brainclaw 1.5.4 → 1.6.0

package/docs/concepts/dispatch-lifecycle.md

@@ -0,0 +1,228 @@
+# Dispatch lifecycle
+
+When brainclaw routes work to another agent — `bclaw_coordinate(intent="assign"|"review"|"consult")`, `bclaw_dispatch(intent="execute")`, or a multi-turn `bclaw_loop` — it spins up **up to six related entities** plus an on-disk **brief-ack sentinel** and (since pln#504) **per-assignment stdout/stderr log files**. Knowing what each one means lets you tell at a glance whether a dispatch is alive, dead, or merely slow.
+
+This doc is the consolidated reference. It complements:
+- [multi-agent-workflows.md](multi-agent-workflows.md) — happy-path coordination patterns
+- [troubleshooting.md](troubleshooting.md) — symptom-driven diagnostic playbooks
+- [loop-engine.md](loop-engine.md) — multi-turn loop protocol details
+- [../integrations/codex.md](../integrations/codex.md), [../integrations/claude-code.md](../integrations/claude-code.md), etc. — per-agent spawn semantics
+
+---
+
+## The six entities
+
+A single `bclaw_coordinate(intent="review", open_loop=true, targetAgents=[codex])` creates:
+
+```
+                         ┌─────────────────┐
+                         │   candidate     │  cnd_…  (review payload)
+                         └────────┬────────┘
+                                  │ references
+              ┌───────────────────┼──────────────────┐
+              ▼                   ▼                  ▼
+        ┌──────────┐       ┌─────────────┐    ┌──────────┐
+        │   loop   │ ◄────►│ assignment  │    │ message  │
+        │  lop_…   │       │  asgn_…     │    │  msg_…   │
+        └──────────┘       └──────┬──────┘    └──────────┘
+                                  │
+                                  │ owned-by
+                                  ▼
+                           ┌──────────────┐
+                           │    claim     │  clm_…  (worktree lock)
+                           └──────┬───────┘
+                                  │ triggers
+                                  ▼
+                           ┌──────────────┐
+                           │  agent_run   │  run_…  (the OS-level spawn)
+                           └──────┬───────┘
+                                  │
+              ┌───────────────────┼─────────────────┐
+              ▼                   ▼                 ▼
+        ┌──────────┐       ┌─────────────┐   ┌────────────┐
+        │ ack file │       │ stdout log  │   │ stderr log │
+        │ .ack     │       │ .stdout.log │   │ .stderr.log│
+        └──────────┘       └─────────────┘   └────────────┘
+        (pln#476)          (pln#504)         (pln#504)
+```
+
+| Entity | Prefix | Created by | Owner | Purpose |
+|---|---|---|---|---|
+| `candidate` | `cnd_` | the coordinate facade (review/ideate) | the dispatcher agent | Review payload that the loop references. Stays after the loop closes. |
+| `loop` | `lop_` | `bclaw_coordinate(open_loop=true)` or `bclaw_loop(intent="open")` | the dispatcher | Multi-turn thread of structured work. Has its own FSM. |
+| `assignment` | `asgn_` | dispatcher when targeting an agent | the **target** agent | Lifecycle event for that agent's turn. The only entity whose FSM tracks the WORKER's progress. |
+| `message` | `msg_` | dispatcher | the dispatcher | The brief delivered to the target's inbox. |
+| `claim` | `clm_` | dispatcher (or `bclaw_claim` directly) | the target agent | Worktree advisory lock. Released when the work is done or the agent gives up. |
+| `agent_run` | `run_` | the CLI execution adapter, only when an OS-level spawn actually happens | the target agent | OS-level subprocess record. Status FSM tracks the LIFETIME of the process — but only the parts brainclaw can observe (see [§Liveness limits](#liveness-limits) below). |
+
+Plus two filesystem-only artefacts created by the worker shell wrapper:
+
+- **Brief-ack sentinel**: `.brainclaw/coordination/runtime/ack/<assignment_id>.ack` — touched by the spawn wrapper BEFORE the agent binary runs (pln#476). Proves the spawn shell got far enough to execute `touch`. Does NOT prove the agent binary itself succeeded.
