fix(#20 ): heid-bug-hunt fixups — CLI open-world container-type hardening (slice-5)

Panel (Gróa + Hulda + Regin, source-verified by Heid): adapter/route-map/ ConnectFailed-at-call-sites sound against the declared invariants; 4 real robustness findings, all in the CLI open-world presenter/probe paths — the container-type layer BELOW the null/element holes the code-review already fixed. Fixed (findings 1-3): - `_format_whoami` (`cli.py`): a non-iterable `scopes`/`allowed_roles` scalar (`{"scopes": 123}`) made `x or []` yield `123` → `for s in 123` TypeError. New `_display_seq` helper degrades any non-list (scalar / bare string / null / absent) to empty; applied to both `scopes` and `allowed_roles`. - `_characters_probe` (`cli.py`): same class on the model catalog `items` (`{"items": 123}`) — now guards `models` is a Mapping and `items` is a list before iterating. - `_characters_probe`: the top-level open-world reads `created` / `state` are now `isinstance(_, Mapping)`-guarded before any `.get` — a non-mapping SDK passthrough (`created=[...]`) aborts cleanly (exit 20) / renders `pad=None` instead of an AttributeError. Accepted (finding 4, documented in contract § slice-5 notes): the `--characters` probe leaks its transient character on a mid-lifecycle failure. PRE-EXISTING (the retired probe had the identical linear no-`finally` structure — cutover did not worsen it), TTL-bounded, one-shot diagnostic; a `try/finally` would swallow a happy-path delete-failure (delete is both teardown and a tested step). Gróa + Heid concur accept is defensible. Dismissed (finding 5): Hulda flagged `sessions.py` dropping `get_me`/etc. as a caller-contract break — it is the intended DEC-3 no-backwards-compat migration (all in-repo callers rewired same-diff); Heid labels it intended-surface-change. Added CLI tests for the three hardened paths (scalar scopes/roles; scalar items + non-mapping state; non-mapping create abort). Suite 488 green; ruff clean; live smoke re-run clean (identical happy-path output). Patch bump 0.21.17 → 0.21.18.
fix(#20 ): heid-code-review fixups — CLI presenter degrade-not-crash (slice-5)
2026-07-19 11:29:10 -07:00 · 2026-07-19 11:11:12 -07:00 · 2026-07-19 11:00:41 -07:00 · 2026-07-19 10:24:35 -07:00 · 2026-07-19 10:18:36 -07:00
17 changed files with 907 additions and 347 deletions
@@ -247,6 +247,54 @@ re-anchor its coverage-map rows.
  per the heid-code-review slice-4 precision flag (the § Error map 404 rows assume a
  well-formed Tier-3 id reaches the route).

+### Slice-5 notes (Characters + me/capabilities/models, decided at TDD)
+
+- **No new § Error map rows.** All six routes (`me.get`, `capabilities.get`,
+  `models.available_for_characters`, `characters.create` / `.state` / `.delete`) are
+  open-world reads/acks (B-OPEN-2) whose SDK ops carry NO discriminated error (no
+  `map_error`), so every `ApiError` maps to the default `SessionApiFailed` — exact
+  parity with the retiring hand-rolled path, which likewise raised only its generic
+  `SessionApiFailed` on any non-2xx (never discriminating a status/code on these
+  routes). The route-map table above already lists all six.
+- **`create_character` body — omit `state` when None.** The adapter sends
+  `{"character": …}` plus `"state"` only when the caller supplies a non-None state
+  (the SDK forwards the body dict as-is via httpx `json=`). This drops the hand-rolled
+  path's redundant explicit `"state": null` — server-equivalent (Worldtree's
+  `CreateCharacterRequest.state` defaults None whether omitted or explicit-null),
+  SDK-idiomatic (matches the SDK's `CreateCharacterInput` `NotRequired` shape), and
+  invisible at the sole call-site (`--characters` never passes a state). Adopt-
+  canonical over byte-for-byte wire parity.
+- **`delete_character` returns the SDK's open ack verbatim (`-> Mapping | None`).**
+  The SDK route returns an open-world ack body (not 204 — `CharacterDeleteResult`), so
+  the adapter passes it through rather than normalizing to the hand-rolled `None`
+  (parity posture: no None-normalization of an open-world read). On a 204 no-content
+  the SDK yields `None`, so the return type is `Mapping | None`; the sole call-site
+  (`--characters`) ignores the value, so the change is unobservable.
+- **Open-world presenter degrade-not-crash (cumulative foot-gun).** `_format_whoami`
+  is already hardened (slice-4 heid bug-hunt). The rewired `_characters_probe` extracts
+  the created id defensively (`created.get("character_id")` + type-guard → clean abort,
+  never a hard-index KeyError) since the create ACK is now an open-world SDK read.
+- **Container-type hardening (heid code-review + bug-hunt slice-5).** The degrade-not-
+  crash floor is guarded at THREE levels for the CLI presenters, not just one: (a) the
+  list-typed fields `scopes` / `allowed_roles` / model `items` degrade a non-list scalar
+  (`123`) or a bare string to empty via `_display_seq` / an `isinstance(_, list)` guard —
+  the older `or []` idiom only caught null/absent and would `for x in 123` `TypeError`;
+  (b) each element is type-guarded (`isinstance(m, dict)`); (c) the top-level open-world
+  reads `created` / `models` / `state` are `isinstance(_, Mapping)`-guarded before any
+  `.get` (a non-mapping passthrough would otherwise `AttributeError`). All three feed
+  `--whoami` / `--characters` only.
+- **Accepted (not fixed): the `--characters` probe leaks its transient character on a
+  mid-lifecycle failure.** create → get-state → delete runs linearly with no `finally`,
+  so a state/delete failure after a successful create orphans the probe character until
+  its TTL. This is PRE-EXISTING (the retired hand-rolled probe had the identical
+  structure — the cutover did not worsen it), TTL-bounded, and `--characters` is a
+  one-shot diagnostic smoke; a `try/finally` cleanup would also swallow a happy-path
+  delete-failure (delete is both the teardown AND a tested lifecycle step). Accepted as
+  known-risk per the heid bug-hunt (Gróa + Heid concur accept is defensible).
+- **CLI-only rewire.** `me` / `capabilities` / `characters` / `models` have NO
+  web-server caller — only the `--whoami` and `--characters` CLI one-shot probes. The
+  web surface is untouched this slice.
+
 ## Out of scope

