feat(sessions): get_persona_state client + persona error taxonomy (v0.12.0)

Adds the read-side half of Worldtree #204's persona-state observability
surface. Pairs with v0.11.0's AffectUpdate SSE event — together they
let a consumer hydrate a persona pane on session-open (this GET) and
keep it live as turns fire (the SSE event).

Public surface:
- `get_persona_state(client, agent_id) -> dict[str, Any]` — GET
  /agents/{agent_id}/persona_state, returns the same `snapshot` dict
  shape as AffectUpdate.snapshot
- New exception types mapped from the spec's documented 4xx error_codes:
  - `PersonaNotConfigured` (404 persona_not_configured) — agent has
    no persona surface (domari, muninn, all Tier 3 in Phase 2.0)
  - `AgentNotAvailable` (404 agent_not_available) — unknown agent_id
  - `AuthScopeDenied` (403 auth_scope_denied) — key lacks the
    requested scope (persona.read here; reusable for future scoped
    endpoints)
- Other non-2xx falls through to the existing SessionApiFailed
  precedent so novel failure modes aren't silently absorbed

Tests: 6 new cases covering happy snapshot return, each typed 4xx
sub-code, unknown 404 fall-through, and 5xx SessionApiFailed parity.

Not yet consumed: TUI persona surface (Persona TabPane / sticky
header line). UX shape pending operator direction — step 3.

docs/SPEC-PIN.md

@@ -7,11 +7,18 @@ documents the pin, the vendored artifacts, and the bump procedure.
 
 | Field | Value |
 |---|---|
-| Worldtree git SHA | `55101e909abcd2219833266b6f905c5bc956e0f0` |
-| Worldtree HEAD message | `memory: snapshot — #177 Vili v1 + persona async-decouple shipped as v0.19.0` |
-| Pinned on | 2026-05-20 |
-| Pinned by | brokkr-smithy-dev (initial scaffold) |
-| Worldtree version at pin | `v0.19.0` |
+| Worldtree git SHA | `da93ca7cf613f1dc229a7a44d07fc1d7efc78e25` |
+| Worldtree HEAD message | `feat(#204): v0.28.0 — persona-state observability surface` |
+| Pinned on | 2026-05-25 |
+| Pinned by | ratatoskr-dev (bump for #204 affect_update SSE) |
+| Worldtree version at pin | `v0.28.0` |
+
+## Pin history
+
+| Date | SHA | Version | Notable deltas consumed |
+|---|---|---|---|
+| 2026-05-25 | `da93ca7` | v0.28.0 | #204 — new SSE event `affect_update` (current/scheduled), new endpoint `GET /agents/{id}/persona_state` (not yet consumed), auth-model doc edits |
+| 2026-05-20 | `55101e9` | v0.19.0 | initial scaffold pin |
 
 ## Vendored artifacts
 

docs/conversation-api-spec.md

@@ -55,6 +55,69 @@ conversation_api:
 
 ---
 
+## Authorization model — agent invocation
+
+When you call `POST /sessions` against an agent, the authorization check that fires depends on **which kind of agent** you target. There are two distinct scope namespaces — the spelling differs by one character (`agent` vs `agents`) and the granting mechanism differs entirely. Confusing the two is a common source of bug reports.
+
+### Tier 1 — foundational agents (no `:` in agent_id)
+
+Agents bundled with Worldtree: `mimir`, `lofn`, `soong`, `forseti`, `domari`, `vili`, `actor`, `saga`, `bragi`, `leif`, `troi`, `cara`, `glados`, and any future Asgardian. The agent_id is a simple slug like `mimir` — no colon.
+
+> **About tiers:** Your `tier` is set on the `users` table row your API key resolves to, assigned at key-mint time (see `POST /admin/keys`). Tiers are `anonymous` (dev-mode unauthenticated), `user` (default for newly-issued keys), `free`/`pro` (subscription-shaped, not actively differentiated), and `admin`. The tier you have is visible via `GET /me`'s `tier` field. Tier-derived scopes come from `config/policies.yaml > tiers.<tier>.scopes` — there is no per-key scope override.
+
+**Authorization rule (singular `agent`):**
+
+```yaml
+- id: agent-call-baseline-allow
+  principal:
+    tiers: ["anonymous", "user", "free", "pro", "admin"]
+  action: "agent.call:*"
+  resource: "*"
+  effect: allow
+```
+
+This baseline rule lives at `config/policies.yaml`. Every authenticated tier — including the `user` tier that newly-issued keys default to — already passes this check for every Tier 1 agent. **There is no per-agent scope you can add to "grant" Tier 1 access; it's covered by tier.**
+
+If you get a 422 calling a Tier 1 agent (e.g., `lofn` rejecting with `end_user_id_required`), that's a **request-body validation**, not a scope denial. Check the `error_code` in the response detail — `END_USER_ID_REQUIRED` means the agent requires an `end_user_id` field in the request body; `AUTH_SCOPE_DENIED` (403) would be the actual scope problem. They're not interchangeable.
+
+### Tier 3 — consumer-defined agents (`:` in agent_id)
+
+Agents created at runtime via `POST /agents/define`. The agent_id is `<owner_user_id>:<agent_name>`, e.g., `acme:support-bot`. The `:` in the path is the trigger that switches the auth model.
+
+**Authorization is DB-backed per-resource, NOT policy-driven (plural `agents`):**
+
+```
+scope action checked: agents.call:<owner_user_id>:<agent_name>
+                       ^^^^^^
+                       PLURAL — different namespace from Tier 1
+```
+
+There is **no blanket allow rule** for `agents.call:*` in policy. The grant comes from the live `consumer_agents` table:
+
+- A non-soft-deleted row in `consumer_agents` owned by `ctx.user_id` IS the grant.
+- Cascade soft-delete and owner-initiated `DELETE` revoke it.
+- Missing row → policy defaults to deny (403 `auth_scope_denied`).
+
+To "add the scope" for a Tier 3 agent, you don't amend any config or call an admin endpoint — you `POST /agents/define` to register it under your `user_id`. Owning the row IS the grant. You cannot call another user's Tier 3 agent; ownership is checked at session-create (`row.user_id == ctx.user_id`).
+
+### Common pitfalls
+
+- **Singular vs plural.** Tier 1 uses `agent.call:*` (singular `agent`). Tier 3 uses `agents.call:<owner>:<name>` (plural `agents`). One character difference, two completely different mechanisms. There is no Tier 1 scope named `agent.call:mimir` or `agents.call:mimir` — Tier 1 is granted by baseline rule, not per-agent name.
+- **No scope-mutation API.** `POST /admin/keys` accepts `{user_id, label, tier}` only. There is no per-key scope override mechanism in the storage schema. To change a user's effective scopes, change their `tier`, not their key. Per-resource Tier 3 grants flow through `POST /agents/define` (and its DELETE counterpart), not through admin endpoints.
+- **422 vs 403.** A 422 is body-validation (e.g., `end_user_id_required`); a 403 is auth-policy denial (`auth_scope_denied`). Different fix paths. Read the `error_code` in `detail`.
+
+### Quick decision table for consumers
+
+| Target | Auth requirement |
+|---|---|
+| Tier 1 agent (e.g., `mimir`) | Authenticated tier ≥ `user`. No additional body requirements |
+| Tier 1 agent `lofn` (the default welcoming intermediary) | Authenticated tier ≥ `user` + `end_user_id` field required in request body. 422 `END_USER_ID_REQUIRED` if absent |
+| Tier 3 agent (any agent_id containing `:`) | `end_user_id` field required in body. AND the row must be owner-matched: `POST /agents/define` first to create a row under your `user_id`, then session-create works against your existing key. Cross-user Tier 3 invocation is rejected with 403 |
+
+> **Programmatic discovery of `end_user_id` requirements:** as of v0.22.x there is no field on `GET /agents` indicating which agents require `end_user_id` — the spec line above (lofn + Tier 3) is the authoritative list, and 422 `END_USER_ID_REQUIRED` is the fallback signal at request time. Adding a discoverable `requires_end_user_id` field on `AgentInfoResponse` is on the table as a small future capability; ping if you want to drive it.
+
+---
+
 ## GET /me
 