+- **stdout/stderr logs** (pln#504): `.brainclaw/coordination/runtime/log/<assignment_id>.{stdout,stderr}.log` — opened by the parent before the spawn, the child inherits dup'd fds and writes its streams there. This is the only window onto what a sandboxed worker actually said before dying.
+
+---
+
+## FSM cheatsheet
+
+### `loop.status`
+
+```
+open ──▶ paused ──▶ open       (pause / resume)
+  │
+  ├──▶ completed                (stop_condition met)
+  ├──▶ cancelled                (manual close — use when the loop dies abnormally)
+  └──▶ blocked                  (external blocker; intent to resume later)
+```
+
+`bclaw_loop(intent="close")` accepts **only** `completed | cancelled | blocked` as `status`. **Not `failed`** — map crashed/dead loops to `cancelled` with a `reason`.
+
+### `assignment.status`
+
+```
+created ──▶ offered ──▶ accepted ──▶ started ──▶ completed
+   │            │            │            │           
+   │            │            │            └──▶ failed (worker self-reported)
+   │            │            │            └──▶ blocked (worker needs supervisor)
+   │            │            │            └──▶ cancelled (rerouted away)
+   │            │            └──▶ acceptance_ttl expired (default 15min) → cancelled
+   │            └──▶ heartbeat_ttl expired (default 30min while running) → cancelled
+   └──▶ removed by `bclaw_assignment_admin` (rare)
+```
+
+Transitions past `offered` require the assigned agent itself (or `bclaw_assignment_admin`). A coordinator that didn't create the assignment **cannot** update it — `Agent X cannot update assignment owned by Y` is the canonical rejection.
+
+### `agent_run.status`
+
+```
+launching ──▶ running ──▶ completed
+                  │           ──▶ failed (non-zero exit, worker reported)
+                  │           ──▶ interrupted (TTL/heartbeat expiry, see below)
+                  │
+                  └──▶ failed (spawn returned no pid, brief-ack timeout)
+```
+
+**Liveness limits** {#liveness-limits}: `last_event_at` is bumped only when the worker writes a lifecycle event (via MCP or via the wrap shell). A worker that crashes before its first output keeps `status=running` and `last_event_at == launched_at` until reconciled. Since pln#503 phase 3.2, **any read of `agent_run` via `bclaw_find` / `bclaw_get` triggers a lazy reconciliation pass**: open runs past the 60s grace window get their pid checked, and dead workers transition to `failed` (`status_reason='silent_termination_no_evidence'`) once past the 30min stale threshold.
+
+For a single consolidated check (run + assignment + claim + loop + pid + log tails + verdict in one response), use **`bclaw_dispatch_status(target_id)`** (pln#503 phase 3.1).
+
+### `claim.status`
+
+```
+active ──▶ released
+   │
+   └──▶ adopted (another session inherited the claim, e.g. reconnect)
+```
+
+Releasing a claim does NOT cancel its assignment / agent_run / loop — those are independent entities. You generally need to clean up all of them together when aborting a dispatch.
+
+---
+
+## Observability decision tree
+
+You called `bclaw_coordinate(intent="review", open_loop=true, …)` and got back `execution_status: "delivered_and_started"`. What does that actually mean?
+
+**Fast path** (recommended since pln#503 phase 3.1): call `bclaw_dispatch_status(target_id="<asgn_…>")` and read its `diagnosis.health` + `diagnosis.recommended_next_action`. The tool consolidates the steps below into a single response — entity fan-out, pid liveness, log tails, verdict, recommended next action.