 - Bifrost PROVIDER planes (memory/affect) — hand-rolled, ADR-0009, untouched.
@@ -94,15 +94,15 @@ sub-gap).
 | `POST /agents/define` | ✅ | `wt.py` `define_agent` (SDK `agents.define`) → `tier3.py` `_run_define` | **wt-adapter re-anchored (slice-4, #20)** — sends AgentDefineInput `{agent_name,role,system_prompt}`, returns open-world `DefinedAgent` (echoes `role`, b128); slug pre-validated; 429→Tier3QuotaExceeded(retry_after=0, header-less floor), 403→Tier3UserIdUnsupported, 422 layer_deferred→Tier3LayerDeferred. **LIVE-SMOKE 2026-07-19**: `define --role thoughtful-character` → `defined ratatoskr:slice4-smoke (thoughtful-character)` |
 | `PATCH /agents/{id}` | ✅ | `wt.py` `patch_agent` (SDK `agents.patch`) → `tier3.py` `_run_patch` | **wt-adapter re-anchored (slice-4, #20)** — Tier-3 mutate (system_prompt/**role**, model→role folded in); 404→Tier3AgentNotFound, 422 field_not_mutable→Tier3FieldNotMutable. **LIVE-SMOKE 2026-07-19**: `patched ratatoskr:slice4-smoke`; a non-existent id via `python -m` → `[agent_not_found]` (exit 20, class-identity fix proven) |
 | `DELETE /agents/{id}` | ✅ | `wt.py` `delete_agent` (SDK `agents.delete`) → `tier3.py` `_run_delete` | **wt-adapter re-anchored (slice-4, #20)** — 204→None; 404→Tier3AgentNotFound (route-discriminated, NOT hide-existence). **LIVE-SMOKE 2026-07-19**: `deleted ratatoskr:slice4-smoke` + local index → `[]` |
-| `GET /me` | ✅ | `sessions.py:411` `get_me` → `cli.py` `--whoami` | identity/whoami probe; 401→SessionApiFailed |
-| `GET /capabilities` | ✅ | `sessions.py` `get_capabilities` → `cli.py` `--whoami` | Echo ephemeral-template discovery. **v0.21.2: `--whoami` renderer reads `allowed_roles`/`default_role`** (was the dead `allowed_models`/`default_model`) + tolerates malformed caps; matches conversation-api-spec **v1.1** (`b4a278c`) |
+| `GET /me` | ✅ | `wt.py` `get_me` (SDK `me.get`) → `cli.py` `--whoami` | **wt-adapter re-anchored (slice-5, #20)** — open-world identity dict verbatim; any error→SessionApiFailed default (401 on a bad/absent key), transport→ConnectFailed→exit 21. **LIVE-SMOKE 2026-07-19** on personal :8081 (b128): identity rendered (user_id ratatoskr, tier user, scopes incl. `character.*`, key_id c990f0be) |
+| `GET /capabilities` | ✅ | `wt.py` `get_capabilities` (SDK `capabilities.get`) → `cli.py` `--whoami` | **wt-adapter re-anchored (slice-5, #20)** — open-world advertisement verbatim; `_format_whoami` reads `allowed_roles`/`default_role` and degrades on a null/non-mapping template (slice-4 hardening); matches conversation-api-spec **v1.1** (`b4a278c`). **LIVE-SMOKE 2026-07-19**: `ephemeral_template echo: default=echo max_bytes=32768 roles=[echo]` |
 | `GET /sessions/{id}/tools` | ✅ | `sessions.py:411` `get_session_tools` → `tui.py` `_hydrate_session_tools` | owner-scoped tool inventory in the TUI Tools pane (#183) |
 | `GET /admin/sessions/{id}/bifrost` | ✅ | `sessions.py:428` `get_session_bifrost` → `tui.py` `_hydrate_bifrost_state` | admin-scoped BifrostState pane (#176); admin key (`RATATOSKR_ADMIN_API_KEY`); live-auth-proven |
 | `GET /admin/events` (SSE) | ✅ | `sse_client.py` `stream_admin_events` → `tui.py` `_stream_admin_events` | admin lifecycle SSE stream (#11), session-filtered AdminEvents pane; admin key; live-auth-proven |
-| `GET /models/available-for-characters` | ✅ | `sessions.py` `list_character_models` → `cli.py` `--characters` | character-capable model profiles (#161) |
-| `POST /characters` | ✅ | `sessions.py` `create_character` → `cli.py` `--characters` | create transient character (#161) |
-| `GET /characters/{id}/state` | ✅ | `sessions.py` `get_character_state` → `cli.py` `--characters` | live character PAD/emotions (#161) |
-| `DELETE /characters/{id}` | ✅ | `sessions.py` `delete_character` → `cli.py` `--characters` | remove transient character (#161) |
+| `GET /models/available-for-characters` | ✅ | `wt.py` `list_character_models` (SDK `models.available_for_characters`) → `cli.py` `--characters` | **wt-adapter re-anchored (slice-5, #20)** — open-world catalog verbatim; the probe reads `items` null-safe (`or []`); any error→SessionApiFailed default. **LIVE-SMOKE 2026-07-19**: `character models: char-rp` |
+| `POST /characters` | ✅ | `wt.py` `create_character` (SDK `characters.create`) → `cli.py` `--characters` | **wt-adapter re-anchored (slice-5, #20)** — body `{character}` (+`state` only when set — SDK-idiomatic, drops the redundant explicit null); open-world create ACK verbatim; the probe degrades on a missing `character_id` (no hard-index). **LIVE-SMOKE 2026-07-19**: `created char_8c00006e…` |
+| `GET /characters/{id}/state` | ✅ | `wt.py` `get_character_state` (SDK `characters.state`) → `cli.py` `--characters` | **wt-adapter re-anchored (slice-5, #20)** — open-world live PAD/emotions verbatim; TTL-refreshing read. **LIVE-SMOKE 2026-07-19**: `state pad=[0.234, -0.136, 0.065]` read back |
+| `DELETE /characters/{id}` | ✅ | `wt.py` `delete_character` (SDK `characters.delete`) → `cli.py` `--characters` | **wt-adapter re-anchored (slice-5, #20)** — returns the SDK's open ACK verbatim (`-> Mapping|None`, NOT normalized to None; 204→None); any error→SessionApiFailed default. **LIVE-SMOKE 2026-07-19**: `deleted char_8c00006e…` |
 | `POST /sessions/{id}/persona_state` | ✅ | `wt.py` `set_persona_state` (SDK `sessions.set_persona_state`, `PadState`) → `cli.py` `--set-persona-pad` | **wt-adapter re-anchored (slice-3, #20)** — SDK owns the canonical `{"pad": {...}}` wire (#317); CLI passes the 3 PAD axes (finiteness pre-validated); 204→None, else SessionApiFailed default. **LIVE-SMOKE 2026-07-19** on personal :8081: `--set-persona-pad 0.4,0.1,-0.2` → **204** |

