- opencode is now a warm HTTP server (was "planned, unshipped").
- SSE: session.next.* event types + subscribe({directory}) requirement.
- Model strings need llama-swap/ prefix + presence in opencode.json.
- config_hash excludes ephemeral port; session FKs are ON DELETE CASCADE.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Deleting a session with linked session_worktrees or agent_sessions rows
threw a FK violation (500 on DELETE /api/sessions/:id). Both FKs now
ON DELETE CASCADE. Idempotent migration: drops the old constraint and
re-adds with CASCADE only if confdeltype != 'c'.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Two independent fixes:
- opencode-server.ts: stripDcpTags() removes <dcp-message-id>…</dcp-message-id>
tags from text deltas before they reach the frame/DB. Applied to all three
text paths (session.next.text.delta, message.part.delta text field,
handleUpdatedPart text type). Reasoning/tool paths untouched.
- useWorkspacePanes.ts: module-level closedPaneStack (capped at 10) captures
pane kind + chatIds on removePane and removeTab auto-remove. reopenPane()
pops the stack and re-attaches a new pane to the existing chat ids (chats
survive pane close server-side). hasClosedPanes drives conditional render.
- ChatTabBar.tsx: [+] is now instant new-tab (no dropdown); split-pane
dropdown (Columns2 icon) opens Chat/Term/Code in a new pane; reopen button
(RotateCcw icon) appears when closed panes exist.
- Workspace.tsx: pass reopenPane + hasClosedPanes through to ChatTabBar.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
/data/skills/boocode/systematic-debugging/SKILL.md — guided root-cause
debugging methodology (investigate before fixing). Available as
/systematic-debugging in both BooChat and BooCoder slash menus via the
shared /api/skills endpoint.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Two independent UI/UX fixes:
- auto_name.ts: pass the session's own model as fallbackModel to
taskModelCompletion, so chat rename uses whatever model is already
loaded on llama-swap instead of forcing a swap to DEFAULT_MODEL
(which times out at 10s when a different model is active).
- useWorkspacePanes.ts: when the last tab in a pane is closed and
other panes exist, remove the pane entirely instead of leaving an
orphaned empty panel.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Schema, interface, and service scaffold for v2.6 persistent agent sessions.
Nothing in this batch alters runtime behavior.
- schema.sql: add session_worktrees (one shared worktree per session, FK
sessions(id)) and agent_sessions (one backend session per (session, agent),
with backend/status CHECKs); add pending_changes.agent column for DiffPanel
attribution. All three statements idempotent (IF NOT EXISTS).
- services/agent-backend.ts: AgentBackend interface + AgentSessionHandle,
EnsureSessionOpts, PromptCtx, TurnResult, and the normalized transport-agnostic
AgentEvent union (text/reasoning/tool_call/tool_update/commands). Types only.
- services/agent-pool.ts: lazy get-or-create AgentPool keyed by
`${sessionId}:${agent}` + shared `agentPool` singleton. Empty in Phase 0.
- index.ts: widen onClose to await dispatcher.stop() then agentPool.dispose()
(pool empty, so dispose() is inert).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The live config is read AND written by the coder (UI provider toggles PATCH it),
so tracking it churned `git status`. Untrack it (now gitignored under data/*),
add a tracked data/coder-providers.example.json reference, and update the
.gitignore exception + CLAUDE.md/BOOCODER.md docs. Loader already falls back to
{providers:{}} (built-ins only) when the live file is absent. + CHANGELOG v2.5.15.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The ACP fs bridge's worktree guard used an unbounded `startsWith(resolve(
worktreePath))`, so a sibling path sharing the worktree as a string prefix
(`<worktree>-evil/...`) escaped the scope. Since writeWorktreeTextFile hits disk
directly (no pending_changes gate), a confused/buggy ACP agent could write
outside its worktree. Now uses a separator-bounded check matching write_guard.ts
(resolve() + `startsWith(root + sep)` / `=== root`) via a shared resolveInWorktree,
with a regression test (../ traversal + the sibling-prefix bug). Symlink-swap
hardening intentionally skipped — consistent with write_guard's no-realpath
stance; the agent runs with host FS access so this is a containment guard, not a
trust boundary. Flagged by the automated push security review.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds to CLAUDE.md: stale boocoder-restart symptom after build (new routes 404 /
old routes 200); boocode container build: . deploys the working tree, web
dev≠prod until container rebuild; PATCH provider-config replaces override
wholesale (send full override) + coder-providers.json is live config (don't
commit drift); external agents one-shot with no ctx tracking + OpenCode-as-server
is unshipped v2.6; ui/ primitive inventory + button-role=switch / Dialog
fallbacks; mobile Dialog scroll containment. Also backfills uncommitted doc