+
+**Long path** (for understanding or when the tool isn't available):
+
+```
+1. execution_status = "delivered_and_started"
+   ├──▶ Means: the spawn wrapper touched the brief-ack sentinel
+   └──▶ Does NOT mean: the worker is doing useful work
+
+2. Verify the spawn is alive — check the agent_run record
+   bclaw_find(entity="agent_run", filter={assignment_id: "<asgn>"})
+   ├──▶ status="running" AND pid alive on OS AND last_event_at < 5min ago → healthy
+   ├──▶ status="running" AND pid alive AND last_event_at == launched_at → stalled (worker never produced output)
+   ├──▶ status="running" AND pid dead → silently died (see logs)
+   └──▶ status="completed" / "failed" / "interrupted" → terminal, read status_reason
+
+3. If silent, read the logs (pln#504)
+   cat .brainclaw/coordination/runtime/log/<asgn>.stderr.log
+   cat .brainclaw/coordination/runtime/log/<asgn>.stdout.log
+   ├──▶ Contains an error → root cause found
+   └──▶ Empty → worker died before any write OR launched without log capture (legacy path)
+
+4. If the worker is alive but doing nothing useful for 15+ min
+   → most likely sandbox / MCP / capability mismatch with the brief
+   → see ../integrations/<agent>.md "Caveats" for per-agent gotchas
+```
+
+---
+
+## Diagnostic playbook
+
+When a dispatch hangs, work top-down through these checks. For the symptom-driven variant see [troubleshooting.md#inbox-messages-stuck--brief-ack-never-arrived](troubleshooting.md#inbox-messages-stuck--brief-ack-never-arrived).
+
+### Quick triage (≤5s)
+
+```bash
+# Single call covers process liveness + ack + log tails + entity state + verdict
+bclaw_dispatch_status(target_id="<asgn>")        # or clm_/lop_/run_
+```
+
+Read `diagnosis.health` (`healthy` | `stalled` | `silent_death` | `terminal` | `not_dispatched` | `unknown`) and `diagnosis.recommended_next_action` — usually that's all you need.
+
+### Manual triage (≤30s — when `bclaw_dispatch_status` isn't available)
+
+```bash
+# 1. Is the OS-level process alive?
+Get-Process -Id <pid>          # Windows
+ps -p <pid>                    # POSIX
+
+# 2. Did the spawn wrapper actually run?
+ls .brainclaw/coordination/runtime/ack/<asgn>.ack
+
+# 3. What did the worker say? (pln#504)
+cat .brainclaw/coordination/runtime/log/<asgn>.stderr.log
+cat .brainclaw/coordination/runtime/log/<asgn>.stdout.log
+```
+
+### Deeper (1-5min)
+
+```bash
+# Full entity state — same fan-out bclaw_dispatch_status does for you
+bclaw_get(entity="assignment", id="<asgn>")     # owner, ttls, status_reason
+bclaw_get(entity="agent_run", id="<run>")       # pid, started_at, last_event_at
+bclaw_get(entity="claim", id="<clm>")           # worktree, agent
+bclaw_get(entity="loop", id="<lop>")            # current_phase, slot states
+
+# Worktree activity
+git -C <worktree> log --oneline -5              # any new commits?
+git -C <worktree> status                        # uncommitted work?
+ls <worktree>/REVIEW_FINDINGS.md                # for review loops
+```
+
+### Abort a dispatch cleanly
+
+A dead dispatch needs four cleanup steps (no single facade does all of them today):
+
+```text
+1. Stop-Process -Id <pid>                                   # if pid still alive
+2. bclaw_loop(intent="close", loop_id="<lop>", status="cancelled", reason="...")
+3. bclaw_release_claim(id="<clm>")
+4. (optional) bclaw_assignment_admin or leave assignment as `offered`
+   — only the owning agent can transition assignment.status, and a
+     released claim already makes it effectively orphan
+```
+
+---
+
+## Per-agent spawn semantics
+
+Spawn behaviour varies by agent. The capability profile in `src/core/agent-capability.ts` describes each agent's prompt delivery, sandbox model, and MCP availability. Per-agent caveats:
+
+- [codex.md](../integrations/codex.md#caveats) — `--sandbox workspace-write` required; spawned codex may not have brainclaw MCP wired; stdin_pipe prompt delivery; brief-ack required for headless dispatch detection.
+- [claude-code.md](../integrations/claude-code.md) — interactive vs `-p` headless modes; tools whitelist.
+- [copilot.md](../integrations/copilot.md), [windsurf.md](../integrations/windsurf.md), [cline.md](../integrations/cline.md), [opencode.md](../integrations/opencode.md), [roo.md](../integrations/roo.md), [kilocode.md](../integrations/kilocode.md), [continue.md](../integrations/continue.md) — per-agent specifics.