 Returns the authenticated principal's identity and key metadata. Lets a client verify its key on boot without triggering agent-config-loading side effects.
@@ -1878,6 +1941,45 @@ Tool-using turns cycle through `CallingLLM → ProcessingTools → CallingLLM
 
 Clients that don't need phase events can filter on `event["type"] != "worker_phase"` client-side. Existing SSE consumers that switch on `event["type"]` ignore this event type without code changes.
 
+### affect_update
+
+Persona-state observability event (issue #204). Fires twice per turn for agents with `persona.enabled: true` on non-ephemeral sessions; suppressed entirely for persona-disabled agents (e.g. `domari`, `muninn`), Tier 3 consumer-defined agents (Phase 2.0), and ephemeral sessions.
+
+**Start-of-turn — `status: "current"`:**
+
+Emitted immediately at the start of each qualifying turn, before any `worker_phase` event. Carries the agent's current persona snapshot reflecting all prior turns' completed appraisals.
+
+```json
+{
+  "type": "affect_update",
+  "status": "current",
+  "turn_id": 42,
+  "snapshot": {
+    "agent_id": "mimir",
+    "pad": {"pleasure": 0.52, "arousal": 0.47, "dominance": 0.50},
+    "dominant_emotion": "curiosity",
+    "emotions_active": [
+      {"type": "curiosity", "intensity": 0.6, "decay_remaining_s": 202.7}
+    ],
+    "baseline_pad": {"pleasure": 0.50, "arousal": 0.40, "dominance": 0.50},
+    "mood_drift": {"valence_delta": 0.02, "arousal_delta": 0.07},
+    "last_updated_at": "2026-05-25T22:30:18+00:00"
+  }
+}
+```
+
+**End-of-turn — `status: "scheduled"`:**
+
+Emitted after the post-turn appraisal task has been scheduled (per #177 Phase A's fire-and-forget discipline) and before `done`. Lightweight notification — no PAD numbers, since the appraisal is still running asynchronously. The result lands in the NEXT turn's `status: "current"` snapshot.
+
+```json
+{"type": "affect_update", "status": "scheduled", "turn_id": 42}
+```
+
+`scheduled` is skipped on turn failure/cancel paths (the appraisal was never reached); `current` still fires unconditionally for qualifying turns.
+
+Bootstrap reads available via `GET /agents/{agent_id}/persona_state` (same `snapshot` shape, requires `persona.read` scope).
+
 ### thinking
 
 Incremental reasoning/thinking content (from thinking-enabled models).

docs/conversation_api.contract.md

@@ -1851,6 +1851,36 @@ SQLite `consumer_agents` table.
   before any other processing; non-slug user_ids return 403
   `tier3_user_id_unsupported`.
 
+### Persona-state observability (issue #204)
+
+- **INV-204-1 (affect_update event type)**: `affect_update` is a
+  top-level SSE event `type` discriminator, sibling to `worker_phase`
+  / `tool_*` / `text` / `thinking` / `done`. Not a `worker_phase` sub-
+  phase. INV-061's "BuildingPrompt is the FIRST event" property is
+  scoped to `worker_phase` events only — `affect_update status="current"`
+  may precede BuildingPrompt for persona-enabled agents.
+- **INV-204-2 (per-turn emission)**: For agents with persona enabled
+  on non-ephemeral sessions, `stream_turn` emits `status="current"`
+  before any other SSE event on a successful or failed turn, and
+  `status="scheduled"` after `update_after_turn` schedules the
+  appraisal task (success path only — skipped on cancel / error
+  before update_after_turn was reached). See contract
+  `docs/contracts/issues/204.contract.md`.
+- **INV-204-3 (emission suppression)**: Persona-disabled agents and
+  ephemeral sessions emit ZERO `affect_update` events.
+- **INV-204-6 / INV-204-7 (persona_state endpoint)**: New
+  `GET /agents/{agent_id}/persona_state` gated on Heimdall scope
+  `persona.read`. Route ordering: auth → Tier 3 short-circuit (404
+  `persona_not_configured`) → Tier 1/2 existence (404
+  `agent_not_available`) → persona-enabled check (404
+  `persona_not_configured`) → snapshot (200).
+- **INV-204-9 (read-only registry primitive)**: `PersonaRegistry.get_state`
+  is mutex-free and never mutates `persona.emotions`. Eventual
+  consistency under concurrent `_appraisal_wrapper` mutations.
+- **INV-204-14 (replay participation)**: `affect_update` events flow
+  through `_publish`, so SSE resume / replay handles them with no
+  special case.
+
 ### Storage extension
 
 The `consumer_agents` table lives in `core/heimdall/storage/sqlite.py`

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "ratatoskr"
-version = "0.9.0"
+version = "0.12.0"
 description = "Worldtree Conversation API debug TUI — multi-pane observability dashboard"
 readme = "README.md"
 requires-python = ">=3.12"
@@ -42,9 +42,9 @@ Repository = "https://gitea.phasefinal.com/vh/ratatoskr"
 # Ratatoskr is built against Worldtree at this commit; the vendored
 # spec snapshot in docs/ reflects that SHA.
 [tool.ratatoskr.spec-pin]
-worldtree-spec-rev = "55101e909abcd2219833266b6f905c5bc956e0f0"
-worldtree-version = "v0.19.0"
-pinned-on = "2026-05-20"
+worldtree-spec-rev = "da93ca7cf613f1dc229a7a44d07fc1d7efc78e25"
+worldtree-version = "v0.28.0"
+pinned-on = "2026-05-25"
 