bullets for the v2.5.7–v2.5.11 coder work. CHANGELOG v2.5.14 entry. Docs only.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Opening the settings pane on mobile set activePaneIdx, but the ?pane= URL-sync
effect snapped it back to the chat pane on the panes change, so the pane never
showed. toggleSettingsPane now returns the new pane id (id generated outside the
updater, strict-mode safe); Session's toggleSettingsAndSync pushes ?pane=<id> on
mobile when opening (and drops it on close) so the sync effect keeps it active —
mirrors the existing addPaneAndSwitch pattern. Desktop unaffected.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
v2.3 Phase 5. Provider management lives in Settings → Providers: lists every
registered provider with a status badge, enable/disable toggle (sends the full
override so a custom ACP entry's command survives the wholesale-replace PATCH),
per-provider refresh, and a plaintext diagnostic. The composer provider picker
now filters to enabled && (status==='ready' || 'loading') — disabled/unavailable
providers leave the picker and are managed only in settings; native boocode
always shows. Adds a curated ACP catalog + AddProviderModal (PATCH config then
subset refresh; the modal caps to the viewport with a single overscroll-contain
scroll region). Loading state uses a capped client poll (no WS frame).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
GET/PATCH /api/providers/config, subset POST /refresh, and
GET /api/providers/:id/diagnostic (JSON { diagnostic }, §6.4). PATCH order
is validate→save→reload→clear; a malformed body or invalid merged config
returns 422 without writing, and a save failure returns 500 without
reloading (no file/registry divergence). Web client + types extended.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
claude is PTY (no ACP discovery), so claude-command-discovery.ts reads its enabled set from disk (user-global): ~/.claude/commands/*.md + every enabled plugin's skills/<name>/SKILL.md (kind=skill) and commands/*.md (kind=command), from ~/.claude/settings.json:enabledPlugins + installed_plugins.json install paths, frontmatter-parsed, bare names, deduped. The snapshot claude branch discovers these live (snapshot cache rate-limits the reads). The coder / menu now shows up to three icon'd groups: <agent> commands (Terminal), <agent> skills (Puzzle), BooCoder skills (Sparkles) via a new optional icon on SlashCommandGroup. AgentCommand gains a kind field in both coder + web copies (parity test enforces); mergeCommandsByName made generic to preserve it. Invocation unchanged (literal /name -> claude). Project-local plugins deferred. BooChat unaffected.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The cold ACP probe captured available_commands but read probedCommands synchronously right after newSession, racing opencode's async available_commands_update notification -> captured nothing, only the static manifest showed. The probe now waits (poll <=3s + 300ms settle) for the notification. Captured commands persist to a new available_agents.commands column and are served (merged with the manifest) on the tier-2-skip path, so the agent's discovered commands survive once models are warm and show without a dispatch. Boot warms via the force:true startup snapshot. Caveat: relies on opencode emitting available_commands_update on session creation, not only post-prompt.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Coder / menu now shows two groups: the active agent's commands first (manifest + live ACP available_commands), BooCoder skills second. SlashCommandPicker gains an opt-in groups prop (flat items path unchanged -> BooChat byte-identical, parity verified); ChatInput takes slashGroups; CoderPane builds the groups. Skills run under the selected agent: coder skill_invoke accepts a provider and, when external, injects the server-side skill body into a dispatched task instead of native inference. Also folds in the initial-chat skill fix (handleLandingSkill: create chat -> assign to pane -> invoke, same transition as a text send) that resolves the landing-page blank screen. BooChat slash menu + skill invocation unchanged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The AgentComposerBar refresh button wrapped to a second line on mobile: the status dot had ml-auto (pinned to the far-right edge) and the refresh button followed it in DOM order, overflowing past the edge. Group the dot + refresh into one right-aligned (ml-auto) unit so the refresh stays on the top line. Also add an iconOnly option to CompactPicker and render the Mode (permission) picker icon-only on mobile (shield + chevron, no label; aria-label/title + tap-to-open list still convey the selection) to free row width. Desktop unchanged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Fix: getProviderSnapshot returned synchronous installed:false 'loading' entries on a cache miss (v2.5.5/Phase 2), which AgentComposerBar filters out — with the Phase 5 client poll not yet built, a single fetch stranded on 'loading' and the picker showed no providers. It now awaits the build and returns terminal entries; the sync loading-return is deferred until Phase 5. Builds stay fast via the tier-2 cold-probe skip.
