import('@/api/types').WorkspacePane[]
+    | import('@/api/types').WorkspaceState;
 }
 
 export interface SessionLoadedEvent {
@@ -75,6 +79,14 @@ export interface OpenChatInActivePaneEvent {
   chat_id: string;
 }
 
+// Open a whole chat in a fresh split pane (vs the active pane). Emitted by the
+// ChatTabBar tab context menu ("Open in new pane") and by MessageBubble.fork()
+// so a fork lands beside the original. useWorkspacePanes subscribes.
+export interface OpenChatInNewPaneEvent {
+  type: 'open_chat_in_new_pane';
+  chat_id: string;
+}
+
 // v1.14.x-html-artifact-panes: ActionRow's "Open in pane" button emits one of
 // these; useWorkspacePanes subscribes and inserts the corresponding artifact
 // pane (or focuses an existing one keyed by message_id).
@@ -178,6 +190,7 @@ export type SessionEvent =
   | OpenFileInBrowserEvent
   | AttachChatFileEvent
   | OpenChatInActivePaneEvent
+  | OpenChatInNewPaneEvent
   | OpenMarkdownArtifactPaneEvent
   | OpenHtmlArtifactPaneEvent
   | OpenSettingsPaneEvent

apps/web/src/hooks/useSidebar.ts

@@ -152,6 +152,7 @@ function applyEvent(prev: SidebarResponse, event: import('./sessionEvents').Sess
     case 'attach_chat_file':
       return prev;
     case 'open_chat_in_active_pane':
+    case 'open_chat_in_new_pane':
       // Consumed by Workspace; sidebar has no business with pane state.
       return prev;
     case 'open_markdown_artifact_pane':

apps/web/src/hooks/useWorkspacePanes.ts

@@ -3,9 +3,11 @@ import type { DragEvent } from 'react';
 import { toast } from 'sonner';
 import { api } from '@/api/client';
 import type {
+  ClosedPaneEntry,
   HtmlArtifactState,
   MarkdownArtifactState,
   WorkspacePane,
+  WorkspaceState,
 } from '@/api/types';
 import { setActivePaneInfo, clearActivePane } from '@/hooks/useActivePane';
 import { sessionEvents } from '@/hooks/sessionEvents';
@@ -32,19 +34,35 @@ function chatPane(chatId: string): WorkspacePane {
   return { id: generateId(), kind: 'chat', chatId, chatIds: [chatId], activeChatIdx: 0 };
 }
 
-interface ClosedPaneEntry {
+// v2.6.x: reopen stack cap. The stack now lives in React state (persisted in
-  kind: WorkspacePane['kind'];
+// the WorkspaceState envelope), not a module-level array. `appendClosed` is the
-  chatIds: string[];
+// pure state-updater helper.
-  activeChatIdx: number;
-}
 const MAX_CLOSED = 10;
-const closedPaneStack: ClosedPaneEntry[] = [];
 
-function pushClosed(pane: WorkspacePane): void {
+// Pure helper: append a closed-pane entry derived from `pane` to `stack`,
-  if (pane.kind === 'empty' || pane.kind === 'settings') return;
+// capped at MAX_CLOSED (most-recent last). Returns the SAME reference when the
-  if (pane.chatIds.length === 0) return;
+// pane is not eligible (empty/settings/no chats) so callers can skip setState.
-  closedPaneStack.push({ kind: pane.kind, chatIds: [...pane.chatIds], activeChatIdx: pane.activeChatIdx });
+function appendClosed(stack: ClosedPaneEntry[], pane: WorkspacePane): ClosedPaneEntry[] {
-  if (closedPaneStack.length > MAX_CLOSED) closedPaneStack.shift();
+  if (pane.kind === 'empty' || pane.kind === 'settings') return stack;
+  if (pane.chatIds.length === 0) return stack;
+  const entry = { kind: pane.kind, chatIds: [...pane.chatIds], activeChatIdx: pane.activeChatIdx };
+  // Dedupe a value-identical top entry. This is called via setClosedPaneStack
+  // inside the setPanes updater in removePane; React StrictMode double-invokes
+  // that updater in dev, which would otherwise push two identical entries.
+  // Real closes never collide (one chat lives in at most one pane).
+  const top = stack[stack.length - 1];
+  if (
+    top &&
+    top.kind === entry.kind &&
+    top.activeChatIdx === entry.activeChatIdx &&
+    top.chatIds.length === entry.chatIds.length &&
+    top.chatIds.every((id, i) => id === entry.chatIds[i])
+  ) {
+    return stack;
+  }
+  const next = [...stack, entry];
+  if (next.length > MAX_CLOSED) next.splice(0, next.length - MAX_CLOSED);
+  return next;
 }
 
 function chatNameForPaneKind(kind: 'coder' | 'terminal'): string {
@@ -110,6 +128,26 @@ function persistablePanes(panes: WorkspacePane[]): WorkspacePane[] {
   return normalizePanes(panes).filter((p) => p.kind !== 'settings');
 }
 
+// v2.6.x: LOCKED migration — a value read from session.workspace_panes (or the
+// session_workspace_updated frame) may be EITHER the legacy bare
+// WorkspacePane[] OR the new WorkspaceState envelope. Normalize to the
+// envelope. Must match the server's normalization byte-for-byte.
+function toWorkspaceState(raw: unknown): WorkspaceState {
+  if (Array.isArray(raw)) {
+    return { panes: raw as WorkspacePane[], tabNumbers: {}, nextTabNumber: 1, closedPaneStack: [] };
+  }
+  if (raw && typeof raw === 'object' && Array.isArray((raw as WorkspaceState).panes)) {
+    const env = raw as WorkspaceState;
+    return {
+      panes: env.panes,
+      tabNumbers: env.tabNumbers ?? {},
+      nextTabNumber: env.nextTabNumber ?? 1,
+      closedPaneStack: env.closedPaneStack ?? [],
+    };
+  }
+  return { panes: [], tabNumbers: {}, nextTabNumber: 1, closedPaneStack: [] };
+}
+
 // v1.9: per recon decision (c), settings panes don't count toward MAX_PANES.
 // Helper used at every pane-insertion site so the rule lives in one place.
 function nonSettingsCount(panes: WorkspacePane[]): number {
@@ -132,6 +170,9 @@ function readLegacyPanes(sessionId: string): WorkspacePane[] | null {
 
 export interface UseWorkspacePanesResult {
   panes: WorkspacePane[];
+  // v2.6.x: stable session-scoped tab number per chat id (Batch 3a). Keyed by
+  // chat.id, NEVER by tab position.
+  tabNumbers: Record<string, number>;
   activePaneIdx: number;
   setActivePaneIdx: React.Dispatch<React.SetStateAction<number>>;
   activePaneIdxRef: React.MutableRefObject<number>;
@@ -171,6 +212,12 @@ export interface UseWorkspacePanesResult {
 export function useWorkspacePanes(sessionId: string): UseWorkspacePanesResult {
   const [panes, setPanes] = useState<WorkspacePane[]>(() => [emptyPane()]);
   const [activePaneIdx, setActivePaneIdx] = useState(0);
+  // v2.6.x envelope state. Persisted alongside `panes` in the WorkspaceState
+  // envelope. `tabNumbers` is the stable session-scoped tab number per chat id;
+  // `nextTabNumber` only ever increments; `closedPaneStack` is the reopen LIFO.
+  const [tabNumbers, setTabNumbers] = useState<Record<string, number>>({});
+  const [nextTabNumber, setNextTabNumber] = useState(1);
+  const [closedPaneStack, setClosedPaneStack] = useState<ClosedPaneEntry[]>([]);
   const draggingIdxRef = useRef<number | null>(null);
   const [dragOverIdx, setDragOverIdx] = useState<number | null>(null);
   // v1.12.1: skip PATCH while hydrating from the server. Without this, the
@@ -237,27 +284,42 @@ export function useWorkspacePanes(sessionId: string): UseWorkspacePanesResult {
       try {
         const session = await api.sessions.get(sessionId);
         if (cancelled) return;
-        let initial: WorkspacePane[] = Array.isArray(session.workspace_panes)
+        let env = toWorkspaceState(session.workspace_panes);
-          ? normalizePanes(session.workspace_panes)
+        let initial: WorkspacePane[] = normalizePanes(env.panes);
-          : [];
         // One-time migration: if server is empty but legacy localStorage has
-        // a layout, seed the server and delete the local key.
+        // a layout, seed the server (as an envelope) and delete the local key.
         if (initial.length === 0) {
           const legacy = readLegacyPanes(sessionId);
           if (legacy && legacy.length > 0) {
             try {
-              const updated = await api.sessions.updateWorkspacePanes(sessionId, legacy);
+              const seedState: WorkspaceState = {
+                panes: persistablePanes(legacy),
+                tabNumbers: {},
+                nextTabNumber: 1,
+                closedPaneStack: [],
+              };
+              const updated = await api.sessions.updateWorkspacePanes(sessionId, seedState);
               if (cancelled) return;
-              initial = updated.workspace_panes;
+              env = toWorkspaceState(updated.workspace_panes);
+              initial = normalizePanes(env.panes);
               localStorage.removeItem(`${LEGACY_STORAGE_KEY}.${sessionId}`);
             } catch {
-              initial = legacy;
+              env = { ...env, panes: legacy };
+              initial = normalizePanes(legacy);
             }
           }
         }
         const next = initial.length > 0 ? initial : [emptyPane()];
-        lastRemoteJsonRef.current = JSON.stringify(persistablePanes(next));
+        lastRemoteJsonRef.current = JSON.stringify({
+          panes: persistablePanes(next),
+          tabNumbers: env.tabNumbers,
+          nextTabNumber: env.nextTabNumber,
+          closedPaneStack: env.closedPaneStack,
+        });
         setPanes(next);
+        setTabNumbers(env.tabNumbers);
+        setNextTabNumber(env.nextTabNumber);
+        setClosedPaneStack(env.closedPaneStack);
         setActivePaneIdx(0);
         seedEmptyScopedPanes(next);
       } finally {
@@ -273,15 +335,25 @@ export function useWorkspacePanes(sessionId: string): UseWorkspacePanesResult {
     return sessionEvents.subscribe((ev) => {
       if (ev.type !== 'session_workspace_updated') return;
       if (ev.session_id !== sessionId) return;
-      const incoming = normalizePanes(
+      const env = toWorkspaceState(ev.workspace_panes);
-        Array.isArray(ev.workspace_panes) ? ev.workspace_panes : [],
+      const incoming = normalizePanes(env.panes);
-      );
+      // Echo-dedup on the FULL envelope so tabNumber / stack-only changes are
-      const json = JSON.stringify(incoming);
+      // not mistaken for our own write echo.
+      const json = JSON.stringify({
+        panes: persistablePanes(incoming),
+        tabNumbers: env.tabNumbers,
+        nextTabNumber: env.nextTabNumber,
+        closedPaneStack: env.closedPaneStack,
+      });
       if (json === lastRemoteJsonRef.current) return;
       lastRemoteJsonRef.current = json;
-      setPanes(incoming.length > 0 ? incoming : [emptyPane()]);
+      const nextPanes = incoming.length > 0 ? incoming : [emptyPane()];
+      setPanes(nextPanes);
+      setTabNumbers(env.tabNumbers);
+      setNextTabNumber(env.nextTabNumber);
+      setClosedPaneStack(env.closedPaneStack);
       setActivePaneIdx((prev) => Math.min(prev, Math.max(0, incoming.length - 1)));
-      seedEmptyScopedPanes(incoming.length > 0 ? incoming : [emptyPane()]);
+      seedEmptyScopedPanes(nextPanes);
     });
   }, [sessionId, seedEmptyScopedPanes]);
 
@@ -333,18 +405,75 @@ export function useWorkspacePanes(sessionId: string): UseWorkspacePanesResult {
   // before saving (ephemeral per v1.9).
   useEffect(() => {
     if (!hydratedRef.current) return;
-    const payload = persistablePanes(panes);
+    // v2.6.x: persist the full WorkspaceState envelope. The dedup ref compares
-    const json = JSON.stringify(payload);
+    // the whole envelope so tabNumber / reopen-stack changes also persist.
+    const envelope: WorkspaceState = {
+      panes: persistablePanes(panes),
+      tabNumbers,
+      nextTabNumber,
+      closedPaneStack,
+    };
+    const json = JSON.stringify(envelope);
     if (json === lastRemoteJsonRef.current) return;
     const timer = setTimeout(() => {
       lastRemoteJsonRef.current = json;
-      api.sessions.updateWorkspacePanes(sessionId, payload).catch(() => {
+      api.sessions.updateWorkspacePanes(sessionId, envelope).catch(() => {
         // Non-fatal: next change retries. Persistent failures surface via
         // the network layer's existing reconnect toast.
       });
     }, SAVE_DEBOUNCE_MS);
     return () => clearTimeout(timer);
-  }, [sessionId, panes]);
+  }, [sessionId, panes, tabNumbers, nextTabNumber, closedPaneStack]);
+
+  // v2.6.x (Batch 3a): maintain stable, session-scoped tab numbers. Collect the
+  // chat ids that appear in CHAT-kind panes in deterministic order (pane index,
+  // then tab index). Assign numbers to any without one (global per session,
+  // only ever increasing, never reused) and prune entries whose chat is no
+  // longer in any chat-kind pane. Guarded against render loops: only setState
+  // when something actually changed.
+  useEffect(() => {
+    const liveChatIds: string[] = [];
+    const liveSet = new Set<string>();
+    for (const pane of panes) {
+      if (pane.kind !== 'chat') continue;
+      for (const id of pane.chatIds) {
+        if (!liveSet.has(id)) {
+          liveSet.add(id);
+          liveChatIds.push(id);
+        }
+      }
+    }
+
+    // Assign: walk live ids in deterministic order, handing out numbers.
+    let counter = nextTabNumber;
+    const additions: Record<string, number> = {};
+    for (const id of liveChatIds) {
+      if (tabNumbers[id] === undefined && additions[id] === undefined) {
+        additions[id] = counter;
+        counter += 1;
+      }
+    }
+
+    // Prune: retire numbers for chats no longer in any chat-kind pane.
+    const removals: string[] = [];
+    for (const id of Object.keys(tabNumbers)) {
+      if (!liveSet.has(id)) removals.push(id);
+    }
+
+    const hasAdditions = Object.keys(additions).length > 0;
+    const hasRemovals = removals.length > 0;
+    if (!hasAdditions && !hasRemovals) return;
+
+    setTabNumbers((prev) => {
+      const next: Record<string, number> = {};
+      for (const [id, n] of Object.entries(prev)) {
+        if (!removals.includes(id)) next[id] = n;
+      }
+      Object.assign(next, additions);
+      return next;
+    });
+    if (hasAdditions) setNextTabNumber(counter);
+  }, [panes, tabNumbers, nextTabNumber]);
 
   useEffect(() => {
     const active = panes[activePaneIdx];
@@ -391,6 +520,37 @@ export function useWorkspacePanes(sessionId: string): UseWorkspacePanesResult {
     setActivePaneIdx(paneIdx);
   }, []);
 