 [tool.hatch.build.targets.wheel]
 packages = ["src/ratatoskr"]

src/ratatoskr/sessions.py

@@ -89,6 +89,46 @@ class SessionApiFailed(Exception):
         self.body = body
 
 
+# Worldtree #204 / v0.28.0 — persona_state endpoint failure modes.
+class PersonaNotConfigured(Exception):
+    """Raised on HTTP 404 `persona_not_configured` from GET persona_state.
+
+    Agent exists but has no persona surface: persona-disabled Tier 1/2
+    agents (e.g. `domari`, `muninn`) and all Tier 3 consumer-defined
+    agents (Phase 2.0). Distinct from `AgentNotAvailable` which means the
+    agent_id is unknown entirely.
+    """
+
+    def __init__(self, *, agent_id: str) -> None:
+        super().__init__(f"persona not configured for agent_id: {agent_id!r}")
+        self.agent_id = agent_id
+
+
+class AgentNotAvailable(Exception):
+    """Raised on HTTP 404 `agent_not_available` from GET persona_state.
+
+    The agent_id is unknown to the server. Distinct from
+    `PersonaNotConfigured` (agent exists but has no persona).
+    """
+
+    def __init__(self, *, agent_id: str) -> None:
+        super().__init__(f"agent not available: {agent_id!r}")
+        self.agent_id = agent_id
+
+
+class AuthScopeDenied(Exception):
+    """Raised on HTTP 403 `auth_scope_denied` from a Heimdall-scoped endpoint.
+
+    The API key lacks the required scope (e.g. `persona.read` for
+    GET /agents/{id}/persona_state). User-tier keys carry `persona.read`
+    by default; this surfaces when a narrower key is in use.
+    """
+
+    def __init__(self, *, scope: str) -> None:
+        super().__init__(f"auth scope denied: required={scope!r}")
+        self.scope = scope
+
+
 async def list_sessions(
     client: httpx.AsyncClient,
     *,
@@ -200,3 +240,45 @@ async def list_agents(client: httpx.AsyncClient) -> list[AgentInfo]:
         )
         for item in body
     ]
+
+
+async def get_persona_state(
+    client: httpx.AsyncClient, agent_id: str
+) -> dict[str, Any]:
+    """GET /agents/{agent_id}/persona_state — fetch current persona snapshot.
+
+    Worldtree #204 / v0.28.0. Returns the same `snapshot` dict shape as the
+    `affect_update` SSE event's `status="current"` emission: pad,
+    dominant_emotion, emotions_active, baseline_pad, mood_drift,
+    last_updated_at. Bootstrap read for clients that want to populate a
+    persona pane on session-open without waiting for turn-1's `affect_update`.
+
+    Auth: requires Heimdall `persona.read` scope (user-tier default).
+
+    Failure modes (mapped to typed exceptions per the spec error_codes):
+      - 404 `persona_not_configured` → PersonaNotConfigured (persona-disabled
+        agents: domari / muninn, and all Tier 3 in Phase 2.0)
+      - 404 `agent_not_available` → AgentNotAvailable (unknown agent_id)
+      - 403 `auth_scope_denied` → AuthScopeDenied (key lacks persona.read)
+      - any other non-2xx → SessionApiFailed (preserves the broader-error
+        precedent from list_agents / list_sessions / create_session)
+    """
+    assert client is not None
+    assert agent_id and isinstance(agent_id, str)
+
+    resp = await client.get(f"/agents/{agent_id}/persona_state")
+    if resp.status_code == 200:
+        return resp.json()
+    # Discriminate the 4xx error_code sub-codes; everything else falls through.
+    try:
+        err = resp.json()
+        error_code = err.get("error_code") if isinstance(err, dict) else None
+    except ValueError:
+        error_code = None
+    if resp.status_code == 404 and error_code == "persona_not_configured":
+        raise PersonaNotConfigured(agent_id=agent_id)
+    if resp.status_code == 404 and error_code == "agent_not_available":
+        raise AgentNotAvailable(agent_id=agent_id)
+    if resp.status_code == 403 and error_code == "auth_scope_denied":
+        raise AuthScopeDenied(scope="persona.read")
+    raise SessionApiFailed(status=resp.status_code, body=resp.content)

src/ratatoskr/sse_client.py

@@ -111,6 +111,30 @@ class Cancelled:
     partial_message_id: int | None
 
 
+@dataclass(frozen=True)
+class AffectUpdate:
+    """SSE event `affect_update`: persona-state observability snapshot.
+
+    Two emissions per qualifying turn (persona-enabled agent on non-
+    ephemeral session): `status="current"` at turn start carrying the full
+    snapshot, `status="scheduled"` after post-turn appraisal kicks off
+    (lightweight — `snapshot` is None). Suppressed entirely for persona-
+    disabled agents (e.g. `domari`, `muninn`), Tier 3 consumer-defined
+    agents (Phase 2.0), and ephemeral sessions.
+
+    Bootstrap reads available via `GET /agents/{agent_id}/persona_state`
+    (same `snapshot` shape, requires `persona.read` scope).
+
+    See docs/conversation-api-spec.md § affect_update (Worldtree #204,
+    v0.28.0).
+    """
+
+    sse_id: SseId
+    status: str  # "current" | "scheduled"
+    turn_id: int
+    snapshot: dict[str, Any] | None  # None when status="scheduled"
+
+
 Event = (
     WorkerPhase
     | Thinking
@@ -121,6 +145,7 @@ Event = (
     | Done
     | Error
     | Cancelled
+    | AffectUpdate
 )
 
 
@@ -284,6 +309,17 @@ def _envelope_for_type(body: dict[str, Any], sse_id: SseId) -> Event:
             reason=body.get("reason"),
             partial_message_id=body.get("partial_message_id"),
         )
+    if t == "affect_update":
+        # Worldtree #204 / v0.28.0: persona-state observability event.
+        # status="current" carries full snapshot at turn start;
+        # status="scheduled" omits snapshot (lightweight post-appraisal-
+        # kickoff notification).
+        return AffectUpdate(
+            sse_id=sse_id,
+            status=body["status"],
+            turn_id=body["turn_id"],
+            snapshot=body.get("snapshot"),
+        )
     raise ValueError(f"unknown SSE event type: {t!r}")
 