+- [mistral-vibe.md](../integrations/mistral-vibe.md) — EU/GDPR self-hosted option.
+
+---
+
+## See also
+
+- [troubleshooting.md](troubleshooting.md) — symptom-driven diagnostic playbooks
+- [loop-engine.md](loop-engine.md) — multi-turn loop protocol, locks, advance gates
+- [multi-agent-workflows.md](multi-agent-workflows.md) — high-level coordination scenarios
+- [../integrations/overview.md](../integrations/overview.md) — index of supported agents
+- [../integrations/mcp.md](../integrations/mcp.md) — full MCP tool catalog

package/docs/concepts/loop-engine.md

@@ -163,6 +163,60 @@ interface LoopConflictRecord {
 }
 ```
 
+## Artifact body shapes
+
+`LoopArtifact.body` has two known shape categories. Ref-based bodies keep large
+content out of the loop thread JSON and store only file metadata in `body`.
+Inline bodies keep the whole structured payload in `body` for small artifacts
+such as operator questions and answers.
+
+Ref-based bodies are JSON encoded as `RefBasedArtifactBody`:
+
+- `ref`: string filename within the loop's `artifacts/` directory.
+- `byte_count`: exact byte length of the referenced file at attach time.
+- `sha256`: lowercase hex SHA-256 digest of the referenced file content.
+
+The referenced file lives at
+`.brainclaw/loops/threads/<loop_id>/artifacts/<ref>`. The champion or driver
+code that calls `complete_turn` / `add_artifact` is responsible for writing the
+file before or during the attach call, then attaching only
+`JSON.stringify({ ref, byte_count, sha256 })` as the artifact body.
+
+These artifact types use the ref-based shape:
+
+- `signals_report`: structured discovery or bootstrap signals, often larger
+  than the inline body cap.
+- `project_md_draft`: draft `PROJECT.md` content prepared by a loop slot.
+- `project_md_final`: final `PROJECT.md` content accepted by the loop.
+- `file_diff`: unified diff or patch content produced for review or apply.
+
+Typical attach flow:
+
+```ts
+const body = '<content>';
+const ref = `<artifact-id>.<ext>`;
+const artifactsDir = path.join(memoryDir(cwd), 'loops', 'threads', loopId, 'artifacts');
+fs.mkdirSync(artifactsDir, { recursive: true });
+fs.writeFileSync(path.join(artifactsDir, ref), body, 'utf8');
+const byte_count = Buffer.byteLength(body, 'utf8');
+const sha256 = crypto.createHash('sha256').update(body, 'utf8').digest('hex');
+complete_turn(
+  {
+    ...,
+    artifact: {
+      phase,
+      type,
+      body: JSON.stringify({ ref, byte_count, sha256 }),
+    },
+  },
+  cwd,
+);
+```
+
+`RefBasedArtifactBodySchema` in `src/core/loops/types.ts` is the authoritative
+validator for this metadata shape. `KNOWN_ARTIFACT_BODY_SCHEMAS` in the same
+file lists which artifact types are ref-based and which use inline JSON bodies.
+
 ## Lifecycle verbs
 
 The engine exposes four active verbs. Each one mutates state, appends an event, and returns the updated `LoopThread`. **All verbs are strictly synchronous-on-state and asynchronous-on-work**: any downstream dispatch (spawning a CLI, calling another MCP tool) is fire-and-forget from the commit window, so the per-loop lock is always released quickly.
@@ -450,6 +504,7 @@ Status after Codex schema review (cnd#574 / `dec_be66ccbf`, verdict `needs_revis
 
 - [plans-and-claims.md](plans-and-claims.md)
 - [coordination.md](coordination.md)
+- [dispatch-lifecycle.md](dispatch-lifecycle.md) — entity FSMs (loop / assignment / agent_run / claim), brief-ack semantics, log-file diagnostic playbook
 - [runtime-notes.md](runtime-notes.md)
 - pln#394 `feat/loop-engine-mvp`
 - pln#395 `feat/review-loop-protocol`

package/docs/concepts/multi-agent-workflows.md

@@ -1,166 +1,167 @@
-# Multi-Agent Workflows
-
-brainclaw is built around a small set of memory primitives — **plans**, **claims**, **handoffs**, **decisions**, **traps**, and **runtime notes** — that work the same way whether you're orchestrating multiple agents in parallel right now or letting the next agent (or the next you) pick up the work next week.