+  // Open a whole chat in its own fresh pane (focused). Detaches the chat from
+  // any pane currently showing it so it lives in exactly one pane (preserves
+  // the one-chat-per-pane model), dropping a source pane left with no tabs. For
+  // fork the chat isn't in any pane yet, so the detach is a no-op (pure append).
+  const openChatInNewPane = useCallback((chatId: string) => {
+    setPanes((prev) => {
+      const detached = prev.flatMap((p) => {
+        if (!p.chatIds.includes(chatId)) return [p];
+        const nextIds = p.chatIds.filter((id) => id !== chatId);
+        if (nextIds.length === 0) return [];
+        const ai = Math.min(p.activeChatIdx, nextIds.length - 1);
+        return [{ ...p, kind: 'chat' as const, chatId: nextIds[ai], chatIds: nextIds, activeChatIdx: ai }];
+      });
+      if (nonSettingsCount(detached) >= MAX_PANES) {
+        toast.error(`Maximum ${MAX_PANES} panes`);
+        return prev;
+      }
+      const next = [...detached, chatPane(chatId)];
+      setActivePaneIdx(next.length - 1);
+      return next;
+    });
+  }, []);
+
+  // ChatTabBar's "Open in new pane" + MessageBubble.fork() emit this.
+  useEffect(() => {
+    return sessionEvents.subscribe((ev) => {
+      if (ev.type !== 'open_chat_in_new_pane') return;
+      openChatInNewPane(ev.chat_id);
+    });
+  }, [openChatInNewPane]);
+
   const switchTab = useCallback((paneIdx: number, tabIdx: number) => {
     setPanes((prev) => {
       const next = [...prev];
@@ -411,7 +571,7 @@ export function useWorkspacePanes(sessionId: string): UseWorkspacePanesResult {
         if (next.length > 1) {
           // Last tab closed and other panes exist — remove the whole pane
           // instead of leaving an orphaned empty panel.
-          pushClosed(pane); setHasClosedPanes(true);
+          setClosedPaneStack((stack) => appendClosed(stack, pane));
           const spliced = next.filter((_, i) => i !== paneIdx);
           setActivePaneIdx((ai) => Math.min(ai, spliced.length - 1));
           return spliced;
@@ -547,7 +707,8 @@ export function useWorkspacePanes(sessionId: string): UseWorkspacePanesResult {
     setPanes((prev) => {
       if (prev.length <= 1) {
         // Settings is the only kind that can be the last pane and still need
-        // closing (X / Esc / sidebar toggle). Fall back to empty.
+        // closing (X / Esc / sidebar toggle). Fall back to empty. One-pane
+        // edge: no relocation — there is no other pane.
         if (prev[idx]?.kind === 'settings') {
           setActivePaneIdx(0);
           return [emptyPane()];
@@ -559,35 +720,101 @@ export function useWorkspacePanes(sessionId: string): UseWorkspacePanesResult {
       // The endpoint is idempotent (404 on missing session) so a strict-mode
       // double-invoke of the updater is safe.
       const removed = prev[idx];
-      if (removed) { pushClosed(removed); setHasClosedPanes(true); }
+      // Push the original pane (with its chatIds intact) to the reopen stack.
+      if (removed) setClosedPaneStack((stack) => appendClosed(stack, removed));
       if (removed?.kind === 'terminal') {
         api.terminals.kill(sessionId, removed.id).catch(() => { /* non-fatal */ });
       }
-      const next = prev.filter((_, i) => i !== idx);
+
+      // v2.6.x (Batch 1): relocate a closing CHAT pane's tabs to the oldest
+      // remaining pane that can host chat tabs, so chats aren't lost on close.
+      // Only chat panes relocate — terminal/coder panes own a scoped chat bound
+      // to the pane, so those close exactly as before (no relocation).
+      let working = prev;
+      if (removed && removed.kind === 'chat' && removed.chatIds.length > 0) {
+        // "Oldest remaining": lowest index, excluding `idx`, that is a chat or
+        // empty pane (the only kinds that can host arbitrary chat tabs). Skip
+        // terminal/coder/settings/artifact panes.
+        let targetIdx = -1;
+        for (let i = 0; i < prev.length; i += 1) {
+          if (i === idx) continue;
+          const p = prev[i]!;
+          if (p.kind === 'chat' || p.kind === 'empty') {
+            targetIdx = i;
+            break;
+          }
+        }
+        if (targetIdx >= 0) {
+          working = prev.map((p, i) => {
+            if (i !== targetIdx) return p;
+            const mergedIds = [...p.chatIds, ...removed.chatIds];
+            // Preserve the target's existing focus — append, don't force-focus
+            // the moved tabs. Clamp only when the target had no active tab.
+            const ai = p.activeChatIdx >= 0 ? p.activeChatIdx : 0;
+            return {
+              ...p,
+              kind: 'chat' as const,
+              chatIds: mergedIds,
+              activeChatIdx: ai,
+              chatId: mergedIds[ai],
+            };
+          });
+        }
+      }
+
+      const next = working.filter((_, i) => i !== idx);
       setActivePaneIdx((ai) => Math.min(ai, next.length - 1));
       return next;
     });
   }, [sessionId]);
 
-  const [hasClosedPanes, setHasClosedPanes] = useState(closedPaneStack.length > 0);
+  const hasClosedPanes = closedPaneStack.length > 0;
 
   const reopenPane = useCallback(() => {
-    const entry = closedPaneStack.pop();
+    // Read the top entry from the current render's stack (not inside the
-    setHasClosedPanes(closedPaneStack.length > 0);
+    // updater) so a StrictMode double-invoke can't pop two entries. The pop
-    if (!entry) return;
+    // setState is idempotent: filtering by reference removes exactly this entry.
+    const e = closedPaneStack[closedPaneStack.length - 1];
+    if (!e) return;
+    setClosedPaneStack((stack) => (stack[stack.length - 1] === e ? stack.slice(0, -1) : stack));
     setPanes((prev) => {
+      // v2.6.x (Batch 4): reversible reopen. The closed tabs may have been
+      // relocated into another pane on close (Batch 1). Strip e.chatIds from
+      // every existing pane first so reopening never duplicates a tab —
+      // whether or not it was relocated (a no-op strip when it wasn't). Mirror
+      // removeTab's emptiness handling: a chat pane emptied by the strip is
+      // dropped when other panes remain, else turned empty.
+      const stripped: WorkspacePane[] = [];
+      for (const p of prev) {
+        const idxs = p.chatIds.filter((id) => !e.chatIds.includes(id));
+        if (idxs.length === p.chatIds.length) {
+          stripped.push(p);
+          continue;
+        }
+        if (idxs.length === 0) {
+          if (p.kind === 'chat') {
+            // Drop the now-empty chat pane (we still have the restored pane plus
+            // possibly others). If it would leave zero panes, turn it empty.
+            continue;
+          }
+          stripped.push({ ...p, chatId: undefined, chatIds: [], activeChatIdx: -1 });
+          continue;
+        }
+        const ai = Math.min(p.activeChatIdx, idxs.length - 1);
+        stripped.push({ ...p, chatIds: idxs, activeChatIdx: ai < 0 ? 0 : ai, chatId: idxs[ai < 0 ? 0 : ai] });
+      }
       const restored: WorkspacePane = {
         id: generateId(),
-        kind: entry.kind,
+        kind: e.kind,
-        chatId: entry.chatIds[entry.activeChatIdx] ?? entry.chatIds[0],
+        chatId: e.chatIds[e.activeChatIdx] ?? e.chatIds[0],
-        chatIds: entry.chatIds,
+        chatIds: e.chatIds,
-        activeChatIdx: Math.min(entry.activeChatIdx, entry.chatIds.length - 1),
+        activeChatIdx: Math.min(e.activeChatIdx, e.chatIds.length - 1),
       };
-      const next = [...prev, restored];
+      const next = [...stripped, restored];
       setActivePaneIdx(next.length - 1);
       return next;
     });
-  }, []);
+  }, [closedPaneStack]);
 
   // Replaces a single empty default pane with a chat pane. Used by the initial
   // chat fetch to land on the most-recent open chat if no saved pane state.
@@ -705,6 +932,7 @@ export function useWorkspacePanes(sessionId: string): UseWorkspacePanesResult {
 
   return {
     panes,
+    tabNumbers,
     activePaneIdx,
     setActivePaneIdx,
     activePaneIdxRef,

apps/web/src/lib/attachments.ts

@@ -56,19 +56,26 @@ export function inferLanguage(filename: string): string | null {
 
 export function flattenToMessage(attachments: Attachment[], text: string): string {
   if (attachments.length === 0) return text;
-  const blocks = attachments.map(a => {
+  // Pasted text is raw context, not code from a file — insert it verbatim with no
-    // Pasted text is raw context, not code from a file — insert it verbatim with
+  // ``` fence or provenance header. It trails the typed text with a leading space
-    // no ``` fence or provenance header. The chip only exists to keep the textarea
+  // so a leading slash command / prompt stays first and the paste reads as its
-    // tidy while composing; on send it should be exactly what the user pasted.
+  // continuation. File/line chips stay fenced provenance blocks, appended after.
+  const pasteBlocks: string[] = [];
+  const fencedBlocks: string[] = [];
+  for (const a of attachments) {
     if (a.kind === 'paste') {
-      return a.content;
+      pasteBlocks.push(a.content);
+      continue;
     }
     const fence = '```' + (a.language ?? '');
     const header =
       a.kind === 'lines'
         ? `// from: ${a.filename}:${a.range?.[0] ?? '?'}-${a.range?.[1] ?? '?'}`
         : `// from: ${a.filename}`;
-    return `${fence}\n${header}\n${a.content}\n\`\`\``;
+    fencedBlocks.push(`${fence}\n${header}\n${a.content}\n\`\`\``);
-  });
+  }
-  return [...blocks, text].filter(Boolean).join('\n\n');
+  // Typed text + pasted content on the same logical line (space-joined), then
+  // any fenced file blocks as separate paragraphs.
+  const lead = [text, ...pasteBlocks].filter(Boolean).join(' ');
+  return [lead, ...fencedBlocks].filter(Boolean).join('\n\n');
 }