 

src/ratatoskr/tui.py

@@ -10,7 +10,9 @@ from __future__ import annotations
 
 import asyncio
 import sys
+import time as _time
 from dataclasses import dataclass
+from datetime import datetime as _datetime
 from typing import ClassVar, Literal
 
 import httpx
@@ -39,6 +41,7 @@ from ratatoskr.sessions import (
     list_agents,
 )
 from ratatoskr.sse_client import (
+    AffectUpdate,
     CancelAlreadyCompleted,
     CancelFailed,
     Cancelled,
@@ -178,6 +181,62 @@ def _plain_label(event: Event) -> str:
     return f"[unknown_event] {type(event).__name__}"
 
 
+def _ts() -> str:
+    """HH:MM:SS.fff wall-clock timestamp for debug-pane log lines."""
+    now = _datetime.now()
+    return now.strftime("%H:%M:%S") + f".{now.microsecond // 1000:03d}"
+
+
+def _audit_line(event: Event) -> str:
+    """One-line wire-level audit summary for the debug pane.
+
+    v0.10.0: every SSE event arrival lands as one of these in the debug
+    pane (Text and Thinking deltas are aggregated into the turn summary
+    instead — token-rate per-delta lines would drown the pane). Shape:
+    `[HH:MM:SS.fff] event_type sse_id=T:S key=val …`.
+    """
+    sid = getattr(event, "sse_id", None)
+    sid_str = f"{sid.turn_id}:{sid.seq}" if sid is not None else "-"
+    kind = type(event).__name__.lower()
+    if isinstance(event, WorkerPhase):
+        detail = f"phase={event.phase} turn_id={event.turn_id}"
+    elif isinstance(event, ToolStart):
+        detail = f"name={event.name} args={event.arguments!r:.80}"
+    elif isinstance(event, ToolResult):
+        detail = f"name={event.name} duration_ms={event.duration_ms}"
+    elif isinstance(event, TextBoundary):
+        detail = f"kind={event.kind} char_offset={event.char_offset}"
+    elif isinstance(event, Done):
+        detail = (
+            f"turn_id={event.sse_id.turn_id} model={event.model} "
+            f"duration_ms={event.duration_ms}"
+        )
+    elif isinstance(event, Error):
+        detail = (
+            f"turn_id={event.sse_id.turn_id} code={event.error_code} "
+            f"message={event.message!r:.80}"
+        )
+    elif isinstance(event, Cancelled):
+        detail = f"turn_id={event.turn_id} reason={event.reason!r}"
+    elif isinstance(event, AffectUpdate):
+        # Worldtree #204 / v0.28.0. status="current" carries the full
+        # snapshot; surface dominant_emotion + PAD inline so the operator
+        # sees persona drift at a glance. status="scheduled" is
+        # lightweight — no PAD, just the appraisal-kickoff marker.
+        if event.snapshot is not None:
+            pad = event.snapshot.get("pad") or {}
+            detail = (
+                f"status={event.status} turn_id={event.turn_id} "
+                f"dominant_emotion={event.snapshot.get('dominant_emotion')!r} "
+                f"pad=({pad.get('pleasure')},{pad.get('arousal')},{pad.get('dominance')})"
+            )
+        else:
+            detail = f"status={event.status} turn_id={event.turn_id}"
+    else:  # Text / Thinking handled by counter path; fallback for safety
+        detail = ""
+    return f"[{_ts()}] {kind} sse_id={sid_str} {detail}".rstrip()
+
+
 @dataclass(slots=True)
 class TuiPresenterState:
     """Per-turn presenter state for TUI mode (issue #12).
@@ -202,6 +261,15 @@ class TuiPresenterState:
     # v0.9.0: reference to the Static widget holding the current turn's
     # response Markdown Renderable. None between turns.
     current_response_widget: object = None
+    # v0.10.0: per-turn counters for the debug-pane turn-summary line. Text
+    # and Thinking events arrive at token rate; emitting per-delta debug
+    # lines would drown the pane. Instead we count them and surface
+    # aggregated totals when the turn closes.
+    text_delta_count: int = 0
+    text_byte_count: int = 0
+    thinking_delta_count: int = 0
+    thinking_byte_count: int = 0
+    turn_start_ts: float = 0.0
 
     def render(
         self,
@@ -230,7 +298,7 @@ class TuiPresenterState:
             event,
             (
                 WorkerPhase, Thinking, Text, TextBoundary,
-                ToolStart, ToolResult, Done, Error, Cancelled,
+                ToolStart, ToolResult, Done, Error, Cancelled, AffectUpdate,
             ),
         )
         from rich.text import Text as RichText
@@ -240,6 +308,37 @@ class TuiPresenterState:
             return RichText(s, style=_AU_DEMOTED)
 
         try:
+            # v0.10.0: per-event audit log line to debug pane. Text and
+            # Thinking arrive at token rate, so we count them rather than
+            # emit a line per delta — totals are reported in the turn-
+            # summary on Done/Error/Cancelled. Everything else gets one
+            # debug-pane line per arrival with timestamp + sse_id + a short
+            # event-specific summary, giving the operator a wire-level
+            # timeline of what the server sent.
+            if isinstance(event, Text):
+                if self.text_delta_count == 0:
+                    if self.turn_start_ts == 0.0:
+                        self.turn_start_ts = _time.monotonic()
+                self.text_delta_count += 1
+                self.text_byte_count += len(event.content)
+            elif isinstance(event, Thinking):
+                if self.thinking_delta_count == 0:
+                    if self.turn_start_ts == 0.0:
+                        self.turn_start_ts = _time.monotonic()
+                self.thinking_delta_count += 1
+                self.thinking_byte_count += len(event.content)
+            else:
+                if self.turn_start_ts == 0.0:
+                    self.turn_start_ts = _time.monotonic()
+                debug_log.write(_dim(_audit_line(event)))
+            # v0.11.0: AffectUpdate is debug-pane-only for now (the audit
+            # line emitted above is the complete handling). Return early
+            # so the event doesn't pass through the thinking-close path
+            # or fall into the unknown-event ValueError branch. A full
+            # persona surface (Persona TabPane, sticky header line, or
+            # similar) is deferred to a later bump pending UX direction.
+            if isinstance(event, AffectUpdate):
+                return
             # v0.7.1: Thinking deltas coalesce by newline before flushing.
             # Worldtree emits Thinking events at token granularity; per-delta
             # RichLog writes produce one visual line per token (per-token-per-
@@ -315,6 +414,28 @@ class TuiPresenterState:
                 transcript.scroll_end(animate=False)
                 return
             if isinstance(event, (Done, Error, Cancelled)):
+                # v0.10.0: emit turn-summary to debug pane before clearing
+                # counters. Aggregates the per-event totals (Text + Thinking
+                # deltas don't get per-event audit lines because they arrive
+                # at token rate; the summary surfaces what was elided).
+                elapsed_ms = (
+                    int((_time.monotonic() - self.turn_start_ts) * 1000)
+                    if self.turn_start_ts
+                    else 0
+                )
+                turn_id = (
+                    event.sse_id.turn_id
+                    if hasattr(event, "sse_id")
+                    else getattr(event, "turn_id", "?")
+                )
+                debug_log.write(_dim(
+                    f"[{_ts()}] turn_summary turn_id={turn_id} "
+                    f"text_deltas={self.text_delta_count} "
+                    f"text_bytes={self.text_byte_count} "
+                    f"thinking_deltas={self.thinking_delta_count} "
+                    f"thinking_bytes={self.thinking_byte_count} "
+                    f"elapsed_ms={elapsed_ms}"
+                ))
                 # Terminal event: finalize the response widget (clear ref so
                 # the next turn mounts a fresh one). The accumulated text is
                 # already rendered as Markdown in the widget — no post-Done
@@ -793,6 +914,14 @@ class RatatoskrApp(App[int]):
         )
         self.state = "idle"
         self._set_hint(self.HINT_IDLE)
+        # v0.10.0: startup audit so the debug pane carries a complete
+        # session bootstrap line (server URL, agent, end_user_id, raw flag,
+        # session tail) before the first turn fires.
+        self._audit(
+            f"app_mounted server={self.args.server_url} agent_id={self.agent_id!r} "
+            f"session={self.session_id[-8:]} raw={self.args.raw} "
+            f"end_user_id={getattr(self.args, 'end_user_id', None)!r}"
+        )
 