Feature: wire the v2.3 config schema's models/additionalModels — buildResolvedRegistry carries them onto ResolvedProviderDef (models replace, additionalModels merge) and provider-snapshot applies them to every ready model list, so /data/coder-providers.json can edit any provider's models with no code change. Claude staticModels bumped from the stale 2-entry list to opus/sonnet/haiku latest-aliases + pinned claude-opus-4-8 / claude-sonnet-4-6 / claude-haiku-4-5-20251001 (passed verbatim to claude --model). +2 tests (109 total).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
ACP dispatch now spawns from the resolved registry's launch spec instead of a hardcoded per-name switch. acp-spawn.ts gains resolveLaunchSpec(resolved, installPath): launchCommand (config override / custom-ACP command) wins, else the kept resolveAcpSpawnArgs switch is the built-in fallback. acp-dispatch.ts spawns spec.binary/spec.args with env { ...process.env, ...spec.env }; dispatcher.ts loads the resolved def by task.agent and passes it through. Config-defined custom ACP providers dispatch with no new switch case. Built-in dispatch (opencode/goose/qwen) is byte-identical to pre-v2.3 — proven by a regression test (opencode->['acp'], goose->['acp'], qwen->['--acp'], binary=installPath ?? id, empty env -> plain process.env). Deliberate deviation from design's !installPath->null: the installPath ?? id fallback is preserved. setSessionMode/permission/streaming and the dispatcher poll/NOTIFY/running-guard untouched. 7 new acp-spawn.test.ts cases. No routes/UI (Phase 4+).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
provider-snapshot no longer returns null for uninstalled/disabled providers: it emits one entry per registered provider with a lifecycle status (loading|ready|unavailable|error), an enabled flag, and a two-tier probe. Tier-1 is a fast which-style check (command-availability.ts, execFile/no-shell); tier-2 (cold ACP probe) is skipped unless forced, last_probed_at is older than PROVIDER_PROBE_TTL_MS (24h), or DB models are empty — the snapshot-latency win. Cache miss returns status:'loading' synchronously while the build settles via the existing inflight promise. ProviderSnapshotStatus/Entry regain loading/unavailable + gain enabled/description?/fetchedAt? in both coder and web copies, guarded by a runtime parity test (provider-types-parity.test.ts; compile-time cross-project check was blocked by TS6307). Also tracks the data/coder-providers.json seed via a .gitignore exception, completing the Phase 1 config file. No dispatch/route/UI changes (Phase 3+); AgentComposerBar filtering unchanged. 13 snapshot tests (+6) + 6 parity tests.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adds a config layer merged over the hardcoded built-ins (tasks 1.1-1.6): CODER_PROVIDERS_PATH env (default /data/coder-providers.json); provider-config.ts (Zod schema + never-throw loader — missing/invalid file falls back to built-ins only — + save); provider-config-registry.ts (ResolvedProviderDef + buildResolvedRegistry merge: override built-ins, add custom extends:'acp' entries, boocode always enabled + singleton); agent-probe now iterates the resolved registry, probes custom-ACP command[0] via execFile (no shell), skips disabled providers (keeps the row), reads enabled from memory only (no DB column). No snapshot/dispatch/route/UI changes (Phase 2+). 6 new unit tests; empty config provably yields exactly the built-ins.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Checkpoint of in-progress backend work present in the tree, not authored this session: auto_name, inference tool-phase/turn, secret_guard, provider-registry, plus a new agent-allowlist test (7 tests, passing).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Bundles in-progress working-tree UI work not authored this session (CoderPane ChatInput migration, AgentComposerBar/CoderMessageList/tab-bar/sidebar/pane refinements, provider icons) with this session's changes to the same files: MessageBubble renders a collapsible 'Thinking' block from reasoning_text/reasoning_parts (surfacing ACP agent_thought_chunk + native reasoning), and the DiffPanel approve/reject calls are repointed to the real /api/coder/pending/:id/apply and /reject routes (the old /sessions/:id/pending/:id/approve|reject paths did not exist).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
POST /api/sessions/:sessionId/pending/create queues a pending_changes create via queueCreate (WriteGuardError -> 422 with the guard message). RightRail gains a 'New file from pasted text' modal (path + content) wired through api.coder.createPendingFile; sessionId is threaded down from App.tsx. The staged change shows in the CoderPane DiffPanel for explicit apply.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
useViewport re-syncs the snapshot on pageshow/visibilitychange/resize/orientationchange — iOS reported a stale width on backgrounded-tab restore, leaving isMobile=false so the sidebar rendered as a permanent column with no close affordance. flattenToMessage now inserts pasted-text chips verbatim instead of wrapping them in a triple-backtick fence.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
AFTER INSERT trigger on tasks fires pg_notify('tasks_new'); the dispatcher listens via porsager sql.listen and triggers an immediate poll, with the setInterval poll kept at 2s as a missed-notification safety net. Per-session guard unchanged (no double-dispatch).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Budget defaults raised from 50/10/50 to 100/100/100 (read-only,
non-read-only, no-agent). Per-agent max_tool_calls from AGENTS.md
still overrides.
