fix(tui): coalesce thinking deltas on \n (v0.7.1)

Operator: "thinking tokens seem to be split by token — each on a newline, is that correct? We don't want that." Root cause: v0.6.5 wrote each Thinking SSE delta as its own `thinking_log.write(event.content)` call. Worldtree emits Thinking events at token granularity (per-token or per-few-tokens), so EACH token became its own RichLog line — visually choppy, one short fragment per visual row. Wrong UX. ## Fix: coalesce-on-newline Thinking deltas accumulate in `TuiPresenterState.thinking_chunk_buffer` (new str field). On each Thinking event: 1. Append delta content to buffer. 2. Flush every COMPLETE line (chars before each `\n`) as one thinking_log.write(line) call. 3. Leave the post-final-`\n` tail in the buffer for the next delta. On any non-thinking event (run close): 1. Flush remaining buffer tail (if any) as one final line. 2. Write Rule(end). Empty lines (blank paragraph separators in the model's `\n\n` flow) are skipped — they'd render as no-content RichLog entries which just add vertical noise. Natural paragraph breaks become single visible lines; multi-paragraph thinking renders top-to-bottom. ## Verified live (tier-3 smoke against personal Worldtree) Defined a `thinky-smoke` agent via `python -m ratatoskr.tier3 define`, asked "What is 12 times 13?". Thinking pane rendered with natural paragraph chunks: ── turn N · thinking #1 start ── Thinking Process: 1. **Analyze the Request:** The user wants to know the result of $12 \times 13$. 2. **Calculate:** * Method 1: Standard multiplication. $$12 \times 10 = 120$$ $$12 \times 3 = 36$$ $$120 + 36 = 156$$ * Method 2: $(10 + 2)(10 + 3) = 100 + 30 + 20 + 6 = 156$. ── turn N · thinking #1 end ── Each line = one natural paragraph or list item. No per-token fragments. ## Edge cases noted - Long-running thinking with NO `\n` at all stays buffered until run close → operator sees nothing until close. Possible follow-up: add a length-threshold flush (e.g., > 500 chars → flush at the last space). For now this is acceptable; thinking content typically has `\n` breaks every few sentences. - Empty deltas (`""`) are ignored implicitly — no buffer growth, no flush. - `\n` at the very start of a delta flushes whatever was buffered before, then leaves the empty post-`\n` tail (empty string) in the buffer, which doesn't show up as an empty line because of the `if line:` guard. ## Contract amendment docs/contracts/issues/13.contract.md INV-022 amended for v0.7.1 coalesce semantics. Drift-check clean. ## Tests 265/265 GREEN; ruff clean. Two updated tests: - `test_thinking_streams_into_thinking_log` → renamed `test_thinking_coalesces_until_newline`: 3 token-shaped deltas with no `\n` → only Rule(start) writes, buffer holds accumulated. - NEW `test_thinking_flushes_on_newline`: delta carrying `\n` → Rule(start) + accumulated line + clear buffer. - `test_thinking_closes_to_thinking_log`: 2 deltas "a", "b" + close → Rule(start) + tail-flush "ab" + Rule(end) = 3 writes (was 4 with per-delta). Patch bump (v0.7.0 → v0.7.1) — internal presenter routing change; no public-API or layout change.
feat(tier3): ratatoskr.tier3 module + CLI (v0.7.0)
2026-05-24 20:39:55 -07:00 · 2026-05-24 20:31:10 -07:00 · 2026-05-24 19:00:58 -07:00 · 2026-05-24 18:33:53 -07:00 · 2026-05-24 18:20:57 -07:00 · 2026-05-24 18:15:54 -07:00
9 changed files with 1767 additions and 384 deletions
@@ -158,8 +158,12 @@ New `Static(id="pane-name")` widget alongside the existing `identity` + `hint` w
 - **INV-016**: Input retains keyboard focus across `Ctrl+1` / `Ctrl+2` tab switches.
 - **INV-017** *(amended v0.5.0)*: `thinking-current` Static docks to the top of the **right column** (above `TabbedContent`), not the left column. Live thinking visibility persists across tab switches. v0.5.0 moves it from left → right so the left column is genuinely content-only.
 - **INV-018**: CLI mode (`ratatoskr.cli._amain`) is unaffected. CLI keeps inline `· tool_start: …` / `· tool_result: …` rendering on stderr per issue #12 INV-005.
- **INV-019** *(new v0.5.0)*: Two TabPanes in the right column: `Tools` (id `tools-tab`, contains `#tools-log`) + `Debug` (id `debug-tab`, contains `#debug-log`). Ctrl+1 activates Tools; Ctrl+2 activates Debug. `pane-name` Static reflects the active tab name dynamically.
- **INV-020** *(new v0.5.0)*: Render-exception fallback (INV-009) preserves routing per event class: `ToolStart` / `ToolResult` fallback writes to `tools_log`; `WorkerPhase` / `Thinking` / `TextBoundary` fallback writes to `debug_log`; everything else falls back to `log`.
+- **INV-019** *(amended v0.6.0)*: Three TabPanes in the right column: `Tools` (id `tools-tab`, contains `#tools-log`) + `Debug` (id `debug-tab`, contains `#debug-log`) + `Thinking` (id `thinking-tab`, contains `#thinking-log`). Ctrl+1/Ctrl+2/Ctrl+3 activate respective tabs. `pane-name` Static reflects active tab name dynamically.
+- **INV-020** *(amended v0.6.0)*: Render-exception fallback (INV-009) preserves routing per event class: `ToolStart` / `ToolResult` → `tools_log`; `Thinking` → `thinking_log`; `WorkerPhase` / `TextBoundary` → `debug_log`; everything else → `log`.
+- **INV-021** *(new v0.6.0)*: `Text` events do NOT route to `log` per-delta. They accumulate into `TuiPresenterState.text_buffer` and update a single `current_text` Static (docked above the prompt). On terminal event (`Done`/`Error`/`Cancelled`), `current_text` is cleared and (raw mode) accumulated text or (non-raw) post-Done `Markdown(response)` is written to `log`. The pre-v0.6.0 per-token RichLog spam is retired.
+- **INV-022** *(amended v0.7.1)*: Thinking deltas COALESCE on `\n` boundaries before writing to `thinking_log`. The first delta of a run writes `Rule(title=f"turn N · thinking #K start")`; subsequent deltas accumulate in `TuiPresenterState.thinking_chunk_buffer`; whenever the buffer contains `\n`, the leading line(s) flush as RichLog entries (one entry per natural paragraph). The run closes on the next non-thinking event: any tail in the buffer flushes as a final line, then `Rule(title=f"turn N · thinking #K end")`. Pre-v0.7.1 per-delta-per-line caused token-spam (Worldtree emits thinking at token granularity); coalescing produces one log line per natural paragraph, not per token.
+- **INV-023** *(new v0.6.0)*: Turn-ID header `Rule(title=f"turn N")` is written to all four log panes (`log`, `tools_log`, `debug_log`, `thinking_log`) by `_stream_turn_worker` on the first event of each turn — enables cross-pane visual correlation during multi-turn debugging.
+- **INV-024** *(amended v0.6.5)*: `thinking-current` Static REMOVED. v0.6.1 placed it inside the Thinking pane (docked bottom); operators reported the bottom-docked Static "scrolling a little section at the bottom" (its 200-char tail acting as a scroll-window) instead of letting the whole pane scroll. v0.6.5 deletes the Static entirely and streams Thinking deltas directly into `thinking_log` (the scrollable RichLog) — the whole pane scrolls naturally as content arrives. The Rule(start) at the first delta of a run is now the live "thinking is happening" indicator.