-
-This doc walks through four concrete scenarios. Pick the one that matches what you're doing.
-
----
-
-## 1. Active orchestration — parallel work across agent instances
-
-**Scenario** — you have a sequence of independent lanes and want several agents (same agent, different instances, or several different agents) to work on them in parallel.
-
-**Walkthrough**:
-
-1. Capture the work as plans, then group them into a sequence with explicit lane labels and dependencies:
-
-   ```text
-   bclaw_create(entity="plan", data={ text: "Refactor auth module", … })
-   bclaw_create(entity="plan", data={ text: "Add e2e tests", … })
-
-   # Then, via CLI or a follow-up call:
-   brainclaw sequence create "auth-refactor-cycle" --items '[
-     {"planId":"pln_aaa","rank":1,"lane":"refactor"},
-     {"planId":"pln_bbb","rank":2,"lane":"tests","hard_after":["pln_aaa"]}
-   ]' --status active
-   ```
-
-2. Dispatch the sequence — the dispatcher picks up the ready lanes (no `hard_after` blocking), creates one claim + worktree per lane, and routes inbox messages by `claim_id`:
-
-   ```text
-   bclaw_dispatch(intent="execute", agents=[<your agents>])
-   ```
-
-3. Each spawned worker runs in its own worktree (so concurrent edits don't collide), reads its inbox, and progresses the plan. Coordinator polls `bclaw_context(kind="board")` to follow progress.
-
-4. As each lane lands a commit, merge it into master and release the claim. Lanes with `hard_after` unblock automatically once their predecessors are `done`.
-
-**What the primitives do here**: claims isolate scope per lane, the sequence's `hard_after` graph orders the work, and worktrees give Git-level isolation so parallel commits don't conflict.
-
----
-
-## 2. Agent switching — when an agent runs out of credits mid-task
-
-**Scenario** — your active agent hits a credit/quota limit while a task is half-done. You want the next agent (a different model, a fresh instance, anything you have available) to resume cleanly without re-explaining the whole project.
-
-**Walkthrough**:
-
-1. Before the active agent shuts down, close out properly:
-
-   ```text
-   bclaw_session_end(narrative="Implemented X. Need to finish Y. Tests for Z still pending.")
-   ```
-
-   This snapshots the session, releases the active claims, and writes a handoff with the narrative + commit list.
-
-2. Bring up the next agent (any compatible one). Its first call is `bclaw_work(intent="resume")`:
-
-   ```text
-   bclaw_work(intent="resume")
-   ```
-
-   This returns the session context: open plans, recent decisions, active constraints, known traps, the latest handoff narrative, and any unfinished claims it can adopt.
-
-3. The new agent reads the handoff, picks up the right plan, and either creates a fresh claim on the same scope or adopts the existing one:
-
-   ```text
-   bclaw_work(intent="execute", planId="pln_…", scope="src/...")
-   ```
-
-4. From here on it's a normal session — the new agent has all the context the previous one had.
-
-**What the primitives do here**: the handoff carries the narrative and the file delta, the session record carries the runtime context, and shared memory (decisions, constraints, traps) means the new agent doesn't relearn what the previous one already knows.
-
----
-
-## 3. Project recovery — returning to a project after weeks
-
-**Scenario** — you (or an agent on your behalf) come back to a project after a couple of weeks. You don't remember exactly where things stood. You want to ramp back up in a few minutes, not an afternoon.
-
-**Walkthrough**:
-
-1. From the project root, ask any compatible agent to load context with the canonical facade:
-
-   ```text
-   bclaw_work(intent="resume")
-   ```
-
-   You get back: in-progress plans, blocked plans, decisions taken since you left, active constraints, known traps, recent handoffs, and a session continuity hint (where the last session left off).