     def _write_turn_headers(self, turn_id: int) -> None:
         """v0.6.0: turn-ID headers across every pane for cross-pane
@@ -833,6 +962,37 @@ class RatatoskrApp(App[int]):
             # Widget may be gone during shutdown; ignore.
             pass
 
+    def _audit(self, line: str) -> None:
+        """Write a timestamped audit line to the debug pane.
+
+        v0.10.0: shared sink for app-level events that don't pass through
+        the presenter — state transitions, worker spawn/cancel, cancel POST
+        lifecycle, startup probes. The presenter's per-event audit lives at
+        `_audit_line()`; this is its app-side counterpart.
+        """
+        try:
+            from rich.text import Text as RichText
+            self.query_one("#debug-log", RichLog).write(
+                RichText(f"[{_ts()}] {line}", style=_AU_DEMOTED)
+            )
+        except Exception:
+            # Widget may not exist yet (pre-mount) or be tearing down.
+            pass
+
+    def _transition(
+        self, new_state: Literal["idle", "streaming", "cancelling"], reason: str
+    ) -> None:
+        """Set self.state with debug-pane audit log.
+
+        Every state machine transition flows through here so the debug pane
+        carries a complete idle→streaming→cancelling→idle timeline with the
+        triggering reason. Cheap; safe to call from any context.
+        """
+        old = self.state
+        self.state = new_state
+        if old != new_state:
+            self._audit(f"state {old} → {new_state} reason={reason}")
+
     async def on_input_submitted(self, event: Input.Submitted) -> None:
         """Echo user prompt, spawn stream worker; busy notice if not idle.
 
@@ -863,7 +1023,8 @@ class RatatoskrApp(App[int]):
         )
         transcript.scroll_end(animate=False)
         event.input.value = ""
-        self.state = "streaming"
+        self._transition("streaming", "input_submitted")
+        self._audit(f"worker_spawn content_len={len(content)}")
         self._set_hint(self.HINT_STREAMING)
         self.stream_worker = self.run_worker(
             self._stream_turn_worker(content), exclusive=True
@@ -909,17 +1070,22 @@ class RatatoskrApp(App[int]):
                 if isinstance(event, (Done, Error, Cancelled)):
                     break
         except SseConnectFailed as exc:
+            self._audit(f"sse_connect_failed status={exc.status} body={exc.body!r:.120}")
             _mount_wire_error(f"[sse_connect_failed] status={exc.status} body={exc.body!r}")
         except SseConnectionDropped as exc:
+            self._audit(f"connection_dropped last_seen={exc.last_seen_sse_id}")
             _mount_wire_error(f"[connection_dropped] last_seen={exc.last_seen_sse_id}")
         except MalformedSseId as exc:
+            self._audit(f"malformed_sse_id raw={exc.raw!r}")
             _mount_wire_error(f"[malformed_sse_id] raw={exc.raw!r}")
         except MalformedSseData as exc:
+            self._audit(f"malformed_sse_data raw={exc.raw!r:.120}")
             _mount_wire_error(f"[malformed_sse_data] raw={exc.raw!r}")
         except TurnIdFlip as exc:
+            self._audit(f"turn_id_flip expected={exc.established} got={exc.got}")
             _mount_wire_error(f"[turn_id_flip] expected={exc.established} got={exc.got}")
         finally:
-            self.state = "idle"
+            self._transition("idle", "worker_finally")
             self.active_turn_id = None
             self._set_hint(self.HINT_IDLE)
 
@@ -931,29 +1097,35 @@ class RatatoskrApp(App[int]):
         """Two-stage Ctrl-C state machine per INV-003."""
         assert self.state in ("idle", "streaming", "cancelling")
         if self.state == "idle":
+            self._audit("ctrl_c state=idle action=exit code=0")
             self.exit(0)
         elif self.state == "streaming":
             if self.active_turn_id is None:
+                self._audit("ctrl_c state=streaming active_turn_id=None action=force_exit code=3")
                 if self.stream_worker is not None:
                     self.stream_worker.cancel()
                 self.exit(3)
                 return
-            self.state = "cancelling"
+            self._audit(f"ctrl_c state=streaming turn_id={self.active_turn_id} action=cancel_post")
+            self._transition("cancelling", "ctrl_c_cancel_post_issued")
             self._set_hint(self.HINT_CANCELLING)
             transcript = self.query_one("#transcript-scroll", VerticalScroll)
             self.run_worker(
                 _cancel_via_sse(
                     self.client, self.session_id, self.active_turn_id,
                     transcript=transcript,
+                    audit=self._audit,
                 )
             )
         elif self.state == "cancelling":
+            self._audit("ctrl_c state=cancelling action=force_exit code=3")
             if self.stream_worker is not None:
                 self.stream_worker.cancel()
             self.exit(3)
 
     def action_quit(self) -> None:
         """Ctrl-D — immediate exit regardless of state."""
+        self._audit(f"ctrl_d state={self.state} action=exit code=0")
         if self.stream_worker is not None and not self.stream_worker.is_finished:
             self.stream_worker.cancel()
         self.exit(0)
@@ -1095,17 +1267,27 @@ async def _cancel_via_sse(
     turn_id: int,
     *,
     transcript: VerticalScroll,
+    audit: "Callable[[str], None] | None" = None,
 ) -> None:
     """Fire-and-forget cancel; never raises (mirrors cli._cancel_and_log; #3 INV-009).
 