 ## TESTS (additions / changes to test_tui.py)

@@ -0,0 +1,290 @@
+---
+contract_version: "2.1"
+target_module: "ratatoskr.tier3"
+scope: "New module `ratatoskr.tier3` exposing Worldtree's Tier 3 (consumer-defined) agent lifecycle: `define_agent` (POST /agents/define), `patch_agent` (PATCH /agents/<id>), `delete_agent` (DELETE /agents/<id>), plus `Tier3AgentInfo` frozen dataclass. Plus a thin CLI entry point (`python -m ratatoskr.tier3 <define|patch|delete>`) that mirrors `ratatoskr.cli`'s env-var posture (`WORLDTREE_API_URL`, `WORLDTREE_API_KEY`). Convention-aligned with `ratatoskr.sessions` (issue #2): caller-owned httpx.AsyncClient, no Worldtree imports, response parsing into frozen dataclass, exception `.body` truncated to `[:1024]`. Picker stays generic — agents with `:` in agent_id show in the list like any other per issue #8's out-of-scope clause. Goal: ratatoskr operators can define, mutate, and delete Tier 3 agents from the command line, then exercise the full session flow against them to observe how Tier 3 agent_ids (colon-containing) flow through the picker / session-create / SSE stream."
+depends_on:
+  - "httpx"
+used_by: []
+language: "python"
+complexity: "low"
+estimated_loc: 250
+confidence: 0.9
+assumptions:
+  - "Tier 3 endpoints land at the same `WORLDTREE_API_URL` as the rest of the Conversation API — no separate hostname / port. Auth via the same bearer key. The caller's user_id is derived server-side from the API key's owner; the agent's `agent_id` is constructed as `<auth_user_id>:<agent_name>`. Live probe against personal Worldtree (2026-05-25) confirmed: POST with `{agent_name: 'smoke-test', ...}` and `Authorization: Bearer <key>` returned `agent_id=ratatoskr:smoke-test`, `user_id=ratatoskr`."
+  - "Per Worldtree spec §2576-2750: `agent_name` is a strict slug `[a-z][a-z0-9-]{2,63}` and immutable after definition. `user_id` is derived from the auth, must be slug-safe (`[a-z][a-z0-9-]{2,63}` per Phase 2.0 gate). PATCH accepts ONLY `system_prompt` and/or `model`; any other key (including the immutable `agent_name`, `user_id`, or layer fields `persona`/`motivational`/`valence`/`memory` — even with `null` value) returns 422 `field_not_mutable` BEFORE the DB lookup."
+  - "**Layer fields are explicitly null** on define. Phase 2.0 ships baseline addressing + ownership + lifecycle only; `persona` / `motivational` / `valence` / `memory` are schema-reserved. Non-null on these → 422 `layer_deferred`. The module's `define_agent` does NOT expose these as parameters at all — sending them would require an amendment when a future Phase enables them."
+  - "**`model` field is a provider model ID, not a profile alias.** Live probe found: `model='default'` (an llm_profiles profile name) returns 422 `model_not_available`; `model='qwen3.6-35-a3b'` (an actual provider model ID) returns 201. The CLI / module take the string verbatim and pass through — validation is server-side. Operators discover valid IDs via the model `metadata` on existing sessions or out-of-band."
+  - "**Quota: 50 Tier 3 agents per Heimdall key.** 51st define → 429 `agent_quota_exceeded` with `Retry-After: 0`. The module raises `Tier3QuotaExceeded(retry_after=0)` — the retry_after field captures the header value verbatim for forward-compat if Worldtree later returns a non-zero throttle."
+  - "**Key-revocation cascade is server-side.** When an API key is revoked (`DELETE /admin/keys/{key_id}`), every Tier 3 agent with `owner_key_hash` equal to the revoked key's hash is soft-deleted in the same SQL transaction. Active sessions on those agents return 401 `auth_revoked` on next message. The ratatoskr module doesn't track or simulate this — operators discover it via runtime 401s and the admin-side audit log."
+  - "**Picker integration is implicit** — no changes to `ratatoskr.tui.AgentPickerApp` for this issue. Tier 3 agents appear in `GET /agents` if defined and the picker's existing format `{agent_id} · {name} — {description}` renders the colon-containing agent_id without special-casing. Per issue #8 out-of-scope clause, ratatoskr does not visually distinguish Tier 1 vs Tier 3 in the picker — same UX surface."
+  - "**Session-create with colon-containing agent_id works unchanged.** Issue #5 already routes `end_user_id` into the POST /sessions body, which Tier 3 session-create requires from Phase 2.0 (per spec §2649-2664). No `ratatoskr.sessions` change needed."
+  - "**CLI uses argparse with subparsers** (define / patch / delete). The subparsers entry point lives at `python -m ratatoskr.tier3` via `__main__.py`. Output on success: prints a one-line summary (`defined ratatoskr:wizard (qwen3.6-35-a3b)` / `patched ratatoskr:wizard` / `deleted ratatoskr:wizard`). Output on error: `[<error_code>] <message>` to stderr + non-zero exit. Exit codes mirror `ratatoskr.cli`: 0 happy / 10 usage / 11 auth / 20 api-failure / 21 network."
+  - "**No `list` subcommand in v1.** A `tier3 list` operation would have to filter `GET /agents` by prefix-matching the caller's user_id, but that prefix isn't exposed in the response — only the agent_id is, and you'd have to introspect the auth's user_id. Operators discover their own Tier 3 agents by reading the `GET /agents` list (which the picker already surfaces) and looking for `<their-user-id>:*` entries. Add `list` in a follow-up if operators report friction."
+  - "**Module is standalone**: does NOT import or interact with `ratatoskr.sessions` / `ratatoskr.sse_client` / `ratatoskr.tui` / `ratatoskr.cli` beyond reusing the `USER_AGENT` constant from `ratatoskr.cli`. Cross-module use is one-way (cli supplies the user-agent string; tier3 does not import sessions). This keeps the module surface minimal and testable in isolation."
+  - "**The CLI's `python -m ratatoskr.tier3` entry point uses sys.argv handling that mirrors `ratatoskr.cli`** — a top-level `main(argv: list[str] | None = None) -> int` function that argparse-dispatches to subcommand handlers. Each subcommand handler is an async coroutine wrapped by `asyncio.run(...)`. Auth resolution: `--api-key` flag > `$WORLDTREE_API_KEY` env > `_AuthError` (exit 11). Server URL: `--server` > `$WORLDTREE_API_URL` > default `http://localhost:8000` (same default as `ratatoskr.cli`)."
+  - "**Tests use `respx` for HTTP mocking** (same pattern as `tests/test_sessions.py`). New test file: `tests/test_tier3.py`. Cover all success + error response codes per the ERROR_ROUTING matrix below. No live network in unit tests — the live smoke is in the acceptance criteria, not the unit tests."
+open_questions:
+  - "Should `define_agent` accept an optional `bifrost` parameter for Bifrost-bound Tier 3 sessions? The spec §2658 shows `bifrost` as a session-create field (not define-time). Draft: no — Bifrost binding is per-session; if a Tier 3 agent needs Bifrost on every session, that's an orthogonal feature on POST /sessions, not POST /agents/define. Issue #5's `--end-user-id` already covers the session-create-side parameters."
+  - "Should the CLI also offer `--end-user-id` for sessions created via tier3 + ratatoskr-cli composition? Draft: no — once an agent is defined, operators use the main `ratatoskr --new --agent <id> --end-user-id <eid>` flow; tier3 CLI is define/patch/delete only."
+  - "Should `delete_agent` support a `--force` flag for 'really delete even if active sessions exist'? Per spec §2634-2639, `DELETE` already cancels active sessions and revokes the per-resource scope grant on the owner — there's no soft fail. Draft: no — the spec's hard-delete-with-cascade behavior is the right shape; ratatoskr doesn't need to wrap it."
+prd:
+  issue: 15
+  issue_url: "https://gitea.phasefinal.com/vh/ratatoskr/issues/15"
+  body_sha256_16: "03367d7b451ab17f"
+  lock_in_comment_id: null
+  lock_in_sha256_16: null
+  lock_in_at: null
+  pinned_at: "2026-05-25T03:21:38+00:00"
+dependencies:
+  - issue: 2
+    path: "src/ratatoskr/sessions.py"
+    reason: "Convention dependency, not a code dependency. Issue #2 (`ratatoskr.sessions`) is the posture template: caller-owned httpx client, async-native, no Worldtree imports, response-parsing into frozen dataclasses, exception body truncation to [:1024]. `ratatoskr.tier3` follows the same shape verbatim."
+  - issue: 3
+    path: "src/ratatoskr/cli.py"
+    reason: "Convention dependency only. `ratatoskr.tier3.__main__` mirrors `ratatoskr.cli`'s argparse + env-fallback + exit-code shape. Imports `USER_AGENT` from `ratatoskr.cli` so outbound HTTP carries the same identity string."
+---
+
+# Tier 3 — Consumer-defined agent lifecycle module
+
+## Context
+
+Worldtree's Tier 3 (Phase 2.0, spec §2576-2750) lets the consumer define their own agents at `<user_id>:<agent_name>`. The agent's `user_id` is the auth's user identity (derived from the API key's owner); the `agent_name` is supplied at define-time. The lifecycle is owner-only — only the key that defined an agent can patch / delete it (modulo the key-revocation cascade).
+
+`ratatoskr.tier3` exposes this lifecycle as a Python module + small CLI tool. Picker integration is implicit (Tier 3 agents already appear in `GET /agents` per issue #8). Session-create works unchanged through `ratatoskr.sessions.create_session` since the colon-containing agent_id is opaque to that layer.
+
+## Public surface
+
+```python
+@dataclass(frozen=True)
+class Tier3AgentInfo:
+    """Worldtree Tier 3 agent envelope returned by define / patch."""
+
+    agent_id: str       # f"{user_id}:{agent_name}"
+    user_id: str
+    agent_name: str
+    system_prompt: str
+    model: str
+    created_at: str     # ISO 8601 with offset
+    updated_at: str     # ISO 8601 with offset
+
+
+async def define_agent(
+    client: httpx.AsyncClient,
+    *,
+    agent_name: str,
+    system_prompt: str,
+    model: str,
+) -> Tier3AgentInfo:
+    """POST /agents/define → 201 with Tier3AgentInfo. See FN define_agent."""
+
+
+async def patch_agent(
+    client: httpx.AsyncClient,
+    agent_id: str,
+    *,
+    system_prompt: str | None = None,
+    model: str | None = None,
+) -> Tier3AgentInfo:
+    """PATCH /agents/<id> → 200 with updated Tier3AgentInfo. See FN patch_agent."""
+
+
+async def delete_agent(client: httpx.AsyncClient, agent_id: str) -> None:
+    """DELETE /agents/<id> → 204. See FN delete_agent."""
+```
+
+## Exception classes
+
+```python
+class Tier3QuotaExceeded(Exception):
+    """429 agent_quota_exceeded — 50-agent cap reached on the Heimdall key."""
+    def __init__(self, *, retry_after: int) -> None: ...
+    retry_after: int
+
+class Tier3UserIdUnsupported(Exception):
+    """403 tier3_user_id_unsupported — auth's user_id not slug-safe."""
+
+class Tier3FieldNotMutable(Exception):
+    """422 field_not_mutable — PATCH carrying an immutable key."""
+    def __init__(self, *, field: str | None) -> None: ...
+    field: str | None
+
+class Tier3LayerDeferred(Exception):
+    """422 layer_deferred — define carrying non-null layer field."""
+    def __init__(self, *, field: str | None) -> None: ...
+    field: str | None
+
+class Tier3AgentNotFound(Exception):
+    """404 — patch/delete on non-existent agent."""
+    def __init__(self, *, agent_id: str) -> None: ...
+    agent_id: str
+
+# Reused from ratatoskr.sessions (one-way import — sessions doesn't depend on tier3):
+# SessionApiFailed(status, body) for all other non-2xx responses.
+```
+
+## Functions
+
+### FN define_agent
+
+```
+FN define_agent(
+    client: httpx.AsyncClient,
+    *, agent_name: str, system_prompt: str, model: str,
+) -> Tier3AgentInfo
+BRIEF: POST /agents/define → 201 with Tier3AgentInfo.
+
+PRE-001: agent_name matches `[a-z][a-z0-9-]{2,63}` (slug guard — client-side
+         assert; the server enforces too, but this prevents wire round-trip
+         for trivially-bad input).
+PRE-002: system_prompt is non-empty.
+PRE-003: model is non-empty.
+
+STEPS:
+  1. assert PRE-001/002/003.
+  2. body = {
+       "agent_name": agent_name,
+       "system_prompt": system_prompt,
+       "model": model,
+     }
+  3. resp = await client.post("/agents/define", json=body)
+  4. ROUTE response status:
+     201 → parse body into Tier3AgentInfo, return.
+     422 → inspect error_code:
+       layer_deferred → raise Tier3LayerDeferred(field=err.get("field"))
+       (others) → raise SessionApiFailed(status=422, body=resp.content)
+     403 + tier3_user_id_unsupported → raise Tier3UserIdUnsupported
+     429 → raise Tier3QuotaExceeded(retry_after=int(resp.headers.get("Retry-After", 0)))
+     other → raise SessionApiFailed(status, body)
+
+POST-001: returned Tier3AgentInfo has agent_id of shape "<user_id>:<agent_name>".
+```
+
+### FN patch_agent
+
+```
+FN patch_agent(
+    client: httpx.AsyncClient, agent_id: str,
+    *, system_prompt: str | None = None, model: str | None = None,
+) -> Tier3AgentInfo
+BRIEF: PATCH /agents/<id> → 200 with updated Tier3AgentInfo.
+
+PRE-001: agent_id contains `:` (Tier 3 shape).
+PRE-002: at least one of system_prompt or model is non-None (no-op patches
+         are still server-accepted but client-side assert avoids the round-trip).
+
+STEPS:
+  1. assert PRE-001/002.
+  2. body = {}; if system_prompt is not None: body["system_prompt"] = system_prompt;
+     if model is not None: body["model"] = model.
+  3. resp = await client.patch(f"/agents/{agent_id}", json=body)
+  4. ROUTE response status:
+     200 → parse, return.
+     404 → raise Tier3AgentNotFound(agent_id=agent_id)
+     422 + field_not_mutable → raise Tier3FieldNotMutable(field=err.get("field"))
+     other → raise SessionApiFailed(status, body)
+```
+
+### FN delete_agent
+
+```
+FN delete_agent(client: httpx.AsyncClient, agent_id: str) -> None
+BRIEF: DELETE /agents/<id> → 204.
+
+PRE-001: agent_id contains `:` (Tier 3 shape).
+
+STEPS:
+  1. assert PRE-001.
+  2. resp = await client.delete(f"/agents/{agent_id}")
+  3. ROUTE response status:
+     204 → return None.
+     404 → raise Tier3AgentNotFound(agent_id=agent_id)
+     other → raise SessionApiFailed(status, body)
+```
+
+## CLI surface (`python -m ratatoskr.tier3`)
+
+```
+$ python -m ratatoskr.tier3 define --name wizard \
+    --system-prompt "You are a guided-elicitation wizard..." \
+    --model qwen3.6-35-a3b
+defined ratatoskr:wizard (qwen3.6-35-a3b)
+
+$ python -m ratatoskr.tier3 patch ratatoskr:wizard --system-prompt "New prompt"
+patched ratatoskr:wizard
+
+$ python -m ratatoskr.tier3 delete ratatoskr:wizard
+deleted ratatoskr:wizard
+```
+
+Auth + server URL: same env-var fallback as `ratatoskr.cli`. Exit codes: 0 / 10 (usage) / 11 (auth) / 20 (api-failure) / 21 (network).
+
+## Invariants
+
+- **INV-001**: `define_agent` request body carries exactly `{agent_name, system_prompt, model}` — no layer fields, no `bifrost`, no `metadata`. Phase 2.0 baseline shape only.
+- **INV-002**: `patch_agent` request body carries ONLY `system_prompt` and/or `model` — every other key is omitted. Server-side 422 `field_not_mutable` is the safety net; client-side body-construction is the first line.
+- **INV-003**: `delete_agent` is fire-and-confirm — no body, no retry, no soft-delete. Cascade handling is server-side; ratatoskr doesn't track it.
+- **INV-004**: All exceptions carry a `[:1024]` body cap (when applicable) per the issue #2 convention.
+- **INV-005**: CLI auth resolution mirrors `ratatoskr.cli`: `--api-key` flag > `$WORLDTREE_API_KEY` > exit 11.
+- **INV-006**: CLI server URL resolution mirrors `ratatoskr.cli`: `--server` > `$WORLDTREE_API_URL` > `http://localhost:8000`.
+- **INV-007**: Module never imports `ratatoskr.sessions` / `ratatoskr.sse_client` / `ratatoskr.tui` (one-way: only `cli.USER_AGENT` is imported, and only by `__main__.py` for the outbound User-Agent header).
+- **INV-008**: All HTTP through caller-owned `httpx.AsyncClient` — module never constructs its own client. (`__main__` constructs one for the CLI entry point per ratatoskr.cli's pattern.)
+
+## TESTS (tests/test_tier3.py — new file)
+
+```
+- test_define_happy: 201 + full response shape → Tier3AgentInfo populated.
+- test_define_quota_exceeded: 429 + Retry-After header → Tier3QuotaExceeded(retry_after=N).
+- test_define_user_id_unsupported: 403 tier3_user_id_unsupported → Tier3UserIdUnsupported.
+- test_define_layer_deferred_persona: 422 layer_deferred → Tier3LayerDeferred (would only fire if the body sent a layer field; the module never sends one, so this asserts server-side defense but reflecting a 422 we don't actually generate. Test exercises the response path, not the request).
+- test_define_bad_slug: PRE-001 assertion fires before HTTP for agent_name="X" (uppercase) or "ab" (too short).
+- test_define_empty_prompt: PRE-002 assertion fires for empty system_prompt.
+- test_define_other_5xx: 503 → SessionApiFailed(status=503).
+- test_patch_happy_both_fields: 200 + updated body → Tier3AgentInfo.
+- test_patch_happy_single_field: 200 with only system_prompt set; body omits model.
+- test_patch_field_not_mutable: 422 field_not_mutable → Tier3FieldNotMutable.
+- test_patch_404: 404 → Tier3AgentNotFound(agent_id=...).
+- test_patch_no_args: PRE-002 assertion fires (both None).
+- test_patch_non_tier3_id: PRE-001 assertion fires for agent_id without `:`.
+- test_delete_happy: 204 → returns None.
+- test_delete_404: 404 → Tier3AgentNotFound.
+- test_delete_non_tier3_id: PRE-001 assertion fires.
+- test_delete_other_5xx: 500 → SessionApiFailed.
+- test_cli_define_happy: argv → 201 mock → stdout="defined ratatoskr:wizard (qwen3.6-35-a3b)" + exit 0.
+- test_cli_patch_happy: argv → 200 mock → stdout="patched ratatoskr:wizard" + exit 0.
+- test_cli_delete_happy: argv → 204 mock → stdout="deleted ratatoskr:wizard" + exit 0.
+- test_cli_missing_auth: no API key → stderr "[auth_error]" + exit 11.
+- test_cli_api_failed: 500 mock → stderr "[api_failed]" + exit 20.
+```
+
+## ERROR_ROUTING (module + CLI)
+
+| HTTP shape | error_code | Exception (module) | CLI label | Exit |
+|---|---|---|---|---|
+| 201 / 200 / 204 | — | (none — happy) | one-line confirmation on stdout | 0 |
+| 429 | agent_quota_exceeded | `Tier3QuotaExceeded(retry_after=N)` | `[quota_exceeded] retry_after=N` | 20 |
+| 403 | tier3_user_id_unsupported | `Tier3UserIdUnsupported` | `[user_id_unsupported]` | 20 |
+| 404 | — | `Tier3AgentNotFound(agent_id=...)` | `[agent_not_found] <id>` | 20 |
+| 422 | field_not_mutable | `Tier3FieldNotMutable(field=...)` | `[field_not_mutable] field=...` | 20 |
+| 422 | layer_deferred | `Tier3LayerDeferred(field=...)` | `[layer_deferred] field=...` | 20 |
+| any other non-2xx | — | `SessionApiFailed(status, body)` | `[api_failed] status=N body=...` | 20 |
+| httpx.ConnectError / ReadTimeout / TransportError | — | propagates | `[network_error] T: M` | 21 |
+| PRE-001/002/003 assertion violation | — | `AssertionError` | `[usage_error] <msg>` | 10 |
+| no auth | — | `_AuthError` (reused from cli) | `[auth_error] no API key` | 11 |
+
+## Layout after this module lands
+
+```
+src/ratatoskr/
+  __init__.py
+  cli.py            (existing, unchanged)
+  sessions.py       (existing, unchanged)
+  sse_client.py     (existing, unchanged)
+  tui.py            (existing, unchanged)
+  tier3.py          NEW
+  __main__/         (no change — main cli still entry-point)
+
+# CLI invocation:
+$ python -m ratatoskr.tier3 define --name wizard ...
+$ python -m ratatoskr.tier3 patch ratatoskr:wizard ...
+$ python -m ratatoskr.tier3 delete ratatoskr:wizard
+```
@@ -32,9 +32,9 @@ separate dev team rather than an in-tree Worldtree tool.

 ## Current state / in-flight

-_As of 2026-05-24 (post-v0.5.0 content-only main pane + Debug tab):_
+_As of 2026-05-25 (post-v0.7.1 thinking coalesce-by-newline):_

-**Status: v0.5.0 shipped.** Nine core issues complete (`sse_client`
+**Status: v0.7.1 shipped.** Ten core features complete (`sse_client`
 #1, `sessions` #2, `cli` #3, `tui` #4, `--end-user-id` #5, TUI
 startup error visibility #6, presenter contract semantics amendment
 #12, startup agent picker #8, §5 layout reshape + Tools pane #13)
@@ -51,7 +51,16 @@ Static in the footer (static "Tools" v1; dynamic when more tabs
 land). CLI mode (--send) unaffected by design — INV-018.