 **Sub-gaps inside ✅ path groups** (the method we use is live; a sibling method
@@ -0,0 +1,66 @@
+`[2026-07-19]` **worldtree-sdk cutover SLICE-4 COMPLETE + committed (`c62b4ee`+`aed9429`+`477d98f`, v0.21.13–.15, 475 green).**
+
+Agents/Tier-3 family onto the `ratatoskr.wt` adapter + the `model`→`role` fold (scope B),
+full House Code Discipline end-to-end (contract error-map → TDD → rewire → delete → live
+smoke → coverage re-anchor → both heid gates → fixups).
+
+**What moved onto the SDK** (`client.agents.*`, open-world dicts, errors mapped by
+route+(status,error_code) per INV-CUT-2): `list_agents` (`agents.list`),
+`get_persona_state` (`agents.persona_state`; 404 persona_not_configured /
+404 agent_not_available / 403 auth_scope_denied dual-key), `define_agent`
+(`agents.define`; 429→Tier3QuotaExceeded(retry_after=0) status-only, 403
+tier3_user_id_unsupported, 422 layer_deferred), `patch_agent` (`agents.patch`; bare-404→
+Tier3AgentNotFound, 422 field_not_mutable), `delete_agent` (`agents.delete`; bare-404).
+Rewired the `python -m ratatoskr.tier3` CLI + the web `_agents_endpoint` /
+`_persona_state_endpoint`. DELETED the hand-rolled `sessions.list_agents` /
+`get_persona_state` / `AgentInfo` and `tier3.define/patch/delete_agent` /
+`Tier3AgentInfo` / parse+extract helpers.
+
+**model→role fold:** define/patch response echoes `role` (spec 1.2 / b128), read off the
+open-world dict; `LocalAgentEntry.model`→`.role`, local-index `_SCHEMA_VERSION` 1→2 (old
+index discarded, no-compat). `project_tier3_agents_model_to_role_pending` is RESOLVED by
+this — the deferred scope-B work landed here (doing it standalone would have been throwaway).
+
+**KEY SLICE-4 FOOT-GUNS (for slices 5-7 + any tier3 work):**
+- **`python -m` double-module exception identity.** Running tier3 as `__main__` while
+  `wt` imports `ratatoskr.tier3` bound TWO copies of each `Tier3*` class → a raised
+  `Tier3AgentNotFound` escaped the CLI's `except` as an uncaught traceback (exit 1, not
+  the mapped exit 20). Unit tests call `main()` in-process (module is `ratatoskr.tier3`,
+  not `__main__`) so they NEVER hit the split — the LIVE SMOKE caught it. Fix: the `Tier3*`
+  exceptions live in `sessions.py` (never run as `__main__`) → single class identity, and
+  it removed the `wt→tier3` import edge. Rule: caller-semantic exceptions the adapter
+  raises + a `-m` CLI catches must NOT live in the `-m` module.
+- **Open-world presenters must degrade, never crash.** The heid-bug-hunt panel (5/5/5, two
+  3/3 crash sites) caught the CLI (`_run_define`/`_run_patch`) and web (`_agents_endpoint`)
+  HARD-INDEXING the open-world dicts (`info["agent_id"]`, `{a["agent_id"] for a in
+  upstream}`) → KeyError/TypeError on a partial/drifted 2xx response (incl. `system_prompt:
+  null` → `None.splitlines()` AttributeError). The wt tests + live smoke used FULL server
+  dicts, so it never surfaced. Fix: `_str_field` (absent/null/non-str → default) in the
+  CLI; well-formed-mapping filter in the web endpoint; a no-agent_id 2xx → controlled exit
+  20. The invariant "open-world reads degrade, never crash the presenter" must hold at
+  EVERY presenter, not just the adapter.
+
+**Both heid gates cleared:**
+- **code-review (panel, zero adapter/error-map/model→role drift):** 3 fixups (v0.21.14,
+  `aed9429`) — persona endpoint now catches `wt.SessionApiFailed` (parity with 3 sibling
+  endpoints; a latent PRE-cutover gap, NOT a slice-4 regression); dual-key NEGATIVE tests
+  for define/patch + flat-`field` test; contract documents the `":" in agent_id` PRE.
+- **bug-hunt (panel 5/5/5, no false positives):** 3 fixups (v0.21.15, `477d98f`) — the two
+  open-world presenter crash sites above + `_error_field_from_body` type-checks `field` is
+  str. HELD (contract-intended, Heid-confirmed): the 429→quota / bare-404→not-found
+  status-only maps (the arms flagged them spec-free; the § Error map specifies them; the
+  SDK's ApiError floor drops Retry-After so retry_after=0 is canonical). Dual-keying
+  define's 429 for full row consistency is an available tightening (contract amendment),
+  surfaced not applied.
+
+**LIVE-SMOKE on personal :8081 (b128):** valid agent roles are `thoughtful-character` /
+`character` / `assistant` (NOT the `/models/available-for-characters` `char-rp` — that's a
+character-model, a different vocab; define 422s on it). define→patch→list(6 agents:
+forseti/lofn/mask/mimir/vili/…)→persona_state(→PersonaNotConfigured mapped)→delete→index
+empty; non-existent-id patch via `-m` → `[agent_not_found]` exit 20 (double-module fix
+proven). Throwaway `ratatoskr:slice4-smoke` deleted, server left clean.
+
+**NEXT = slice-5** (characters + me/capabilities/models — the remaining consumer reads);
+then slice-6 (admin: `stream_admin_events` + `get_session_bifrost`, admin_auth), slice-7
+(teardown: delete residual hand-rolled, drop `httpx-sse`, retire contracts #2/#15, MINOR
+bump per DEC-6 w/ operator approval). Consumer layer ONLY; Bifrost provider planes untouched.
@@ -0,0 +1,31 @@
+`[2026-07-19]` **wyrd-dev #368 silo-enforcement consult DELIVERED (althing thread `01KXXNDH3JE4`) — ratatoskr's store-side memory silo is CONVENTIONAL, wyrd going STRUCTURAL off my framing.**
+
+wyrd-dev is standing up their `bifrost-memory-store-server` (unit-4) and asked for
+ratatoskr's hands-on read of the #368 `(end_user, agent)` silo mechanics before writing
+their contract. I answered artifact-only from `src/ratatoskr/provider/memory_store.py`
+(reference-impl posture: verified against code, not memory).
+
+**The load-bearing finding:** ratatoskr's silo is **conventional (query-time scope
+filter), NOT structural.** Scope axes live inside `record_json` (+ a mirror `scope_json`
+column), and every read path (`search`, `scan`, `list_chunks`) calls `_matches_scope` in
+Python — "an `if` a caller can forget." Inherited byte-faithfully from bifrost's reference
+`InMemoryMemoryStore`. Sharpest leak surfaces: `get`/`get_many` do ZERO scope check
+(trust caller-knows-entitled-ids); the vec-search must over-fetch-ALL-then-Python-filter
+(a naive `LIMIT top_k` in SQL silently under-recalls or leaks). ratatoskr has NO
+`clear_partition` verb — forget is by-id `delete_many` (two-table chunk+vec atomicity in
+one txn); the idempotency table is a hidden replay channel a total-forget must purge.
+
+**Outcome — wyrd committed to STRUCTURAL** (msg 3, `01KXXNQYGX0K`): one-DB-file-per-campaign
+(campaign_id silo structurally unrepresentable across files) + `(scope_end_user,
+scope_agent_self)` first-class NOT NULL composite-indexed columns, every query incl. the
+vec JOIN carrying the partition in SQL `WHERE`. Dissolves my two sharpest leak surfaces
+(by-id reads enforce the predicate; the vec JOIN filters+ranks+caps in ONE statement).
+Folding my foot-guns as contract STEPS/invariants (two-table+producer-candidate delete
+atomicity; forget purges idempotency + reaches superseded; `scope_any` = list of
+whole-element-conjunctive dicts never flatten axes #297; `check_same_thread=False`;
+`SortableChunkField` needs name+type or handshake dies; advertise⟹implement;
+revision+idempotency-check before writes in one txn). worldtree-dev already pushed wyrd
+structural in the record-shape re-read, so aligned; wyrd will flag the
+reference-`InMemoryMemoryStore`-divergence to bifrost-dev (internal enforcement, wire
+unchanged). **OPEN LOOP:** I offered to eyeball wyrd's data model once the unit-4 contract
+is cut — they took it; they'll ping. No action pending on ratatoskr now.
@@ -46,34 +46,34 @@ upstream API key stays server-side (INV-003).

 _As of 2026-07-19:_

-**🔨 ACTIVE MIGRATION — worldtree-sdk cutover (issue #20): SLICE-1 + SLICE-2 + SLICE-3 COMPLETE, slice-4 next.**
+**🔨 ACTIVE MIGRATION — worldtree-sdk cutover (issue #20): SLICE-1–4 COMPLETE, slice-5 next.**
 Operator ruled ADOPT (2026-07-18): ratatoskr cuts its CONSUMER client layer over to **worldtree-sdk (Python)
 1.0.0**, retiring the hand-rolled httpx wrappers behind a thin `ratatoskr.wt` adapter. Design locked (6 DECs,
 vor-cross'd, heid-panel-reviewed); contract `docs/contracts/worldtree_sdk_cutover.contract.md`. **SLICE-1+2
-(foundation + sessions/turn) ✅ PUSHED** origin `aba1730` (arc `b1fbadd`→`aba1730`, tags v0.21.3–.10). **SLICE-3
-(persona + authored-history + first-message) ✅ DONE** — `ca9a339` (feat) + `fc256bb` (heid-bug-hunt fixups),
-tags v0.21.11–.12; full House Code Discipline (TDD → heid-code-review CLEAN/zero-drift → heid-bug-hunt).
-Suite **469 green**. Slice-3 migrated `set_persona_state` (SDK `PadState`), `write_authored_history`
-(`write_history`, 404→AuthoredHistoryUnavailable hide-existence), `get_session_messages`, + routed
-`first_message` seed through the adapter; DELETED the last hand-rolled `sessions.py` paths (`create_session`+
-`SessionInfo`, `set_persona_state`, `write_authored_history`, `get_session_messages`, `_bifrost_error_from`).
-LIVE-SMOKE on :8081 (b128): seed→201(seq0)→read-back; persona→204; create-path preset seed. **KEY ADAPTER FACTS
-(foot-guns for slices 4-7):** SDK returns **open-world dicts** for reads → `info["session_id"]`; `TurnEvent`
-carries `sse_id` + a **`turn_id` ABSENT on text/thinking frames** → parse cancel-target from `sse_id`; the SDK
-**normalizes ANY transport failure to `ConnectFailed(status=0)`** (`request.py:196`, NOT raw httpx) — every
-caller through the adapter must `except ConnectFailed` (the slice-3 bug-hunt caught both probes missing it);
-`consumer_key` is BOUND-create-only; the SDK's envelope parser **prefers nested `detail`** (why bound-502 isn't
-error_code-gated). **NEXT = slice-4** (agents/tier3 — list/get/define/patch/delete/persona_state, FOLDS the
-`model`→`role` cutover); then slice-5 (characters/me/caps), slice-6 (admin — `stream_admin_events` +
-`get_session_bifrost` still hand-rolled), slice-7 (teardown: retire contracts #2/#15, drop `httpx-sse`, minor
-bump per DEC-6 w/ operator approval). Scope: consumer layer ONLY; Bifrost provider planes untouched. Full
-design → auto-memory `project_worldtree_sdk_cutover`.
+(foundation + sessions/turn) ✅ PUSHED** origin `aba1730`. **SLICE-3 (persona + authored-history + first-message)
+✅ DONE** `ca9a339`+`fc256bb`. **SLICE-4 (agents/Tier-3 + `model`→`role` fold) ✅ DONE** — `c62b4ee` (feat) +
+`aed9429` (heid-code-review fixups) + `477d98f` (heid-bug-hunt fixups), tags v0.21.13–.15; full House Code
+Discipline, both heid panels cleared. Suite **475 green**. Slice-4 migrated
+list_agents/get_persona_state/define/patch/delete onto `client.agents.*` (open-world dicts, errors mapped by
+route+(status,error_code)), folded `model`→`role` (`LocalAgentEntry.role`, index schema v2), and DELETED the
+hand-rolled `sessions.list_agents`/`get_persona_state`/`AgentInfo` + `tier3.define/patch/delete_agent`. Full arc
+ the two slice-4 foot-guns → `persistent-memory.d/2026-07-19-worldtree-sdk-cutover-slice-4-complete.md`.
+**KEY ADAPTER FACTS (foot-guns, cumulative for slices 5-7):** SDK reads = **open-world dicts** —
+presenters MUST degrade not crash (slice-4 bug-hunt: hard-indexing `info["x"]` crashes on partial wire; use
+`.get`/type-guards; `system_prompt: null` → `None.splitlines()`); the SDK **normalizes ANY transport failure to
+`ConnectFailed(status=0)`** (NOT raw httpx) — every adapter caller must `except ConnectFailed`;
+**caller-semantic exceptions the adapter raises + a `-m` CLI catches must NOT live in the `-m` module** (the
+`python -m ratatoskr.tier3` double-module split gave two `Tier3*` class identities → uncaught traceback; fixed
+by homing them in `sessions.py`; unit tests can't catch this, the live smoke did); `TurnEvent` `turn_id` ABSENT
+on text/thinking frames; `consumer_key` is BOUND-create-only; envelope parser prefers nested `detail`.
+**NEXT = slice-5** (characters + me/capabilities/models — remaining consumer reads); then slice-6 (admin:
+`stream_admin_events` + `get_session_bifrost`, admin_auth), slice-7 (teardown: retire contracts #2/#15, drop
+`httpx-sse`, MINOR bump per DEC-6 w/ operator approval). Scope: consumer layer ONLY; Bifrost provider untouched.
+Full design → auto-memory `project_worldtree_sdk_cutover`.