-
-2. If you want a narrower view focused on one area:
-
-   ```text
-   bclaw_context(kind="memory", path="src/auth", profile="briefing")
-   ```
-
-3. Capture the things you remember in the moment — even rough — as runtime notes. They live in memory and can be promoted later to durable decisions or traps:
-
-   ```text
-   bclaw_create(entity="runtime_note", data={ text: "Token rotation logic was the next thing to ship" })
-   ```
-
-4. Pick the next plan, claim its scope, and start working. The agent has everything it needs.
-
-**What the primitives do here**: durable memory means decisions and constraints survive long absences, the session continuity record bridges the gap between runs, and runtime notes give a low-friction way to capture half-formed ideas as they come back to you.
-
----
-
-## 4. Team async — multiple humans and agents on the same project
-
-**Scenario** — two or more people work on the same project, possibly with their own agents. Everyone needs to see the same plans, the same constraints, the same decisions, without constant Slack pings.
-
-**Walkthrough**:
-
-1. Whenever someone takes a non-trivial decision (architecture, library choice, naming convention), capture it once:
-
-   ```text
-   bclaw_create(entity="decision", data={ text: "Use OAuth 2.0 with PKCE", outcome: "approved" })
-   bclaw_create(entity="constraint", data={ text: "All auth endpoints must rate-limit", category: "security" })
-   bclaw_create(entity="trap", data={ text: "Don't import from src/legacy/", severity: "high" })
-   ```
-
-   These become visible to every agent (and every teammate's agent) on the next `bclaw_context` call.
-
-2. When someone starts a non-trivial chunk of work, claim its scope so others can see it:
-
-   ```text
-   bclaw_work(intent="execute", scope="src/auth", task="Token rotation rework")
-   ```
-
-   The agent board (`bclaw_context(kind="board")` or `brainclaw agent-board`) now shows that scope as taken — anyone considering the same area sees the claim and either coordinates or picks something else.
-
-3. When work is ready for review, hand it off explicitly. The handoff includes the file delta, the narrative, and any open questions:
-
-   ```text
-   bclaw_coordinate(intent="review", task="Auth refactor ready for review", scope="src/auth")
-   ```
-
-4. Reviewers pick up the handoff via inbox (`bclaw_read_inbox`) and respond either by accepting + closing it, or by sending back fixes through the same coordination loop.
-
-**What the primitives do here**: shared memory means every teammate's agent operates with the same constraints and traps, claims prevent double-work even without coordination meetings, and handoffs replace ad-hoc "hey, can you look at this?" pings with auditable artifacts.
-
----
-
-## How the four scenarios share the same model
-
-Notice that the four walkthroughs above use the **same primitives**, just composed differently:
-
-| Primitive | Active orchestration | Agent switching | Project recovery | Team async |
-|---|---|---|---|---|
-| **plan** | unit of work in a lane | what the next agent picks up | what you ramp back into | what teammates see in the board |
-| **claim** | scope lock per lane | snapshotted on session_end, adoptable later | shows what was in flight | prevents teammates from double-editing |
-| **handoff** | between sequential lanes | carries the narrative + delta | bridges across the gap | replaces "ping me when ready" |
-| **decision / constraint / trap** | guides every spawned worker | survives the credit-limit cutover | reminds you of past choices | propagates team knowledge |
-| **runtime_note** | per-lane observations | quick captures before shutdown | half-formed thoughts on return | informal observations to share |
-
-You don't pick a "mode" up front. You compose the primitives in whatever way fits the moment, and brainclaw keeps them durable across all of it.
-
----
-
-## Next reads
-
-- [memory.md](memory.md) — what counts as memory and how it's organized
-- [plans-and-claims.md](plans-and-claims.md) — coordination layer in depth
-- [loop-engine.md](loop-engine.md) — structured multi-turn protocols (review loops, ideation, etc.)