 Last commits on `main`:
- v0.5.0 refactor(tui): content-only main pane + Debug tab + chrome dark
+- v0.7.1 fix(tui): coalesce thinking deltas on `\n` — no more per-token newlines
+- `c086ae2` feat(tier3): ratatoskr.tier3 module + CLI (v0.7.0)
+- `d356990` refactor(tui): thinking streams into thinking-log (v0.6.5)
+- `82437bd` style(tui): picker highlighted item → Aurora blue (v0.6.4)
+- `ac690c1` style(tui): restore Australis palette, only $background → pure black (v0.6.3)
+- `d845b20` style(tui): neutralize Australis dark palette (v0.6.2, reverted)
+- `8463eb2` style(tui): kill remaining blue + thinking-current into pane (v0.6.1)
+- `cfee89a` refactor(tui): streaming + turn headers + Thinking pane (v0.6.0)
+- `7106af5` style(tui): UI polish pass — terminal label colors, placeholders (v0.5.1)
+- `ffd22fb` refactor(tui): content-only main pane + Debug tab + chrome dark (v0.5.0)
 - `2756f5f` style(tui): apply Australis theme to TUI chrome + widgets (v0.4.1)
 - `24e4371` feat(tui): issue #13 — §5 layout reshape + Tools pane (v0.4.0)
 - `d30be12` feat(sessions,cli,tui): issue #8 — startup agent picker (v0.3.0)
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"

 [project]
 name = "ratatoskr"
-version = "0.5.0"
+version = "0.7.1"
 description = "Worldtree Conversation API debug TUI — multi-pane observability dashboard"
 readme = "README.md"
 requires-python = ">=3.12"
@@ -0,0 +1,438 @@
+"""Worldtree Tier 3 (consumer-defined) agent lifecycle client.
+
+Implements docs/contracts/issues/15.contract.md. Caller-owned httpx.AsyncClient
+posture (same as ratatoskr.sessions). Exposes three lifecycle operations:
+
+- ``define_agent`` — POST /agents/define
+- ``patch_agent`` — PATCH /agents/<id>
+- ``delete_agent`` — DELETE /agents/<id>
+
+Plus a frozen ``Tier3AgentInfo`` dataclass for the response shape. The picker
+already handles colon-containing agent_ids generically (issue #8); session
+creation works unchanged via ``ratatoskr.sessions.create_session``.
+
+Spec reference: ``docs/conversation-api-spec.md`` §2576-2750 (Phase 2.0).
+"""
+
+from __future__ import annotations
+
+import argparse
+import re
+from dataclasses import dataclass
+
+import httpx
+
+from ratatoskr.sessions import SessionApiFailed
+
+# Per spec §2627: agent_name + user_id slugs are `[a-z][a-z0-9-]{2,63}`.
+_SLUG_RE = re.compile(r"^[a-z][a-z0-9-]{2,63}$")
+
+
+@dataclass(frozen=True)
+class Tier3AgentInfo:
+    """Worldtree Tier 3 agent envelope returned by define / patch.
+
+    INV-001: ``agent_id`` is always shape ``"<user_id>:<agent_name>"`` —
+    constructed server-side from the auth's user_id + the supplied agent_name.
+    """
+
+    agent_id: str
+    user_id: str
+    agent_name: str
+    system_prompt: str
+    model: str
+    created_at: str
+    updated_at: str
+
+
+class Tier3QuotaExceeded(Exception):
+    """Raised on HTTP 429 ``agent_quota_exceeded`` — 50-agent cap reached
+    on the Heimdall key. ``retry_after`` captures the Retry-After header
+    verbatim (defaults to 0 per spec §2675; forward-compat for non-zero)."""
+
+    def __init__(self, *, retry_after: int) -> None:
+        super().__init__(f"Tier 3 agent quota exceeded (retry_after={retry_after})")
+        self.retry_after = retry_after
+
+
+class Tier3UserIdUnsupported(Exception):
+    """Raised on HTTP 403 ``tier3_user_id_unsupported`` — auth's user_id
+    is not slug-safe per Phase 2.0 gate (spec §2626)."""
+
+    def __init__(self) -> None:
+        super().__init__("tier3 caller user_id is not slug-safe")
+
+
+class Tier3FieldNotMutable(Exception):
+    """Raised on HTTP 422 ``field_not_mutable`` — PATCH request body
+    carried a key that's immutable post-define (``agent_name``, ``user_id``,
+    or any layer field). Server rejects BEFORE the DB lookup (spec §2644)."""
+
+    def __init__(self, *, field: str | None) -> None:
+        super().__init__(f"field not mutable on Tier 3 patch: {field!r}")
+        self.field = field
+
+
+class Tier3LayerDeferred(Exception):
+    """Raised on HTTP 422 ``layer_deferred`` — define request carried a
+    non-null layer field (``persona`` / ``motivational`` / ``valence`` /
+    ``memory``). Phase 2.0 ships baseline only; layers are schema-reserved.
+
+    Note: ``define_agent`` never sends layer fields, so this exception is
+    defense-against-server-side-changes / forward-compat. INV-001 in the
+    request body construction is the first line of defense.
+    """
+
+    def __init__(self, *, field: str | None) -> None:
+        super().__init__(f"tier3 layer field deferred: {field!r}")
+        self.field = field
+
+
+class Tier3AgentNotFound(Exception):
+    """Raised on HTTP 404 — PATCH or DELETE on a non-existent agent_id
+    (spec §2634 + §2641)."""
+
+    def __init__(self, *, agent_id: str) -> None:
+        super().__init__(f"tier3 agent not found: {agent_id!r}")
+        self.agent_id = agent_id
+
+
+def _extract_error_code(resp: httpx.Response) -> str | None:
+    """Pluck the ``detail.error_code`` from a Worldtree error envelope.
+
+    Worldtree wraps API errors in ``{"detail": {"error_code": "...", ...}}``
+    per the spec. Returns None on shape mismatch (so callers fall through
+    to the generic ``SessionApiFailed`` branch).
+    """
+    try:
+        body = resp.json()
+    except ValueError:
+        return None
+    detail = body.get("detail") if isinstance(body, dict) else None
+    if isinstance(detail, dict):
+        code = detail.get("error_code")
+        if isinstance(code, str):
+            return code
+    return None
+
+
+def _extract_error_field(resp: httpx.Response) -> str | None:
+    """Pluck ``detail.field`` from a Worldtree error envelope (used for
+    ``field_not_mutable`` and ``layer_deferred`` to surface which field
+    triggered the rejection). Returns None on shape mismatch.
+    """
+    try:
+        body = resp.json()
+    except ValueError:
+        return None
+    detail = body.get("detail") if isinstance(body, dict) else None
+    if isinstance(detail, dict):
+        field = detail.get("field")
+        if isinstance(field, str):
+            return field
+    return None
+
+
+def _parse_tier3_agent_info(body: dict) -> Tier3AgentInfo:
+    """Parse a Worldtree Tier 3 agent JSON body into the frozen dataclass."""
+    return Tier3AgentInfo(
+        agent_id=body["agent_id"],
+        user_id=body["user_id"],
+        agent_name=body["agent_name"],
+        system_prompt=body["system_prompt"],
+        model=body["model"],
+        created_at=body["created_at"],
+        updated_at=body["updated_at"],
+    )
+
+
+async def define_agent(
+    client: httpx.AsyncClient,
+    *,
+    agent_name: str,
+    system_prompt: str,
+    model: str,
+) -> Tier3AgentInfo:
+    """POST /agents/define — create a Tier 3 agent.
+
+    See contract FN define_agent. Validates the agent_name slug client-side
+    before the network round-trip; server-side validation is the safety net.
+    Returns a fully populated Tier3AgentInfo on 201. Routes documented error
+    codes to typed exceptions; unknown non-2xx → SessionApiFailed.
+    """
+    assert client is not None
+    assert _SLUG_RE.match(agent_name), (
+        f"agent_name must match [a-z][a-z0-9-]{{2,63}}: {agent_name!r}"
+    )
+    assert system_prompt, "system_prompt must be non-empty"
+    assert model, "model must be non-empty"
+
+    body = {
+        "agent_name": agent_name,
+        "system_prompt": system_prompt,
+        "model": model,
+    }
+    resp = await client.post("/agents/define", json=body)
+
+    if resp.status_code == 201:
+        return _parse_tier3_agent_info(resp.json())
+    if resp.status_code == 429:
+        # Spec §2675: 51st define → 429 with Retry-After: 0.
+        try:
+            retry_after = int(resp.headers.get("Retry-After", "0"))
+        except (TypeError, ValueError):
+            retry_after = 0
+        raise Tier3QuotaExceeded(retry_after=retry_after)
+    if resp.status_code == 403:
+        if _extract_error_code(resp) == "tier3_user_id_unsupported":
+            raise Tier3UserIdUnsupported()
+    if resp.status_code == 422:
+        code = _extract_error_code(resp)
+        if code == "layer_deferred":
+            raise Tier3LayerDeferred(field=_extract_error_field(resp))
+    raise SessionApiFailed(status=resp.status_code, body=resp.content)
+
+
+async def patch_agent(
+    client: httpx.AsyncClient,
+    agent_id: str,
+    *,
+    system_prompt: str | None = None,
+    model: str | None = None,
+) -> Tier3AgentInfo:
+    """PATCH /agents/<id> — mutate system_prompt and/or model.
+
+    See contract FN patch_agent. Per spec §2641: only system_prompt + model
+    are mutable in Phase 2.0; any other key returns 422 field_not_mutable.
+    """
+    assert client is not None
+    assert ":" in agent_id, f"tier 3 agent_id must contain ':': {agent_id!r}"
+    assert system_prompt is not None or model is not None, (
+        "patch requires at least one of system_prompt or model"
+    )
+
+    body: dict[str, str] = {}
+    if system_prompt is not None:
+        body["system_prompt"] = system_prompt
+    if model is not None:
+        body["model"] = model
+    resp = await client.patch(f"/agents/{agent_id}", json=body)
+
+    if resp.status_code == 200:
+        return _parse_tier3_agent_info(resp.json())
+    if resp.status_code == 404:
+        raise Tier3AgentNotFound(agent_id=agent_id)
+    if resp.status_code == 422:
+        code = _extract_error_code(resp)
+        if code == "field_not_mutable":
+            raise Tier3FieldNotMutable(field=_extract_error_field(resp))
+    raise SessionApiFailed(status=resp.status_code, body=resp.content)
+
+
+async def delete_agent(client: httpx.AsyncClient, agent_id: str) -> None:
+    """DELETE /agents/<id> — owner hard-delete (cancels active sessions
+    server-side per spec §2636).
+
+    See contract FN delete_agent. 204 on success; 404 if the agent_id
+    doesn't exist; other non-2xx → SessionApiFailed.
+    """
+    assert client is not None
+    assert ":" in agent_id, f"tier 3 agent_id must contain ':': {agent_id!r}"
+
+    resp = await client.delete(f"/agents/{agent_id}")
+    if resp.status_code == 204:
+        return
+    if resp.status_code == 404:
+        raise Tier3AgentNotFound(agent_id=agent_id)
+    raise SessionApiFailed(status=resp.status_code, body=resp.content)
+
+
+# ---- CLI (`python -m ratatoskr.tier3 <subcommand>`) ------------------------
+#
+# Auth + server URL resolution mirrors ratatoskr.cli verbatim. Exit codes
+# mirror ratatoskr.cli: 0 happy / 10 usage / 11 auth / 20 api-failure /
+# 21 network. Outbound requests carry the same User-Agent string.
+
+
+class _Tier3UsageError(Exception):
+    """Argparse usage violation → exit 10."""
+
+
+class _Tier3AuthError(Exception):
+    """No API key resolvable → exit 11."""
+
+
+def _build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(
+        prog="python -m ratatoskr.tier3",
+        description="Worldtree Tier 3 (consumer-defined) agent lifecycle.",
+    )
+    parser.add_argument("--api-key", dest="api_key", default=None)
+    parser.add_argument("--server", dest="server", default=None)
+    sub = parser.add_subparsers(dest="cmd", required=True)
+
+    p_define = sub.add_parser("define", help="Create a Tier 3 agent.")
+    p_define.add_argument("--name", required=True, help="agent_name (slug).")
+    p_define.add_argument(
+        "--system-prompt", dest="system_prompt", required=True,
+        help="System prompt the agent ships with.",
+    )
+    p_define.add_argument(
+        "--model", required=True,
+        help="Provider model ID (NOT a profile alias; e.g., qwen3.6-35-a3b).",
+    )
+
+    p_patch = sub.add_parser("patch", help="Mutate system_prompt and/or model.")
+    p_patch.add_argument("agent_id", help='Full "<user_id>:<agent_name>" form.')
+    p_patch.add_argument("--system-prompt", dest="system_prompt", default=None)
+    p_patch.add_argument("--model", default=None)
+
+    p_delete = sub.add_parser("delete", help="Hard-delete a Tier 3 agent.")
+    p_delete.add_argument("agent_id", help='Full "<user_id>:<agent_name>" form.')
+
+    return parser
+
+
+def _resolve_auth(ns: argparse.Namespace) -> tuple[str, str]:
+    """Resolve API key + server URL with the same env-var fallback as cli.py."""
+    import os
+
+    api_key = ns.api_key or os.environ.get("WORLDTREE_API_KEY") or ""
+    if not api_key:
+        raise _Tier3AuthError("no API key (set --api-key or WORLDTREE_API_KEY)")
+    server_url = (
+        ns.server or os.environ.get("WORLDTREE_API_URL") or "http://localhost:8000"
+    )
+    return api_key, server_url
+
+
+async def _run_define(ns: argparse.Namespace) -> int:
+    api_key, server_url = _resolve_auth(ns)
+    from ratatoskr.cli import USER_AGENT
+
+    async with httpx.AsyncClient(
+        base_url=server_url,
+        headers={
+            "Authorization": f"Bearer {api_key}",
+            "User-Agent": USER_AGENT,
+        },
+        timeout=httpx.Timeout(connect=10.0, read=30.0, write=10.0, pool=10.0),
+    ) as client:
+        info = await define_agent(
+            client,
+            agent_name=ns.name,
+            system_prompt=ns.system_prompt,
+            model=ns.model,
+        )
+        print(f"defined {info.agent_id} ({info.model})")
+        return 0
+
+
+async def _run_patch(ns: argparse.Namespace) -> int:
+    api_key, server_url = _resolve_auth(ns)
+    from ratatoskr.cli import USER_AGENT
+
+    if ns.system_prompt is None and ns.model is None:
+        raise _Tier3UsageError(
+            "patch requires at least one of --system-prompt or --model"
+        )
+    async with httpx.AsyncClient(
+        base_url=server_url,
+        headers={
+            "Authorization": f"Bearer {api_key}",
+            "User-Agent": USER_AGENT,
+        },
+        timeout=httpx.Timeout(connect=10.0, read=30.0, write=10.0, pool=10.0),
+    ) as client:
+        info = await patch_agent(
+            client,
+            ns.agent_id,
+            system_prompt=ns.system_prompt,
+            model=ns.model,
+        )
+        print(f"patched {info.agent_id}")
+        return 0
+
+
+async def _run_delete(ns: argparse.Namespace) -> int:
+    api_key, server_url = _resolve_auth(ns)
+    from ratatoskr.cli import USER_AGENT
+
+    async with httpx.AsyncClient(
+        base_url=server_url,
+        headers={
+            "Authorization": f"Bearer {api_key}",
+            "User-Agent": USER_AGENT,
+        },
+        timeout=httpx.Timeout(connect=10.0, read=30.0, write=10.0, pool=10.0),
+    ) as client:
+        await delete_agent(client, ns.agent_id)
+        print(f"deleted {ns.agent_id}")
+        return 0
+
+
+def main(argv: list[str] | None = None) -> int:
+    """Sync entry point — argparse + dispatch + error → exit-code mapping.
+
+    Mirrors ratatoskr.cli.main()'s error-routing matrix:
+      0  happy
+      10 usage error
+      11 auth error
+      20 api-failure (typed exception or generic SessionApiFailed)
+      21 network error
+    """
+    import asyncio
+    import sys
+
+    parser = _build_parser()
+    try:
+        ns = parser.parse_args(argv)
+    except SystemExit as exc:
+        return int(exc.code) if exc.code is not None else 0
+
+    handler = {
+        "define": _run_define,
+        "patch": _run_patch,
+        "delete": _run_delete,
+    }[ns.cmd]
+
+    try:
+        return asyncio.run(handler(ns))
+    except _Tier3UsageError as exc:
+        sys.stderr.write(f"[usage_error] {exc}\n")
+        return 10
+    except _Tier3AuthError as exc:
+        sys.stderr.write(f"[auth_error] {exc}\n")
+        return 11
+    except AssertionError as exc:
+        sys.stderr.write(f"[usage_error] {exc}\n")
+        return 10
+    except Tier3QuotaExceeded as exc:
+        sys.stderr.write(f"[quota_exceeded] retry_after={exc.retry_after}\n")
+        return 20
+    except Tier3UserIdUnsupported:
+        sys.stderr.write("[user_id_unsupported]\n")
+        return 20
+    except Tier3AgentNotFound as exc:
+        sys.stderr.write(f"[agent_not_found] {exc.agent_id}\n")
+        return 20
+    except Tier3FieldNotMutable as exc:
+        sys.stderr.write(f"[field_not_mutable] field={exc.field}\n")
+        return 20
+    except Tier3LayerDeferred as exc:
+        sys.stderr.write(f"[layer_deferred] field={exc.field}\n")
+        return 20
+    except SessionApiFailed as exc:
+        sys.stderr.write(
+            f"[api_failed] status={exc.status} body={exc.body!r}\n"
+        )
+        return 20
+    except (httpx.ConnectError, httpx.ReadTimeout, httpx.TransportError) as exc:
+        sys.stderr.write(f"[network_error] {type(exc).__name__}: {exc}\n")
+        return 21
+
+
+if __name__ == "__main__":
+    import sys
+
+    sys.exit(main())
@@ -22,7 +22,6 @@ from textual.widgets import (
    Footer,
    Header,
    Input,
-    Label,
    ListItem,
    ListView,
    RichLog,
@@ -69,16 +68,25 @@ from ratatoskr.sse_client import (
 # for primary surfaces; Dawn accents (red/yellow/magenta) used sparingly for
 # terminal-event labels (error/cancelled).
 #
+# **v0.6.3 single deviation from spec**: `$background` is `#000000` (pure
+# black), NOT Australis Ice black `#222531`. The Ice black is RGB(34,37,49)
+# — blue dominant — and at App-wide scale the cumulative cast reads as
+# "the whole app is blue" to operators (even though no single surface is
+# "blue" in the strict-color sense). Pure black for the App background
+# kills that perception. EVERY OTHER Australis value — Aurora accents,
+# Sea darks for chrome (surface/panel), Ice white foreground, Dawn
+# accents — stays verbatim per spec.
+#
 # Mapping to Textual's Theme semantic tokens:
 #   primary    = Aurora blue (#6388D8) — focus rings, active selection.
 #   secondary  = Aurora cyan (#00b1a8) — secondary highlights.
-#   accent     = Aurora bright cyan (#42dcd1) — bright accents (pane-name, prompt echo).
+#   accent     = Aurora bright cyan (#42dcd1) — bright accents.
 #   success    = Aurora green (#16B866) — [done] label.
 #   warning    = Dawn yellow (#e1c631) — [cancelled] label.
 #   error      = Dawn red (#ff491a) — [error] label.
 #   foreground = Ice white (#a9bcc3) — default text.
-#   background = Ice black (#222531) — App background.
-#   surface    = Sea bright black (#373b46) — raised chrome (header/footer/input).
+#   background = pure black (#000000) — App background (v0.6.3 deviation).
+#   surface    = Sea bright black (#373b46) — raised chrome.
 #   panel      = Sea dark 30 (#414751) — borders, separators.