-**⏸️ DEFERRED — tier3 agents `model`→`role` (scope B), folds into cutover slice-4.** WT renamed the
-agents-RESPONSE selector `model`→`role` (spec 1.2). **DEPLOY NOW LIVE** on :8080/:8081 (v1.0.0b128,
-worldtree-dev confirmed 2026-07-19 — was the deploy-flag gate; acked). Operator chose scope B (full tier3
-`model`→`role` incl. contract #15 + CLI `--model`→`--role`); lands in cutover slice-4 where tier3.py routes
-through the SDK (doing it standalone now = throwaway). Auto-memory `project_tier3_agents_model_to_role_pending`.
+**✅ RESOLVED — tier3 agents `model`→`role` (scope B) folded into cutover slice-4** (`c62b4ee`, v0.21.13). The
+deferred deploy-gated scope-B work (response `model`→`role` per spec 1.2 / b128, `LocalAgentEntry`, index schema
+v2) landed with the agents-family SDK cutover — no longer pending. See the slice-4 detail file + Recent decisions.

 **✅ RESOLVED — the "app product" workstreams leave Rata entirely (operator 2026-07-18).**
 **No arbo fork, no SillyTavern-on-Rata** — a NEW repo (template-dev standing up) takes over BOTH
@@ -117,13 +117,13 @@ Full record → `persistent-memory.d/2026-07-18-368-silo-test-passed.md`. Siblin
 (2) R39 Phase-2 **matched-quartets rebuild** (confirmatory, "whenever"); (3) bifrost **snapshot-cursor
 adoption** (ruled normative, not blocking → `persistent-memory.d/2026-07-16-bifrost-cursor-conformance.md`).

-**Substrate / environment:** branch `main` at **v0.21.12**, **PUSHED to origin** (slice-3 arc `ca9a339`+
-`fc256bb` + this snapshot, tags v0.21.11–.12, pushed 2026-07-19; slice-1+2 arc `b1fbadd`→`aba1730` +
-v0.21.3–.10 earlier). origin `git@gitea.phasefinal.com:vh/ratatoskr.git`. **NEW core dep:
+**Substrate / environment:** branch `main` at **v0.21.15** — slice-4 arc `c62b4ee`→`477d98f` + this snapshot
+**COMMITTED, not-yet-pushed** (tags v0.21.13–.15; push is the operator's call); slice-1–3 (v0.21.3–.12,
+`b1fbadd`→`4f92a21`) PUSHED to origin earlier. origin `git@gitea.phasefinal.com:vh/ratatoskr.git`. **NEW core dep:
 `worldtree-sdk==1.0.0`** (gitea PyPI, `[tool.uv.sources]`; `httpx-sse` retires at slice-7). bifrost
 **`==1.1.4`** / wire v0.7; WT openapi vendored 2.3.0, **conversation-api-spec re-synced to v1.1** (`b4a278c`);
-**suite 469 green** (was 497 post-slice-2; net delta = slice-3 adapter/probe tests added, ~50 deleted
-hand-rolled sessions tests). Personal WT on **b128**
+**suite 475 green** (slice-4 added the agents-family adapter tests + heid-gate fixup tests, ~offset by the
+deleted hand-rolled agent/persona tests). Personal WT on **b128**
 (`http://10.250.50.152:8081`; #368 silo + #364 promotion-hygiene live both instances). The combined
 **:8392** provider (memory+affect) + **:8765** web are THE surfaces, dev-box BACKGROUND SHELLS —
 restart via `scratchpad/relaunch_by_pid.py <pid>` (pid via `ss -ltnp | grep <port>`). `env.sh` sets
@@ -274,6 +274,10 @@ decision. Captures rationale that won't be obvious from code alone.
 - `[2026-07-19]` **worldtree-sdk cutover SLICE-1 + SLICE-2 COMPLETE + PUSHED (origin `aba1730`, v0.21.10, 497 green).** The biggest, riskiest cutover slice done end-to-end through the full House Code Discipline (adapter→cli→web→delete→live-smoke→both heid gates); the bug-hunt caught 4 real confirmed bugs the conformance lens couldn't, and a convergent code-review finding was correctly REJECTED as category-5 (SDK envelope-parser behavior). Slice-3 next. → `persistent-memory.d/2026-07-19-worldtree-sdk-cutover-slice-1-2-complete.md`
 - `[2026-07-19]` **worldtree-sdk cutover SLICE-3 COMPLETE + pushed (`ca9a339`+`fc256bb`, v0.21.11–.12, 469 green).** Persona/authored-history/first-message onto the wt adapter; last hand-rolled `sessions.py` paths deleted; both heid gates cleared — code-review ZERO drift, bug-hunt caught + fixed a real regression I shipped (ConnectFailed escaping both rewired probes → uncaught crash; the SDK normalizes ALL transport failures to `ConnectFailed`, not raw httpx) plus a finite-PAD chokepoint gap. Slice-4 (agents/tier3 + model→role) next. → `persistent-memory.d/2026-07-19-worldtree-sdk-cutover-slice-3-complete.md`

+- `[2026-07-19]` **worldtree-sdk cutover SLICE-4 COMPLETE (agents/Tier-3 + `model`→`role` fold, `c62b4ee`+`aed9429`+`477d98f`, v0.21.13–.15, 475 green).** Full House Code Discipline; the LIVE SMOKE caught a `python -m` double-module exception-class-identity bug unit tests structurally can't; both heid panels cleared (code-review zero-drift + 3 fixups; bug-hunt 5/5/5 → open-world-presenter degrade-not-crash fixes). Resolves the deferred scope-B model→role. Slice-5 next. → `persistent-memory.d/2026-07-19-worldtree-sdk-cutover-slice-4-complete.md`
+
+- `[2026-07-19]` **wyrd-dev #368 silo-enforcement consult delivered — ratatoskr's store-side silo is CONVENTIONAL (query-time filter); wyrd going STRUCTURAL off the framing.** Answered artifact-only from the provider memory-store code; wyrd folded my foot-guns into their unit-4 contract + committed to one-DB-file-per-campaign + first-class partition columns. OPEN LOOP: I'll eyeball their data model once the contract's cut (they'll ping). → `persistent-memory.d/2026-07-19-wyrd-368-silo-consult-delivered.md`
+
 _67 older entries (2026-05-* debug-TUI/web era + the 2026-06-14 → 06-18 Bifrost-provider build / #17+#18 / #295-296 era) archived to archival-memory.md._