boocode_code_review_v2.md

@@ -0,0 +1,249 @@
+# BooCode — External Code Review v2 (lift findings)
+
+Last updated: 2026-05-31
+
+A point-in-time **findings** doc, not a standing inventory. It consolidates two reconnaissance passes against the upstream forks at `/opt/forks/` and decides, per area, what BooCode should do about it. Pin it so the same upstreams aren't re-evaluated from scratch next month.
+
+> **Companion docs:** `boocode_code_review.md` is the standing external-repo inventory (every repo BooCode references, *why* each earned its row, license analysis). `boocode_roadmap.md` is the canonical shipping-state / version-ordering source. This v2 doc is the **action layer** on top of both: "given what's upstream as of 2026-05-31, here's the lift/cross-check/re-derive/n-a call." Reconcile shipping state via the roadmap when in doubt; fold durable rows back into `boocode_code_review.md`.
+
+## Sources feeding this doc
+
+1. **Paseo recon (Sam)** — two passes: a Phase 2/3 server-manager recon and a claude-transport recon. Conclusions consolidated by area below (§2a). AGPL-3.0 — **pattern-only, no code lift, ever.**
+2. **Three-fork agent sweep (this session, 2026-05-31)** — read-only general-purpose agents over `anomalyco/opencode` (MIT, code-liftable), `getpaseo/paseo` (AGPL, pattern-only), `ggml-org/llama.cpp` (consumed via llama-swap/sidecar — adopt features/flags, not C++). Detail in §2–§4.
+3. **Second fork sweep (this session, 2026-05-31)** — 8 read-only agents over the remaining 11 repos in `/opt/forks/` (conductor, superset, openchamber, happy, cline, qwen-code, amp-acp, pi-acp, claude-code, goose, unsloth). Detail in §5; high-value items folded into §1.
+
+### Caveats
+- `/opt/forks/llama.cpp` is a **shallow clone** (90 commits, ~5 days visible). llama.cpp findings are read from source as it stands today; "what changed when" attribution is limited. `git fetch --unshallow` before the next review.
+- `/opt/forks/opencode` arrived shallow (rooted 2026-05-25); the agent ran `git fetch --unshallow` and re-surveyed the real 6-week window. opencode also did a v2 Effect/event-sourced rewrite (`packages/core/`, `packages/llm/`) — most of that churn is architecturally divergent and ruled out.
+- HEADs at review time: paseo `41cb1af` (main, v0.1.87), opencode `1afa9e3` (dev, ~v1.15.13), llama.cpp `aa46bda8` (detached).
+
+## Verdict legend
+
+| Verdict | Meaning |
+|---|---|
+| **LIFT** | Take it. Flavor noted: *code-lift* (MIT), *pattern-lift* (AGPL/clean-room re-impl), *config-adopt* (new upstream flag), *drop-our-code* (upstream now does it → delete ours). |
+| **RE-DERIVE** | Idea is right, their impl is insufficient/divergent for our needs — write fresh, don't adapt theirs. |
+| **CROSS-CHECK** | We already have it; confirmed current vs upstream. No action. |
+| **TRACK** | Behavioral/external change to be aware of. No code action now. |
+| **N-A** | Not liftable into our architecture, or reduces to a separate decision. |
+
+-----
+
+## 1. Net actionables (priority roll-up)
+
+Updated after the **second fork sweep** (2026-05-31, §5). New items from that sweep are tagged ⁺.
+
+| # | Item | Source | Verdict | Maps to | Effort |
+|---|------|--------|---------|---------|--------|
+| 1 | **Retire the AGPL tool-call parser + html-to-md** — llama-server parses qwen3.x `<tool_call>`/`<function=>` server-side; both lifted files are **confirmed AGPL-3.0-only** (§5k); swap html-to-md to a permissive lib | llama.cpp + unsloth⁺ | LIFT · drop-our-code | license-debt / inference; new batch | M, staged + gated on jinja |
+| 2 | **Warm-ACP backend (goose/qwen)** — one spawn, one `session/new`, many prompts; **validated by qwen's own `qwen --acp` reference impl** (the "qwen ACP was HTTP-only" premise is stale) | Paseo recon + qwen-code⁺ | LIFT · pattern | **v2.6 Phase 2** | M |
+| 3 ⁺ | **Fuzzy patch applier for `edit_file`** — exact→whitespace→Levenshtein match ladder + unicode canon + multi-occurrence guard; BooCoder's `edit_file` is exact-`.includes`-or-throw today | cline⁺ | LIFT · code | edit/diff robustness (local-model drift) | M |
+| 4 ⁺ | **`git stash create` + private-ref checkpoint** — per-turn workspace snapshot capturing **all** state incl. external-agent edits (BooCode `rewind` only undoes its own queued edits) | cline⁺ | LIFT · code | checkpoint/restore UX | M |
+| 5 ⁺ | **opencode lifecycle hardening** — health monitor + crash auto-restart + busy-aware restart + port reclaim + stall-detecting SSE; **MIT, same warm-server architecture** (supersedes the paseo RE-DERIVE — better source) | openchamber⁺ | LIFT · pattern/code | **v2.6 Phase 3** | M |
+| 6 | **Post-interrupt stale-terminal guard** — confirmed correctness bug in `opencode-server.ts` | opencode/paseo (verified) | LIFT · pattern (bugfix) | v2.6 Phase 1/2 | S (~½ day) |
+| 7 ⁺ | **Parse qwen/claude `stream-json` NDJSON in PTY fallback** — today stdout is sliced opaque; one parser serves both (Claude-Code-compatible schema) | qwen-code⁺ | LIFT · pattern | v2.6 Phase 2 / dispatch parsing | S |
+| 8 | **ctx/token usage for opencode sessions** — `session.next.step.ended` already on the wire | opencode + paseo (converged) | LIFT · code | v2.6 Phase 1 UX | S–M (~80–150 LoC) |
+| 9 | **Claude continuity + transport** — `--resume` via hook/jsonl-watcher → `claudeSessionId`; **happy proves the `@anthropic-ai/claude-agent-sdk` path** (resolves the SDK-vs-PTY decision — lean SDK) | Paseo recon + happy⁺ | LIFT · code + decision | claude-provider batch | M |
+| 10 ⁺ | **Universal-agent notify-hook → normalized status** — inject a hook into each PTY agent's config, normalize ~30 event names → 5 states; gives goose/qwen/claude real working/blocked/done signals | superset⁺ (clean-room, ELv2) | RE-DERIVE | v2.6 Phase 2/3 status | M–H |
+| 11 | **New sampling knobs** `top_n_sigma`, `dry_*` family; **`--reasoning-budget`** | llama.cpp | LIFT · config-adopt | AGENTS.md frontmatter + validator allowlist | S |
+| 12 ⁺ | **File-provenance compaction ledger** (`## Files Read/Modified`) + **`MistakeTracker`** (heterogeneous-failure recovery) | cline⁺ | LIFT · pattern | context-mgmt / recovery | S–M |
+| 13 | Bundle/watch: stall-timeout + retry/backoff (opencode); worktree-archive cascade (paseo); LRU-bound caches; subagent permission demux; tool-pair-atomic prune cross-check (cline)⁺; diff-line→agent re-prompt (superset)⁺ | mixed | WATCH | Phase 2/3, review UX, resilience | varies |
+
+**Headline:** #1 stays the strategic win and is now **settled, not speculative** — the unsloth recon confirmed both lifted files are AGPL-3.0-only (§5k); the only gate is the jinja config check (§6). The second sweep added four genuinely-new code lifts: **#3 fuzzy patch applier** and **#4 git-stash checkpoint** (both cline, both directly fix where BooCoder's write/edit surface is weakest for local models), **#5 openchamber lifecycle hardening** (the concrete, MIT, same-architecture answer to v2.6 Phase 3 — supersedes the weaker paseo re-derive), and **#7 stream-json parsing** (cheap, shared by qwen+claude PTY). #2 Phase-2 warm-ACP is now de-risked by qwen's own reference impl. #9 resolves the claude direction (lean SDK).
+
+-----
+
+## 2. Paseo (AGPL-3.0 — pattern-only)
+
+### 2a. Consolidated recon, by area (Sam's two passes)
+
+| Area | Verdict | One-line |
+|------|---------|----------|
+| OpenCode server lifecycle | **CROSS-CHECK** | Paseo hand-rolls the spawn (not `createOpencodeServer`), waits for "listening on" on stdout, port-0 allocation, concurrent callers wait on one `startPromise`, no `OPENCODE_SERVER_PASSWORD`. Same shape BooCode shipped in v2.6.1 — nothing to lift. |
+| OpenCode crash recovery + reconnect | **RE-DERIVE → superseded** | Lazy restart-on-demand (exit handler nulls the server, next `getCurrentServer()` respawns), no active supervision; `resumeSession` does **not** verify the session exists on disk before resuming. Insufficient for Phase 3. **Update (2nd sweep):** `openchamber` (§5c) has a *better, MIT, same-architecture* version — health-monitor state machine + crash auto-restart + busy-aware restart. Lift from openchamber, not paseo. |
+| Warm-ACP supervision (goose/qwen) | **LIFT · pattern** | `SpawnedACPProcess`: one spawn, one `session/new`, many prompts; child lives for the session not the turn; per-turn abort = `connection.cancel({sessionId})` **without killing the child**; child-exit fires `turn_failed` (no restart). Clean signal split; integrates against BooCode's existing `acp-dispatch.ts`. **This is the Phase 2 lift — and qwen-code (§5f) ships its own `qwen --acp` reference impl that validates the whole approach.** |
+| OpenCode reasoning dedup | **CROSS-CHECK** | `streamedPartKeys` keyed `reasoning:${partID}`; delta adds the key, final part skips if present, cleared per turn. Identical to v2.6.1. |
+| Claude transport | **N-A** | Paseo uses `@anthropic-ai/claude-agent-sdk` in stream-json mode, not PTY. Getting Paseo's transport means adopting the SDK — net-new integration, not a lift. |
+| Claude continuity | **LIFT · code** | `claude --resume <sessionId>` across turns: capture the session id from claude's output, store it, pass `--resume` next turn; claude re-reads its transcript and continues. Small change to BooCode's PTY dispatch (run with `--output-format stream-json`, parse the id, persist, resume). **The actionable claude finding.** |
+| Claude streaming/parsing | **N-A** | Structured events (tool calls, reasoning, partials) come from the SDK; PTY degrades to scraping. Adopting structured claude streaming = adopting the SDK — separate decision. |
+| Claude session persistence | **CROSS-CHECK** | Same `describePersistence`/`resumeSession` shape BooCode already has for opencode; claude slots in. Neither Paseo nor BooCode verifies the transcript exists on disk before resume (**shared open question** — see §5). |
+
+**Recon's net:** LIFT = warm-ACP supervision (Phase 2) + claude `--resume` continuity (standalone batch). RE-DERIVE = OpenCode crash recovery (Phase 3). Everything else cross-check or n/a. The two n/a claude items both reduce to **one deferred decision: adopt `@anthropic-ai/claude-agent-sdk` or stay PTY.**
+
+### 2b. Additional findings (this session's Paseo agent sweep)
+
+These came from the broader agent pass, not the targeted Phase 2/3 recon. Where they touch the same code as §2a, the §2a recon is authoritative.
+
+| Finding | Verdict | Notes |
+|---------|---------|-------|
+| **Post-interrupt stale-terminal suppression** (paseo `1d38aac`) | **LIFT · pattern (bugfix)** | See §3 #3 — verified to be a live bug in BooCode. Highest-confidence paseo item. |
+| **Provider-agnostic `AgentUsage`** normalized usage/cost frame | **LIFT · pattern** | Converges with opencode's `session.next.step.ended` (§3 #4). Paseo's `{inputTokens, cachedInputTokens, outputTokens, totalCostUsd, contextWindowMax/Used}` is the target *shape* for normalizing across providers; do the opencode slice first. |
+| **Worktree-archive → cascade-archive agents + schedule cleanup** (paseo `b6103a5`) | **WATCH → adopt in Phase 3** | Soft-delete (keep `archivedAt`), single archive event fans out to children + downstream rows, `Promise.allSettled` so one failed delete doesn't abandon the rest. Right shape for the v2.6 Phase 3 worktree reaper. |
+| **Server retire/refcount + LRU-bound caches** (paseo `server-manager.ts`, leak-fix `f20393d`) | **WATCH** (low confidence) | The agent read a retire-set/refcount mechanism; the §2a server-manager recon concluded "nothing to lift." Treat the *lifecycle* as cross-check (§2a wins). The one durable takeaway: **bound the per-session/per-worktree Maps in the warm opencode server** (long-lived daemon → unbounded caches leak). Confirm against §2a before acting. |
+| **Subagent permission forwarding** (paseo `44863ec`) | **WATCH (gated)** | opencode `task` tool spawns child sessions; forward `permission.asked` from tracked children by `parentID` demux. **Blocked:** BooCode's opencode-SSE path has zero permission handling today (runs auto-approve). Reachable only after BooCoder builds opencode-SSE permission cards at all. Ties to v2.4. |
+
+-----
+
+## 3. OpenCode (MIT — code-liftable)
+
+| # | Finding | Evidence | Verdict | Notes |
+|---|---------|----------|---------|-------|
+| 1 | **Consume the fuller `session.next.*` event set** in `opencode-server.ts` | `packages/core/src/session/event.ts:105-365`; BooCode handles only ~5 arms (`opencode-server.ts:215-311`) | **LIFT · code** | Events already in the **installed** `@opencode-ai/sdk` — **no dep bump.** High-value arms: **`step.ended`** (`{tokens{input,output,reasoning,cache},cost}` → #4 below); **`compaction.{started,delta,ended}`** (warm server auto-compacts mid-conversation; today shows as a silent context gap); `tool.progress`, `tool.input.{started,delta}`, `retried`, `step.failed`. |
+| 4 | **ctx/token usage for opencode** (the high-value slice of #1) | `event.ts:117-135` | **LIFT · code** | Closes the roadmap-named gap: *"opencode/goose/qwen/claude dispatch with no ctx/token usage; only native boocode tracks ctx."* Mirror BooChat's existing `'usage'` WS frame on the coder side; accumulate per `(chat, agent)`. Converges with paseo `AgentUsage` (§2b). |
+| 2 | **Stalled-stream chunk-timeout** (`wrapSSE` + header timeout) | `provider/provider.ts:40-96` (`f965db9`, `c7e1fc5`) | **WATCH · pattern** | BooChat's `stream-phase.ts` has **no server-side stall timeout** — a hung llama-swap stream relies entirely on the frontend 60s `discard_stale` watchdog. ~40-60 LoC to wrap the `fullStream` loop with a per-chunk timeout firing the existing abort path. Low incidence on a single local instance; do it if stuck rows recur. |
+| 3 | **Retry-with-backoff + retryability classifier** (`session/retry.ts`) | `session/retry.ts`, `message-v2.ts:1155` (`14e0b9b`) | **WATCH · pattern** | BooChat has **zero** retry logic. `delay()` parses `retry-after[-ms]` headers w/ exp-backoff fallback; `retryable()` classifies transient-5xx / rate-limit / context-overflow-exclusion. Strip the Go-billing arms. Pairs naturally with #2. llama-swap rarely emits `retry-after`, so value is mostly transient-5xx/stall retry. |
+| — | **MCP auth file-lock** (`mcp/auth.ts`, `fa73ec4`) | — | **N-A (deferred)** | Serializes concurrent OAuth token refreshes. Can't trigger — BooCode's config schema *rejects* OAuth MCP servers until secret storage lands (roadmap). Note for when OAuth MCP is un-deferred. |
+
+**Confirmed current (cross-check, no refresh needed):** compaction algorithm (incl. `tail_start_id`/`splitTurn` post-fix — verified identical), two-tier prune, truncate, run-loop (BooCode drives off live `result.toolCalls`, not a history scan — not vulnerable to opencode's interrupted-tool re-prompt bug), doom-loop guard, MCP client, permission ruleset. **Ruled out:** v2 Effect/event-sourced core, `packages/llm/` native runtime (diverges from the AI SDK v6 BooCode just adopted), adaptive-reasoning (cloud-Anthropic only), `acp-next` (BooCoder is the ACP *client*).
+
+-----
+
+## 4. llama.cpp (consumed via llama-swap / llama-sidecar — adopt features, not C++)
+
+### 4a. ⭐ Retire the AGPL tool-call parser — **LIFT · drop-our-code**
+
+llama-server moved to a **template-learning PEG auto-parser + lazy grammar** that parses qwen3.5/3.6's tool markup server-side into OpenAI `tool_calls`.
+
+- **Evidence:** `common/chat-auto-parser-generator.cpp`, `common/chat-diff-analyzer.cpp` (1570 lines), `common/chat-peg-parser.cpp`; shipped `models/templates/Qwen3.5-4B.jinja` (uses BooCode's exact Pattern-2 `<tool_call><function=…><parameter=…>` + `<think>`); server emits structured `tool_calls` in **both** non-streaming and streaming (`tools/server/server-chat.cpp:421-577`), reasoning split into `reasoning_content`/`reasoning_content_delta`. `tool_choice=required` + grammar-constrained calls exist (`common/chat.cpp:290-300`).
+- **Gate (the one open question):** only fires if llama-server runs with **`--jinja` + a qwen3.x template**. BooCode already treats `--jinja`/`--chat-template*` as managed flags (`llama-args-validator.ts:92-102`) and sends `tools`/`toolChoice:'auto'` through the AI SDK (`stream-phase.ts:202,438`) — the path is wired; the unknown is whether the **live llama-swap/sidecar model config passes `--jinja`** (§5).
+- **What's missing:** no qwen3.x-named native handler — qwen3.6 rides the generic template-driven path. The template teaches Patterns 1 (`<tool_call>{json}`) and 2 (`<function=…>`) but **not Pattern 3 (`<invoke name=…>`)**, the Anthropic-shape residue qwen drifts into.
+- **Staged plan (do not delete blind — CLAUDE.md notes qwen3.6 was unreliable):**
+  1. Confirm `--jinja` + Qwen3.5 template are live (add the flags if not).
+  2. Validate native `tool_calls` against **real qwen3.6 streaming** for one release, behind a feature flag.
+  3. Trim `tool-call-parser.ts` to a **clean-room `<invoke>`-only fallback** (~250 of 427 lines deletable; rewrite the remainder without Unsloth/AGPL provenance). **Net: AGPL-3.0 liability eliminated** even if a thin fallback stays.
+
+### 4b. Config-level adopts — **LIFT · config-adopt** (pass straight through llama-swap as OpenAI-compat body fields; no binary upgrade)
+
+- **New sampling params** (`server-task.cpp:279-290`): `top_n_sigma`, `xtc_probability/threshold`, `typical_p`, the **`dry_*` repetition family** (`dry_multiplier/base/allowed_length/penalty_last_n/sequence_breakers`), `frequency_penalty`, `repeat_penalty`. `top_n_sigma` + `dry_*` are the high-value pair for an agentic model prone to loops — ties to the doom-loop sentinel. Surface in AGENTS.md frontmatter + the validator allowlist.
+- **`--reasoning-budget N`** (`LLAMA_ARG_THINK_BUDGET`) + `--reasoning on|off|auto`, default `reasoning_format=auto`: server-side cap on qwen3.6 thinking (cheaper turns) without prompt hacks, and `reasoning_content` arrives as a **separate field** — BooCode could consume it directly instead of scraping `<think>`.
+
+### 4c. Behavioral changes — **TRACK** (no code action; awareness)
+
+- **SSE headers sent at slot-start** (`0821c5fcf`): in stream mode, HTTP 200 + headers flush when prompt processing *begins*, before the first token. BooCode keys its stale-stream timer on **token activity**, not header arrival → safe, but time-to-headers semantics shift. Also `task_params.stream` default flipped `true → false` — harmless for BooCode (always sets `stream`), but any llama-swap/sidecar code omitting `stream` now defaults to non-streaming.
+- **`/props` router-mode dummy `n_ctx:0`** (`server-models.cpp:1170-1173`): llama.cpp gained a native multi-model router; its **bare** `/props` (no `?model=`) returns `n_ctx:0`. BooCode reads `/upstream/<model>/props` which resolves to a specific model → still correct today. Silent failure mode only if a bare router `/props` is ever hit: `ctx_max=0` → rejected → negative-cache masks the misconfig → compaction budget degrades. (Aside: the native router could eventually **replace llama-swap** — separate evaluation.)
+- **`LLAMA_ARG_` env-prefix unification** (`6b4e4bd58`): confirm the sidecar's `LLAMA_*` env vars use the `LLAMA_ARG_` prefix.
+
+### 4d. **SKIP**
+
+- Native **Anthropic Messages API** in llama-server (`test_compat_anthropic.py`) — BooCode is OpenAI-compat via the AI SDK; switching wire formats buys nothing. (Minor TRACK: could in principle back a local "claude-compatible" provider — net-new feature, not a lift.)
+- Qwen 3.5/3.6 **TP granularity fix** (`8b0e0db60`) — only relevant if running qwen3.6 across 3 GPUs with tensor-parallel; then it's a binary-upgrade correctness fix, not an API change.
+- HTTP ETags / `--api-key-file` / timeout bump — irrelevant behind Authelia + llama-swap.
+
+-----
+
+## 5. Second fork sweep (2026-05-31) — 11 repos
+
+Read-only agent review of everything else in `/opt/forks/` except the three already covered (paseo/opencode/llama.cpp), BooCode's own `llama-sidecar`, and `codecontext`/`codesight` (skipped on request). Repos: **conductor, superset, openchamber, happy, cline, qwen-code, amp-acp, pi-acp, claude-code, goose, unsloth.** Shallow clones (history-limited but source intact): cline, qwen-code, amp-acp, pi-acp, claude-code, goose, unsloth. Full: conductor, superset, openchamber, happy.