 AUSTRALIS_THEME = Theme(
@@ -90,7 +98,7 @@ AUSTRALIS_THEME = Theme(
    warning="#e1c631",
    error="#ff491a",
    foreground="#a9bcc3",
-    background="#222531",
+    background="#000000",
    surface="#373b46",
    panel="#414751",
    dark=True,
@@ -116,8 +124,9 @@ AUSTRALIS_THEME = Theme(
 _AU_SUCCESS = "#16B866"
 _AU_ERROR = "#ff491a"
 _AU_WARNING = "#e1c631"
-_AU_USER_ECHO = "#42dcd1"  # bright cyan — operator's voice
-_AU_DEMOTED = "#86929d"  # dark 60 — demoted telemetry (was bare "dim")
+_AU_USER_ECHO = "#42dcd1"  # Aurora bright cyan — operator's voice
+_AU_DEMOTED = "#86929d"  # Sea dark 60 — demoted telemetry
+_AU_DEMOTED_FAINT = "#6e7882"  # Sea dark 50 — empty-state placeholders


 # ---- Issue #12 presenter contract semantics amendment -------------------------
@@ -176,29 +185,46 @@ class TuiPresenterState:
    See `docs/contracts/issues/12.contract.md` for the full spec.
    """

-    thinking_buffer: list[str] = field(default_factory=list)
    thinking_open: bool = False
+    # v0.6.0: per-turn streaming text buffer. Text deltas accumulate here
+    # and update `current_text` Static in place — no per-token RichLog spam.
+    text_buffer: list[str] = field(default_factory=list)
+    # Thinking-run counter for turn-scoped start/end markers.
+    thinking_run_index: int = 0
+    # v0.7.1: thinking-content accumulator. Worldtree emits Thinking deltas
+    # at token granularity; flushing each delta as its own RichLog line
+    # produces per-token-per-newline visual spam. Buffer here and flush
+    # only on `\n` boundaries (one written line per natural paragraph) or
+    # when the run closes (any leftover tail).
+    thinking_chunk_buffer: str = ""

    def render(
        self,
        event: Event,
        *,
        log: RichLog,
-        thinking_widget: Static,
+        current_text: Static,
        tools_log: RichLog,
        debug_log: RichLog,
+        thinking_log: RichLog,
        raw: bool,
    ) -> None:
        """Render one Worldtree SSE event with the TUI hierarchy + coalescing.

-        v0.5.0 routing: main `log` (transcript) is CONTENT-ONLY — Text,
-        terminal labels ([done] / [error] / [cancelled]), and the
-        post-Done Markdown render. All telemetry (Thinking closed runs,
-        WorkerPhase, TextBoundary) routes to `debug_log` (Debug tab); all
-        tool activity (ToolStart, ToolResult) routes to `tools_log` (Tools
-        tab). Live thinking deltas continue to update `thinking_widget`.
+        v0.6.5 routing:
+          - `log` (transcript) = content only: user-prompt echo (written
+            outside the presenter), terminal labels, post-Done Markdown body.
+          - `current_text` (Static below transcript) = live-streaming Text
+            deltas accumulated into one growing line; cleared on terminal.
+          - `tools_log` = ToolStart + ToolResult.
+          - `debug_log` = WorkerPhase + TextBoundary.
+          - `thinking_log` = streaming Thinking deltas inline (each chunk =
+            one line in the scrollable log). Rule(start)/Rule(end) markers
+            wrap each run. The whole pane scrolls naturally — no separate
+            tail-scrolling Static at the bottom (v0.6.5 removed
+            `thinking-current`).

-        Exceptions are caught at the presenter boundary (INV-009 fallback).
+        Exceptions caught at the presenter boundary (INV-009 fallback).
        """
        assert isinstance(
            event,
@@ -210,69 +236,99 @@ class TuiPresenterState:
        from rich.text import Text as RichText

        def _dim(s: str) -> RichText:
-            """Wrap a demoted-telemetry line in Australis dark-60 grey.
-
-            v0.4.1 retheme: was `style="dim"` (terminal-dim filter, varies by
-            emulator); now explicit Australis Sea dark-60 (#86929d) so the
-            shade renders consistently across terminals and stays anchored to
-            the brand palette.
-            """
+            """Wrap a demoted-telemetry line in Australis Sea dark-60 grey."""
            return RichText(s, style=_AU_DEMOTED)

        try:
-            # Thinking events: accumulate into buffer, update widget per delta.
+            # 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-
+            # newline spam). Buffer the deltas and flush only on `\n` (one
+            # written line per natural paragraph) or run close.
            if isinstance(event, Thinking):
+                from rich.rule import Rule
+
                if not self.thinking_open:
-                    thinking_widget.display = True
+                    self.thinking_run_index += 1
+                    turn_id = event.sse_id.turn_id
+                    thinking_log.write(Rule(
+                        title=f"turn {turn_id} · thinking #{self.thinking_run_index} start",
+                        style=_AU_DEMOTED,
+                    ))
                    self.thinking_open = True
-                self.thinking_buffer.append(event.content)
-                acc = "".join(self.thinking_buffer)
-                display_text = ("…" + acc[-200:]) if len(acc) > 200 else acc
-                thinking_widget.update(display_text)
+                self.thinking_chunk_buffer += event.content
+                # Flush every complete line in the buffer. Whatever's after
+                # the final `\n` stays buffered for the next delta or close.
+                while "\n" in self.thinking_chunk_buffer:
+                    line, _, rest = self.thinking_chunk_buffer.partition("\n")
+                    if line:  # skip empty lines (blank paragraph separators)
+                        thinking_log.write(line)
+                    self.thinking_chunk_buffer = rest
                return
-            # Non-thinking event: close any open thinking run.
-            # v0.5.0: closed thinking runs land in debug_log (Debug pane), not
-            # transcript — keeps the main pane content-only.
+            # Non-thinking event: close any open thinking run with Rule(end).
            if self.thinking_open:
-                full_thinking = "".join(self.thinking_buffer)
-                debug_log.write(_dim(f"· thinking: {full_thinking}"))
-                self.thinking_buffer.clear()
+                from rich.rule import Rule
+
+                # Flush the tail (content with no trailing `\n`) before the
+                # end rule so nothing gets lost on close.
+                if self.thinking_chunk_buffer:
+                    thinking_log.write(self.thinking_chunk_buffer)
+                    self.thinking_chunk_buffer = ""
+                turn_id = event.sse_id.turn_id if hasattr(event, "sse_id") else (
+                    event.turn_id if hasattr(event, "turn_id") else "?"
+                )
+                thinking_log.write(Rule(
+                    title=f"turn {turn_id} · thinking #{self.thinking_run_index} end",
+                    style=_AU_DEMOTED,
+                ))
                self.thinking_open = False
-                thinking_widget.update("")
-                thinking_widget.display = False
            # Now render the non-thinking event itself.
            if isinstance(event, Text):
-                # Streamed text content — no prefix, no demotion.
-                log.write(event.content)
+                # v0.6.0: streaming text accumulates into current_text Static
+                # — one growing live line, NOT per-delta RichLog entries.
+                self.text_buffer.append(event.content)
+                current_text.update("".join(self.text_buffer))
                return
            if isinstance(event, (Done, Error, Cancelled)):
-                # Terminal events: load-bearing label (no demotion).
+                # Terminal event: clear the streaming Static first so the
+                # live-preview band collapses. Then write the colored label
+                # + (non-raw) Markdown body / (raw) accumulated plain text
+                # to the transcript.
+                accumulated = "".join(self.text_buffer)
+                self.text_buffer.clear()
+                current_text.update("")
+                # Terminal labels tinted per outcome (Aurora green / Dawn red
+                # / Dawn yellow) for at-a-glance scanning.
                if isinstance(event, Done):
-                    log.write(
+                    log.write(RichText(
                        f"[done] turn_id={event.sse_id.turn_id} model={event.model} "
                        f"duration={_format_duration_ms(event.duration_ms)} "
-                        f"usage {_format_usage(event.usage, arrow='→')}"
-                    )
-                    if not raw:
+                        f"usage {_format_usage(event.usage, arrow='→')}",
+                        style=_AU_SUCCESS,
+                    ))
+                    if raw:
+                        # Raw mode: emit the accumulated streamed text verbatim
+                        # so the operator has a record after the Static clears.
+                        if accumulated:
+                            log.write(accumulated)
+                    else:
                        from rich.markdown import Markdown
                        from rich.rule import Rule

-                        log.write(Rule())
+                        log.write(Rule(style=_AU_DEMOTED))
                        log.write(Markdown(event.response))
                elif isinstance(event, Error):
-                    log.write(
+                    log.write(RichText(
                        f"[error] turn_id={event.sse_id.turn_id} code={event.error_code} "
-                        f"message={event.message!r}"
-                    )
+                        f"message={event.message!r}",
+                        style=_AU_ERROR,
+                    ))
                else:  # Cancelled
-                    log.write(
+                    log.write(RichText(
                        f"[cancelled] turn_id={event.turn_id} reason={event.reason!r} "
-                        f"partial_message_id={event.partial_message_id}"
-                    )
-                # Belt-and-braces (Volva F3): ensure widget cleared+hidden on EVERY
-                # terminal event, even if thinking_open was False — per STEPS 5-6.
-                thinking_widget.update("")
-                thinking_widget.display = False
+                        f"partial_message_id={event.partial_message_id}",
+                        style=_AU_WARNING,
+                    ))
                return
            if isinstance(event, WorkerPhase):
                # v0.5.0: telemetry → Debug pane, not transcript.
@@ -304,14 +360,17 @@ class TuiPresenterState:
            # the original event AND a render_error line with the class name only
            # (NO exception message — security clause). Volva F1 fix.
            #
-            # v0.5.0: routing-under-failure preservation — fallback writes go
+            # v0.6.0 routing-under-failure preservation — fallback writes go
            # to the same destination the successful render would have used:
            #   - ToolStart/ToolResult       → tools_log
-            #   - WorkerPhase/Thinking/TextBoundary → debug_log
-            #   - everything else (Text/Done/Error/Cancelled) → log
+            #   - Thinking                   → thinking_log
+            #   - WorkerPhase/TextBoundary   → debug_log
+            #   - everything else            → log
            if isinstance(event, (ToolStart, ToolResult)):
                target = tools_log
-            elif isinstance(event, (WorkerPhase, Thinking, TextBoundary)):
+            elif isinstance(event, Thinking):
+                target = thinking_log
+            elif isinstance(event, (WorkerPhase, TextBoundary)):
                target = debug_log
            else:
                target = log
@@ -330,6 +389,28 @@ class AgentPickerApp(App[str | None]):
    """

    DEFAULT_CSS = """
+    /* v0.6.1: kill Textual's $primary-blue tints everywhere — Header sub-
+       widgets (HeaderIcon etc.) have their own $primary tinting that the
+       parent `Header { background: $surface }` rule alone doesn't cover.
+       Sub-selectors force the cool palette down to every level. */
+    Header, HeaderIcon, HeaderTitle, HeaderClock {
+        background: $surface;
+        color: $au-bright-blue;
+    }
+    Footer {
+        background: $surface;
+    }
+    /* v0.6.1: scrollbar uses Textual's $primary-tint by default. Force
+       Australis Sea darks so the scrollbar gutter doesn't read as a blue
+       strip. Applied to ListView (the scrollable widget here). */
+    ListView {
+        scrollbar-background: $background;
+        scrollbar-background-hover: $background;
+        scrollbar-background-active: $background;
+        scrollbar-color: $au-dark-50;
+        scrollbar-color-hover: $au-dark-60;
+        scrollbar-color-active: $au-bright-cyan;
+    }
    #picker-prompt {
        dock: top;
        height: 1;
@@ -341,9 +422,41 @@ class AgentPickerApp(App[str | None]):
        height: 1fr;
        background: $background;
    }
-    #agent-list > ListItem.--highlight {
+    /* Multi-line agent items. Each ListItem is auto-height so the full
+       description wraps below the agent_id/name line — no truncation.
+       v0.6.4: lock bg to $background so Textual's auto background-tint on
+       focus doesn't bleed through unwanted color into the non-highlighted
+       items. */
+    #agent-list > ListItem {
+        height: auto;
+        padding: 1 1;
+        background: $background;
+    }
+    /* v0.6.4: highlighted item gets Aurora blue background (Textual's
+       default $block-cursor-background = $primary). Override only the
+       text-color descendants so id-line/desc stay readable on blue. The
+       background itself comes from Textual's default ListItem.-highlight
+       rule — we removed our previous overriding selectors.
+
+       Textual's class is `-highlight` (single dash). Use plain descendant
+       combinator to bypass internal DOM wrappers. */
+    #agent-list:focus ListItem.-highlight {
        background: $primary;
+    }
+    #agent-list:focus ListItem.-highlight .agent-id-line {
        color: $au-bright-white;
+        text-style: bold;
+    }
+    #agent-list:focus ListItem.-highlight .agent-desc {
+        color: $au-bright-80;
+    }
+    /* Default (unhighlighted) item text styling. */
+    .agent-id-line {
+        color: $au-bright-blue;
+        text-style: bold;
+    }
+    .agent-desc {
+        color: $au-bright-70;
    }
    """