 _For per-issue TDD implementation notes, Volva findings, and contract amendments, see the git log — every per-issue commit carries a structured message capturing the trail._
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"

 [project]
 name = "ratatoskr"
-version = "0.21.14"
+version = "0.21.18"
 description = "Worldtree Conversation API debug console (web + headless CLI) — multi-pane observability"
 readme = "README.md"
 requires-python = ">=3.12"
@@ -43,21 +43,14 @@ from ratatoskr.sessions import (
    BifrostBinding,
    BifrostConsumerKeyMissing,
    BifrostHandshakeFailed,
-    SessionApiFailed,
-    create_character,
-    delete_character,
    endpoint_for_plane,
-    get_capabilities,
-    get_character_state,
-    get_me,
-    list_character_models,
 )

-# The turn path (create / stream / cancel) is served by the worldtree-sdk adapter
-# (`wt.*`); these caller-semantic exceptions are what the adapter raises, so the
-# presenter keeps catching ratatoskr's own types (DEC-2). The hand-rolled probes
-# (--whoami / --characters / --set-persona / --seed-first-message) stay on the
-# `sessions` wrappers until their own slices.
+# The turn path (create / stream / cancel) and all consumer reads are served by the
+# worldtree-sdk adapter (`wt.*`); these caller-semantic exceptions are what the adapter
+# raises, so the presenter keeps catching ratatoskr's own types (DEC-2). Only the
+# Bifrost-binding inputs + `endpoint_for_plane` remain hand-rolled here (the provider
+# planes are consumer-orthogonal); `get_session_bifrost`'s admin surface lands in slice-6.
 from ratatoskr.sse_client import (
    MalformedSseData,
    MalformedSseId,
@@ -752,12 +745,29 @@ async def _amain(args: ParsedArgs) -> int:
            loop.remove_signal_handler(signal.SIGINT)


-def _format_whoami(me: dict[str, Any], caps: dict[str, Any]) -> str:
+def _display_seq(value: Any) -> list[str]:
+    """Coerce an open-world wire value to a list of display strings — the degrade-not-
+    crash floor for a list-typed field (`scopes`, `allowed_roles`, model `items`, ...).
+
+    A non-list scalar (absent, null, `123`, or a bare string) → empty rather than a
+    crash: the older `or []` idiom handles absent/null but NOT a truthy non-iterable
+    (`123 or [] == 123` → `for x in 123` `TypeError`) and would char-iterate a bare
+    string. Only a genuine list/tuple is str-mapped (heid bug-hunt slice-5, findings 1-2).
+    """
+    if not isinstance(value, (list, tuple)):
+        return []
+    return [str(x) for x in value]
+
+
+def _format_whoami(me: Mapping[str, Any], caps: Mapping[str, Any]) -> str:
    """Render the --whoami report: identity (GET /me) + server capabilities."""
    lines = ["identity:"]
    lines.append(f"  user_id: {me.get('user_id', '?')}")
    lines.append(f"  tier: {me.get('tier', '?')}")
-    lines.append(f"  scopes: {', '.join(me.get('scopes', [])) or '(none)'}")
+    # Open-world read: `scopes` may be absent, null, a scalar, or carry non-strings —
+    # `_display_seq` degrades every non-list to empty (the contract names this function
+    # the degrade-not-crash exemplar; heid code-review + bug-hunt slice-5).
+    lines.append(f"  scopes: {', '.join(_display_seq(me.get('scopes'))) or '(none)'}")
    for k in ("display_name", "key_id", "key_label"):
        if k in me:
            lines.append(f"  {k}: {me[k]}")
@@ -766,16 +776,17 @@ def _format_whoami(me: dict[str, Any], caps: dict[str, Any]) -> str:
    if isinstance(templates, dict) and templates:
        for name, spec in templates.items():
            # A diagnostic renderer must tolerate a malformed / partially-cutover
-            # server (heid bug-hunt Gróa#1/#2): a non-mapping template value, or an
-            # explicit-null `allowed_roles` (`.get(k, [])` returns None on null, not
-            # the default), must degrade — not abort the whole --whoami report.
+            # server: a non-mapping template value, or an `allowed_roles` that is null
+            # / a scalar / carries non-strings, must degrade — not abort the whole
+            # --whoami report (heid bug-hunt slice-5: `_display_seq` guards the
+            # container type, not just null/element as the prior `or []` did).
            if not isinstance(spec, dict):
                lines.append(f"  ephemeral_template {name}: (malformed)")
                continue
            # Canonical post-cutover shape (worldtree-dev althing 2026-07-18,
            # ADR-0012): roles, not models. `config.role` selects; `config.model`
            # is now rejected server-side.
-            roles = ", ".join(str(r) for r in (spec.get("allowed_roles") or []))
+            roles = ", ".join(_display_seq(spec.get("allowed_roles")))
            lines.append(
                f"  ephemeral_template {name}: default={spec.get('default_role', '?')} "
                f"max_bytes={spec.get('system_prompt_max_bytes', '?')} roles=[{roles}]"
@@ -794,18 +805,23 @@ async def _whoami(args: ParsedArgs) -> int:
    vocab + exit codes as the other modes.
    """
    assert isinstance(args, ParsedArgs)
-    async with httpx.AsyncClient(
-        base_url=args.server_url,
-        headers={"Authorization": f"Bearer {args.api_key}", "User-Agent": USER_AGENT},
-        timeout=httpx.Timeout(connect=10.0, read=10.0, write=10.0, pool=10.0),
-    ) as client:
+    async with _probe_client(args) as transport:
+        client = wt.build_client(args.server_url, api_key=args.api_key, transport=transport)
        try:
-            me = await get_me(client)
-            caps = await get_capabilities(client)
-        except SessionApiFailed as exc:
-            sys.stderr.write(f"[session_api_failed] status={exc.status} body={exc.body!r}\n")
+            me = await wt.get_me(client)
+            caps = await wt.get_capabilities(client)
+        except wt.SessionApiFailed as exc:
+            sys.stderr.write(
+                f"[session_api_failed] status={exc.status} "
+                f"error_code={exc.error_code!r} body={exc.body!r}\n"
+            )
            return 20
-        except (httpx.ConnectError, httpx.ReadTimeout, httpx.TransportError) as exc:
+        except (
+            httpx.ConnectError,
+            httpx.ReadTimeout,
+            httpx.TransportError,
+            ConnectFailed,  # SDK normalizes a pre-response transport failure here
+        ) as exc:
            sys.stderr.write(f"[network_error] {type(exc).__name__}: {exc}\n")
            return 21
        sys.stdout.write(_format_whoami(me, caps))
@@ -826,12 +842,21 @@ async def _characters_probe(args: ParsedArgs) -> int:
    (models → create → get-state → delete), print a report, exit. A reference-
    consumer smoke of the #161 character surface (needs character.read/write)."""
    assert isinstance(args, ParsedArgs)
-    async with _probe_client(args) as client:
+    async with _probe_client(args) as transport:
+        client = wt.build_client(args.server_url, api_key=args.api_key, transport=transport)
        try:
-            models = await list_character_models(client)
-            names = ", ".join(m.get("name", "?") for m in models.get("items", []))
+            models = await wt.list_character_models(client)
+            # Open-world reads degrade, never crash (heid code-review + bug-hunt slice-5):
+            # guard the top-level `models` is a mapping AND `items` is a list before
+            # iterating (a scalar `items: 123` makes `... or []` yield `123` → `for m in
+            # 123` TypeError), then guard each entry is a dict with a str-coerced `name`.
+            raw_items = models.get("items") if isinstance(models, Mapping) else None
+            items = raw_items if isinstance(raw_items, (list, tuple)) else []
+            names = ", ".join(
+                str(m.get("name", "?")) for m in items if isinstance(m, dict)
+            )
            sys.stdout.write(f"character models: {names or '(none)'}\n")
-            created = await create_character(
+            created = await wt.create_character(
                client,
                {
                    "schema_version": "1",
@@ -845,16 +870,35 @@ async def _characters_probe(args: ParsedArgs) -> int:
                    "voice_profile_block": "plain",
                },
            )
-            cid = created["character_id"]
+            # Open-world create ACK: degrade, don't hard-index (cumulative cutover
+            # foot-gun). A non-mapping ACK or an absent/blank character_id aborts the
+            # probe cleanly (exit 20) rather than raising AttributeError/KeyError — the
+            # lifecycle needs the id for state + delete (heid bug-hunt slice-5). Past the
+            # guard, `created`/`state` are known mappings.
+            cid = created.get("character_id") if isinstance(created, Mapping) else None
+            if not (isinstance(cid, str) and cid):
+                sys.stderr.write(
+                    f"[session_api_failed] create returned no character_id: {created!r}\n"
+                )
+                return 20
            sys.stdout.write(f"created: {cid} (ttl {created.get('ttl_expires_at')})\n")
-            state = await get_character_state(client, cid)
-            sys.stdout.write(f"state: pad={state.get('pad')}\n")
-            await delete_character(client, cid)
+            state = await wt.get_character_state(client, cid)
+            pad = state.get("pad") if isinstance(state, Mapping) else None
+            sys.stdout.write(f"state: pad={pad}\n")
+            await wt.delete_character(client, cid)
            sys.stdout.write(f"deleted: {cid}\n")
-        except SessionApiFailed as exc:
-            sys.stderr.write(f"[session_api_failed] status={exc.status} body={exc.body!r}\n")
+        except wt.SessionApiFailed as exc:
+            sys.stderr.write(
+                f"[session_api_failed] status={exc.status} "
+                f"error_code={exc.error_code!r} body={exc.body!r}\n"
+            )
            return 20
-        except (httpx.ConnectError, httpx.ReadTimeout, httpx.TransportError) as exc:
+        except (
+            httpx.ConnectError,
+            httpx.ReadTimeout,
+            httpx.TransportError,
+            ConnectFailed,  # SDK normalizes a pre-response transport failure here
+        ) as exc:
            sys.stderr.write(f"[network_error] {type(exc).__name__}: {exc}\n")
            return 21
    return 0
@@ -230,81 +230,6 @@ def endpoint_for_plane(plane: str, base_host: str) -> str:
    return f"http://{base_host}:{ports[plane]}"