+
+### 5a. openchamber (`openchamber/openchamber`, **MIT** — code-liftable) ⭐
+Multi-runtime (web/PWA/Electron/VS Code) GUI for **opencode-as-warm-server** — the closest architectural sibling to BooCoder's backend. **Stronger than BooCode in exactly one dimension: opencode process-lifecycle hardening** (BooCode's v2.6 Phase 3 frontier). Divergence shaping every lift: openchamber runs **one global opencode server + one `/global/event` stream**; BooCode runs per-`(chat,agent)` sessions with per-session `event.subscribe({directory})` — so these are pattern/code-adaptation lifts, not drop-ins.
+
+| # | Finding | Evidence (HEAD `a394a877`) | Verdict | Maps to |
+|---|---------|---------|---------|---------|
+| 5c | **Lifecycle hardening: health monitor + crash auto-restart + busy-aware restart** | `packages/web/server/lib/opencode/lifecycle.js` — `runHealthCheckCycle` (L896), `HEALTH_CHECK_MAX_CONSECUTIVE_FAILURES=20`, `shouldSkipRestartForBusySessions`+`STALE_BUSY_GRACE_MS` (L872/838), `startHealthMonitoring` 15s (L938), `triggerHealthCheck` (L930). BooCode's `opencode-server.ts:143` literally comments *"recovery is Phase 3"* | **LIFT · pattern** | **v2.6 Phase 3** (#5) |
+| | **Port reclaim before respawn** (`killProcessOnPort` lsof+kill, `waitForPortRelease` net.connect poll) | `lifecycle.js:44,101`, used in `restartOpenCode` L595 | LIFT · code (S) | Phase 3 |
+| | **Stall-detecting SSE reader + `Last-Event-ID` replay** (2048-event ring, 20s stall-abort) | `lib/event-stream/upstream-reader.js:110-131`, `global-hub.js:88-149` | LIFT · pattern (the stall-timer half is S, high-value) | hardens `runSessionEventLoop` |
+| | **`OPENCODE_SERVER_PASSWORD` scheme confirmed** = `Authorization: Basic base64("opencode:"+pw)`, rotate-on-restart | `packages/vscode/src/opencode.ts:55-65,786`; `lifecycle.js:458` | CROSS-CHECK → LIFT · config | closes a known unknown (BooCode runs the warm server unsecured on loopback) |
+| | Worktree layout/reaper mirrors opencode's `<data>/worktree/<projectID>/`; `removeWorktree` saga | `packages/vscode/src/gitService.ts:1062,1874` | CROSS-CHECK | Phase 3 reaper; check BooCode's worktree paths align with opencode's expected layout |
+
+Ruled out: warm-ACP/goose/qwen/claude (openchamber is **opencode-only**), SSE part-translation/reasoning-dedup (BooCode's is more complete), Arena-equivalent, permission cards — all already-better-in-BooCode or N-A.
+
+### 5b. cline (`cline/cline`, **Apache-2.0** — code-liftable) ⭐
+Re-architected into a layered SDK. Two strong **code** lifts that hit exactly where BooCoder's write/edit surface is weakest for local quantized models.
+
+| # | Finding | Evidence (HEAD `31a118f`) | Verdict | Maps to |
+|---|---------|---------|---------|---------|
+| 5d | **`git stash create` + private-ref checkpoint** — per-turn snapshot of full dirty worktree, GC-safe, invisible to `git stash list`, restorable with conversation-trim in sync | `sdk/packages/core/src/hooks/checkpoint-hooks.ts:177-253`; `session/checkpoint-restore.ts:161-189` | **LIFT · code+pattern** (#4) | checkpoint/restore — captures **external-agent** edits BooCode's `rewind` can't |
+| 5e | **Fuzzy patch applier** — exact→`trimEnd`→`trim`→Levenshtein≥0.66 ladder + unicode canon (dashes/curly-quotes/nbsp) + multi-occurrence guard; unmatched→warning not throw | `extensions/tools/executors/apply-patch-parser.ts:347-431,58-83`; `editor.ts:133-143` | **LIFT · code** (#3) | BooCoder `edit_file` is exact `.includes`-or-throw (`pending_changes.ts:111`) |
+| | **File-provenance carry-forward** — `## Files {Read,Modified}` ledger merged across compactions, deterministic | `extensions/context/compaction-shared.ts:351-410` | LIFT · pattern (#12) | context-mgmt |
+| | **`MistakeTracker`** — counts *heterogeneous* consecutive failures (api/invalid-tool/exec), injects recovery guidance + resets vs hard-stop | `runtime/safety/mistake-tracker.ts:82-142` | LIFT · pattern (#12) | complements doom-loop (which only catches *identical* repeats) |
+| | Tool-pair-atomic compaction eviction (BFS over `tool_use_id`, turn-boundary cut) | `extensions/context/basic-compaction.ts:181-205` | CROSS-CHECK | verify `selectPruneTargets` never orphans a `tool_result` |
+
+Ruled out: prompt-caching (Anthropic `cache_control` markers — N-A, llama.cpp auto-prefix-caches), stream retry (delegated to AI SDK — same as BooCode), MCP marketplace, hub/daemon (multi-client — BooCode is single-process).
+
+### 5f. qwen-code (`QwenLM/qwen-code` v0.17.0, **Apache-2.0** — code-liftable) ⭐
+**The "qwen = one-shot PTY because ACP was HTTP-only" premise is obsolete.** qwen now ships a full stdio-ACP agent, a `qwen serve` HTTP+SSE daemon, and a Claude-Code-compatible stream-json protocol.
+
+| # | Finding | Evidence | Verdict | Maps to |
+|---|---------|---------|---------|---------|
+| | **Warm `qwen --acp` is real** — multi-session `Map<sessionId,Session>`, `loadSession`/`unstable_resumeSession`, `setSessionMode`/`unstable_setSessionModel`, stdio NDJSON via `@agentclientprotocol/sdk` | `packages/cli/src/acp-integration/acpAgent.ts:308,322-351,384-568` | CROSS-CHECK → **LIFT · pattern** (#2) | **v2.6 Phase 2** — validates the openspec plan; wire goose/qwen to `acp-dispatch.ts` |
+| 5g | **stream-json = Claude-compatible NDJSON** (`system`/`assistant`/`result`/`stream_event` with `content_block_delta` text/thinking/tool deltas, `usage`, `session_id`) — BooCode **parses none of it** (`dispatcher.ts:406` slices stdout opaque) | `nonInteractive/types.ts:88-262`, `StreamJsonOutputAdapter.ts` | **LIFT · pattern** (#7) | one parser serves qwen **and** claude PTY fallbacks |
+| | **Resume primitives** `--resume <uuid\|title>` / `--continue` / `--session-id <uuid>` / `--fork-session` | `config/config.ts:825-985,1668-1721` | LIFT · config | mint a stable per-`(chat,agent)` UUID; parity with claude `--resume` |
+| | `qwen serve` daemon + `@qwen-code/sdk` (HTTP+SSE, **`Last-Event-ID` replay ring**, better than opencode's SSE) | `commands/serve.ts:51-266`; `packages/sdk-typescript/src/daemon/*` | TRACK | stdio-ACP is cheaper now; mine its SSE-reconnect design when hardening opencode SSE (converges w/ openchamber 5c) |
+
+Note: BooCode ships `@agentclientprotocol/sdk@^0.22.1` (newer than qwen's `^0.14.1`) — same package family, BooCode ahead; **cross-check the v0.14↔v0.22 `initialize`/capability handshake before relying on `unstable_resumeSession`** (the `unstable_` prefix signals churn). Ruled out: the `rewind` commit (`c699738`) is a qwen-TUI history-count fix, not a wire event — N-A.
+
+### 5h. happy (`slopus/happy`, **MIT** — code-liftable) ⭐
+Mobile/remote client that drives **Claude Code** via the **`@anthropic-ai/claude-agent-sdk`** (NOT PTY). A working existence-proof for BooCode's claude SDK-vs-PTY decision.
+
+| # | Finding | Evidence (HEAD `21c6ced`) | Verdict | Maps to |
+|---|---------|---------|---------|---------|
+| | **Claude Agent SDK in streaming-input mode** — one persistent `query()` fed a `PushableAsyncIterable<SDKUserMessage>`; structured `system/init` (tools/skills/mcp), `assistant`, `result`, tool parts — no stdout scraping | `claude/sdk/query.ts`, `claude/claudeRemote.ts:152-259`; dep `@anthropic-ai/claude-agent-sdk@^0.2.96` | **LIFT · pattern** + resolves the decision → **lean SDK** (#9) | claude-provider direction |
+| 5i | **`--resume` continuity via SessionStart-hook + JSONL watcher** → captures Claude's UUID as `claudeSessionId`, fed back as SDK `resume:`; reconnect-safe (`treatExistingAsProcessed`) | `claude/utils/generateHookSettings.ts`, `sessionScanner.ts`, `claude/session.ts:113-127` | **LIFT · code** (#9) | cleanly separates Claude's UUID from BooCode's `(chat_id,agent)` key; **transport-independent — pays off even on PTY** |
+| | `canUseTool` permission callback — single chokepoint, live `setPermissionMode`, bash-prefix allow-cache | `claude/claudeRemote.ts:134,169`, `permissionHandler.ts` | CROSS-CHECK | cleaner integration point than parsing PTY permission prompts |
+| | Local↔remote single-session handoff (TTY ⇄ SDK share one Claude UUID); E2E socket.io relay | `claude/loop.ts:77-115`; `api/encryption.ts` | TRACK / N-A | relay N-A (Authelia owns auth); handoff only if BooTerm⇄CoderPane session-continue is ever wanted |
+
+### 5j. superset (`superset-sh/superset`, **Elastic License 2.0 — source-available, PATTERN-ONLY**)
+Electron macOS "code editor for AI agents"; runs every agent as a **raw PTY process** and learns state purely from **hooks the agents POST back** (no editor↔agent protocol, tracks **zero** tokens/cost). All items clean-room only.
+
+| # | Finding | Evidence (HEAD `7f3e5b3`) | Verdict | Maps to |
+|---|---------|---------|---------|---------|
+| 5j | **Universal-agent lifecycle hooks → normalized status** — inject a notify hook into each agent's native config (`~/.claude/settings.json`, `~/.codex/hooks.json`, opencode plugin), POST `{terminalId,eventType,agent}`; server collapses ~30 vendor event names → 5 states | `apps/desktop/.../agent-setup/*`, `templates/notify-hook.template.sh`, `host-service/.../map-event-type.ts` | **RE-DERIVE** (#10) | gives BooCode's **PTY agents (goose/qwen/claude) real working/blocked/done state** it lacks today |
+| | Worktree destroy saga — preflight `inspect` (dirty/unpushed) + ordered failure semantics + in-flight guard | `host-service/.../workspace-cleanup.ts` | RE-DERIVE | Phase 3 worktree reaper |
+| | Out-of-process PTY daemon w/ crash supervision + adoption (circuit-breaker, adopted-PID liveness poll) | `host-service/.../DaemonSupervisor.ts` | RE-DERIVE / TRACK | Phase 3 (BooTerm tmux already does some) |
+| | Diff-line → agent-comment re-prompt loop (select lines → send to existing session or new agent) | `apps/desktop/.../DiffPane/AgentCommentComposer/*` | RE-DERIVE | review/diff UX frontier |
+
+Ruled out: token/cost (superset tracks **none** — BooCode ahead), permission cards (BooCode's intercept-and-render is richer; superset just chimes + bypass-flags the agent), editor↔agent protocol (there is none), all SaaS/cloud/billing plumbing.
+
+### 5k. unsloth (`unslothai/unsloth`) — **decision-settling: CONFIRMED AGPL-3.0-only**
+The lifted parser + HTML→MD converter ARE AGPL-3.0; the v2 clean-room recommendation stands. Unsloth is **dual-licensed**: core `unsloth/` lib = Apache-2.0 (`LICENSE`, `pyproject.toml`), but the `studio/` subtree = **AGPL-3.0-only** — dedicated `studio/LICENSE.AGPL-3.0`, `studio/package.json` `"license":"AGPL-3.0-only"`, README §line 262 carves Studio out explicitly, and **both lifted files carry per-file SPDX headers** (`studio/backend/core/inference/{tool_call_parser.py,_html_to_md.py}` → `# SPDX-License-Identifier: AGPL-3.0-only`). BooCode's ports already carry the AGPL SPDX header (obligation on-record). Network-served ⇒ **AGPL §13 network-copyleft is the live liability.** HTML→MD can be replaced outright by a permissive lib (turndown / node-html-markdown); the tool-call parser needs a clean-room rewrite from spec (the `<tool_call>`/`<function=>` grammar is short and re-derivable).
+
+### 5l. conductor (`conductor-oss/conductor`, **Apache-2.0**, Java) — **LOW / near-NONE**
+Confirmed **Netflix/Orkes Conductor** — enterprise distributed workflow engine (5600 commits, Spring/Flyway/Cassandra), **not** the Mac Claude-Code app. Wrong scale + wrong substrate (polling workers + Redis queues vs BooCode's single-user Postgres LISTEN/NOTIFY), and BooCode already sourced its task-DAG/dispatcher/pipelines/human_inbox from `agent-hub` + Roo Boomerang. **One** worth-a-glance reference: the **retry/backoff/timeout taxonomy** (`TaskDef.java` `RetryLogic{FIXED,LINEAR,EXP}` + `TimeoutPolicy`, delay formula in `DeciderService.java:634-680`, with jitter + total-time-budget guard) — BooCode has **no retries today**; copy the *field set + three formulas* when retries land. Everything else (decider-replay engine, 24 task mappers, fork-join, sub-workflow, human-task) = N-A, already-covered or wrong-scale.
+
+### 5m. ACP provider candidates — amp-acp **SKIP**, pi-acp **WATCH**
+Both are config-only adds to BooCode's v2.3 catalog (`{extends:'acp', label, command, env}`) and both use **`@agentclientprotocol/sdk@~0.22/0.12`, proto v1 — wire-compatible with BooCode's own `@agentclientprotocol/sdk@0.22.1`** (see correction in §6).
+- **amp-acp** (`tao12345666333/amp-acp`, Apache-2.0): adapter for Sourcegraph **Amp**. `npx -y amp-acp` + `AMP_API_KEY`. **SKIP** — Amp is a **paid cloud product with no self-host / no BYO-key / no local-model path**; can't point at llama-swap. Keep only as the canonical *"does add-from-catalog work"* smoke entry (lowest-risk Apache-2.0 ACP adapter).
+- **pi-acp** (`svkozak/pi-acp`, MIT): bridge for **pi** (spawns `pi --mode rpc`). `npx -y pi-acp`, pi free + self-hostable, dynamic model discovery. **WATCH** — but found **no evidence pi supports an OpenAI-compatible/llama-swap base URL** (cloud BYO-keys only today) + v0.0.27 maturity ("MVP", MCP not wired). Re-evaluate if pi adds a local provider — then it's a strong config-only ADD.
+
+### 5n. claude-code & goose — low/cosmetic
+- **claude-code** (`anthropics/claude-code`, depth-1): the public **issue-tracker/docs repo, not source.** Thin. No stream-json schema doc (keep relying on observed output). Notables: `CLAUDE_CODE_SESSION_ID` env injected into Bash-tool subprocesses (hook↔session correlation); `examples/settings/*.json` permission/sandbox shapes; `SKILL.md` frontmatter is simpler (`name/description/version`) than BooCode's `eval.yaml`. The one example hook (`bash_command_validator`) is the same family BooCode already vendored. **Nothing net-new liftable.**
+- **goose** (`block/goose`, depth-1, Apache-2.0 Rust → pattern-only): the **AAIF/Linux-Foundation move is cosmetic** — binary `goose`, `goose acp` invocation, and `~/.config/goose/` config path all **UNCHANGED**; only org/URLs changed (`block/goose` → `aaif-goose/goose`). **Watch:** grep BooCode install docs for `block/goose` URLs (will eventually 404). **For v2.6 Phase 2:** goose ACP supports multi-session + mid-session model/mode switch + session persistence, but **no `loadSession`/resume method surfaced** → cross-restart resume looks thinner than opencode's; don't assume opencode-style `agent_sessions` resume works identically for goose.
+
+-----
+
+## 6. Open decisions / things to think about
+
+1. **The jinja gate (blocks #1, the top item).** Is `--jinja` + a qwen3.x template live in the llama-swap/sidecar model config? Read-only to answer, but the config may live with the sidecar on sam-desktop (`100.101.41.16`) — needs Sam's OK before any SSH. *This single check decides whether the AGPL-parser retirement is actionable now or needs a config change first.*
+2. **Claude transport: SDK vs PTY — now evidenced, leaning SDK.** `happy` (§5h) is a working existence-proof that `@anthropic-ai/claude-agent-sdk` in streaming-input mode drives Claude Code with structured events (tool calls, reasoning, `system/init` tool/skill/mcp lists, usage) and clean continuity — richer than PTY stdout-scraping. **Decision narrowed to: adopt the SDK** (net-new integration, ~100-line streaming-input pump) **vs. stay PTY + just add `--resume`.** Independent of warm-ACP Phase 2. Note the continuity mechanism (§5i hook + jsonl-watcher → `claudeSessionId`) is **transport-independent**, so ship it either way.
+3. **`stream-json` parser is shared infrastructure, not a per-agent chore.** qwen-code (§5g) and claude-code emit the *same* Claude-Code-compatible NDJSON. One parser keyed on `type` / `stream_event.event.type` unlocks tool/reasoning/usage surfacing for **both** qwen and claude PTY fallbacks (today both are sliced opaque). Decide whether to build it as a shared module now (cheap) rather than twice later.
+4. **Transcript/session verification before resume (shared gap).** Neither Paseo nor BooCode (nor openchamber, nor goose's ACP) verifies the session/transcript exists on disk before resuming — true for opencode, claude, qwen. Folds into v2.6 Phase 3 (crash recovery + active supervision, now lifting from openchamber §5c). Decide whether "resume blindly, recover on failure" is good enough for single-user, or worth a pre-resume existence check. **Caveat:** goose ACP exposes no `loadSession`/resume (§5n) → its cross-restart resume needs a different design than opencode's.
+5. **Usage *and status* normalization scope.** Two converging gaps: (a) **tokens/cost** — the opencode token slice (#8) converges with paseo `AgentUsage`; (b) **liveness/status** — superset's notify-hook pattern (§5j, #10) is the only way to know whether a one-shot PTY agent (goose/qwen/claude) is working / blocked-on-permission / done. Decide whether to design one normalized per-`(chat,agent)` "agent telemetry" shape (tokens + status) up front so all providers slot in, or ship opencode-token-only and generalize at Phase 2.
+6. **Correction — ACP SDK package.** This doc and the roadmap state BooCode uses `@zed-industries/agent-client-protocol`; the live `apps/coder/package.json` actually declares **`@agentclientprotocol/sdk@^0.22.1`** (verified installed). Both amp-acp and pi-acp use the same package, so the "version-drift" worry is moot. Worth correcting in `boocode_roadmap.md`'s lift table on the next pass.
+
+-----
+
+## 7. Housekeeping
+
+- **Stale `.bak` in the working tree:** `apps/server/src/services/inference/tool-phase.ts.bak-20260531` (today, 15.5 KB). Violates CLAUDE.md's "don't accumulate `.bak-*`". Dated today and `tool-phase.ts` is on the active path — may be an in-progress safety copy. **Confirm before removing.**
+- **Unshallow `/opt/forks/llama.cpp`** (`git fetch --unshallow`) before the next review so commit-level attribution is possible. (opencode was unshallowed mid-review; cline/qwen-code/amp-acp/pi-acp/claude-code/goose/unsloth remain shallow but their source was intact.)
+- **Grep BooCode install docs/scripts for `block/goose` URLs** — goose moved to `aaif-goose/goose` (§5n); old release URLs will eventually 404.
+- **Correct the ACP-SDK package name** in `boocode_roadmap.md`'s lift table → `@agentclientprotocol/sdk@0.22.1` (§6.6).
+
+-----
+
+## 8. Roadmap mapping (where each actionable lands)
+
+| Roadmap slot | Items from this review |
+|---|---|
+| **v2.6 Phase 2** (warm ACP goose/qwen) | #2 warm-ACP backend — **validated by qwen's own `qwen --acp`** (§5f); #7 parse qwen/claude stream-json in the one-shot fallback |
+| **v2.6 Phase 3** (lifecycle hardening) | **#5 openchamber lifecycle hardening** (health monitor + crash restart + port reclaim + stall-SSE — §5c, supersedes the paseo re-derive); worktree-archive cascade (paseo) + superset destroy-saga (§5j); LRU-bound caches; pre-resume session verification |
+| **v2.6 Phase 1 UX** | #6 interrupt-bug fix; #8 opencode token/ctx usage; richer SSE arms (compaction surfacing) |
+| **Write/edit robustness (NEW batch)** | **#3 fuzzy patch applier** + **#4 git-stash checkpoint** (cline §5b) — both directly harden BooCoder's edit/rewind surface for local models |
+| **Cross-agent telemetry (NEW)** | #10 superset notify-hook → normalized **status** for PTY agents (§5j); pairs with #8 token usage |
+| **Standalone claude-provider batch** | #9 `--resume` via hook/jsonl-watcher (§5i) + the SDK-vs-PTY decision (now lean-SDK, §6.2); #12 MistakeTracker + file-provenance ledger (cline) |
+| **Inference / license-debt batch** | #1 AGPL parser retirement (**AGPL confirmed §5k**; gated on the jinja check §6.1); #11 sampling/reasoning-budget config adopts |
+| **BooChat resilience (opportunistic)** | stall-timeout + retry/backoff (opencode); tool-pair-atomic prune cross-check (cline §5b) |
+| **Provider catalog** | amp-acp = keep as add-from-catalog **smoke test only** (§5m); pi-acp = WATCH for a local-provider mode |
+| **Deferred / gated** | subagent permission demux (needs opencode-SSE permission cards first); MCP auth lock (needs OAuth MCP un-deferred); `qwen serve` HTTP backend (stdio-ACP cheaper) |
+| **Not actionable** | conductor (wrong scale — only the retry-taxonomy reference §5l); claude-code public repo (docs only §5n) |