@@ -366,9 +479,16 @@ class AgentPickerApp(App[str | None]):
    def compose(self) -> ComposeResult:
        yield Header()
        yield Static("Pick an agent for the new session:", id="picker-prompt")
+        # v0.6.0: each ListItem has two Static children — the id/name line
+        # in bold blue + the wrapped description in muted dark-60. No
+        # description truncation; tall items breathe so the operator can
+        # actually read what each agent does.
        yield ListView(
            *[
-                ListItem(Label(f"{a.agent_id} · {a.name} — {a.description}"))
+                ListItem(
+                    Static(f"{a.agent_id} · {a.name}", classes="agent-id-line"),
+                    Static(a.description, classes="agent-desc"),
+                )
                for a in self.agents
            ],
            id="agent-list",
@@ -411,13 +531,27 @@ class RatatoskrApp(App[int]):
    # Australis theme variables ($primary/$accent/$au-dark-60/$au-bright-cyan/
    # etc.) carry colors so a future theme swap rebinds centrally.
    DEFAULT_CSS = """
-    Header {
+    /* v0.6.1: kill Textual's default $primary-blue tinting on chrome —
+       Header sub-widgets (HeaderIcon, HeaderTitle, HeaderClock) each carry
+       their own $primary tint that the parent `Header { background }` rule
+       doesn't override; sub-selectors force the cool palette down. */
+    Header, HeaderIcon, HeaderTitle, HeaderClock {
        background: $surface;
        color: $au-bright-blue;
    }
    Footer {
        background: $surface;
    }
+    /* v0.6.1: scrollbars default to $primary-tint blue. Force Sea darks
+       on the scrollable widgets (RichLog instances). */
+    RichLog {
+        scrollbar-background: $background;
+        scrollbar-background-hover: $background;
+        scrollbar-background-active: $background;
+        scrollbar-color: $au-dark-50;
+        scrollbar-color-hover: $au-dark-60;
+        scrollbar-color-active: $au-bright-cyan;
+    }
    #main-row {
        height: 1fr;
    }
@@ -428,28 +562,50 @@ class RatatoskrApp(App[int]):
    #right-column {
        width: 1fr;
    }
-    #thinking-current {
-        dock: top;
-        height: auto;
-        color: $au-dark-60;
-        padding: 0 1;
-    }
+    /* v0.6.5: thinking-current Static removed; thinking now streams
+       directly into thinking-log so the whole pane scrolls naturally. */
    #transcript {
        height: 1fr;
        background: $background;
+        padding: 0 1;
    }
-    #tools-log, #debug-log {
+    /* v0.6.0: streaming-text Static carries in-flight assistant tokens.
+       Replaces per-token RichLog spam — one growing line that updates in
+       place. Cleared on terminal event; final Markdown body lands in the
+       transcript. */
+    #current-text {
+        dock: bottom;
+        height: auto;
        background: $background;
+        padding: 0 1;
    }
-    #side-panes Tabs {
+    #tools-log, #debug-log, #thinking-log {
+        background: $background;
+        padding: 0 1;
+    }
+    /* Tab strip + active-tab underline — kill blue, use Australis cyan. */
+    #side-panes > ContentTabs {
        background: $surface;
    }
+    #side-panes ContentTab.-active {
+        color: $au-bright-cyan;
+        text-style: bold;
+    }
+    #side-panes Underline > .underline--bar {
+        color: $au-bright-cyan;
+    }
    #prompt {
        dock: bottom;
        border: tall $panel;
    }
+    /* v0.6.0: focused border uses Australis bright-cyan instead of $primary
+       (Aurora blue) — kills the lingering blue tint the user flagged. */
    #prompt:focus {
-        border: tall $primary;
+        border: tall $au-bright-cyan;
+    }
+    /* Placeholder text in the Input — dimmer than typed content. */
+    #prompt > .input--placeholder {
+        color: $au-dark-50;
    }
    #identity {
        dock: bottom;
@@ -478,6 +634,7 @@ class RatatoskrApp(App[int]):
        # without losing Input focus (INV-016).
        Binding("ctrl+1", "focus_tools", "Tools tab", priority=False),
        Binding("ctrl+2", "focus_debug", "Debug tab", priority=False),
+        Binding("ctrl+3", "focus_thinking", "Thinking tab", priority=False),
    ]

    HINT_IDLE = "Ctrl-C twice to exit"
@@ -506,20 +663,24 @@ class RatatoskrApp(App[int]):

    def compose(self) -> ComposeResult:
        yield Header()
-        # v0.5.0 layout: left column is content-only (transcript + prompt).
-        # Right column houses ALL telemetry — thinking-current live preview
-        # docked above the TabbedContent; tabs cycle Tools / Debug.
-        # markup=False on RichLog so labeled lines like "[cancel_failed] ..."
-        # render verbatim; Rich would otherwise interpret bracket spans as
-        # style markup. The post-Done markdown render uses Markdown() directly
-        # which is a Rich Renderable and renders correctly without
-        # widget-level markup=True.
+        # v0.6.0 layout: left column is content-only (transcript + streaming
+        # text Static + prompt). Right column hosts thinking-current live
+        # preview above TabbedContent cycling Tools / Debug / Thinking.
+        #
+        # The current-text Static buffers in-flight assistant tokens so
+        # streaming doesn't spam the RichLog with one line per delta —
+        # the operator sees a single growing live line, then on Done the
+        # Static clears and the final Markdown body lands in the transcript.
+        #
+        # markup=False on RichLog so labeled lines render verbatim; the
+        # post-Done Markdown() / Rule() renders are Rich Renderables and
+        # work without widget-level markup=True.
        with Horizontal(id="main-row"):
            with Vertical(id="left-column"):
                yield RichLog(id="transcript", wrap=True, markup=False, highlight=False)
+                yield Static("", id="current-text")
                yield Input(id="prompt", placeholder="Type a message and press Enter")
            with Vertical(id="right-column"):
-                yield Static("", id="thinking-current")
                with TabbedContent(id="side-panes"):
                    with TabPane("Tools", id="tools-tab"):
                        yield RichLog(
@@ -529,6 +690,16 @@ class RatatoskrApp(App[int]):
                        yield RichLog(
                            id="debug-log", wrap=True, markup=False, highlight=False
                        )
+                    with TabPane("Thinking", id="thinking-tab"):
+                        # v0.6.5: thinking streams directly into this
+                        # RichLog (no separate bottom Static). Each delta
+                        # writes a line; Rule(start)/Rule(end) mark run
+                        # boundaries. The whole pane scrolls naturally
+                        # as content arrives — no more "200-char tail
+                        # window scrolling at the bottom".
+                        yield RichLog(
+                            id="thinking-log", wrap=True, markup=False, highlight=False
+                        )
        # INV-002 + INV-003: visible identity + hint widgets (Footer-area).
        # pane-name widget displays current side-pane name.
        yield Static("", id="identity")
@@ -547,11 +718,48 @@ class RatatoskrApp(App[int]):
        identity = f"{agent_slot} · …{self.session_id[-8:]}"
        self.sub_title = identity  # mirror to Header subtitle for redundancy
        self.query_one("#identity", Static).update(identity)
-        # Issue #12: thinking widget hidden until a thinking event fires.
-        self.query_one("#thinking-current", Static).display = False
+        # v0.5.1 polish: empty-state placeholder lines so the operator sees
+        # the pane is intentionally empty (not broken) before any turn fires.
+        # Wrapped in Australis dark-50 italic so they read distinctly as
+        # placeholder text, not real telemetry. Disappear naturally as the
+        # log fills with real events (the placeholders scroll off the top).
+        from rich.text import Text as RichText
+        placeholder_style = f"{_AU_DEMOTED_FAINT} italic"
+        self.query_one("#tools-log", RichLog).write(
+            RichText("(no tool events yet — start a turn that uses tools)",
+                     style=placeholder_style)
+        )
+        self.query_one("#debug-log", RichLog).write(
+            RichText("(waiting for worker_phase + text_boundary telemetry)",
+                     style=placeholder_style)
+        )
+        self.query_one("#thinking-log", RichLog).write(
+            RichText("(no chain-of-thought captured yet — start a turn)",
+                     style=placeholder_style)
+        )
        self.state = "idle"
        self._set_hint(self.HINT_IDLE)

+    def _write_turn_headers(self, turn_id: int) -> None:
+        """v0.6.0: Write `── turn N ──` Rule headers across every pane so
+        operators can visually correlate sections during cross-pane
+        debugging. Called from `_stream_turn_worker` on first event of
+        each new turn (idempotent per turn via active_turn_id guard).
+        """
+        from rich.rule import Rule
+
+        title = f"turn {turn_id}"
+        rule = Rule(title=title, style=_AU_DEMOTED)
+        try:
+            self.query_one("#transcript", RichLog).write(rule)
+            self.query_one("#tools-log", RichLog).write(rule)
+            self.query_one("#debug-log", RichLog).write(rule)
+            self.query_one("#thinking-log", RichLog).write(rule)
+        except Exception:
+            # Defensive: widget tree may be tearing down — never let a
+            # turn-header write block the SSE consumer.
+            pass
+
    def _set_hint(self, hint: str) -> None:
        """Set the hint state attribute AND update the visible Static widget."""
        self.hint = hint
@@ -590,21 +798,26 @@ class RatatoskrApp(App[int]):
        assert self.client is not None
        assert content
        log = self.query_one("#transcript", RichLog)
-        thinking_widget = self.query_one("#thinking-current", Static)
-        # v0.5.0: separate panes for tools vs telemetry; transcript is content only.
+        current_text = self.query_one("#current-text", Static)
        tools_log = self.query_one("#tools-log", RichLog)
        debug_log = self.query_one("#debug-log", RichLog)
+        thinking_log = self.query_one("#thinking-log", RichLog)
        presenter = TuiPresenterState()
        try:
            async for event in stream_turn(self.client, self.session_id, content):
                if self.active_turn_id is None:
                    self.active_turn_id = event.sse_id.turn_id
+                    # v0.6.0: turn-ID headers across all panes so the
+                    # operator can visually correlate sections during
+                    # cross-pane debugging.
+                    self._write_turn_headers(self.active_turn_id)
                presenter.render(
                    event,
                    log=log,
-                    thinking_widget=thinking_widget,
+                    current_text=current_text,
                    tools_log=tools_log,
                    debug_log=debug_log,
+                    thinking_log=thinking_log,
                    raw=self.args.raw,
                )
                if isinstance(event, (Done, Error, Cancelled)):
@@ -672,6 +885,11 @@ class RatatoskrApp(App[int]):
        self.query_one("#side-panes", TabbedContent).active = "debug-tab"
        self.query_one("#pane-name", Static).update("Debug")

+    def action_focus_thinking(self) -> None:
+        """v0.6.0: Ctrl+3 activates the Thinking tab. INV-016 preserves Input focus."""
+        self.query_one("#side-panes", TabbedContent).active = "thinking-tab"
+        self.query_one("#pane-name", Static).update("Thinking")
+