-async def get_me(client: httpx.AsyncClient) -> dict[str, Any]:
-    """GET /me — the authenticated principal's identity + key metadata (spec §GET /me).
-
-    Boot-time whoami: verify the key without agent-config side effects. Returns
-    the parsed dict verbatim (freeform per the frozen OpenAPI; the spec documents
-    `{user_id, scopes, tier, display_name?, key_id?, key_label?, ...}`, optional
-    fields omitted-not-null). 401 (bad/absent key when auth is enabled) — like
-    every other non-200 — surfaces as SessionApiFailed (get_persona_state
-    precedent). Read-only, rate-exempt, no audit emission.
-    """
-    assert client is not None
-    resp = await client.get("/me")
-    if resp.status_code == 200:
-        return resp.json()
-    raise SessionApiFailed(status=resp.status_code, body=resp.content)
-
-
-async def list_character_models(client: httpx.AsyncClient) -> dict[str, Any]:
-    """GET /models/available-for-characters — character-capable model profiles (#161).
-
-    Requires `character.read`. Returns `{items: [{name, description, thinking}]}`.
-    Parsed dict verbatim; any non-200 → SessionApiFailed.
-    """
-    assert client is not None
-    resp = await client.get("/models/available-for-characters")
-    if resp.status_code == 200:
-        return resp.json()
-    raise SessionApiFailed(status=resp.status_code, body=resp.content)
-
-
-async def create_character(
-    client: httpx.AsyncClient, character: dict[str, Any], *, state: dict[str, Any] | None = None
-) -> dict[str, Any]:
-    """POST /characters — create a transient character (#161). Requires `character.write`.
-
-    Body is `{character, state}` (state optional — a CharacterStateSchema for
-    mid-conversation rehydration). Returns 201 `{character_id, ttl_expires_at}`;
-    any non-201 → SessionApiFailed.
-    """
-    assert client is not None
-    assert isinstance(character, dict) and character
-    resp = await client.post("/characters", json={"character": character, "state": state})
-    if resp.status_code == 201:
-        return resp.json()
-    raise SessionApiFailed(status=resp.status_code, body=resp.content)
-
-
-async def get_character_state(client: httpx.AsyncClient, character_id: str) -> dict[str, Any]:
-    """GET /characters/{character_id}/state — live runtime state (#161). Requires `character.read`.
-
-    Returns `{schema_version, pad, emotions_active, mood_drift, goal_signal_history}`;
-    refreshes the character's TTL. Any non-200 → SessionApiFailed.
-    """
-    assert client is not None
-    assert character_id and isinstance(character_id, str)
-    resp = await client.get(f"/characters/{character_id}/state")
-    if resp.status_code == 200:
-        return resp.json()
-    raise SessionApiFailed(status=resp.status_code, body=resp.content)
-
-
-async def delete_character(client: httpx.AsyncClient, character_id: str) -> None:
-    """DELETE /characters/{character_id} — remove a transient character (#161).
-
-    Requires `character.write`. Bound sessions detach (next turn → 410
-    character_not_found). 200/204 → None; any other status → SessionApiFailed.
-    """
-    assert client is not None
-    assert character_id and isinstance(character_id, str)
-    resp = await client.delete(f"/characters/{character_id}")
-    if resp.status_code in (200, 204):
-        return None
-    raise SessionApiFailed(status=resp.status_code, body=resp.content)
-
-
 async def get_session_bifrost(
    client: httpx.AsyncClient, session_id: str, *, admin_key: str
 ) -> dict[str, Any]:
@@ -328,18 +253,3 @@ async def get_session_bifrost(
    if resp.status_code == 200:
        return resp.json()
    raise SessionApiFailed(status=resp.status_code, body=resp.content)
-
-
-async def get_capabilities(client: httpx.AsyncClient) -> dict[str, Any]:
-    """GET /capabilities — server capability discovery (spec §Ephemeral Templates).
-
-    Returns `{ephemeral_templates: {echo: {allowed_models, default_model,
-    system_prompt_max_bytes}}}` — what the server offers before a client decides
-    to instantiate. Any authenticated caller may read it (no scope). Parsed dict
-    verbatim; any non-200 → SessionApiFailed.
-    """
-    assert client is not None
-    resp = await client.get("/capabilities")
-    if resp.status_code == 200:
-        return resp.json()
-    raise SessionApiFailed(status=resp.status_code, body=resp.content)
@@ -17,6 +17,9 @@ mappings. ``wt`` imports this module's exceptions at module level; this module i
 from __future__ import annotations

 import argparse
+import sys
+from collections.abc import Mapping
+from typing import Any

 import httpx

@@ -31,6 +34,15 @@ from ratatoskr.sessions import (
    Tier3UserIdUnsupported,
 )

+
+def _str_field(info: Mapping[str, Any], key: str, *, default: str = "") -> str:
+    """A string field off an open-world response dict, or `default` when the key is
+    absent / null / non-string — so a partial or drifted 2xx define/patch response
+    degrades rather than KeyError/AttributeError-crashing the CLI presenter (the
+    "open-world reads degrade, never crash the presenter" invariant; heid-bug-hunt)."""
+    value = info.get(key)
+    return value if isinstance(value, str) else default
+
 # ---- CLI (`python -m ratatoskr.tier3 <subcommand>`) ------------------------
 #
 # Auth + server URL resolution mirrors ratatoskr.cli verbatim. Exit codes
@@ -122,18 +134,27 @@ async def _run_define(ns: argparse.Namespace) -> int:
            system_prompt=ns.system_prompt,
            role=ns.role,
        )
-        # v0.8.0: persist to local index so the picker can show it. The SDK returns
-        # the open-world define dict — read `role` (echoed post-b128), not `model`.
-        add_local_agent(
-            LocalAgentEntry(
-                agent_id=info["agent_id"],
-                agent_name=info["agent_name"],
-                role=info["role"],
-                description=make_description(info.get("system_prompt", "")),
-                defined_at=info.get("created_at", ""),
+        # Open-world define dict — read defensively (echoes `role` post-b128, not
+        # `model`). A partial/drifted 2xx must not crash the presenter.
+        agent_id = _str_field(info, "agent_id")
+        if not agent_id:  # a 2xx with no usable agent_id is a malformed success
+            sys.stderr.write(f"[api_failed] define returned no usable agent_id: {info!r}\n")
+            return 20
+        role = _str_field(info, "role", default="?")
+        agent_name = _str_field(info, "agent_name")
+        # v0.8.0: persist to local index so the picker can show it — only for a
+        # well-formed identity (agent_id + agent_name); else skip the write, still print.
+        if agent_name:
+            add_local_agent(
+                LocalAgentEntry(
+                    agent_id=agent_id,
+                    agent_name=agent_name,
+                    role=role,
+                    description=make_description(_str_field(info, "system_prompt")),
+                    defined_at=_str_field(info, "created_at"),
+                )
            )
-        )
-        print(f"defined {info['agent_id']} ({info['role']})")
+        print(f"defined {agent_id} ({role})")
        return 0