boocode_roadmap.md

@@ -1,6 +1,6 @@
 # BooCode roadmap (v1.x–v2.x)
 
-Last updated: 2026-05-26
+Last updated: 2026-05-31
 
 > **Companion doc:** `boocode_code_review.md` holds the full external-repo inventory, lift rationale, and license analysis. This document is the canonical source for shipping state, version ordering, and what's planned vs. shipped.
 
@@ -9,7 +9,7 @@ Last updated: 2026-05-26
 BooCode is a **3-app monorepo** at `/opt/boocode/` (locked 2026-05-22):
 
 - **BooChat** (`apps/server` + `apps/web`, port `9500`, `code.indifferentketchup.com`) — read-only chat with file-inspection tools. Backend in `apps/server`, SPA in `apps/web`. Database `boochat` (renamed from `boocode` at v2.0).
-- **BooCoder** (`apps/coder`, port `9502`, `coder.indifferentketchup.com`) — write tools + external-CLI dispatch. **Shipped v2.0.0–v2.2.1.** Host systemd service (not Docker since v2.1.0). In-process inference (with `pending_changes` table) AND Paseo-style ACP dispatch for seven providers (cursor, opencode, goose, claude, qwen, copilot + native boocode) with PTY fallback where ACP is unavailable.
+- **BooCoder** (`apps/coder`, port `9502`, `coder.indifferentketchup.com`) — write tools + external-CLI dispatch. **Shipped v2.0.0–v2.6.4.** Host systemd service (not Docker since v2.1.0). In-process inference (with `pending_changes` table) AND Paseo-style ACP dispatch for five providers (opencode, goose, claude, qwen + native boocode; cursor + copilot retired at v2.5.3) with PTY fallback where ACP is unavailable. Provider lifecycle is config-backed (`data/coder-providers.json`, enable/disable, two-tier probe — shipped v2.5.4–v2.5.13). opencode now runs as a **warm HTTP server** with persistent per-chat sessions (v2.6 Phase 1); goose/qwen/claude still dispatch one-shot.
 - **BooTerm** (`apps/booterm`, port `9501`) — PTY/tmux/xterm.js. **Live since May 2026.** bookworm-slim + node-pty + tmux + xterm.js. Tmux session per pane (`bc-<uuid>`), SSH-out works (openssh-client + gosu in the image). Shares Postgres database `boochat`.
 