Added .claude/worktrees/ to .codecontextignore to prevent
get_codebase_overview from parsing empty stub files in stale
worktree node_modules.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Task model infrastructure for cheap LLM calls (auto-naming, search
rewrite, tags, summaries) via a dedicated llama-server instance at
TASK_MODEL_URL, falling back to LLAMA_SWAP_URL with FAST_MODEL when
unset. Replaces the inline fetch in auto_name.ts with taskModelCompletion.
Adds search query rewriting: on step 0 when web tools are enabled, the
user's message is summarized into a search intent hint appended to the
system prompt, improving web_search relevance.
Schema: tasks table for provider dispatch and arena, sessions.tags column.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Batch 3c: when an agent has llama_extra_args in AGENTS.md, provider.ts
routes inference through LLAMA_SIDECAR_URL instead of LLAMA_SWAP_URL.
X-Agent-Flags header built from the agent's flags. Boot-time guard
refuses to start if any agent has llama_extra_args but LLAMA_SIDECAR_URL
is unset. PrefixFingerprint gains a route field (swap/sidecar) for
per-turn visibility. 9 provider tests.
AGENTS.md tool gap: all agents (except Prompt Builder) were missing 8
tools that were added after the original tool lists were written:
request_read_access, view_truncated_output, ask_user_input, git_status,
get_blast_radius, get_hot_files, get_middleware, get_routes. The missing
request_read_access caused silent "permission denied" when reading files
outside the project root.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The CoderPane runs its own inference runner and broker on the boocoder
service. The AskUserInputCard was calling /api/chats/:id/answer_user_input
on the main BooChat server, which has a different inference runner — the
answer was accepted but the next turn was enqueued on the wrong runner,
so nothing happened.
Fix: register the same answer_user_input endpoint on the boocoder, and
add an apiPrefix prop to AskUserInputCard so the CoderPane routes
through /api/coder/chats/:id/answer_user_input. BooChat's MessageList
continues to use the default (no prefix) path.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The permission_requested WS frame now carries kind ('tool'|'question'|'plan'|
'elicitation'), input (the tool's rawInput payload), and description fields.
PermissionCard detects question-type permissions (Claude Code's AskUserQuestion)
and renders an interactive radio/checkbox form instead of approve/deny buttons.
Submitting answers auto-selects the first allow option.
Also wires up ACP createElicitation (unstable/experimental) — JSON Schema-driven
forms for structured user input. The same PermissionCard renders elicitation
fields with type-appropriate inputs. Both flows use the existing permission-waiter
blocking pattern with 120s timeout.
The response path (POST /api/coder/tasks/:id/permission) now accepts optional
updated_input alongside option_id, forwarded to the ACP agent as the user's
answer payload. Elicitation responses map to accept/decline/cancel actions.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add top_p/top_k/min_p/presence_penalty to AGENTS.md frontmatter and thread
through inference (agents.ts parser → Agent type → stream-phase → sentinel
summaries). Null means omit from request body, preserving provider defaults.
Wire ask_user_input interactive card into both BooCoder frontends: the
CoderPane in BooChat's SPA (CoderMessageList now renders AskUserInputCard
instead of ToolCallLine for ask_user_input tool calls) and the standalone
coder SPA (MessageBubble + new AskUserInputCard + shadcn ui primitives).
Additional fixes: SessionLandingPage uses ChatInput with slash-command
support and lazy chat creation; Session.tsx hydrate-race fix for empty pane
promotion; AgentPicker wider dropdown with line-clamp; ModelPicker min-width;
Textarea converted to forwardRef; Recon agent added to AGENTS.md; codecontext
host port exposed in docker-compose.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Reject qwen3.6 spurious <invoke> tails with path "..." or empty args before
they enter toolCalls, preventing duplicate assistant answers. Dropped blocks
append to flushed text; four new xml-parser tests. DEFERRED-WORK §6 for
console.debug → pino cleanup.
Co-authored-by: Cursor <cursoragent@cursor.com>
Mark v2.2/v2.2.1 shipped and v2.3 planned in roadmap and README; fix
DEFERRED-WORK §2 (ACP probe skip is planned, not resolved).