     v0.9.0: mounts a `[cancel_failed]` Static into the transcript-scroll
     container on failure (was log.write to RichLog).
+    v0.10.0: optional `audit` callback (RatatoskrApp._audit) receives one
+    line on POST issue + one on POST result, so the debug pane carries the
+    full cancel lifecycle. Defaults to no-op for legacy callers.
     """
     assert client is not None
     assert isinstance(turn_id, int) and turn_id > 0
+    if audit is not None:
+        audit(f"cancel_post issued session_id={session_id} turn_id={turn_id}")
     try:
         await cancel_turn(client, session_id, turn_id)
+        if audit is not None:
+            audit(f"cancel_post ok turn_id={turn_id}")
     except (CancelFailed, CancelTurnNotFound, CancelAlreadyCompleted, httpx.RequestError) as exc:
+        if audit is not None:
+            audit(f"cancel_post failed turn_id={turn_id} {type(exc).__name__}: {exc!s:.120}")
         try:
             transcript.mount(Static(
                 f"[cancel_failed] {type(exc).__name__}: {exc}",

tests/test_sessions.py

@@ -6,11 +6,15 @@ import respx
 
 from ratatoskr.sessions import (
     AgentInfo,
+    AgentNotAvailable,
     AgentNotFound,
+    AuthScopeDenied,
     InvalidCursor,
+    PersonaNotConfigured,
     SessionApiFailed,
     SessionPage,
     create_session,
+    get_persona_state,
     list_agents,
     list_sessions,
 )
@@ -556,3 +560,108 @@ class TestListAgents:
             with pytest.raises(SessionApiFailed) as excinfo:
                 await list_agents(client)
         assert excinfo.value.status == 401
+
+
+class TestGetPersonaState:
+    """Worldtree #204 / v0.28.0 — GET /agents/{agent_id}/persona_state.
+
+    Bootstrap read for the persona snapshot — same shape as `affect_update`'s
+    `current` snapshot. Auth via `persona.read` scope (user-tier default).
+    """
+
+    @respx.mock
+    async def test_happy_full_snapshot(self) -> None:
+        """happy_full_snapshot [happy,tracer]: 200 → snapshot dict with pad +
+        dominant_emotion + emotions_active + baseline_pad + mood_drift.
+        """
+        snapshot = {
+            "agent_id": "mimir",
+            "pad": {"pleasure": 0.52, "arousal": 0.47, "dominance": 0.50},
+            "dominant_emotion": "curiosity",
+            "emotions_active": [
+                {"type": "curiosity", "intensity": 0.6, "decay_remaining_s": 202.7}
+            ],
+            "baseline_pad": {"pleasure": 0.50, "arousal": 0.40, "dominance": 0.50},
+            "mood_drift": {"valence_delta": 0.02, "arousal_delta": 0.07},
+            "last_updated_at": "2026-05-25T22:30:18+00:00",
+        }
+        respx.get("https://w.example/agents/mimir/persona_state").mock(
+            return_value=httpx.Response(200, json=snapshot)
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            result = await get_persona_state(client, "mimir")
+        assert result == snapshot
+
+    @respx.mock
+    async def test_persona_not_configured_404(self) -> None:
+        """persona_not_configured_404 [error]: 404 with error_code
+        persona_not_configured → PersonaNotConfigured. Agent exists but has
+        no persona surface (e.g. domari, muninn, Tier 3).
+        """
+        respx.get("https://w.example/agents/domari/persona_state").mock(
+            return_value=httpx.Response(
+                404, json={"error_code": "persona_not_configured", "message": "no persona"}
+            )
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            with pytest.raises(PersonaNotConfigured) as exc_info:
+                await get_persona_state(client, "domari")
+        assert exc_info.value.agent_id == "domari"
+
+    @respx.mock
+    async def test_agent_not_available_404(self) -> None:
+        """agent_not_available_404 [error]: 404 with error_code
+        agent_not_available → AgentNotAvailable. Distinct from
+        persona_not_configured — the agent_id itself is unknown.
+        """
+        respx.get("https://w.example/agents/bogus/persona_state").mock(
+            return_value=httpx.Response(
+                404, json={"error_code": "agent_not_available", "message": "unknown agent"}
+            )
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            with pytest.raises(AgentNotAvailable) as exc_info:
+                await get_persona_state(client, "bogus")
+        assert exc_info.value.agent_id == "bogus"
+
+    @respx.mock
+    async def test_auth_scope_denied_403(self) -> None:
+        """auth_scope_denied_403 [error]: 403 with error_code auth_scope_denied
+        → AuthScopeDenied. Key lacks `persona.read` scope.
+        """
+        respx.get("https://w.example/agents/mimir/persona_state").mock(
+            return_value=httpx.Response(
+                403,
+                json={"error_code": "auth_scope_denied", "message": "missing persona.read"},
+            )
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            with pytest.raises(AuthScopeDenied) as exc_info:
+                await get_persona_state(client, "mimir")
+        assert exc_info.value.scope == "persona.read"
+
+    @respx.mock
+    async def test_404_unknown_error_code_falls_through(self) -> None:
+        """404_unknown_error_code_falls_through [adversarial]: 404 without the
+        two known error codes → SessionApiFailed (don't swallow novel failure
+        modes as something more specific than they are).
+        """
+        respx.get("https://w.example/agents/mimir/persona_state").mock(
+            return_value=httpx.Response(404, json={"error_code": "novel_404"})
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            with pytest.raises(SessionApiFailed) as exc_info:
+                await get_persona_state(client, "mimir")
+        assert exc_info.value.status == 404
+
+    @respx.mock
+    async def test_500_unexpected_status(self) -> None:
+        """500_unexpected_status [error]: 5xx → SessionApiFailed (matches the
+        list_agents / list_sessions / create_session precedent)."""
+        respx.get("https://w.example/agents/mimir/persona_state").mock(
+            return_value=httpx.Response(500, content=b"boom")
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            with pytest.raises(SessionApiFailed) as exc_info:
+                await get_persona_state(client, "mimir")
+        assert exc_info.value.status == 500