 def run_tui(args: ParsedArgs) -> int:
    """Sync entry point — delegates to the async resolve-then-run flow.
@@ -0,0 +1,437 @@
+"""Tests for ratatoskr.tier3 per docs/contracts/issues/15.contract.md."""
+
+import httpx
+import pytest
+import respx
+
+from ratatoskr.sessions import SessionApiFailed
+from ratatoskr.tier3 import (
+    Tier3AgentInfo,
+    Tier3AgentNotFound,
+    Tier3FieldNotMutable,
+    Tier3LayerDeferred,
+    Tier3QuotaExceeded,
+    Tier3UserIdUnsupported,
+    define_agent,
+    delete_agent,
+    main,
+    patch_agent,
+)
+
+_FULL_AGENT_RESP = {
+    "agent_id": "ratatoskr:wizard",
+    "user_id": "ratatoskr",
+    "agent_name": "wizard",
+    "system_prompt": "You are a wizard.",
+    "model": "qwen3.6-35-a3b",
+    "created_at": "2026-05-25T03:20:09.703601+00:00",
+    "updated_at": "2026-05-25T03:20:09.703601+00:00",
+}
+
+
+class TestDefineAgent:
+    @respx.mock
+    async def test_happy_define(self) -> None:
+        """happy_define [happy,tracer]: 201 → fully populated Tier3AgentInfo."""
+        respx.post("https://w.example/agents/define").mock(
+            return_value=httpx.Response(201, json=_FULL_AGENT_RESP)
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            info = await define_agent(
+                client,
+                agent_name="wizard",
+                system_prompt="You are a wizard.",
+                model="qwen3.6-35-a3b",
+            )
+        assert isinstance(info, Tier3AgentInfo)
+        assert info.agent_id == "ratatoskr:wizard"
+        assert info.user_id == "ratatoskr"
+        assert info.agent_name == "wizard"
+        assert info.model == "qwen3.6-35-a3b"
+
+    @respx.mock
+    async def test_request_body_shape(self) -> None:
+        """request_body_shape [trace]: outbound JSON is exactly the three keys."""
+        import json as _json
+
+        route = respx.post("https://w.example/agents/define").mock(
+            return_value=httpx.Response(201, json=_FULL_AGENT_RESP)
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            await define_agent(
+                client,
+                agent_name="wizard",
+                system_prompt="You are a wizard.",
+                model="qwen3.6-35-a3b",
+            )
+        body = _json.loads(route.calls[0].request.content)
+        # INV-001: exactly these three keys — no layer fields, no metadata.
+        assert body == {
+            "agent_name": "wizard",
+            "system_prompt": "You are a wizard.",
+            "model": "qwen3.6-35-a3b",
+        }
+
+    @respx.mock
+    async def test_quota_exceeded(self) -> None:
+        """quota_exceeded [error]: 429 + Retry-After → Tier3QuotaExceeded."""
+        respx.post("https://w.example/agents/define").mock(
+            return_value=httpx.Response(
+                429,
+                headers={"Retry-After": "0"},
+                json={"detail": {"error_code": "agent_quota_exceeded"}},
+            )
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            with pytest.raises(Tier3QuotaExceeded) as exc:
+                await define_agent(
+                    client,
+                    agent_name="overflow",
+                    system_prompt="x",
+                    model="m",
+                )
+        assert exc.value.retry_after == 0
+
+    @respx.mock
+    async def test_user_id_unsupported(self) -> None:
+        """user_id_unsupported [error]: 403 + error_code → Tier3UserIdUnsupported."""
+        respx.post("https://w.example/agents/define").mock(
+            return_value=httpx.Response(
+                403, json={"detail": {"error_code": "tier3_user_id_unsupported"}}
+            )
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            with pytest.raises(Tier3UserIdUnsupported):
+                await define_agent(
+                    client, agent_name="wizard", system_prompt="x", model="m"
+                )
+
+    @respx.mock
+    async def test_layer_deferred(self) -> None:
+        """layer_deferred [error]: 422 + layer_deferred → Tier3LayerDeferred(field)."""
+        respx.post("https://w.example/agents/define").mock(
+            return_value=httpx.Response(
+                422,
+                json={"detail": {"error_code": "layer_deferred", "field": "persona"}},
+            )
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            with pytest.raises(Tier3LayerDeferred) as exc:
+                await define_agent(
+                    client, agent_name="wizard", system_prompt="x", model="m"
+                )
+        assert exc.value.field == "persona"
+
+    @respx.mock
+    async def test_bad_slug_assert(self) -> None:
+        """bad_slug_assert [adversarial]: agent_name with uppercase → AssertionError, no HTTP."""
+        route = respx.post("https://w.example/agents/define").mock(
+            return_value=httpx.Response(201, json=_FULL_AGENT_RESP)
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            with pytest.raises(AssertionError):
+                await define_agent(
+                    client, agent_name="Wizard", system_prompt="x", model="m"
+                )
+        assert route.call_count == 0
+
+    @respx.mock
+    async def test_short_slug_assert(self) -> None:
+        """short_slug_assert [adversarial]: agent_name len < 3 → AssertionError."""
+        route = respx.post("https://w.example/agents/define").mock(
+            return_value=httpx.Response(201, json=_FULL_AGENT_RESP)
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            with pytest.raises(AssertionError):
+                await define_agent(
+                    client, agent_name="ab", system_prompt="x", model="m"
+                )
+        assert route.call_count == 0
+
+    @respx.mock
+    async def test_empty_prompt_assert(self) -> None:
+        """empty_prompt_assert [adversarial]: empty system_prompt → AssertionError."""
+        route = respx.post("https://w.example/agents/define").mock(
+            return_value=httpx.Response(201, json=_FULL_AGENT_RESP)
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            with pytest.raises(AssertionError):
+                await define_agent(
+                    client, agent_name="wizard", system_prompt="", model="m"
+                )
+        assert route.call_count == 0
+
+    @respx.mock
+    async def test_other_5xx(self) -> None:
+        """other_5xx [error]: 503 → SessionApiFailed(status=503)."""
+        respx.post("https://w.example/agents/define").mock(
+            return_value=httpx.Response(503, content=b"upstream out")
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            with pytest.raises(SessionApiFailed) as exc:
+                await define_agent(
+                    client, agent_name="wizard", system_prompt="x", model="m"
+                )
+        assert exc.value.status == 503
+
+
+class TestPatchAgent:
+    @respx.mock
+    async def test_happy_patch_both_fields(self) -> None:
+        """happy_patch_both_fields: both fields set → request body has both."""
+        import json as _json
+
+        updated = {
+            **_FULL_AGENT_RESP,
+            "system_prompt": "new prompt",
+            "model": "different-model",
+        }
+        route = respx.patch("https://w.example/agents/ratatoskr:wizard").mock(
+            return_value=httpx.Response(200, json=updated)
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            info = await patch_agent(
+                client,
+                "ratatoskr:wizard",
+                system_prompt="new prompt",
+                model="different-model",
+            )
+        body = _json.loads(route.calls[0].request.content)
+        assert body == {"system_prompt": "new prompt", "model": "different-model"}
+        assert info.system_prompt == "new prompt"
+        assert info.model == "different-model"
+
+    @respx.mock
+    async def test_happy_patch_single_field(self) -> None:
+        """happy_patch_single_field: omit model → body has system_prompt only."""
+        import json as _json
+
+        updated = {**_FULL_AGENT_RESP, "system_prompt": "only this"}
+        route = respx.patch("https://w.example/agents/ratatoskr:wizard").mock(
+            return_value=httpx.Response(200, json=updated)
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            await patch_agent(client, "ratatoskr:wizard", system_prompt="only this")
+        body = _json.loads(route.calls[0].request.content)
+        # INV-002: body omits the None-valued field entirely
+        assert body == {"system_prompt": "only this"}
+
+    @respx.mock
+    async def test_field_not_mutable(self) -> None:
+        """field_not_mutable [error]: 422 + error_code → Tier3FieldNotMutable(field)."""
+        respx.patch("https://w.example/agents/ratatoskr:wizard").mock(
+            return_value=httpx.Response(
+                422,
+                json={
+                    "detail": {"error_code": "field_not_mutable", "field": "agent_name"}
+                },
+            )
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            with pytest.raises(Tier3FieldNotMutable) as exc:
+                await patch_agent(
+                    client, "ratatoskr:wizard", system_prompt="x"
+                )
+        assert exc.value.field == "agent_name"
+
+    @respx.mock
+    async def test_404(self) -> None:
+        """404 [error]: PATCH on non-existent agent → Tier3AgentNotFound."""
+        respx.patch("https://w.example/agents/ratatoskr:ghost").mock(
+            return_value=httpx.Response(404, content=b"")
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            with pytest.raises(Tier3AgentNotFound) as exc:
+                await patch_agent(
+                    client, "ratatoskr:ghost", system_prompt="x"
+                )
+        assert exc.value.agent_id == "ratatoskr:ghost"
+
+    @respx.mock
+    async def test_no_fields_assert(self) -> None:
+        """no_fields_assert [adversarial]: both None → AssertionError, no HTTP."""
+        route = respx.patch("https://w.example/agents/ratatoskr:wizard").mock(
+            return_value=httpx.Response(200, json=_FULL_AGENT_RESP)
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            with pytest.raises(AssertionError):
+                await patch_agent(client, "ratatoskr:wizard")
+        assert route.call_count == 0
+
+    @respx.mock
+    async def test_non_tier3_id_assert(self) -> None:
+        """non_tier3_id_assert [adversarial]: agent_id without `:` → AssertionError."""
+        route = respx.patch("https://w.example/agents/mimir").mock(
+            return_value=httpx.Response(200, json=_FULL_AGENT_RESP)
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            with pytest.raises(AssertionError):
+                await patch_agent(client, "mimir", system_prompt="x")
+        assert route.call_count == 0
+
+
+class TestDeleteAgent:
+    @respx.mock
+    async def test_happy_delete(self) -> None:
+        """happy_delete [happy,tracer]: 204 → returns None."""
+        respx.delete("https://w.example/agents/ratatoskr:wizard").mock(
+            return_value=httpx.Response(204)
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            result = await delete_agent(client, "ratatoskr:wizard")
+        assert result is None
+
+    @respx.mock
+    async def test_404(self) -> None:
+        """404 [error]: DELETE on non-existent agent → Tier3AgentNotFound."""
+        respx.delete("https://w.example/agents/ratatoskr:ghost").mock(
+            return_value=httpx.Response(404)
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            with pytest.raises(Tier3AgentNotFound) as exc:
+                await delete_agent(client, "ratatoskr:ghost")
+        assert exc.value.agent_id == "ratatoskr:ghost"
+
+    @respx.mock
+    async def test_non_tier3_id_assert(self) -> None:
+        """non_tier3_id_assert [adversarial]: agent_id without `:` → AssertionError."""
+        route = respx.delete("https://w.example/agents/mimir").mock(
+            return_value=httpx.Response(204)
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            with pytest.raises(AssertionError):
+                await delete_agent(client, "mimir")
+        assert route.call_count == 0
+
+    @respx.mock
+    async def test_other_5xx(self) -> None:
+        """other_5xx [error]: 500 → SessionApiFailed."""
+        respx.delete("https://w.example/agents/ratatoskr:wizard").mock(
+            return_value=httpx.Response(500, content=b"oops")
+        )
+        async with httpx.AsyncClient(base_url="https://w.example") as client:
+            with pytest.raises(SessionApiFailed) as exc:
+                await delete_agent(client, "ratatoskr:wizard")
+        assert exc.value.status == 500
+
+
+class TestCli:
+    @respx.mock
+    def test_cli_define_happy(
+        self, capsys: pytest.CaptureFixture[str], monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        """cli_define_happy [happy]: argv → 201 mock → stdout confirmation."""
+        monkeypatch.setenv("WORLDTREE_API_URL", "https://w.example")
+        monkeypatch.setenv("WORLDTREE_API_KEY", "k")
+        respx.post("https://w.example/agents/define").mock(
+            return_value=httpx.Response(201, json=_FULL_AGENT_RESP)
+        )
+        rc = main([
+            "define",
+            "--name", "wizard",
+            "--system-prompt", "You are a wizard.",
+            "--model", "qwen3.6-35-a3b",
+        ])
+        out = capsys.readouterr()
+        assert rc == 0
+        assert out.out.strip() == "defined ratatoskr:wizard (qwen3.6-35-a3b)"
+
+    @respx.mock
+    def test_cli_patch_happy(
+        self, capsys: pytest.CaptureFixture[str], monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        """cli_patch_happy [happy]: argv → 200 mock → stdout confirmation."""
+        monkeypatch.setenv("WORLDTREE_API_URL", "https://w.example")
+        monkeypatch.setenv("WORLDTREE_API_KEY", "k")
+        respx.patch("https://w.example/agents/ratatoskr:wizard").mock(
+            return_value=httpx.Response(200, json=_FULL_AGENT_RESP)
+        )
+        rc = main(["patch", "ratatoskr:wizard", "--system-prompt", "new"])
+        out = capsys.readouterr()
+        assert rc == 0
+        assert out.out.strip() == "patched ratatoskr:wizard"
+
+    @respx.mock
+    def test_cli_delete_happy(
+        self, capsys: pytest.CaptureFixture[str], monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        """cli_delete_happy [happy]: argv → 204 mock → stdout confirmation."""
+        monkeypatch.setenv("WORLDTREE_API_URL", "https://w.example")
+        monkeypatch.setenv("WORLDTREE_API_KEY", "k")
+        respx.delete("https://w.example/agents/ratatoskr:wizard").mock(
+            return_value=httpx.Response(204)
+        )
+        rc = main(["delete", "ratatoskr:wizard"])
+        out = capsys.readouterr()
+        assert rc == 0
+        assert out.out.strip() == "deleted ratatoskr:wizard"
+
+    def test_cli_missing_auth(
+        self, capsys: pytest.CaptureFixture[str], monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        """cli_missing_auth [error]: no api-key → stderr [auth_error] + exit 11."""
+        monkeypatch.delenv("WORLDTREE_API_KEY", raising=False)
+        rc = main([
+            "define",
+            "--name", "wizard",
+            "--system-prompt", "x",
+            "--model", "m",
+        ])
+        err = capsys.readouterr().err
+        assert rc == 11
+        assert "[auth_error]" in err
+
+    @respx.mock
+    def test_cli_api_failed(
+        self, capsys: pytest.CaptureFixture[str], monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        """cli_api_failed [error]: 500 → stderr [api_failed] + exit 20."""
+        monkeypatch.setenv("WORLDTREE_API_URL", "https://w.example")
+        monkeypatch.setenv("WORLDTREE_API_KEY", "k")
+        respx.post("https://w.example/agents/define").mock(
+            return_value=httpx.Response(500, content=b"upstream out")
+        )
+        rc = main([
+            "define",
+            "--name", "wizard",
+            "--system-prompt", "x",
+            "--model", "m",
+        ])
+        err = capsys.readouterr().err
+        assert rc == 20
+        assert "[api_failed]" in err
+
+    @respx.mock
+    def test_cli_quota_exceeded(
+        self, capsys: pytest.CaptureFixture[str], monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        """cli_quota_exceeded [error]: 429 → stderr [quota_exceeded] + exit 20."""
+        monkeypatch.setenv("WORLDTREE_API_URL", "https://w.example")
+        monkeypatch.setenv("WORLDTREE_API_KEY", "k")
+        respx.post("https://w.example/agents/define").mock(
+            return_value=httpx.Response(
+                429,
+                headers={"Retry-After": "0"},
+                json={"detail": {"error_code": "agent_quota_exceeded"}},
+            )
+        )
+        rc = main([
+            "define",
+            "--name", "wizard",
+            "--system-prompt", "x",
+            "--model", "m",
+        ])
+        err = capsys.readouterr().err
+        assert rc == 20
+        assert "[quota_exceeded]" in err
+
+    def test_cli_patch_no_fields(
+        self, capsys: pytest.CaptureFixture[str], monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        """cli_patch_no_fields [error]: patch with no flags → [usage_error] + exit 10."""
+        monkeypatch.setenv("WORLDTREE_API_URL", "https://w.example")
+        monkeypatch.setenv("WORLDTREE_API_KEY", "k")
+        rc = main(["patch", "ratatoskr:wizard"])
+        err = capsys.readouterr().err
+        assert rc == 10
+        assert "[usage_error]" in err
@@ -11,7 +11,6 @@ from ratatoskr.cli import ParsedArgs
 from ratatoskr.sse_client import (
    Cancelled,
    Done,
-    Error,
    SseId,
    Text,
    Thinking,
@@ -61,13 +60,18 @@ def _args_existing(session_id: str = "s-1existing", **overrides) -> ParsedArgs:


 def _spy_writes(monkeypatch) -> list:
-    """Patch RichLog.write to record every arg into a list (returned)."""
+    """Patch RichLog.write to record every arg into a list (returned).
+
+    Accepts *args/**kwargs so Textual's internal deferred-render path
+    (which calls write positionally with width/expand/shrink/scroll_end)
+    still works after a write-during-mount + Resize sequence.
+    """
    writes: list = []
    original = RichLog.write

-    def spy(self, content, **kw):
+    def spy(self, content, *args, **kw):
        writes.append(content)
-        return original(self, content, **kw)
+        return original(self, content, *args, **kw)

    monkeypatch.setattr(RichLog, "write", spy)
    return writes
@@ -111,235 +115,179 @@ SID = SseId(42, 5)
 class TestTuiPresenterState:
    """Tests for the new TuiPresenterState — per issue #12 contract."""

-    def test_thinking_coalesce_single_widget_update(self) -> None:
-        """thinking_coalesce_single_widget_update [happy,tracer]:
-        3 Thinking events → thinking_widget.update called 3 times with cumulative content;
-        RichLog has 0 thinking entries (closure hasn't fired yet).
+    def test_thinking_coalesces_until_newline(self) -> None:
+        """thinking_coalesces_until_newline [happy,tracer, v0.7.1]:
+        Per-token deltas accumulate in the buffer; flush only on `\\n`.
+        Three short token-shaped deltas without `\\n` → thinking_log gets
+        ONLY Rule(start); content stays buffered.
        """
+        from rich.rule import Rule
+
        from ratatoskr.tui import TuiPresenterState

        log = MagicMock()
-        widget = MagicMock()
+        thinking_log = MagicMock()
        state = TuiPresenterState()
-        state.render(
-            Thinking(sse_id=SID, content="a"),
-            log=log,
-            thinking_widget=widget,
-            tools_log=MagicMock(),
-            debug_log=MagicMock(),
-            raw=False,
-        )
-        state.render(
-            Thinking(sse_id=SID, content="b"),
-            log=log,
-            thinking_widget=widget,
-            tools_log=MagicMock(),
-            debug_log=MagicMock(),
-            raw=False,
-        )
-        state.render(
-            Thinking(sse_id=SID, content="c"),
-            log=log,
-            thinking_widget=widget,
-            tools_log=MagicMock(),
-            debug_log=MagicMock(),
-            raw=False,
-        )
-        # Widget updated 3 times — once per delta — with cumulative content
-        assert widget.update.call_count == 3
-        # Latest call shows the full accumulated content (under 200 chars so no truncation)
-        assert widget.update.call_args_list[-1][0][0] == "abc"
-        # Widget became visible at first delta
-        assert widget.display is True
-        # No RichLog write yet — closure hasn't fired
+        for chunk in ("Let", " me", " think"):
+            state.render(
+                Thinking(sse_id=SID, content=chunk),
+                log=log,
+                tools_log=MagicMock(),
+                debug_log=MagicMock(),
+                current_text=MagicMock(),
+                thinking_log=thinking_log,
+                raw=False,
+            )
+        writes = [c[0][0] for c in thinking_log.write.call_args_list]
+        # Only Rule(start) — content stays buffered (no `\n` seen).
+        assert len(writes) == 1
+        assert isinstance(writes[0], Rule)
+        assert state.thinking_chunk_buffer == "Let me think"
        assert log.write.call_count == 0

-    def test_thinking_closes_one_debuglog_entry(self) -> None:
-        """thinking_closes_one_debuglog_entry [happy, v0.5.0]: 2x Thinking + WorkerPhase →
-        debug_log has ONE closed thinking entry + one worker_phase entry; widget cleared+hidden;
-        transcript (log) untouched.
+    def test_thinking_flushes_on_newline(self) -> None:
+        """thinking_flushes_on_newline [happy, v0.7.1]:
+        Delta carrying `\\n` flushes the accumulated buffer as ONE line.
        """
        from ratatoskr.tui import TuiPresenterState