-- [memory-staleness.md](memory-staleness.md) — how brainclaw signals when stored items may be outdated
-- [../integrations/overview.md](../integrations/overview.md) — connecting your specific agent
+# Multi-Agent Workflows
+
+brainclaw is built around a small set of memory primitives — **plans**, **claims**, **handoffs**, **decisions**, **traps**, and **runtime notes** — that work the same way whether you're orchestrating multiple agents in parallel right now or letting the next agent (or the next you) pick up the work next week.
+
+This doc walks through four concrete scenarios. Pick the one that matches what you're doing.
+
+---
+
+## 1. Active orchestration — parallel work across agent instances
+
+**Scenario** — you have a sequence of independent lanes and want several agents (same agent, different instances, or several different agents) to work on them in parallel.
+
+**Walkthrough**:
+
+1. Capture the work as plans, then group them into a sequence with explicit lane labels and dependencies:
+
+   ```text
+   bclaw_create(entity="plan", data={ text: "Refactor auth module", … })
+   bclaw_create(entity="plan", data={ text: "Add e2e tests", … })
+
+   # Then, via CLI or a follow-up call:
+   brainclaw sequence create "auth-refactor-cycle" --items '[
+     {"planId":"pln_aaa","rank":1,"lane":"refactor"},
+     {"planId":"pln_bbb","rank":2,"lane":"tests","hard_after":["pln_aaa"]}
+   ]' --status active
+   ```
+
+2. Dispatch the sequence — the dispatcher picks up the ready lanes (no `hard_after` blocking), creates one claim + worktree per lane, and routes inbox messages by `claim_id`:
+
+   ```text
+   bclaw_dispatch(intent="execute", agents=[<your agents>])
+   ```
+
+3. Each spawned worker runs in its own worktree (so concurrent edits don't collide), reads its inbox, and progresses the plan. Coordinator polls `bclaw_context(kind="board")` to follow progress.
+
+4. As each lane lands a commit, merge it into master and release the claim. Lanes with `hard_after` unblock automatically once their predecessors are `done`.
+
+**What the primitives do here**: claims isolate scope per lane, the sequence's `hard_after` graph orders the work, and worktrees give Git-level isolation so parallel commits don't conflict.
+
+---
+
+## 2. Agent switching — when an agent runs out of credits mid-task
+
+**Scenario** — your active agent hits a credit/quota limit while a task is half-done. You want the next agent (a different model, a fresh instance, anything you have available) to resume cleanly without re-explaining the whole project.
+
+**Walkthrough**:
+
+1. Before the active agent shuts down, close out properly:
+
+   ```text
+   bclaw_session_end(narrative="Implemented X. Need to finish Y. Tests for Z still pending.")
+   ```
+
+   This snapshots the session, releases the active claims, and writes a handoff with the narrative + commit list.
+
+2. Bring up the next agent (any compatible one). Its first call is `bclaw_work(intent="resume")`:
+
+   ```text
+   bclaw_work(intent="resume")
+   ```
+
+   This returns the session context: open plans, recent decisions, active constraints, known traps, the latest handoff narrative, and any unfinished claims it can adopt.
+
+3. The new agent reads the handoff, picks up the right plan, and either creates a fresh claim on the same scope or adopts the existing one:
+
+   ```text
+   bclaw_work(intent="execute", planId="pln_…", scope="src/...")
+   ```
+
+4. From here on it's a normal session — the new agent has all the context the previous one had.
+
+**What the primitives do here**: the handoff carries the narrative and the file delta, the session record carries the runtime context, and shared memory (decisions, constraints, traps) means the new agent doesn't relearn what the previous one already knows.
+
+---
+
+## 3. Project recovery — returning to a project after weeks
+
+**Scenario** — you (or an agent on your behalf) come back to a project after a couple of weeks. You don't remember exactly where things stood. You want to ramp back up in a few minutes, not an afternoon.
+
+**Walkthrough**:
+
+1. From the project root, ask any compatible agent to load context with the canonical facade:
+
+   ```text
+   bclaw_work(intent="resume")
+   ```
+
+   You get back: in-progress plans, blocked plans, decisions taken since you left, active constraints, known traps, recent handoffs, and a session continuity hint (where the last session left off).