 Caddy → Authelia → Tailscale → `100.114.205.53` → 9500/9501/9502. Three apps, **one shared Postgres** (Docker service `boocode_db`, database name `boochat`).
@@ -348,9 +348,43 @@ Per-session Docker sandbox spawned by BooCoder on first write. Only project path
 
 -----
 
+## Shipped (v2.2.2–v2.6.4 — interactive ACP, provider lifecycle, persistent agent sessions)
+
+All tags `vMAJOR.MINOR.PATCH-slug`, monotonic per minor, assigned at ship time (planning slugs differ — see the numbering-discipline note below). `CHANGELOG.md` is the canonical per-tag record. **Note on numbering divergence:** the *planned-feature* "v2.3 — Provider lifecycle" actually shipped under the **v2.5.4–v2.5.13** tags; the *planned-feature* "v2.4 — BooCoder as ACP agent" remains **unshipped** even though v2.4.0/v2.4.1 *tags* shipped unrelated content (Unsloth lifts, sidecar routing). The patch-tag thread and the conceptual-milestone thread have diverged — read tags as the ship record, the `## v2.x` feature sections below as the milestone plan. The v2.3.0–v2.5.1 tags were never CHANGELOG-backfilled; summarized here from commit bodies.
+
+- `v2.2.2-xml-placeholder-reject` — reject placeholder XML tool args (`...`, `<path>`, empty/whitespace, angle-bracket sentinels) at parse time; appends raw block to prose instead of silent-deleting. Fixes qwen3.6 answer-then-spurious-tools duplicate-row tail
+- `v2.3.0-sampling-params-ask-user` — per-agent sampling params (`top_p`/`top_k`/`min_p`/`presence_penalty`) in AGENTS.md frontmatter threaded through inference (null = omit, preserve provider default); `ask_user_input` interactive card wired into both BooCoder frontends (CoderPane + standalone coder SPA)
+- `v2.3.1-permission-questions` — enrich ACP `permission_requested` frame with `kind` (`tool`|`question`|`plan`|`elicitation`) + `input` + `description`; PermissionCard renders interactive radio/checkbox forms for AskUserQuestion; ACP `createElicitation` (experimental) JSON-Schema-driven forms
+- `v2.3.2-coder-answer-endpoint` — fix `ask_user_input` submit in CoderPane (register `answer_user_input` on the boocoder service; `apiPrefix` routes through `/api/coder/...` so the right inference runner picks up the answer)
+- `v2.4.0-unsloth-studio-lift` — port of Unsloth Studio modules: `tool-call-parser.ts` (replaces `xml-parser.ts`; balanced-brace JSON scanner, `hasToolSignal`/`stripToolMarkup`/`parseToolCallsFromText`, stripping at all 3 final-write sites) + `web/html-to-md.ts` (parse5 HTML→Markdown for `web_fetch`). **License flag:** Unsloth Studio is AGPL-3.0 — tension with the roadmap's MIT / no-AGPL-code-lift commitment; revisit before any network-served distribution
+- `v2.4.1-sidecar-routing` — route per-agent `llama_extra_args` to `LLAMA_SIDECAR_URL` via `X-Agent-Flags` (boot guard if set but URL unset); `resolveRoute` + PrefixFingerprint `route` field. AGENTS.md tool-gap fix: 8 post-hoc tools (`request_read_access`, `view_truncated_output`, `ask_user_input`, `git_status`, …) added to every agent's whitelist
+- `v2.5.0-task-model` — lightweight task-model services (`TASK_MODEL_URL` dedicated llama-server, falls back to `LLAMA_SWAP_URL`+`FAST_MODEL`) for auto-naming/search-rewrite/tags/summaries; search-query rewriting on step 0 when web tools enabled; `sessions.tags` column
+- `v2.5.1-budget-100` — tool-call budgets raised 50/10/50 → **100/100/100** (read-only / non-read-only / no-agent); per-agent `max_tool_calls` still overrides. `.claude/worktrees/` added to `.codecontextignore`
+- `v2.5.2-coder-ux-fixes` — dispatcher reacts immediately via Postgres `LISTEN/NOTIFY` (`tasks_new` trigger, 2s poll fallback); mobile nav-drawer bfcache fix (`useViewport` re-syncs on `pageshow`/`visibilitychange`); reasoning "Thinking" collapsible in MessageBubble (ACP `agent_thought_chunk` + native `reasoning_parts`); paste-to-chip verbatim; "New file from pasted text" RightRail affordance; DiffPanel approve/reject repointed to real routes. Ships the `v2-6-persistent-agent-sessions` openspec as planning docs only
+- `v2.5.3-remove-cursor-copilot` — retire cursor + copilot providers entirely (argv cases, manifest, command maps, cursor model-CLI branch, `cursor-models.ts`). Built-ins now: claude, opencode, goose, qwen, native boocode
+- `v2.5.4-provider-lifecycle-phase1` — **(v2.3 milestone, phase 1/5)** config-backed provider layer (`CODER_PROVIDERS_PATH` default `/data/coder-providers.json`; `provider-config.ts` never-throws loader; `buildResolvedRegistry` merge) over built-ins; `agent-probe` iterates the resolved registry. No runtime change when no config file exists
+- `v2.5.5-provider-lifecycle-phase2` — **(phase 2/5)** snapshot lifecycle status (`loading`|`ready`|`unavailable`|`error`) + `enabled` flag; always lists every registered provider; two-tier probe (fast `which` vs cold ACP, skipped unless forced / `PROVIDER_PROBE_TTL_MS` 24h stale / DB-empty); `provider-types-parity.test.ts`
+- `v2.5.6-provider-lifecycle-phase3` — **(phase 3/5)** generic ACP dispatch (`resolveLaunchSpec` from config `launchCommand`; spawn `spec.binary`/`args`/`env`); built-in dispatch byte-identical (regression-tested). Config-defined custom ACP providers dispatch with no new switch case
+- `v2.5.7-claude-models-and-picker-fix` — fix the empty provider picker (a v2.5.5 regression: `getProviderSnapshot` returned sync `loading` entries the composer filtered out → now awaits build, returns terminal entries); wire config `models` (replace) / `additionalModels` (merge); claude static models bumped to opus/sonnet/haiku latest-aliases + pinned full names
+- `v2.5.8-mobile-composer-row` — AgentComposerBar mobile fix (dot + refresh as one right-aligned unit, was wrapping); Mode picker icon-only on mobile via `CompactPicker` `iconOnly`. Desktop unchanged
+- `v2.5.9-agent-slash-commands` — segmented per-agent slash menu (active agent's commands first, BooCoder skills second; opt-in `groups` prop, BooChat flat path byte-identical); skills now run under the selected external agent (skill body injected into a dispatched task); landing-chat skill-invoke fix
+- `v2.5.10-opencode-live-commands` — capture opencode's live ACP `available_commands` (poll for the async `available_commands_update`, was racing to 0); persist to new `available_agents.commands` JSONB; serve merged on the tier-2-probe-skip path
+- `v2.5.11-claude-skill-discovery` — surface Claude Code's real enabled commands + plugin skills in the coder slash menu (`claude-command-discovery.ts` reads `~/.claude/commands` + `enabledPlugins` skills/commands); three icon'd groups (agent commands / agent skills / BooCoder skills); `AgentCommand.kind`
+- `v2.5.12-provider-lifecycle-phase4` — **(phase 4/5)** HTTP API: `GET`/`PATCH /api/providers/config`, optional-subset `POST /refresh`, `GET /:id/diagnostic`. PATCH ordering validate→save→reload→clear (malformed body → 422 no-write; save-fail → 500 no-divergence); `mergeProviderConfigPatch`; +28 tests
+- `v2.5.13-provider-lifecycle-phase5` — **(phase 5/5, closes the v2.3 arc)** Settings → Providers UI (status badge, enable/disable toggle, per-provider refresh, plaintext diagnostic); composer filters to `enabled && ready|loading`; curated ACP catalog + `AddProviderModal`; two mobile fixes (Settings reachable on phones; modal scroll-containment). `docs/DEFERRED-WORK.md` §2 marked addressed
+- `v2.5.14-claude-md` — docs-only CLAUDE.md session-learnings (stale boocoder process after build, container `build:.` deploys working tree, wholesale `PATCH /providers/config` merge, one-shot external dispatch has no ctx tracking, `ui/` switch/sheet fallbacks, mobile Dialog scroll recipe); backfills v2.5.7–v2.5.11 doc bullets
+- `v2.5.15-acp-path-guard` — security: separator-bounded worktree path guard in `acp-client-fs.ts` (closes a sibling-prefix `<worktree>-evil/` escape; `writeWorktreeTextFile` bypasses `pending_changes`, writes disk directly) via shared `resolveInWorktree` + regression test; stop tracking live `data/coder-providers.json` (gitignore + `data/coder-providers.example.json` reference; loader falls back to built-ins-only)
+- `v2.6.0-phase0-foundations` — **(v2.6 Phase 0, no behavior change)** schema + interface scaffold: `session_worktrees` (one shared worktree per session) + `agent_sessions` (one backend session per `(session, agent)`) tables, `pending_changes.agent` attribution column; `AgentBackend`/`AgentSessionHandle` interface + normalized transport-agnostic `AgentEvent` union (types only)
+- `v2.6.1-phase1-opencode` — **(Phase 1)** opencode as a **warm HTTP server** (`opencode serve` per BooCoder process, one opencode session per BooCode session resumed across turns via `agent_sessions`); single SSE read loop, Paseo reasoning-dedup, inactivity watchdog, stale-session guard (`config_hash` = `opencode_server|<model>`, excludes the ephemeral port so cross-restart resume survives). Hard-won: opencode streams `session.next.*` (not `message.part.*`), `event.subscribe()` must pass the worktree `directory`, models must be `llama-swap/`-prefixed + in opencode's config. Bundled: dcp-message-id strip, reopen-pane control, `[+]`/split separation, auto-name on session model, `systematic-debugging` slash command. Known limit (closed in v2.6.2): single SSE scoped to the most-recent directory
+- `v2.6.2-delete-guard-and-sse` — session-delete work-loss guard (server gates `DELETE /api/sessions/:id`: reads `session_worktrees`, calls BooCoder `/worktree-risk` which runs git on the host; dirty/unpushed/unmerged → 409 + per-worktree `RiskReport[]`, `force` bypasses, fail-closed; sidebar block dialog distinguishes at-risk from couldn't-verify, never auto-commits). **Per-session SSE (P1.5-a):** one `event.subscribe({directory})` per live opencode session, each with an `AbortController`, so sessions in different worktrees stream concurrently (was: second silently dropped); `sessionID` demux guard + zombie-loop fix
+- `v2.6.3-chatkey-and-skills` — re-key `agent_sessions` to **`(chat_id, agent)`** (P1.5-b: the tab/chat is the agent-context unit; two opencode tabs in one session = two contexts sharing one worktree); `tasks.chat_id` threaded end-to-end (`runOpenCodeServerTask` resolve-or-creates a chat for session-less creators); first-class `worktrees` table (one-per-session, survives session delete) supersedes the defanged `session_worktrees`; `agent_sessions.chat_id` CASCADEs from `chats`; stateful cross-chunk dcp-message-id stripper; `committing-changes` + `using-worktrees` judgment skills in `data/skills/boocode/` + parser-safe `data/AGENTS.md` preamble
+- `v2.6.4-agent-sessions-fk` — converge the live `agent_sessions.session_id` FK `CASCADE → SET NULL` (standalone `confdeltype`-guarded `DO` block, idempotent — the P1.5-b re-key gate skipped already-re-keyed DBs and left it diverged); CLAUDE.md doc-sync (per-session SSE, `(chat_id, agent)` re-key, `data/AGENTS.md` parsing + `data/skills/<vendor>/` conventions)
+
+-----
+
 ## v2.3 — Provider lifecycle (Paseo-style registry)
 
-**Planned.** Config-backed provider registry (`/data/coder-providers.json`), merged built-ins + overrides, enable/disable toggles, two-tier probe (fast binary vs slow ACP session), generic ACP spawn from config without new code paths. Depends on v2.2 snapshot wire shape. Openspec: `openspec/changes/v2-3-provider-lifecycle/`. See `CURRENT.md`.
+**Shipped across `v2.5.4`–`v2.5.13` (5 phases, 2026-05-29).** Config-backed provider registry (`data/coder-providers.json`), merged built-ins + overrides, enable/disable toggles in Settings → Providers, two-tier probe (fast binary vs slow ACP session, TTL-gated), generic ACP spawn from config without new code paths, HTTP config/refresh/diagnostic API, curated add-from-catalog. The milestone shipped under v2.5.x patch tags (not "v2.3.x") because patch numbers are assigned at ship time. Openspec: `openspec/changes/v2-3-provider-lifecycle/` (design §2–§6 map to phases 1–4; phase 5 = UI). `docs/DEFERRED-WORK.md` §2 marked addressed; Tier-2 follow-ups (WS `provider_snapshot_updated` frame, `available_agents.enabled` column, shared types package, MCP provider tools) stay deferred.
 
 **Lift source:** Paseo provider docs (design only — no AGPL code lift).
 
@@ -360,6 +394,8 @@ Per-session Docker sandbox spawned by BooCoder on first write. Only project path
 
 ## v2.4 — BooCoder as ACP agent (driveable from external editors)
 
+**Status: not shipped.** This is a conceptual milestone, not yet built. The `v2.4.0`/`v2.4.1` *patch tags* shipped unrelated content (Unsloth Studio parser/HTML-to-md lift, llama-sidecar routing) — patch numbers are assigned at ship time and have outrun the milestone plan. The outbound ACP-agent surface below is still future work.
+
 **Goal:** expose `boocoder acp` so Zed, JetBrains, Avante.nvim, CodeCompanion.nvim can drive BooCoder as their agent. Outbound exposure of the BooCoder write-tool surface to ACP-compatible editors.
 