+        thinking_log = MagicMock()
+        state = TuiPresenterState()
+        for chunk in ("Hello", " world", "\n"):
+            state.render(
+                Thinking(sse_id=SID, content=chunk),
+                log=MagicMock(),
+                tools_log=MagicMock(),
+                debug_log=MagicMock(),
+                current_text=MagicMock(),
+                thinking_log=thinking_log,
+                raw=False,
+            )
+        writes = [c[0][0] for c in thinking_log.write.call_args_list]
+        # Rule(start) + "Hello world" (one coalesced line) = 2 writes
+        assert len(writes) == 2
+        assert writes[1] == "Hello world"
+        assert state.thinking_chunk_buffer == ""
+
+    def test_thinking_closes_to_thinking_log(self) -> None:
+        """thinking_closes_to_thinking_log [happy, v0.7.1]: 2x Thinking + WorkerPhase →
+        v0.7.1 coalesces "a"+"b" into one buffered string; the close flushes
+        "ab" as a single line before Rule(end). Result: Rule(start) + "ab" +
+        Rule(end) = 3 writes. debug_log gets worker_phase; transcript untouched.
+        """
+        from rich.rule import Rule
+
+        from ratatoskr.tui import TuiPresenterState
+
        log = MagicMock()
        debug_log = MagicMock()
-        widget = MagicMock()
+        thinking_log = MagicMock()
        state = TuiPresenterState()
-        state.render(
-            Thinking(sse_id=SID, content="a"),
-            log=log,
-            thinking_widget=widget,
-            tools_log=MagicMock(),
-            debug_log=debug_log,
-            raw=False,
-        )
-        state.render(
-            Thinking(sse_id=SID, content="b"),
-            log=log,
-            thinking_widget=widget,
-            tools_log=MagicMock(),
-            debug_log=debug_log,
-            raw=False,
-        )
+        for content in ("a", "b"):
+            state.render(
+                Thinking(sse_id=SID, content=content),
+                log=log,
+                tools_log=MagicMock(),
+                debug_log=debug_log,
+                current_text=MagicMock(),
+                thinking_log=thinking_log,
+                raw=False,
+            )
        state.render(
            WorkerPhase(sse_id=SID, phase="streaming", turn_id=42),
            log=log,
-            thinking_widget=widget,
            tools_log=MagicMock(),
            debug_log=debug_log,
+            current_text=MagicMock(),
+            thinking_log=thinking_log,
            raw=False,
        )
-        # v0.5.0: closure + worker_phase write to debug_log; transcript untouched.
-        assert debug_log.write.call_count == 2
+        thinking_writes = [c[0][0] for c in thinking_log.write.call_args_list]
+        # v0.7.1: 1 Rule(start) + 1 coalesced "ab" tail-flush + 1 Rule(end) = 3 writes
+        assert len(thinking_writes) == 3
+        assert isinstance(thinking_writes[0], Rule)
+        assert thinking_writes[1] == "ab"
+        assert isinstance(thinking_writes[2], Rule)
+        # worker_phase still goes to debug_log; transcript untouched.
+        assert "· worker_phase:" in _text_of(debug_log.write.call_args_list[-1][0][0])
        assert not log.write.called
-        # First write = closed thinking entry containing the full accumulated text
-        assert "· thinking: ab" in _text_of(debug_log.write.call_args_list[0][0][0])
-        # Second write = worker_phase with demotion prefix (also in debug_log)
-        assert "· worker_phase:" in _text_of(debug_log.write.call_args_list[1][0][0])
-        # Widget cleared + hidden
-        widget.update.assert_called_with("")
-        assert widget.display is False

-    def test_thinking_widget_truncation(self) -> None:
-        """thinking_widget_truncation [trace]: buffer 500 chars → widget shows "…" + last 200."""
-        from ratatoskr.tui import TuiPresenterState
+    # v0.6.5: thinking-current Static removed; test_thinking_widget_truncation
+    # and test_thinking_widget_visibility_lifecycle deleted (no longer apply).

-        log = MagicMock()
-        widget = MagicMock()
-        state = TuiPresenterState()
-        # Push 500 chars across multiple deltas.
-        long = "x" * 500
-        state.render(
-            Thinking(sse_id=SID, content=long),
-            log=log,
-            thinking_widget=widget,
-            tools_log=MagicMock(),
-            debug_log=MagicMock(),
-            raw=False,
-        )
-        last_update = widget.update.call_args_list[-1][0][0]
-        # …-prefix + last-200 = 201 chars
-        assert last_update.startswith("…")
-        assert len(last_update) == 201
-
-    def test_thinking_widget_visibility_lifecycle(self) -> None:
-        """thinking_widget_visibility_lifecycle [trace]: hidden at start; visible during thinking;
-        hidden after closing event.
+    def test_multiple_thinking_runs_each_get_thinking_log_section(self) -> None:
+        """multiple_thinking_runs_each_get_section [scenario, v0.6.5]:
+        Thinking → Text → Thinking → Done → TWO start/end Rule pairs in
+        thinking_log, each wrapping their delta lines. Text goes to
+        current_text (buffered). Transcript: [done] + Markdown body.
        """
+        from rich.rule import Rule
+
        from ratatoskr.tui import TuiPresenterState

        log = MagicMock()
-        widget = MagicMock()
-        widget.display = False  # initial state (composed hidden)
+        thinking_log = MagicMock()
+        current_text = MagicMock()
        state = TuiPresenterState()
-        # First thinking delta → widget visible
-        state.render(
-            Thinking(sse_id=SID, content="x"),
-            log=log,
-            thinking_widget=widget,
-            tools_log=MagicMock(),
-            debug_log=MagicMock(),
-            raw=False,
-        )
-        assert widget.display is True
-        # Closure (WorkerPhase) → widget hidden
-        state.render(
-            WorkerPhase(sse_id=SID, phase="streaming", turn_id=42),
-            log=log,
-            thinking_widget=widget,
-            tools_log=MagicMock(),
-            debug_log=MagicMock(),
-            raw=False,
-        )
-        assert widget.display is False
-
-    def test_multiple_thinking_runs_each_get_debuglog_entry(self) -> None:
-        """multiple_thinking_runs_each_get_debuglog_entry [scenario, v0.5.0]:
-        Thinking → Text → Thinking → Done → TWO closed thinking entries in debug_log
-        (transcript receives only the Text + Done content).
-        """
-        from ratatoskr.tui import TuiPresenterState
-
-        log = MagicMock()
-        debug_log = MagicMock()
-        widget = MagicMock()
-        state = TuiPresenterState()
-        state.render(
+        for evt in (
            Thinking(sse_id=SID, content="first"),
-            log=log,
-            thinking_widget=widget,
-            tools_log=MagicMock(),
-            debug_log=debug_log,
-            raw=False,
-        )
-        state.render(
            Text(sse_id=SID, content="hi"),
-            log=log,
-            thinking_widget=widget,
-            tools_log=MagicMock(),
-            debug_log=debug_log,
-            raw=False,
-        )
-        state.render(
            Thinking(sse_id=SID, content="second"),
-            log=log,
-            thinking_widget=widget,
-            tools_log=MagicMock(),
-            debug_log=debug_log,
-            raw=False,
-        )
-        # Close the second run with a Done.
+        ):
+            state.render(
+                evt, log=log,
+                tools_log=MagicMock(), debug_log=MagicMock(),
+                current_text=current_text, thinking_log=thinking_log, raw=False,
+            )
        state.render(
            _make_tui_done(),
            log=log,
-            thinking_widget=widget,
-            tools_log=MagicMock(),
-            debug_log=debug_log,
-            raw=True,
+            tools_log=MagicMock(), debug_log=MagicMock(),
+            current_text=current_text, thinking_log=thinking_log, raw=False,
        )
-        # v0.5.0: closed thinking entries land in debug_log, NOT log.
-        thinking_entries = [_text_of(call[0][0]) for call in debug_log.write.call_args_list]
-        thinking_entries = [t for t in thinking_entries if t.startswith("· thinking:")]
-        assert len(thinking_entries) == 2
-        assert "first" in thinking_entries[0]
-        assert "second" in thinking_entries[1]
-        # transcript receives: "hi" (Text) + "[done] ..." (terminal label) only.
+        # v0.6.5: thinking_log holds 4 Rules (start + end per run) + 2 delta lines.
+        thinking_writes = [c[0][0] for c in thinking_log.write.call_args_list]
+        rules = [w for w in thinking_writes if isinstance(w, Rule)]
+        delta_strs = [w for w in thinking_writes if isinstance(w, str)]
+        assert len(rules) == 4, f"expected 4 Rules (2 start + 2 end), got {len(rules)}"
+        assert "first" in delta_strs
+        assert "second" in delta_strs
+        # Text "hi" went to current_text (buffered), not the transcript directly.
+        current_text.update.assert_any_call("hi")
+        # Transcript: [done] label + Markdown(response) (raw=False).
        log_writes = [_text_of(c[0][0]) for c in log.write.call_args_list]
-        assert "hi" in log_writes
        assert any(w.startswith("[done]") for w in log_writes if isinstance(w, str))

    def test_render_exception_fallback(self) -> None:
-        """render_exception_fallback [adversarial, v0.5.0]:
-        widget.update raises → debug_log gets BOTH a plain-labeled fallback line
-        for the original Thinking event AND a `[render_error] <ExceptionClassName>`
-        line (NO exception message per INV-009 security clause). transcript
-        receives nothing — routing preservation under failure (debug-shaped
-        event falls back to debug_log).
+        """render_exception_fallback [adversarial, v0.6.5]:
+        thinking_log.write raises → catch in presenter, write plain-label
+        fallback + render_error line via INV-009 fallback path (routing
+        preservation: thinking events still route to thinking_log).
        """
        from ratatoskr.tui import TuiPresenterState

        log = MagicMock()
-        debug_log = MagicMock()
-        widget = MagicMock()
-        widget.update.side_effect = AttributeError("widget gone (msg should NOT leak)")
+        thinking_log = MagicMock()
+        # First call (Rule write) raises; subsequent calls succeed for fallback.
+        thinking_log.write.side_effect = [
+            AttributeError("rule write failed (msg should NOT leak)"),
+            None,
+            None,
+        ]
        state = TuiPresenterState()
        state.render(
            Thinking(sse_id=SID, content="x"),
            log=log,
-            thinking_widget=widget,
            tools_log=MagicMock(),
-            debug_log=debug_log,
+            debug_log=MagicMock(),
+            current_text=MagicMock(),
+            thinking_log=thinking_log,
            raw=False,
        )
-        writes = [c[0][0] for c in debug_log.write.call_args_list if isinstance(c[0][0], str)]
-        # POST-007: plain-label fallback for the original Thinking event.
+        writes = [c[0][0] for c in thinking_log.write.call_args_list if isinstance(c[0][0], str)]
        assert any(w.startswith("[thinking]") for w in writes), writes
-        # POST-007: render_error line with class name ONLY.
        assert any(w == "[render_error] AttributeError" for w in writes), writes
-        # Critical: exception message MUST NOT appear in any write (INV-009 security).
-        assert not any("widget gone" in w for w in writes), writes
-        # v0.5.0 routing preservation: transcript receives NOTHING on a
-        # debug-shaped event's failure path.
+        assert not any("rule write failed" in w for w in writes), writes
        assert not log.write.called

    def test_state_reset_per_worker(self) -> None:
@@ -350,9 +298,10 @@ class TestTuiPresenterState:
        s1.render(
            Thinking(sse_id=SID, content="x"),
            log=MagicMock(),
-            thinking_widget=MagicMock(),
            tools_log=MagicMock(),
            debug_log=MagicMock(),
+            current_text=MagicMock(),
+            thinking_log=MagicMock(),
            raw=False,
        )
        s2 = TuiPresenterState()
@@ -367,37 +316,35 @@ class TestTuiPresenterState:
        from ratatoskr.tui import TuiPresenterState

        log = MagicMock()
-        debug_log = MagicMock()
-        widget = MagicMock()
+        thinking_log = MagicMock()
        state = TuiPresenterState()
        state.render(
            Thinking(sse_id=SID, content="partial"),
            log=log,
-            thinking_widget=widget,
            tools_log=MagicMock(),
-            debug_log=debug_log,
-            raw=False,
+            debug_log=MagicMock(),
+            current_text=MagicMock(), thinking_log=thinking_log, raw=False,
        )
        state.render(
            Cancelled(
                sse_id=SID, phase="cancelled", turn_id=42, reason="user", partial_message_id=None
            ),
            log=log,
-            thinking_widget=widget,
            tools_log=MagicMock(),
-            debug_log=debug_log,
-            raw=False,
+            debug_log=MagicMock(),
+            current_text=MagicMock(), thinking_log=thinking_log, raw=False,
        )
-        # v0.5.0: closed thinking entry lands in debug_log; terminal [cancelled] in transcript.
-        debug_writes = [_text_of(c[0][0]) for c in debug_log.write.call_args_list]
+        # v0.6.5: streamed thinking + Rule(end) in thinking_log; [cancelled] in transcript.
        log_writes = [_text_of(c[0][0]) for c in log.write.call_args_list]
-        assert any(w.startswith("· thinking: partial") for w in debug_writes)
        assert any(w.startswith("[cancelled]") for w in log_writes)
-        assert widget.display is False
+        # thinking_log got at least Rule(start) + "partial" delta + Rule(end)
+        assert thinking_log.write.call_count >= 3

    def test_done_renders_markdown_after_label(self) -> None:
-        """done_renders_markdown_after_label [happy]:
-        Text("hi"), Done(response="hi") with raw=False → [done] label, Rule, Markdown in RichLog.
+        """done_renders_markdown_after_label [happy, v0.6.0]:
+        Text("hi") accumulates into current_text Static (buffered streaming);
+        Done(response="hi") with raw=False → [done] label + Rule + Markdown
+        in transcript. current_text cleared on terminal.
        """
        from rich.markdown import Markdown
        from rich.rule import Rule
@@ -405,30 +352,32 @@ class TestTuiPresenterState:
        from ratatoskr.tui import TuiPresenterState

        log = MagicMock()
-        widget = MagicMock()
+        current_text = MagicMock()
        state = TuiPresenterState()
        state.render(
            Text(sse_id=SID, content="hi"),
            log=log,
-            thinking_widget=widget,
            tools_log=MagicMock(),
            debug_log=MagicMock(),
+            current_text=current_text,
+            thinking_log=MagicMock(),
            raw=False,
        )
+        # Text accumulated to current_text, NOT written to log.
+        current_text.update.assert_any_call("hi")
        state.render(
            _make_tui_done(),
            log=log,
-            thinking_widget=widget,
            tools_log=MagicMock(),
            debug_log=MagicMock(),
+            current_text=current_text,
+            thinking_log=MagicMock(),
            raw=False,
        )
+        # Done cleared current_text and wrote [done] label + Rule + Markdown.
+        current_text.update.assert_any_call("")
        writes = [c[0][0] for c in log.write.call_args_list]
-        # Text stream wrote "hi" with no prefix.
-        assert "hi" in writes
-        # [done] label wrote.
-        assert any(isinstance(w, str) and w.startswith("[done]") for w in writes)
-        # Rule + Markdown render present (post-Done body re-render per issue #4 INV-005).
+        assert any(_text_of(w).startswith("[done]") for w in writes)
        assert any(isinstance(w, Rule) for w in writes)
        assert any(isinstance(w, Markdown) for w in writes)