Co-authored-by: Cursor <cursoragent@cursor.com>
- BooCoder moves from Docker to host systemd service (boocoder.service)
- Agent dispatch (ACP + PTY) switches from SSH to direct spawn/exec
- SSH helpers marked @deprecated (kept for one release cycle)
- Provider registry (5 providers: boocode, opencode, goose, claude, qwen)
- Agent probe with direct which/exec + model discovery (qwen settings, static claude models)
- GET /api/providers route with installed status, models, transport fallback
- ProviderPicker frontend component in CoderPane header
- External provider messages route through tasks row instead of inference enqueue
- Smart scroll: MessageList only auto-scrolls when near bottom (150px threshold)
- DB: available_agents gets models, label, transport columns
- Bug fix: loadContext SELECT includes allowed_read_paths
- Bug fix: cap hit sentinel inserted before buildMessagesPayload
- docker-compose.yml: boocoder service commented out, BOOCODER_URL env var added
- CLAUDE.md: updated docs for systemd, provider registry, JSONB gotcha, loadContext
Source-level recon of QwenLM/qwen-code (Apache-2.0) informed 4 lifts:
1. FAST_MODEL config: optional env var routes cheap LLM calls (titles,
summaries, labeling) to a smaller model on llama-swap. auto_name.ts
uses ctx.config.FAST_MODEL ?? session.model. Set FAST_MODEL=nemotron-
nano-4b to avoid loading the 35B model for 20-token title generation.
2. Tool-use summaries (services/inference/tool-summaries.ts): utility
that generates "git-commit-subject-style" labels for tool batches via
a fast-model LLM call. System prompt + truncation logic ported from
Qwen Code's toolUseSummary.ts. Exported via @boocode/server/inference
for BooCoder's dispatcher to call after task completion.
3. Qwen as dispatchable agent: added to agent-probe.ts KNOWN_AGENTS.
PTY dispatch builds: qwen -p "<task>" --output-format stream-json
(NDJSON structured events over stdout). Env: OPENAI_BASE_URL +
OPENAI_API_KEY points Qwen Code at llama-swap. execution_path CHECK
constraint extended with 'qwen'.
4. Arena routes (routes/arena.ts): POST /api/arena dispatches the same
task to N contestants (2-5, each with different agent/model), each
getting its own task row linked by arena_id UUID. GET /api/arena/:id
shows all contestants. POST /api/arena/:id/select/:task_id marks
winner. Schema: arena_id column added to tasks.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Phase 8 of v2.0. Final hardening pass before production tag.
Path-guard fuzz suite (34 tests): traversal attacks (../ all depths,
encoded %2e%2e, null bytes, absolute escapes, prefix-without-separator,
backslash), secret-file deny list (.env, *.pem, id_rsa*, *.key,
credentials.json, *.kdbx, .netrc), valid-path positives, edge cases
(empty, whitespace, very long, triple-dot, multiple slashes).
write_guard.ts hardened: added null-byte rejection and whitespace-only
rejection (previously only checked empty string).
Pending-changes integration test skeleton: 4 tests covering the full
queue→apply→rewind cycle against a real DB + filesystem. Gated on
DATABASE_URL via describe.runIf (same pattern as apps/server's
tool_cost_stats.test.ts). Skips cleanly when unset.
57 tests passing (23 existing + 34 fuzz), 4 integration skipped.
All builds clean. All services healthy.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Phase 7 of v2.0. BooCoder gains a terminal-driven UX and subagent
isolation primitive.
CLI (src/cli.ts): standalone entry point for terminal use.
- boocode run "task" [--agent x] [--model y] — create + stream output
- boocode ls [--state x] — formatted task table
- boocode attach <id> — WS stream of running task
- boocode send <id> "msg" — follow-up message to task session
Connects to BOOCODER_URL (default http://100.114.205.53:9502).
Human inbox (routes/inbox.ts): GET /api/inbox (failed/blocked tasks),
POST /api/inbox/:id/retry (reset to pending for re-dispatch).
Cost tracking: dispatcher aggregates tokens_used from all messages in
the task's session after completion, stores in tasks.cost_tokens.
GET /api/stats/costs?group_by=project|agent|day for aggregation.
Boomerang subagent isolation (3 new tools):
- new_task: creates child task with parent_task_id linkage, runs in
fresh isolated session. Orchestrator sees only output_summary.
- list_tasks: query child tasks of current parent
- check_task_status: read task state + output_summary
The orchestrator pattern: an agent with tools: [new_task, list_tasks,
check_task_status] can ONLY dispatch — can't read files or MCP. This
is the Roo Code Boomerang Tasks capability-restriction principle.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