 **Scope:**
@@ -378,6 +414,32 @@ Per-session Docker sandbox spawned by BooCoder on first write. Only project path
 
 -----
 
+## v2.6 — Persistent agent sessions (warm processes + OpenCode server)
+
+**Goal:** make a BooCode chat map to a **persistent agent backend + a persistent worktree** that live for the whole conversation, so turns are warm and the agent sees its own accumulating edits. Replaces the one-shot-per-task model (fresh worktree + process spawn + ACP handshake every turn) with Paseo's pattern: OpenCode as a long-lived HTTP server, goose/qwen as warm stdio-ACP processes. Reasoning passthrough was already solved in v2.5.2's Thinking block — this batch is about persistence, not capability.
+
+**Decisions locked:** persistent worktree per session (shared across agents); free agent-switch with per-agent memory (one backend session per `(chat, agent)` pair, re-keyed from `(session, agent)` in P1.5-b); OpenCode → one shared `opencode serve` HTTP server (multi-session, directory-routed); goose/qwen → warm stdio ACP per live session; claude stays one-shot PTY.
+
+**Shipped so far:**
+
+1. `v2.6.0-phase0-foundations` ✅ — schema + `AgentBackend`/`AgentEvent` interface scaffold (no behavior change).
+1. `v2.6.1-phase1-opencode` ✅ — OpenCode warm-server backend, per-chat resumable session, SSE demux, reasoning dedup, watchdog, stale-session guard.
+1. `v2.6.2-delete-guard-and-sse` ✅ — session-delete work-loss guard + **per-session SSE (P1.5-a)** so concurrent opencode sessions in different worktrees stream independently.
+1. `v2.6.3-chatkey-and-skills` ✅ — **P1.5-b** re-key `agent_sessions` to `(chat_id, agent)`; first-class `worktrees` table; `tasks.chat_id` threading; cross-chunk dcp-strip; judgment skills.
+1. `v2.6.4-agent-sessions-fk` ✅ — converge `agent_sessions.session_id` FK to `SET NULL`; doc-sync.
+
+**Remaining (per openspec `v2-6-persistent-agent-sessions/tasks.md`):**
+
+- **Phase 1 UX** — DiffPanel per-change agent attribution (`pending_changes.agent` badges), resumed/new-session chip on AgentComposerBar (`GET /api/sessions/:id/agent-sessions`), staging-boundary hint.
+- **Phase 2 — warm ACP backend (goose, qwen)** — persistent `SpawnedACPProcess` connection reused across turns (one `session/new`, many prompts); dispatcher routes goose/qwen to the warm backend; switch round-trip smoke (opencode → boocode → opencode resumes the same session).
+- **Phase 3 — lifecycle hardening** — idle TTL eviction per `(chat, agent)`, crash recovery, chat-close/archive worktree cleanup, orphan reaper + max-live-worktrees LRU cap, re-baseline diff after `apply_pending`, reconnect test.
+
+**Lift sources:** `getpaseo/paseo` (design only — OpenCode-as-HTTP-server pattern, `streamedPartKeys` reasoning dedup), `@opencode-ai/sdk` (v2 client), `/opt/forks/opencode`.
+
+**Dependencies:** v2.2 (ACP dispatch) + v2.3 provider lifecycle (registry/snapshot). Openspec: `openspec/changes/v2-6-persistent-agent-sessions/`.
+
+-----
+
 ## v2.1.0 — Provider picker + model discovery
 
 **Shipped `v2.1.0-provider-picker`.** Provider registry with 5 providers (boocode, opencode, goose, claude, qwen). Model discovery via `LLAMA_SWAP_URL/upstream/<model>/props`. `/api/providers` route returns installed providers with models. v2.1 `ProviderPicker` UI **superseded by `AgentComposerBar` in v2.2.** Agent-probe startup probe discovers installed agents on host, their versions, ACP support, and models. Booterm SSH host configurable via `BOOTERM_SSH_HOST`/`BOOTERM_SSH_USER` env vars.
@@ -412,7 +474,7 @@ Per-session Docker sandbox spawned by BooCoder on first write. Only project path
 |-------------------------------|---------------------|-----------------------------|------------------------------------------------------------------------|----------------------|
 |`boochat` (was `boocode`)      |`100.114.205.53:9500`|`/opt:/opt:ro`               |Read-only chat + SPA host + MCP client                                  |Live (renames at v2.0)|
 |`booterm`                      |`100.114.205.53:9501`|`/opt:/opt`                  |PTY/tmux terminal sessions                                              |**Live (May 2026)**   |
-|`boocoder` (host systemd)       |`100.114.205.53:9502`|full host FS (policy-gated)  |Write tools + ACP client + MCP client + MCP server + external-CLI dispatch|**Shipped v2.0.0–v2.2.1** (systemd since v2.1.0) |
+|`boocoder` (host systemd)       |`100.114.205.53:9502`|full host FS (policy-gated)  |Write tools + ACP client + MCP client + MCP server + external-CLI dispatch + warm opencode server|**Shipped v2.0.0–v2.6.4** (systemd since v2.1.0) |
 |**`boochat`** (Docker service `boocode_db`)|`127.0.0.1:5500`     |`boocode_pgdata` volume      |Postgres 16-alpine (shared by all three)                                |**Live** (DB renamed from `boocode` at v2.0)|
 |`codecontext`                  |`:8080` (internal, Docker network)   |`/opt:/opt:ro`|Go HTTP sidecar for code graph tools                                          |**Live (v1.12.0)**    |
 
@@ -459,7 +521,12 @@ term.indifferentketchup.com         → booterm   :9501   (or routed under code.
 - **v1.16:** `repo_health_cache (project_id, file_hashes_sig, payload JSONB, created_at)`
 - **v2.0 (shipped):** `pending_changes`, `tasks`, `available_agents`, `human_inbox` view; database renamed `boocode` → `boochat`
 - **v2.2 (shipped):** none (provider snapshot + ACP dispatch are runtime/services; pane chat scoping uses existing `sessions.workspace_panes` + `chats`)
-- **v2.4:** none (`boocoder acp` is a new entry point, not a schema change)
+- **v2.5.0 (shipped):** `sessions.tags` column (task-model tagging)
+- **v2.5.10 (shipped):** `available_agents.commands jsonb` column (persisted ACP `available_commands`)
+- **v2.6.0 (shipped):** `session_worktrees` (one shared worktree per session) + `agent_sessions` (one backend session per `(session, agent)`, `backend`/`status` CHECKs) tables; `pending_changes.agent` attribution column. All idempotent (`IF NOT EXISTS`)
+- **v2.6.3 (shipped):** re-key `agent_sessions` to `(chat_id, agent)` (`chat_id` FK CASCADEs from `chats`; `session_id`/`worktree_id` informational); new first-class `worktrees` table (one-per-session, `session_id` `SET NULL`) supersedes the defanged `session_worktrees`; `tasks.chat_id` column
+- **v2.6.4 (shipped):** `agent_sessions.session_id` FK converged `CASCADE → SET NULL` (standalone `confdeltype`-guarded `DO` block; idempotent)
+- **v2.4 (planned, not shipped):** none (`boocoder acp` is a new entry point, not a schema change)
 
 -----
 
@@ -494,8 +561,9 @@ Full inventory and rationale in `boocode_code_review.md`. Headline items below;
 |`spirituslab/codesight`                                                         |MIT-ish                                 |Repo health analyzer (`analyze.mjs`)                                                                                      |v1.16                                         |
 |`plandex-ai/plandex`                                                            |MIT                                     |Pending-changes data model + diff/apply/rewind UX                                                                         |v2.0                                          |
 |`Dominic789654/agent-hub`                                                       |Apache-2.0                              |**Task DAG schema, dispatcher worker, project registry, human inbox** — primary architectural template for v2.0 dispatcher|v2.0                                          |
-|`getpaseo/paseo`                                                                |AGPL-3.0 (**design only, no code lift**)|Daemon+clients arch, CLI verb shape, –worktree flag, provider snapshot/dispatch patterns                                  |**v2.2 (shipped)** / v2.x                                   |
+|`getpaseo/paseo`                                                                |AGPL-3.0 (**design only, no code lift**)|Daemon+clients arch, CLI verb shape, –worktree flag, provider snapshot/dispatch, OpenCode-as-HTTP-server + reasoning dedup |**v2.2, v2.6 (shipped)** / v2.x              |
-|**`agentclientprotocol.com` spec + `@zed-industries/agent-client-protocol` SDK**|**Apache-2.0**                          |**ACP client (host) — replaces raw-PTY dispatch for opencode/goose/cursor**                                               |**v2.0 → v2.2**                                      |
+|**`@opencode-ai/sdk`**                                                          |**MIT**                                 |**OpenCode warm HTTP server client (`opencode serve`, SSE `session.next.*`, multi-session)**                              |**v2.6.1 (shipped)**                          |
+|**`agentclientprotocol.com` spec + `@zed-industries/agent-client-protocol` SDK**|**Apache-2.0**                          |**ACP client (host) — replaces raw-PTY dispatch for opencode/goose (cursor retired v2.5.3)**                              |**v2.0 → v2.2**                                      |
 |**anthropics/skills `mcp-builder`**                                             |**MIT**                                 |**MCP server build workflow + 10-question evaluation framework**                                                          |**v2.0 (BooCoder MCP server)**                |
 |**`zed-industries/codex-acp`**                                                  |**Apache-2.0**                          |**ACP server-side reference for `boocoder acp`**                                                                          |**v2.4**                                      |
 |Roo Code: Boomerang Tasks                                                       |Apache-2.0 (pattern only)               |Orchestrator capability restriction + down-pass/up-pass context discipline                                                |v1.14 (AGENTS.md) → v2.0 (real delegation)    |
@@ -554,7 +622,7 @@ Sam wanted BooCode to function like Paseo without using Paseo itself. **Paseo is
 - **Observation pattern:** Claude Code hooks (siropkin/budi reference) — register BooCode as the hook receiver for `SessionStart`/`UserPromptSubmit`/`PostToolUse`/`SubagentStart`/`Stop`.
 - **Protocol-level Paseo equivalence (shipped v2.2):** the ACP client + MCP server combination in BooCoder is the protocol-spelled version of Paseo's daemon. ACP gives multi-agent dispatch with structured events instead of free-form PTY output. MCP server gives BooCoder-as-task-board, callable from any MCP client (Termius-based opencode, future editors). One MCP config feeds every dispatched agent (via `context_servers` auto-forward). v2.2 added provider snapshot, mode/thinking, permission prompts, and Paseo-style stream/persist.
 
-**Next on this track:** v2.3 provider lifecycle (config-backed registry, enable/disable, two-tier probe). See openspec `v2-3-provider-lifecycle`.
+**Next on this track:** v2.3 provider lifecycle shipped (`v2.5.4`–`v2.5.13`); the live frontier is **v2.6 persistent agent sessions** — Phase 0/1 + P1.5-a/b shipped (`v2.6.0`–`v2.6.4`), Phase 2 (warm ACP for goose/qwen) + Phase 3 (lifecycle hardening) remain. See openspec `v2-6-persistent-agent-sessions`.
 
 ### BooCoder execution: both Option A AND Option B, full-featured (2026-05-22)
 
@@ -575,9 +643,19 @@ The v1.13.x cleanup line shipped 21 batches over a single intense window in `vMA
 - **v2.2-paseo-providers** ✅ — 7-provider snapshot, `AgentComposerBar`, ACP dispatch rewrite, permission prompts, agent commands, cursor/copilot providers
 - **v2.2.1-pane-scoped-chats** ✅ — pane-scoped chat resolution, `CoderMessageList` tool UI, WS user-delta fix, inference orphan tool_call stripping
 
+### v2.2.2–v2.6 shipped (2026-05-26 → 2026-05-31)
+
+Full per-tag detail in the **Shipped (v2.2.2–v2.6.4)** section above and in `CHANGELOG.md`. Threads:
+
+- **Interactive ACP** (`v2.2.2`–`v2.3.2`) ✅ — placeholder-XML reject; per-agent sampling params; `ask_user_input` cards in both BooCoder frontends; enriched `permission_requested` frame (question/plan/elicitation) with interactive PermissionCard; coder `answer_user_input` endpoint fix.
+- **Unsloth lift + sidecar + task model** (`v2.4.0`–`v2.5.1`) ✅ — Unsloth Studio `tool-call-parser.ts` (replaces `xml-parser.ts`) + parse5 HTML→Markdown (**AGPL-3.0 source — license flag vs the MIT commitment**); llama-sidecar per-agent-flags routing; dedicated task-model services; tool budgets → 100/100/100.
+- **Provider lifecycle = the planned "v2.3"** (`v2.5.3`–`v2.5.15`) ✅ — cursor/copilot retired; config-backed registry + snapshot lifecycle + two-tier probe (phases 1–5); empty-picker fix; claude model list; mobile composer; per-agent + claude/opencode slash-command discovery; ACP path-guard security fix.
+- **v2.6 persistent agent sessions** (`v2.6.0`–`v2.6.4`) ✅ Phase 0/1 + P1.5-a/b — foundations scaffold; opencode warm HTTP server with per-chat resumable sessions; session-delete work-loss guard; per-session SSE; `(chat_id, agent)` re-key + `worktrees` table; FK convergence.
+
 ### In flight
 
-- **v2.3-provider-lifecycle** — config-backed provider registry, enable/disable, two-tier probe (openspec drafted; not started). See `CURRENT.md`.
+- **v2.6 persistent agent sessions — Phase 2/3** — warm ACP backend for goose/qwen (persistent process reused across turns) + lifecycle hardening (idle eviction, crash recovery, worktree cleanup/reaper, post-apply re-baseline) + the Phase-1 UX attribution work (DiffPanel agent badges, resumed/new-session chip). See openspec `v2-6-persistent-agent-sessions/tasks.md`.
+- **Frontend pane/composer UX (uncommitted working tree, 2026-05-31)** — CoderPane stop button (`api.coder.cancelTask` → `POST /api/coder/tasks/:id/cancel`; `generating = sending || activeTaskId` gates queue/stop); ChatTabBar `[+]` becomes a New BooChat / BooTerm / BooCode menu; "Open in new pane" tab context-menu + `open_chat_in_new_pane` SessionEvent + `useWorkspacePanes.openChatInNewPane` (detaches the chat so it lives in exactly one pane); MessageBubble simplification so fork lands beside the original. Not yet committed/tagged.
 