@@ -440,23 +389,20 @@ class TestTuiPresenterState:
        from ratatoskr.tui import TuiPresenterState

        log = MagicMock()
-        widget = MagicMock()
        state = TuiPresenterState()
        state.render(
            Text(sse_id=SID, content="hi"),
            log=log,
-            thinking_widget=widget,
            tools_log=MagicMock(),
            debug_log=MagicMock(),
-            raw=True,
+            current_text=MagicMock(), thinking_log=MagicMock(), raw=True,
        )
        state.render(
            _make_tui_done(),
            log=log,
-            thinking_widget=widget,
            tools_log=MagicMock(),
            debug_log=MagicMock(),
-            raw=True,
+            current_text=MagicMock(), thinking_log=MagicMock(), raw=True,
        )
        writes = [c[0][0] for c in log.write.call_args_list]
        assert not any(isinstance(w, Rule) for w in writes)
@@ -477,10 +423,9 @@ class TestTuiPresenterState:
        state.render(
            WorkerPhase(sse_id=SID, phase="streaming", turn_id=42),
            log=log,
-            thinking_widget=MagicMock(),
            tools_log=MagicMock(),
            debug_log=debug_log,
-            raw=False,
+            current_text=MagicMock(), thinking_log=MagicMock(), raw=False,
        )
        # v0.5.0: WorkerPhase routes to debug_log, NOT transcript.
        assert not log.write.called
@@ -494,36 +439,10 @@ class TestTuiPresenterState:
        assert text.startswith("· worker_phase:")
        assert "[worker_phase]" not in text

-    def test_terminal_events_belt_and_braces_widget_cleanup(self) -> None:
-        """terminal_events_belt_and_braces_widget_cleanup [trace]:
-        Done / Error / Cancelled MUST clear+hide the thinking widget even when
-        thinking_open is False (Volva F3 fix; POST-005 + STEPS 5-6).
-        """
-        from ratatoskr.tui import TuiPresenterState
-
-        for terminal in (
-            _make_tui_done(),
-            Error(sse_id=SID, phase="failed", message="boom", error_code="x"),
-            Cancelled(
-                sse_id=SID, phase="cancelled", turn_id=42, reason="r", partial_message_id=None
-            ),
-        ):
-            log = MagicMock()
-            widget = MagicMock()
-            widget.display = True  # pre-set to non-default to detect the clear
-            state = TuiPresenterState()
-            # thinking_open is False (state just constructed).
-            state.render(
-                terminal,
-                log=log,
-                thinking_widget=widget,
-                tools_log=MagicMock(),
-                debug_log=MagicMock(),
-                raw=True,
-            )
-            # Belt-and-braces: widget cleared + hidden on EVERY terminal event.
-            widget.update.assert_called_with("")
-            assert widget.display is False, type(terminal).__name__
+    # v0.6.5: test_terminal_events_belt_and_braces_widget_cleanup deleted.
+    # The thinking-current Static is gone, so there's no widget to clean up
+    # on terminal events. The corresponding Volva F3 invariant is obsoleted
+    # by the streaming-into-thinking_log architecture.

    def test_tool_start_routes_to_tools_log(self) -> None:
        """tool_start_routes_to_tools_log [INV-014]: ToolStart writes to tools_log, NOT transcript.
@@ -540,10 +459,9 @@ class TestTuiPresenterState:
        state.render(
            ToolStart(sse_id=SID, name="read_file", arguments={"path": "/x"}),
            log=log,
-            thinking_widget=MagicMock(),
            tools_log=tools_log,
            debug_log=MagicMock(),
-            raw=False,
+            current_text=MagicMock(), thinking_log=MagicMock(), raw=False,
        )
        # INV-014: write went to tools_log
        assert tools_log.write.called
@@ -561,52 +479,57 @@ class TestTuiPresenterState:
        state.render(
            ToolResult(sse_id=SID, name="read_file", result="ok", duration_ms=12),
            log=log,
-            thinking_widget=MagicMock(),
            tools_log=tools_log,
            debug_log=MagicMock(),
-            raw=False,
+            current_text=MagicMock(), thinking_log=MagicMock(), raw=False,
        )
        assert tools_log.write.called
        assert _text_of(tools_log.write.call_args[0][0]).startswith("· tool_result:")
        assert not log.write.called

-    def test_text_event_does_not_route_to_tools_log(self) -> None:
-        """text_event_does_not_route_to_tools_log [INV-015]: Text → transcript, NOT tools_log."""
+    def test_text_event_buffers_into_current_text(self) -> None:
+        """text_event_buffers_into_current_text [v0.6.0]: Text → current_text Static
+        (accumulated), NOT log or tools_log. Streaming UX fix — no per-token spam.
+        """
        from ratatoskr.tui import TuiPresenterState

        log = MagicMock()
        tools_log = MagicMock()
+        current_text = MagicMock()
        state = TuiPresenterState()
        state.render(
            Text(sse_id=SID, content="hello"),
            log=log,
-            thinking_widget=MagicMock(),
            tools_log=tools_log,
            debug_log=MagicMock(),
+            current_text=current_text,
+            thinking_log=MagicMock(),
            raw=False,
        )
-        assert log.write.called
-        assert log.write.call_args[0][0] == "hello"
-        # INV-015: tools_log was NOT written to
+        current_text.update.assert_called_once_with("hello")
+        assert not log.write.called
        assert not tools_log.write.called

-    def test_text_no_prefix(self) -> None:
-        """text_no_prefix [trace]: Text → RichLog line has no `·` prefix, no demotion."""
+    def test_text_deltas_accumulate(self) -> None:
+        """text_deltas_accumulate [v0.6.0]: multiple Text deltas → current_text shows
+        concatenated content, NOT separate per-delta lines.
+        """
        from ratatoskr.tui import TuiPresenterState

-        log = MagicMock()
+        current_text = MagicMock()
        state = TuiPresenterState()
-        state.render(
-            Text(sse_id=SID, content="hello"),
-            log=log,
-            thinking_widget=MagicMock(),
-            tools_log=MagicMock(),
-            debug_log=MagicMock(),
-            raw=False,
-        )
-        line = log.write.call_args[0][0]
-        # Pure content, no demotion prefix.
-        assert line == "hello"
+        for tok in ("Hel", "lo", " ", "world"):
+            state.render(
+                Text(sse_id=SID, content=tok),
+                log=MagicMock(),
+                tools_log=MagicMock(),
+                debug_log=MagicMock(),
+                current_text=current_text,
+                thinking_log=MagicMock(),
+                raw=False,
+            )
+        # Final update reflects the full concatenation.
+        assert current_text.update.call_args_list[-1][0][0] == "Hello world"

    def test_duration_format_seconds(self) -> None:
        """duration_format_seconds [trace]: Done(duration_ms=5467) → label has "duration=5.5s"."""
@@ -617,15 +540,14 @@ class TestTuiPresenterState:
        state.render(
            _make_tui_done(duration_ms=5467),
            log=log,
-            thinking_widget=MagicMock(),
            tools_log=MagicMock(),
            debug_log=MagicMock(),
-            raw=True,
+            current_text=MagicMock(), thinking_log=MagicMock(), raw=True,
        )
        done_line = next(
-            c[0][0]
+            _text_of(c[0][0])
            for c in log.write.call_args_list
-            if isinstance(c[0][0], str) and c[0][0].startswith("[done]")
+            if _text_of(c[0][0]).startswith("[done]")
        )
        assert "duration=5.5s" in done_line
        assert "duration_ms=5467" not in done_line
@@ -645,15 +567,14 @@ class TestTuiPresenterState:
        state.render(
            _make_tui_done(usage=usage),
            log=log,
-            thinking_widget=MagicMock(),
            tools_log=MagicMock(),
            debug_log=MagicMock(),
-            raw=True,
+            current_text=MagicMock(), thinking_log=MagicMock(), raw=True,
        )
        done_line = next(
-            c[0][0]
+            _text_of(c[0][0])
            for c in log.write.call_args_list
-            if isinstance(c[0][0], str) and c[0][0].startswith("[done]")
+            if _text_of(c[0][0]).startswith("[done]")
        )
        assert "usage 6756 in → 126 out (6882 total, 0 cached)" in done_line

@@ -807,27 +728,28 @@ class TestLayoutShape:
            assert row is not None

    async def test_left_column_content_only(self) -> None:
-        """left_column_content_only [v0.5.0]: left column = transcript + prompt ONLY.
-
-        thinking-current Static moved to right column so the left column is
-        genuinely content-only (transcript + prompt input).
+        """left_column_content_only [v0.6.5]: left column = transcript + prompt
+        + current-text (streaming text Static). thinking-current Static
+        removed entirely as of v0.6.5.
        """
        from textual.containers import Vertical
-        from textual.widgets import Input, RichLog, Static
+        from textual.widgets import Input, RichLog

        app = _resolved_app(_args_new(), session_id="s-new12345", agent_id="mimir")
        async with app.run_test() as pilot:
            await pilot.pause()
            left = app.query_one("#left-column", Vertical)
-            right = app.query_one("#right-column", Vertical)
            transcript = app.query_one("#transcript", RichLog)
            prompt = app.query_one("#prompt", Input)
-            thinking = app.query_one("#thinking-current", Static)
            assert transcript in left.walk_children()
            assert prompt in left.walk_children()
-            # v0.5.0: thinking-current is now under the right column, NOT left.
-            assert thinking not in left.walk_children()
-            assert thinking in right.walk_children()
+            # v0.6.5: thinking-current Static removed; no longer in DOM at all.
+            from textual.css.query import NoMatches
+            try:
+                app.query_one("#thinking-current")
+                raise AssertionError("thinking-current should not exist in v0.6.5")
+            except NoMatches:
+                pass  # expected

    async def test_right_column_has_tabbed_content_with_tools_tab(self) -> None:
        """right_column_has_tabbed_content_with_tools_tab: #side-panes + TabPane#tools-tab."""
@@ -914,6 +836,58 @@ class TestLayoutShape:
            await pilot.pause()
            assert app.query_one("#side-panes", TabbedContent).active == "debug-tab"

+    async def test_done_label_styled_success(self) -> None:
+        """done_label_styled_success [v0.5.1]: [done] label renders in Aurora green."""
+        from rich.text import Text as RichText
+        from textual.widgets import RichLog
+
+        app = _resolved_app(_args_new(), session_id="s-new12345", agent_id="mimir")
+        async with app.run_test() as pilot:
+            await pilot.pause()
+            # Probe the presenter directly — write a Done via state.render.
+            from ratatoskr.tui import TuiPresenterState
+            log = app.query_one("#transcript", RichLog)
+            state = TuiPresenterState()
+            seen: list = []
+            orig = log.write
+            log.write = lambda c, *a, **kw: (seen.append(c), orig(c, *a, **kw))[1]
+            state.render(
+                _make_tui_done(),
+                log=log,
+                tools_log=app.query_one("#tools-log", RichLog),
+                debug_log=app.query_one("#debug-log", RichLog),
+                current_text=MagicMock(), thinking_log=MagicMock(), raw=True,
+            )
+            done = next(
+                c for c in seen
+                if isinstance(c, RichText) and _text_of(c).startswith("[done]")
+            )
+            assert done.style == "#16B866"  # Aurora green
+
+    async def test_empty_state_placeholders_present(self) -> None:
+        """empty_state_placeholders_present [v0.5.1]: tools-log + debug-log show
+        placeholder lines before any turn fires."""
+        from textual.widgets import RichLog
+
+        app = _resolved_app(_args_new(), session_id="s-new12345", agent_id="mimir")
+        async with app.run_test() as pilot:
+            await pilot.pause()
+            # Activate Debug tab so its content actually renders.
+            from textual.widgets import TabbedContent
+            tabbed = app.query_one("#side-panes", TabbedContent)
+            tabbed.active = "debug-tab"
+            await pilot.pause()
+            tabbed.active = "tools-tab"
+            await pilot.pause()
+            tools_log = app.query_one("#tools-log", RichLog)
+            debug_log = app.query_one("#debug-log", RichLog)
+            tools_text = " ".join(str(line) for line in tools_log.lines)
+            tabbed.active = "debug-tab"
+            await pilot.pause()
+            debug_text = " ".join(str(line) for line in debug_log.lines)
+            assert "no tool events" in tools_text
+            assert "worker_phase" in debug_text
+
    async def test_pane_name_updates_on_tab_switch(self) -> None:
        """pane_name_updates_on_tab_switch [v0.5.0]: pane-name reflects active tab.

@@ -1100,7 +1074,10 @@ async def _submit_and_wait(app: RatatoskrApp, pilot, content: str) -> None:
 class TestStreamTurnWorker:
    @respx.mock
    async def test_happy_text_done_renders_markdown(self, monkeypatch: pytest.MonkeyPatch) -> None:
-        """happy_text_done_renders_markdown [happy,tracer]: …"""
+        """happy_text_done_renders_markdown [happy,tracer, v0.6.0]:
+        Text deltas go to current_text (not transcript); on Done, transcript
+        gets turn-header Rule, [done] label, post-Done Rule + Markdown body.
+        """
        stream = _sse_chunk("42:1", {"type": "text", "content": "hello"}) + _sse_chunk(
            "42:2", _DONE_BODY
        )
@@ -1115,20 +1092,25 @@ class TestStreamTurnWorker:
            await pilot.pause()
            await _submit_and_wait(app, pilot, "hi")
            assert app.state == "idle"
-            # Streamed delta + done label + rule + markdown render
-            assert any(w == "hello" for w in writes)
-            assert any("[done]" in str(w) for w in writes)
-            # The post-Done markdown render uses rich Rule + Markdown — non-string writes.
-            # INV-005: BOTH separator (Rule) AND markdown render must be present in non-raw.
+            # v0.6.0: Text("hello") goes to current_text Static, NOT log.
+            # writes spy captures RichLog.write only, so "hello" SHOULD NOT appear.
            from rich.markdown import Markdown
            from rich.rule import Rule

+            assert not any(w == "hello" for w in writes)
+            assert any("[done]" in str(w) for w in writes)
+            # Post-Done: Markdown body + Rule + turn-header Rule all present.
            assert any(isinstance(w, Markdown) for w in writes)
            assert any(isinstance(w, Rule) for w in writes)

    @respx.mock
    async def test_raw_flag_skips_markdown_render(self, monkeypatch: pytest.MonkeyPatch) -> None:
-        """raw_flag_skips_markdown_render [trace]: …"""
+        """raw_flag_skips_markdown_render [trace, v0.6.0]:
+        With --raw, no Markdown render. A turn-header Rule IS still written
+        (v0.6.0 INV — turn correlation lives in every pane). The post-Done
+        Rule(separator) is suppressed; accumulated streamed text is written
+        as a plain string instead.
+        """
        stream = _sse_chunk("42:1", {"type": "text", "content": "hi"}) + _sse_chunk(
            "42:2", _DONE_BODY
        )
@@ -1140,12 +1122,17 @@ class TestStreamTurnWorker:
        async with app.run_test() as pilot:
            await pilot.pause()
            await _submit_and_wait(app, pilot, "x")
-            # INV-005: with --raw, NEITHER Rule separator NOR Markdown render appears.
            from rich.markdown import Markdown
            from rich.rule import Rule

+            # No Markdown in raw mode.
            assert not any(isinstance(w, Markdown) for w in writes)
-            assert not any(isinstance(w, Rule) for w in writes)
+            # Only turn-header Rules — one per pane (transcript + tools +
+            # debug + thinking = 4). No post-Done separator Rule.
+            rules = [w for w in writes if isinstance(w, Rule)]
+            assert len(rules) == 4, f"expected 4 turn-header Rules, got {len(rules)}"
+            # Accumulated text "hi" written as plain string post-Done.
+            assert "hi" in writes

    @respx.mock
    async def test_error_terminal_returns_to_idle(self, monkeypatch: pytest.MonkeyPatch) -> None:
@@ -968,7 +968,7 @@ wheels = [

 [[package]]
 name = "ratatoskr"
-version = "0.5.0"
+version = "0.7.1"
 source = { editable = "." }
 dependencies = [
    { name = "httpx" },