+
+2. If you want a narrower view focused on one area:
+
+   ```text
+   bclaw_context(kind="memory", path="src/auth", profile="briefing")
+   ```
+
+3. Capture the things you remember in the moment — even rough — as runtime notes. They live in memory and can be promoted later to durable decisions or traps:
+
+   ```text
+   bclaw_create(entity="runtime_note", data={ text: "Token rotation logic was the next thing to ship" })
+   ```
+
+4. Pick the next plan, claim its scope, and start working. The agent has everything it needs.
+
+**What the primitives do here**: durable memory means decisions and constraints survive long absences, the session continuity record bridges the gap between runs, and runtime notes give a low-friction way to capture half-formed ideas as they come back to you.
+
+---
+
+## 4. Team async — multiple humans and agents on the same project
+
+**Scenario** — two or more people work on the same project, possibly with their own agents. Everyone needs to see the same plans, the same constraints, the same decisions, without constant Slack pings.
+
+**Walkthrough**:
+
+1. Whenever someone takes a non-trivial decision (architecture, library choice, naming convention), capture it once:
+
+   ```text
+   bclaw_create(entity="decision", data={ text: "Use OAuth 2.0 with PKCE", outcome: "approved" })
+   bclaw_create(entity="constraint", data={ text: "All auth endpoints must rate-limit", category: "security" })
+   bclaw_create(entity="trap", data={ text: "Don't import from src/legacy/", severity: "high" })
+   ```
+
+   These become visible to every agent (and every teammate's agent) on the next `bclaw_context` call.
+
+2. When someone starts a non-trivial chunk of work, claim its scope so others can see it:
+
+   ```text
+   bclaw_work(intent="execute", scope="src/auth", task="Token rotation rework")
+   ```
+
+   The agent board (`bclaw_context(kind="board")` or `brainclaw agent-board`) now shows that scope as taken — anyone considering the same area sees the claim and either coordinates or picks something else.
+
+3. When work is ready for review, hand it off explicitly. The handoff includes the file delta, the narrative, and any open questions:
+
+   ```text
+   bclaw_coordinate(intent="review", task="Auth refactor ready for review", scope="src/auth")
+   ```
+
+4. Reviewers pick up the handoff via inbox (`bclaw_read_inbox`) and respond either by accepting + closing it, or by sending back fixes through the same coordination loop.
+
+**What the primitives do here**: shared memory means every teammate's agent operates with the same constraints and traps, claims prevent double-work even without coordination meetings, and handoffs replace ad-hoc "hey, can you look at this?" pings with auditable artifacts.
+
+---
+
+## How the four scenarios share the same model
+
+Notice that the four walkthroughs above use the **same primitives**, just composed differently:
+
+| Primitive | Active orchestration | Agent switching | Project recovery | Team async |
+|---|---|---|---|---|
+| **plan** | unit of work in a lane | what the next agent picks up | what you ramp back into | what teammates see in the board |
+| **claim** | scope lock per lane | snapshotted on session_end, adoptable later | shows what was in flight | prevents teammates from double-editing |
+| **handoff** | between sequential lanes | carries the narrative + delta | bridges across the gap | replaces "ping me when ready" |
+| **decision / constraint / trap** | guides every spawned worker | survives the credit-limit cutover | reminds you of past choices | propagates team knowledge |
+| **runtime_note** | per-lane observations | quick captures before shutdown | half-formed thoughts on return | informal observations to share |
+
+You don't pick a "mode" up front. You compose the primitives in whatever way fits the moment, and brainclaw keeps them durable across all of it.
+
+---
+
+## Next reads
+
+- [memory.md](memory.md) — what counts as memory and how it's organized
+- [plans-and-claims.md](plans-and-claims.md) — coordination layer in depth
+- [loop-engine.md](loop-engine.md) — structured multi-turn protocols (review loops, ideation, etc.)
+- [dispatch-lifecycle.md](dispatch-lifecycle.md) — what actually happens when a dispatch goes wrong: 6-entity dance, brief-ack sentinel, stdout/stderr logs, observability decision tree
+- [memory-staleness.md](memory-staleness.md) — how brainclaw signals when stored items may be outdated
+- [../integrations/overview.md](../integrations/overview.md) — connecting your specific agent