@@ -158,17 +179,24 @@ async def _run_patch(ns: argparse.Namespace) -> int:
            system_prompt=ns.system_prompt,
            role=ns.role,
        )
-        # v0.8.0: refresh local index with the post-patch state.
-        update_local_agent(
-            LocalAgentEntry(
-                agent_id=info["agent_id"],
-                agent_name=info["agent_name"],
-                role=info["role"],
-                description=make_description(info.get("system_prompt", "")),
-                defined_at=info.get("updated_at", ""),
+        # Open-world patch dict — read defensively (same degrade-not-crash posture).
+        agent_id = _str_field(info, "agent_id")
+        if not agent_id:  # a 2xx with no usable agent_id is a malformed success
+            sys.stderr.write(f"[api_failed] patch returned no usable agent_id: {info!r}\n")
+            return 20
+        agent_name = _str_field(info, "agent_name")
+        # v0.8.0: refresh local index with the post-patch state (well-formed identity only).
+        if agent_name:
+            update_local_agent(
+                LocalAgentEntry(
+                    agent_id=agent_id,
+                    agent_name=agent_name,
+                    role=_str_field(info, "role", default="?"),
+                    description=make_description(_str_field(info, "system_prompt")),
+                    defined_at=_str_field(info, "updated_at"),
+                )
            )
-        )
-        print(f"patched {info['agent_id']}")
+        print(f"patched {agent_id}")
        return 0


@@ -141,11 +141,18 @@ async def _agents_endpoint(request: Request) -> JSONResponse:
            {"error_code": "network_error", "message": str(exc)},
            status_code=502,
        )
-    # Open-world upstream dicts (parity: no AgentInfo normalization); read `agent_id`
-    # as a mapping key. Local tier3 entries dedup against the upstream ids (remote-wins).
-    upstream_ids = {a["agent_id"] for a in upstream}
+    # Open-world upstream (parity: no AgentInfo normalization). Degrade, never crash:
+    # a non-list envelope OR a malformed item (missing/non-str agent_id, non-mapping)
+    # is dropped rather than KeyError/TypeError'ing the endpoint into a 500 before the
+    # local fallback merges (heid-bug-hunt: the "open-world reads degrade" invariant).
+    upstream_items = upstream if isinstance(upstream, list) else []
+    well_formed = [
+        a for a in upstream_items
+        if isinstance(a, Mapping) and isinstance(a.get("agent_id"), str)
+    ]
+    upstream_ids = {a["agent_id"] for a in well_formed}
    local = _local_agents.load_local_agents()
-    merged = [_as_dict(a) for a in upstream] + [
+    merged = [_as_dict(a) for a in well_formed] + [
        _as_dict(le) for le in local if le.agent_id not in upstream_ids
    ]
    return JSONResponse(merged, status_code=200)
@@ -464,7 +464,10 @@ def _error_field_from_body(body: str | None) -> str | None:
    field = err.get("field")
    if field is None and isinstance(err.get("detail"), dict):
        field = err["detail"].get("field")
-    return field
+    # The exception surface declares `field: str | None` (and the CLI prints it), so a
+    # non-string envelope value (`{"field": {…}}` / `{"field": 1}`) collapses to None —
+    # same guard the retired hand-rolled `_extract_error_field` applied (heid-bug-hunt).
+    return field if isinstance(field, str) else None


 async def list_agents(client: WorldtreeClient) -> Sequence[Mapping[str, Any]]:
@@ -573,3 +576,111 @@ async def delete_agent(client: WorldtreeClient, agent_id: str) -> None:
        if exc.status == 404:
            raise Tier3AgentNotFound(agent_id=agent_id) from exc
        raise translate_error(exc) from exc
+
+
+# ── slice-5: characters + me/capabilities/models adapter routes ───────────────
+# The remaining consumer READS + transient-character CRUD over `client.me` /
+# `client.capabilities` / `client.models` / `client.characters.*`. All six are
+# open-world reads/acks (B-OPEN-2) returned verbatim; NONE carries a discriminated
+# error on the SDK floor (no `map_error`), so each maps any `ApiError` → the
+# `SessionApiFailed` default (INV-CUT-2) — exact parity with the retiring hand-rolled
+# path, which never discriminated a status/code on these routes. No new § Error map
+# rows. CLI-only: `--whoami` (me + capabilities) and `--characters` (models + CRUD);
+# no web-server caller this slice.
+
+
+async def get_me(client: WorldtreeClient) -> Mapping[str, Any]:
+    """The caller's identity + key metadata (GET /me), open-world dict verbatim.
+
+    The boot whoami — verifies the key with no agent-config side effects. Any error →
+    the `SessionApiFailed` default (notably 401 on a bad/absent key when auth is on).
+    """
+    try:
+        return await client.me.get()
+    except ApiError as exc:
+        raise translate_error(exc) from exc
+
+
+async def get_capabilities(client: WorldtreeClient) -> Mapping[str, Any]:
+    """The server capability advertisement (GET /capabilities), open-world verbatim.
+
+    Any authenticated caller may read it (no scope). Any error → the `SessionApiFailed`
+    default. The `--whoami` renderer degrades on a malformed advertisement rather than
+    crashing (`_format_whoami`, already hardened).
+    """
+    try:
+        return await client.capabilities.get()
+    except ApiError as exc:
+        raise translate_error(exc) from exc
+
+
+async def list_character_models(client: WorldtreeClient) -> Mapping[str, Any]:
+    """The character-capable model catalog (GET /models/available-for-characters, #161),
+    open-world dict verbatim. Requires `character.read`. Any error → the
+    `SessionApiFailed` default."""
+    try:
+        return await client.models.available_for_characters()
+    except ApiError as exc:
+        raise translate_error(exc) from exc
+
+
+async def create_character(
+    client: WorldtreeClient,
+    character: Mapping[str, Any],
+    *,
+    state: Mapping[str, Any] | None = None,
+) -> Mapping[str, Any]:
+    """Create a transient character (POST /characters, #161). Requires `character.write`.
+
+    The body is `{character}` plus `state` ONLY when supplied — the SDK forwards the
+    dict as-is, so ratatoskr omits the hand-rolled path's redundant explicit
+    `state: null` (server-equivalent — Worldtree's `CreateCharacterRequest.state`
+    defaults None whether omitted or explicit-null; SDK-idiomatic). Returns the
+    open-world create ACK verbatim (`{character_id, ttl_expires_at, ...}`). Any error →
+    the `SessionApiFailed` default (notably 403 when the key lacks `character.write`).
+    """
+    assert isinstance(character, Mapping) and character
+    try:
+        # Inline literals (per branch) so each type-checks structurally against the
+        # SDK's `CreateCharacterInput` TypedDict (`character` required, `state`
+        # NotRequired) without importing the SDK's private `_types` — same posture as
+        # `define_agent`. `state` is present ONLY when supplied (no redundant null).
+        if state is not None:
+            return await client.characters.create(
+                {"character": dict(character), "state": dict(state)}
+            )
+        return await client.characters.create({"character": dict(character)})
+    except ApiError as exc:
+        raise translate_error(exc) from exc
+
+
+async def get_character_state(
+    client: WorldtreeClient, character_id: str
+) -> Mapping[str, Any]:
+    """The character's live runtime state (GET /characters/{id}/state, #161), open-world
+    dict verbatim; the read refreshes the character's TTL. Requires `character.read`.
+    Any error → the `SessionApiFailed` default."""
+    assert character_id and isinstance(character_id, str)
+    try:
+        return await client.characters.state(character_id)
+    except ApiError as exc:
+        raise translate_error(exc) from exc
+
+
+async def delete_character(
+    client: WorldtreeClient, character_id: str
+) -> Mapping[str, Any] | None:
+    """Delete a transient character (DELETE /characters/{id}, #161). Requires
+    `character.write`; bound sessions detach (next turn → 410 `character_not_found`).
+
+    Returns the SDK's open-world delete ACK verbatim (`CharacterDeleteResult` —
+    Worldtree returns a body here, NOT 204) rather than normalizing to the hand-rolled
+    `None` (parity: no None-normalization of an open-world read). A 204 no-content
+    yields `None`, hence the `Mapping | None` return; the sole call-site ignores it.
+    Any error → the `SessionApiFailed` default.
+    """
+    assert character_id and isinstance(character_id, str)
+    try:
+        return await client.characters.delete(character_id)
+    except ApiError as exc:
+        raise translate_error(exc) from exc
@@ -1879,6 +1879,49 @@ class TestWhoami:
        assert rc == 20
        assert "[session_api_failed]" in capsys.readouterr().err