tests/test_sse_client.py

@@ -5,6 +5,7 @@ import pytest
 import respx
 
 from ratatoskr.sse_client import (
+    AffectUpdate,
     CancelAlreadyCompleted,
     Cancelled,
     CancelResult,
@@ -877,3 +878,80 @@ class TestEmptyDataSkipped:
         assert exc_info.value.raw == "x" * 200
         # Exception message also only contains the truncated form
         assert "x" * 5000 not in str(exc_info.value)
+
+
+class TestAffectUpdate:
+    """Worldtree #204 / v0.28.0 — persona-state observability SSE event.
+
+    Two emissions per qualifying turn (persona-enabled agent, non-ephemeral
+    session): `status: "current"` at turn start with full snapshot, then
+    `status: "scheduled"` near turn end (lightweight, no snapshot).
+
+    See docs/conversation-api-spec.md § affect_update.
+    """
+
+    @respx.mock
+    async def test_current_status_parsed_with_snapshot(self) -> None:
+        """current_status_parsed_with_snapshot [tracer]: status=current carries
+        the full snapshot dict; AffectUpdate.snapshot is populated with the
+        nested PAD / dominant_emotion / emotions_active fields.
+        """
+        snapshot = {
+            "agent_id": "mimir",
+            "pad": {"pleasure": 0.52, "arousal": 0.47, "dominance": 0.50},
+            "dominant_emotion": "curiosity",
+            "emotions_active": [
+                {"type": "curiosity", "intensity": 0.6, "decay_remaining_s": 202.7}
+            ],
+            "baseline_pad": {"pleasure": 0.50, "arousal": 0.40, "dominance": 0.50},
+            "mood_drift": {"valence_delta": 0.02, "arousal_delta": 0.07},
+            "last_updated_at": "2026-05-25T22:30:18+00:00",
+        }
+        stream = _sse_chunk(
+            "42:1",
+            {
+                "type": "affect_update",
+                "status": "current",
+                "turn_id": 42,
+                "snapshot": snapshot,
+            },
+        ) + _sse_chunk("42:2", _DONE_42_6)
+        respx.post("https://w.example/sessions/s1/messages").mock(
+            return_value=httpx.Response(
+                200, headers={"content-type": "text/event-stream"}, content=stream
+            )
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            events = [e async for e in stream_turn(client, "s1", "hi")]
+        affect = events[0]
+        assert isinstance(affect, AffectUpdate)
+        assert affect.status == "current"
+        assert affect.turn_id == 42
+        assert affect.snapshot == snapshot
+        assert affect.sse_id == SseId(42, 1)
+
+    @respx.mock
+    async def test_scheduled_status_parsed_no_snapshot(self) -> None:
+        """scheduled_status_parsed_no_snapshot [trace]: status=scheduled carries
+        no snapshot field; AffectUpdate.snapshot is None.
+        """
+        stream = (
+            _sse_chunk("42:1", {"type": "text", "content": "x"})
+            + _sse_chunk(
+                "42:2",
+                {"type": "affect_update", "status": "scheduled", "turn_id": 42},
+            )
+            + _sse_chunk("42:3", _DONE_42_6)
+        )
+        respx.post("https://w.example/sessions/s1/messages").mock(
+            return_value=httpx.Response(
+                200, headers={"content-type": "text/event-stream"}, content=stream
+            )
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            events = [e async for e in stream_turn(client, "s1", "hi")]
+        affect = next(e for e in events if isinstance(e, AffectUpdate))
+        assert affect.status == "scheduled"
+        assert affect.turn_id == 42
+        assert affect.snapshot is None
+        assert affect.sse_id == SseId(42, 2)

tests/test_tui.py

@@ -605,6 +605,183 @@ class TestTuiPresenterState:
         assert "usage 6756 in → 126 out (6882 total, 0 cached)" in done_line
 