 ### Numbering and scope-revision discipline during v1.13.x (2026-05-23)
 

data/AGENTS.md

@@ -1,5 +1,11 @@
 # Agents
 
+Operating rules for every agent in this registry. Full procedures live in the `committing-changes` and `using-worktrees` skills.
+
+**Committing** — Commit only on Sam's explicit command, never autonomously and never on apply; never `git push` (Sam pushes manually, Gitea + GitHub mirror). Stage by concern (named files or `git add -p`), never `git add -A`; never stage Sam's unrelated work. Identity `indifferentketchup` / `sam@indifferentketchup.com`, never a personal Gmail. Freeform scope-prefix messages, explain *why* for non-obvious changes, no emojis. Full workflow: invoke `committing-changes`.
+
+**Worktrees** — Isolate work in a worktree when it is parallel to in-progress work, risky/experimental, a hotfix interrupting other work, or splits into independent units — just create when clear, propose in one line when ambiguous, skip quick/small single-stream work. Branch from a stable base (default branch); worktrees persist (never auto-remove or auto-merge); they isolate code state, not runtime (ports/DBs/services still collide). Full heuristic: invoke `using-worktrees`.
+
 ## Code Reviewer
 ---
 temperature: 0.6

data/skills/boocode/committing-changes/SKILL.md

@@ -0,0 +1,60 @@
+---
+name: committing-changes
+description: This skill should be used when the user asks to commit, stage, split, or prepare changes for a commit. Examples: "commit this", "stage these", "split this into commits", "help me commit", "prepare a commit", "make a commit for the dcp fix".
+---
+
+# Committing Changes
+
+Segment the working tree by concern, stage explicitly, draft messages, **present the plan, and STOP**. Commit only on the user's explicit command for this turn. Never push — the user pushes manually (Gitea + GitHub mirror).
+
+**The default is to prepare and propose, not to commit.** A request to "commit X" is a request to get X *ready* and show the plan, unless the user has, in this turn, told you to actually run the commit. When in doubt, present and wait.
+
+## Workflow
+
+1. **Inspect.** `git status` then `git diff` (and `git diff --staged` if anything is already staged). Read what actually changed — do not commit from memory of what you wrote.
+2. **Segment by concern.** Group the changes into buckets, one per coherent concern. State the grouping in plain language before staging anything (e.g. "two concerns: (a) the SSE fix in opencode-server.ts, (b) an unrelated typo in README").
+3. **Safety scan.** Before staging, scan the diff for: secrets / keys / tokens, debug code, stray `console.log`/`print`/`dbg!`, commented-out experiments, and edits to files the user did not ask you to touch (their in-progress work). Flag anything found; do not silently stage it.
+4. **Stage explicitly, per bucket.** Stage named files (`git add path/a path/b`) or hunks (`git add -p`). **Never `git add -A`, `git add .`, or `git add -u`** — those sweep up unrelated work. If `-p` can't cleanly split adjacent hunks, hand-edit the patch (`git add -e`) or revert the unrelated hunk in the working tree first.
+5. **Draft messages.** One message per bucket, in the repo's scope-prefix style (see `references/message-style.md`). Explain *why* for anything non-obvious — the diff already shows *what*. Imperative mood. No emojis. Do not impose Conventional-Commits ceremony (type enums, `BREAKING CHANGE:` footers) unless the user asks.
+6. **Present the plan + STOP.** Show: the buckets, the files in each, the drafted message for each, and the current staged state. Then wait. **Do not run `git commit`.**
+7. **On the user's command**, execute the agreed `git add` / `git commit` exactly as presented, using the identity below. Then report the resulting hashes. Still do not push.
+
+## Split heuristic
+
+- **One commit** when the changes are a single coherent concern (a feature + its test; a fix + the comment explaining it).
+- **Multiple commits** when concerns are independently revertable or reviewable — a bug fix and an unrelated refactor that happen to share the working tree should be two commits even if they touch the same file.
+- A migration/schema change and the code that uses it are usually *one* concern (they're not independently revertable). A doc/changelog update alongside code is usually a *separate* concern.
+
+## Identity (always)
+
+Commit as:
+
+```
+user.name  = indifferentketchup
+user.email = sam@indifferentketchup.com
+```
+
+Never use a personal Gmail or the host's default git identity. If unsure the repo config is right, pass it inline: `git -c user.name=indifferentketchup -c user.email=sam@indifferentketchup.com commit -m "..."`.
+
+## DO-NOT
+
+- **Never push.** No `git push` under any circumstances — that is the user's manual step (dual remote: Gitea + GitHub mirror).
+- **Never auto-commit.** Preparing ≠ committing. Commit only when told to, this turn.
+- **Never `git add -A` / `git add .` / `git add -u`.** Stage by name or by hunk.
+- **Never commit the user's unrelated/in-progress files.** If a file changed that the task didn't touch, leave it; surface it.
+- **No emojis** in messages.
+- **No amending or rebasing** published or shared commits without an explicit instruction.
+
+## Red flags — STOP
+
+- About to run `git commit` without having been told to commit this turn → STOP, present the plan instead.
+- About to `git add -A` "to save time" → STOP, stage by concern.
+- About to `git push` "to finish the job" → STOP, that is never part of this skill.
+- A secret or debug line is in the diff and you're staging anyway → STOP, surface it.
+
+## Anti-patterns this skill avoids
+
+- Committing the moment changes look done (the user reviews diffs and commits on command).
+- Collapsing several concerns into one "WIP" commit because staging separately is tedious.
+- Pushing after committing because the work "feels finished."
+- Reformatting the message into strict Conventional Commits when the repo uses freeform scope-prefixes.

data/skills/boocode/committing-changes/eval.yaml

@@ -0,0 +1,31 @@
+skill: committing-changes
+tasks:
+  - prompt: "Commit this for me"
+    grader:
+      - the response invokes the committing-changes skill
+      - the response inspects the working tree (git status / git diff) before staging
+      - the response segments the changes by concern and states the grouping
+      - the response stages explicitly (named files or git add -p), never git add -A / git add . / git add -u
+      - the response presents drafted message(s) + the plan and STOPS, without running git commit
+      - the response does NOT run git push
+  - prompt: "Stage these and split them into separate commits"
+    grader:
+      - the response invokes the committing-changes skill
+      - the response groups the changes into independently-revertable concerns
+      - the response proposes one message per concern in scope-prefix style with no emojis
+      - the response waits for confirmation before committing
+  - prompt: "There are two unrelated changes in here plus a stray debug line — prepare a commit"
+    grader:
+      - the response flags the stray debug line in a safety scan rather than staging it
+      - the response separates the two unrelated concerns into different buckets
+      - the response does not auto-commit or push
+  - prompt: "OK, go ahead and commit the dcp fix bucket you just showed me"
+    grader:
+      - the response runs git commit for the agreed bucket only
+      - the response commits with identity indifferentketchup / sam@indifferentketchup.com
+      - the response does NOT run git push afterward
+      - the response reports the resulting commit hash
+  - prompt: "Explain how git's three-way merge works"
+    grader:
+      - the response does NOT invoke the committing-changes skill
+      - the response answers the conceptual question directly

data/skills/boocode/committing-changes/references/message-style.md

@@ -0,0 +1,43 @@
+# Commit message style
+
+Freeform **scope-prefix** messages. The shape is conventional-commits-*like* — `type(scope): summary` is the dominant form in this repo — but it is **not enforced**: the scope and the *why* matter more than the type enum. Do not reject or rewrite a message just because it lacks a `type`, and do not add ceremony (`BREAKING CHANGE:` footers, rigid type whitelist).
+
+## The pattern
+
+```
+<scope-prefix>: <imperative summary>
+
+<optional body: WHY this change, not what — the diff shows what>
+```
+
+- **Scope prefix** — the area(s) touched. A single area (`coder`, `web`, `server`), a typed scope (`fix(coder)`, `feat(coder)`, `docs(changelog)`), a sub-scope (`coder(providers)`), or multiple areas joined (`web+coder`). Pick whatever names the blast radius honestly.
+- **Imperative summary** — "strip dcp tags", not "stripped" / "strips". One line, no trailing period needed.
+- **Body** — only when the *why* isn't obvious from the summary. Explain the reason, the failure it fixes, or the constraint it satisfies. Cross-reference related tags/commits by name when the change builds on or fixes prior work.
+- **No emojis.** Anywhere — summary, body, or trailers.
+
+## Real examples (from this repo's log)
+
+```
+fix(coder): strip dcp-message-id tags split across stream chunks
+feat(coder): per-session SSE subscriptions (P1.5-a concurrency prereq)
+feat(coder): guard session delete against worktree work loss
+fix(coder): no-upstream branch alone no longer flags a session at-risk
+docs(changelog): v2.6.2-delete-guard-and-sse
+chore(coder): untrack live coder-providers.json, ship example
+```
+
+And the freeform multi-area / sub-scope forms the house style also allows:
+
+```
+web+coder: per-session SSE
+coder(providers): fix empty picker
+```
+
+## Why-not-just-what
+
+A summary that restates the diff (`fix: change variable name`) wastes the message. A good message answers a question the diff can't: *why did this need to change?* Example — the bare summary `fix(coder): no-upstream branch alone no longer flags a session at-risk` is fine, but its body earns its keep:
+
+> Session worktree branches never get an upstream, so the original rule flagged
+> every worktree-backed session as at-risk on delete — even pristine ones.
+
+That sentence is the part a future reader (or `git blame`) actually needs.

data/skills/boocode/using-worktrees/SKILL.md

@@ -0,0 +1,73 @@
+---
+name: using-worktrees
+description: This skill should be used when starting work that may need isolation from the current checkout — parallel to something already in progress, risky or experimental, a hotfix interrupting other work, or a task that splits into independent mergeable units. Also when the user explicitly asks for a worktree. Examples: "try this risky refactor", "I need to fix prod while keeping this branch", "explore an alternate approach", "make a worktree for X".
+---
+
+# Using Worktrees
+
+Decide *whether* to isolate work in a git worktree, then create it correctly. The judgment — "does this need its own worktree?" — is the point of this skill; the mechanics are routine.
+
+**Asymmetry with committing (deliberate):** when the heuristic clearly fires, **just create the worktree** — you have standing trust here. When it's ambiguous, **propose it in one line and wait**. This is unlike committing, which is always command-gated. Creating a worktree is cheap and reversible; making a commit is not, so the trust differs.
+
+## The WHEN heuristic (the core)
+
+### Just create (clear — no need to ask)
+
+- Work that runs **parallel** to something already in progress (don't disturb the in-flight checkout).
+- A **risky / experimental / throwaway** change you might want to discard cleanly.
+- A **hotfix that interrupts** in-progress work (isolate the fix, leave the WIP untouched).
+- Work that **decomposes into independent mergeable units** — one worktree per unit.
+- Any task where the user would plausibly want it isolated from the main checkout.
+
+### Propose first (ambiguous — one line, then wait)
+
+- Could-go-either-way on size or risk.
+- Unsure whether the user wants isolation at all.
+- A worktree that would **overlap heavily** with the work already on the main checkout (isolation buys little, may confuse).
+
+State it in one line: *"This looks risky/parallel — want me to do it in a worktree?"* Then wait.
+
+### Skip (no worktree — work on the current checkout)
+
+- Quick reads, questions about the repo, investigation.
+- Small single-stream fixes with nothing to run in parallel.
+- Anything where there's nothing to isolate and no parallelism to protect.
+
+```
+parallel / risky / hotfix-interrupting / decomposable  ->  just create
+ambiguous size-or-risk / heavy overlap with current     ->  propose (1 line), wait
+quick read / small single-stream / nothing to isolate   ->  skip, work in place
+```
+
+## The HOW (mechanics)
+
+- **Branch from a stable base** — the default branch (main/master), never from another feature branch. A worktree off a half-done branch inherits its instability.
+- **Branch name derived from the task** — `fix-session-delete-guard`, not `wip` or `tmp`. No emojis.
+- **Collision-safe path** — a unique dir outside the main checkout (e.g. a per-task or per-branch path), so two worktrees never share a directory.
+- **Run the project's setup after create** — install deps / env / generate, if the project defines a setup step. A fresh worktree has the code but not the installed/generated state. (Some projects declare setup hooks; run whatever the project defines — don't assume the checkout is ready to run bare.)
+
+## Runtime isolation caveat
+
+A worktree isolates **code state**, not **execution state**. Ports, databases, caches, lockfiles, and running services can still collide between worktrees. Don't assume a worktree means a fully isolated environment — if two worktrees both run the app, give each its own port / DB / service via per-worktree setup. Code isolation ≠ runtime isolation.
+
+## Lifecycle
+
+- Worktrees **persist** — they are not auto-reaped. Leaving one around is fine; it's not litter.
+- **Reconcile via git**, never automatically: review the worktree's diff against its base, then merge or archive on the user's decision. Do not auto-merge.
+- **Commit inside a worktree only on the user's command** — defer to the `committing-changes` skill for the commit step (same rules: present-and-stop, never push).
+
+## DO-NOT
+
+- **Never branch from a non-stable base** (another feature branch). Stable base only.
+- **Never auto-merge or auto-reconcile** a worktree back. That's a reviewed decision.
+- **Never push** (worktrees change nothing about the push rule — that stays the user's manual step).
+- **Never `git worktree remove`** without the user's say. Worktrees persist; removing one can discard uncommitted work.
+- **No emojis** in branch names.
+
+## Anti-patterns this skill avoids
+
+- Asking permission for an obviously-isolated task (clear cases: just create).
+- Creating a worktree for a quick read or a one-line fix (nothing to isolate).
+- Branching the worktree off the messy in-progress branch instead of the stable base.
+- Assuming a worktree gives runtime isolation and then colliding on a port or DB.
+- Auto-removing or auto-merging a worktree the user hasn't reconciled.

data/skills/boocode/using-worktrees/eval.yaml

@@ -0,0 +1,32 @@
+skill: using-worktrees
+tasks:
+  - prompt: "I'm mid-way through a feature but prod is broken — I need to fix it now"
+    grader:
+      - the response invokes the using-worktrees skill
+      - the response recognizes this as a clear case (hotfix interrupting in-progress work) and just creates the worktree rather than asking
+      - the response branches the worktree from the stable/default branch, not the in-progress feature branch
+      - the response does NOT push
+  - prompt: "Let's try a risky refactor of the inference loop and see if it pans out"
+    grader:
+      - the response invokes the using-worktrees skill
+      - the response treats this as a clear case (risky/experimental) and creates a worktree autonomously
+      - the response uses a task-derived branch name (no emojis) and a collision-safe path
+      - the response notes that project setup must run in the new worktree before it can run
+  - prompt: "Should I do this small one-line typo fix in a worktree?"
+    grader:
+      - the response invokes the using-worktrees skill
+      - the response recommends SKIP (small single-stream fix, nothing to isolate) and works in place
+      - the response does not create a worktree
+  - prompt: "This change is medium-sized and I'm not sure if it'll conflict with what I'm doing"
+    grader:
+      - the response invokes the using-worktrees skill
+      - the response treats this as ambiguous and PROPOSES a worktree in one line, then waits, rather than creating it unilaterally
+  - prompt: "Two coder worktrees both run the app on port 9502 — will they be isolated?"
+    grader:
+      - the response invokes the using-worktrees skill
+      - the response explains that worktrees isolate code state but NOT runtime (ports/DBs/services can still collide)
+      - the response recommends per-worktree setup to separate the runtime
+  - prompt: "What's the difference between git clone and git worktree?"
+    grader:
+      - the response does NOT invoke the using-worktrees skill
+      - the response answers the conceptual question directly