 
+class TestPresenterAuditLogging:
+    """v0.10.0 — per-event audit lines + turn-summary in the debug pane.
+
+    The presenter emits one debug-pane line per arriving event (Text and
+    Thinking are aggregated into the turn-summary instead of per-delta to
+    avoid drowning the pane at token rate).
+    """
+
+    def test_worker_phase_emits_audit_line(self) -> None:
+        """worker_phase_emits_audit_line: WorkerPhase arrival adds an audit
+        line to debug_log alongside the existing `· worker_phase:` entry.
+        Audit line shape: `[HH:MM:SS.fff] workerphase sse_id=N:M …`.
+        """
+        from ratatoskr.tui import TuiPresenterState
+
+        debug_log = MagicMock()
+        state = TuiPresenterState()
+        state.render(
+            WorkerPhase(sse_id=SID, phase="streaming", turn_id=42),
+            transcript=MagicMock(),
+            tools_log=MagicMock(),
+            debug_log=debug_log,
+            thinking_log=MagicMock(),
+            raw=False,
+        )
+        # Two writes: audit line + worker_phase telemetry.
+        assert debug_log.write.call_count == 2
+        audit_line = _text_of(debug_log.write.call_args_list[0][0][0])
+        assert "workerphase" in audit_line
+        assert "sse_id=42:5" in audit_line
+        assert "phase=streaming" in audit_line
+
+    def test_tool_start_emits_audit_line(self) -> None:
+        """tool_start_emits_audit_line: ToolStart adds one audit line to
+        debug_log even though the tool event itself routes to tools_log.
+        """
+        from ratatoskr.tui import TuiPresenterState
+
+        debug_log = MagicMock()
+        state = TuiPresenterState()
+        state.render(
+            ToolStart(sse_id=SID, name="read_file", arguments={"path": "/x"}),
+            transcript=MagicMock(),
+            tools_log=MagicMock(),
+            debug_log=debug_log,
+            thinking_log=MagicMock(),
+            raw=False,
+        )
+        assert debug_log.write.call_count == 1
+        audit_line = _text_of(debug_log.write.call_args[0][0])
+        assert "toolstart" in audit_line
+        assert "sse_id=42:5" in audit_line
+        assert "name=read_file" in audit_line
+
+    def test_text_delta_counted_not_per_event_audit_line(self) -> None:
+        """text_delta_counted_not_per_event_audit_line: a Text delta does
+        NOT emit a per-event audit line (token-rate would drown the pane);
+        instead it bumps text_delta_count / text_byte_count for the turn-
+        summary at Done.
+        """
+        from ratatoskr.tui import TuiPresenterState
+
+        debug_log = MagicMock()
+        state = TuiPresenterState()
+        state.render(
+            Text(sse_id=SID, content="hello world"),
+            transcript=MagicMock(),
+            tools_log=MagicMock(),
+            debug_log=debug_log,
+            thinking_log=MagicMock(),
+            raw=False,
+        )
+        # No debug-pane writes — text deltas are silent at token rate.
+        assert not debug_log.write.called
+        assert state.text_delta_count == 1
+        assert state.text_byte_count == len("hello world")
+
+    def test_affect_update_routes_to_audit_only(self) -> None:
+        """affect_update_routes_to_audit_only [v0.11.0]: AffectUpdate emits ONE
+        debug-pane audit line (with dominant_emotion + PAD for status=current)
+        and touches NO other pane (no transcript mount, no tools_log, no
+        thinking_log). UX shape (persona pane / sticky header) is deferred.
+        """
+        from ratatoskr.sse_client import AffectUpdate
+        from ratatoskr.tui import TuiPresenterState
+
+        transcript = MagicMock()
+        tools_log = MagicMock()
+        thinking_log = MagicMock()
+        debug_log = MagicMock()
+        state = TuiPresenterState()
+        snapshot = {
+            "agent_id": "mimir",
+            "pad": {"pleasure": 0.5, "arousal": 0.4, "dominance": 0.5},
+            "dominant_emotion": "curiosity",
+        }
+        state.render(
+            AffectUpdate(sse_id=SID, status="current", turn_id=42, snapshot=snapshot),
+            transcript=transcript,
+            tools_log=tools_log,
+            debug_log=debug_log,
+            thinking_log=thinking_log,
+            raw=False,
+        )
+        assert debug_log.write.call_count == 1
+        audit = _text_of(debug_log.write.call_args[0][0])
+        assert "affectupdate" in audit
+        assert "status=current" in audit
+        assert "dominant_emotion='curiosity'" in audit
+        assert "pad=(0.5,0.4,0.5)" in audit
+        assert not transcript.mount.called
+        assert not tools_log.write.called
+        assert not thinking_log.write.called
+
+    def test_affect_update_scheduled_has_no_pad_detail(self) -> None:
+        """affect_update_scheduled_has_no_pad_detail [v0.11.0]: status=scheduled
+        carries no snapshot — the audit line omits dominant_emotion / pad and
+        contains only status + turn_id.
+        """
+        from ratatoskr.sse_client import AffectUpdate
+        from ratatoskr.tui import TuiPresenterState
+
+        debug_log = MagicMock()
+        state = TuiPresenterState()
+        state.render(
+            AffectUpdate(sse_id=SID, status="scheduled", turn_id=42, snapshot=None),
+            transcript=MagicMock(),
+            tools_log=MagicMock(),
+            debug_log=debug_log,
+            thinking_log=MagicMock(),
+            raw=False,
+        )
+        audit = _text_of(debug_log.write.call_args[0][0])
+        assert "status=scheduled" in audit
+        assert "turn_id=42" in audit
+        assert "dominant_emotion" not in audit
+        assert "pad=" not in audit
+
+    def test_done_emits_turn_summary_line(self) -> None:
+        """done_emits_turn_summary_line: when Done arrives the presenter
+        emits a `turn_summary` line aggregating per-delta Text + Thinking
+        counters. The shape exposes the totals that per-event audit lines
+        elided.
+        """
+        from ratatoskr.tui import TuiPresenterState
+
+        debug_log = MagicMock()
+        state = TuiPresenterState()
+        # 3 Text deltas + 2 Thinking deltas, then Done.
+        state.render(
+            Text(sse_id=SID, content="a"),
+            transcript=MagicMock(), tools_log=MagicMock(),
+            debug_log=debug_log, thinking_log=MagicMock(), raw=False,
+        )
+        state.render(
+            Text(sse_id=SID, content="bc"),
+            transcript=MagicMock(), tools_log=MagicMock(),
+            debug_log=debug_log, thinking_log=MagicMock(), raw=False,
+        )
+        state.render(
+            Thinking(sse_id=SID, content="thought\n"),
+            transcript=MagicMock(), tools_log=MagicMock(),
+            debug_log=debug_log, thinking_log=MagicMock(), raw=False,
+        )
+        state.render(
+            _make_tui_done(),
+            transcript=MagicMock(), tools_log=MagicMock(),
+            debug_log=debug_log, thinking_log=MagicMock(), raw=False,
+        )
+        writes = [_text_of(c[0][0]) for c in debug_log.write.call_args_list]
+        summary = next(w for w in writes if "turn_summary" in w)
+        assert "text_deltas=2" in summary
+        assert "text_bytes=3" in summary  # "a" + "bc"
+        assert "thinking_deltas=1" in summary
+        assert "elapsed_ms=" in summary
+
+
 def _text_of(write_arg: object) -> str:
     """Extract plain text from a RichLog.write() arg (str or rich.text.Text).
 
@@ -715,6 +892,47 @@ class TestCancelViaSse:
         assert "[cancel_failed]" in line
         assert "ConnectError" in line
 
+    @respx.mock
+    async def test_audit_callback_records_lifecycle(self) -> None:
+        """audit_callback_records_lifecycle [v0.10.0]: when the caller passes
+        an `audit` callback, _cancel_via_sse emits two lines on the happy
+        path (`cancel_post issued …` + `cancel_post ok …`) and two lines on
+        the failure path (`issued` + `failed …`). Gives the debug pane a
+        complete cancel-POST timeline.
+        """
+        respx.post("https://w.example/sessions/s-1/turns/42/cancel").mock(
+            return_value=httpx.Response(200, json=_CANCEL_OK_RESP)
+        )
+        transcript = MagicMock()
+        audit_lines: list = []
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            await _cancel_via_sse(
+                client, "s-1", 42, transcript=transcript, audit=audit_lines.append
+            )
+        assert len(audit_lines) == 2
+        assert audit_lines[0].startswith("cancel_post issued ")
+        assert "session_id=s-1" in audit_lines[0]
+        assert "turn_id=42" in audit_lines[0]
+        assert audit_lines[1] == "cancel_post ok turn_id=42"
+
+    @respx.mock
+    async def test_audit_callback_records_failure(self) -> None:
+        """audit_callback_records_failure [v0.10.0]: failure path emits
+        `cancel_post issued` then `cancel_post failed …` with exception type.
+        """
+        respx.post("https://w.example/sessions/s-1/turns/42/cancel").mock(
+            return_value=httpx.Response(500, content=b"boom")
+        )
+        transcript = MagicMock()
+        audit_lines: list = []
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            await _cancel_via_sse(
+                client, "s-1", 42, transcript=transcript, audit=audit_lines.append
+            )
+        assert len(audit_lines) == 2
+        assert audit_lines[0].startswith("cancel_post issued ")
+        assert audit_lines[1].startswith("cancel_post failed turn_id=42 CancelFailed")
+
 
 class TestAppMount:
     """on_mount narrows per issue #6: only identity-widget population.

uv.lock

@@ -968,7 +968,7 @@ wheels = [
 
 [[package]]
 name = "ratatoskr"
-version = "0.9.0"
+version = "0.12.0"
 source = { editable = "." }
 dependencies = [
     { name = "httpx" },