+    @respx.mock
+    def test_whoami_tolerates_null_and_nonstring_scopes(
+        self, capsys: pytest.CaptureFixture[str]
+    ) -> None:
+        """scopes present-null / non-string → renders '(none)' or str-coerced, never a
+        `join(None)` TypeError (heid-code-review slice-5: `_format_whoami` is the
+        contract's degrade-not-crash exemplar; `allowed_roles` was hardened, `scopes`
+        was not)."""
+        # scopes: null (present, not absent) → `.get('scopes', [])` would return None.
+        respx.get("https://w.example/me").mock(
+            return_value=httpx.Response(200, json={"user_id": "u", "scopes": None, "tier": "user"})
+        )
+        respx.get("https://w.example/capabilities").mock(
+            return_value=httpx.Response(200, json={"ephemeral_templates": {}})
+        )
+        rc = main(["--whoami", "--api-key", "k", "--server", "https://w.example"])
+        assert rc == 0
+        assert "scopes: (none)" in capsys.readouterr().out
+
+    @respx.mock
+    def test_whoami_tolerates_scalar_scopes_and_roles(
+        self, capsys: pytest.CaptureFixture[str]
+    ) -> None:
+        """Non-iterable (scalar) `scopes` / `allowed_roles` → degrade to empty, never a
+        `for x in 123` TypeError (heid bug-hunt slice-5: `_display_seq` guards the
+        container TYPE, the next layer past the code-review null/element fix)."""
+        respx.get("https://w.example/me").mock(
+            return_value=httpx.Response(200, json={"user_id": "u", "scopes": 123, "tier": "user"})
+        )
+        respx.get("https://w.example/capabilities").mock(
+            return_value=httpx.Response(
+                200,
+                json={
+                    "ephemeral_templates": {"echo": {"allowed_roles": 7, "default_role": "echo"}}
+                },
+            )
+        )
+        rc = main(["--whoami", "--api-key", "k", "--server", "https://w.example"])
+        assert rc == 0
+        out = capsys.readouterr().out
+        assert "scopes: (none)" in out
+        assert "roles=[]" in out
+

 class TestTier2Probes:
    """--characters + --set-persona-pad one-shot probes (Tier-2: #161 + persona_state-write)."""
@@ -1923,6 +1966,102 @@ class TestTier2Probes:
        assert "deleted: char_z" in out
        assert del_route.call_count == 1  # lifecycle cleaned up

+    @respx.mock
+    def test_characters_probe_tolerates_malformed_models(
+        self, capsys: pytest.CaptureFixture[str]
+    ) -> None:
+        """models catalog with non-mapping / non-string-name items → degrades (no
+        AttributeError/TypeError), lifecycle still proceeds (heid-code-review slice-5:
+        element-level completion of the list-level `or []` guard)."""
+        respx.get("https://w.example/models/available-for-characters").mock(
+            return_value=httpx.Response(
+                200, json={"items": [None, "x", {"name": 123}, {"name": "ok"}]}
+            )
+        )
+        respx.post("https://w.example/characters").mock(
+            return_value=httpx.Response(201, json={"character_id": "c1", "ttl_expires_at": "t"})
+        )
+        respx.get("https://w.example/characters/c1/state").mock(
+            return_value=httpx.Response(200, json={"pad": [0.0, 0.0, 0.0]})
+        )
+        respx.delete("https://w.example/characters/c1").mock(return_value=httpx.Response(204))
+        rc = main(["--characters", "--api-key", "k", "--server", "https://w.example"])
+        assert rc == 0
+        out = capsys.readouterr().out
+        # non-mappings dropped; {"name":123}→"123", {"name":"ok"}→"ok" — no crash.
+        assert "character models: 123, ok" in out
+        assert "created: c1" in out
+
+    @respx.mock
+    def test_characters_probe_tolerates_scalar_items_and_nonmapping_state(
+        self, capsys: pytest.CaptureFixture[str]
+    ) -> None:
+        """Scalar `items` (`123`) → '(none)' not a `for m in 123` TypeError; a non-mapping
+        `state` → 'pad=None' not an AttributeError. Lifecycle still completes (heid
+        bug-hunt slice-5: container-type + top-level-mapping guards)."""
+        respx.get("https://w.example/models/available-for-characters").mock(
+            return_value=httpx.Response(200, json={"items": 123})
+        )
+        respx.post("https://w.example/characters").mock(
+            return_value=httpx.Response(201, json={"character_id": "c1", "ttl_expires_at": "t"})
+        )
+        # non-mapping state body (open-world passthrough of a JSON array).
+        respx.get("https://w.example/characters/c1/state").mock(
+            return_value=httpx.Response(200, json=["not", "a", "mapping"])
+        )
+        del_route = respx.delete("https://w.example/characters/c1").mock(
+            return_value=httpx.Response(204)
+        )
+        rc = main(["--characters", "--api-key", "k", "--server", "https://w.example"])
+        assert rc == 0
+        out = capsys.readouterr().out
+        assert "character models: (none)" in out
+        assert "state: pad=None" in out
+        assert "deleted: c1" in out
+        assert del_route.call_count == 1
+
+    @respx.mock
+    def test_characters_probe_create_missing_id_aborts(
+        self, capsys: pytest.CaptureFixture[str]
+    ) -> None:
+        """create ACK without character_id → clean abort (exit 20), never a hard-index
+        KeyError (open-world degrade-not-crash; slice-5 cutover foot-gun)."""
+        respx.get("https://w.example/models/available-for-characters").mock(
+            return_value=httpx.Response(200, json={"items": []})
+        )
+        # 201 but the open-world ACK omits character_id — the probe must degrade.
+        respx.post("https://w.example/characters").mock(
+            return_value=httpx.Response(201, json={"ttl_expires_at": "t"})
+        )
+        del_route = respx.delete(url__regex=r"https://w\.example/characters/.+").mock(
+            return_value=httpx.Response(204)
+        )
+        rc = main(["--characters", "--api-key", "k", "--server", "https://w.example"])
+        assert rc == 20
+        assert "no character_id" in capsys.readouterr().err
+        assert del_route.call_count == 0  # aborted before state/delete — nothing to clean
+
+    @respx.mock
+    def test_characters_probe_non_mapping_create_aborts(
+        self, capsys: pytest.CaptureFixture[str]
+    ) -> None:
+        """A non-mapping create ACK (open-world passthrough of a JSON array/scalar) →
+        clean exit-20 abort, never an AttributeError on `created.get(...)` (heid
+        bug-hunt slice-5, finding #3)."""
+        respx.get("https://w.example/models/available-for-characters").mock(
+            return_value=httpx.Response(200, json={"items": []})
+        )
+        respx.post("https://w.example/characters").mock(
+            return_value=httpx.Response(201, json=["not", "a", "mapping"])
+        )
+        del_route = respx.delete(url__regex=r"https://w\.example/characters/.+").mock(
+            return_value=httpx.Response(204)
+        )
+        rc = main(["--characters", "--api-key", "k", "--server", "https://w.example"])
+        assert rc == 20
+        assert "no character_id" in capsys.readouterr().err
+        assert del_route.call_count == 0
+
    @respx.mock
    def test_set_persona_probe(self, capsys: pytest.CaptureFixture[str]) -> None:
        """set_persona_probe [happy,tracer]: POST pad to /sessions/{id}/persona_state; 204."""
@@ -6,14 +6,8 @@ import respx

 from ratatoskr.sessions import (
    SessionApiFailed,
-    create_character,
-    delete_character,
    endpoint_for_plane,
-    get_capabilities,
-    get_character_state,
-    get_me,
    get_session_bifrost,
-    list_character_models,
 )


@@ -38,99 +32,6 @@ class TestEndpointForPlane:
            endpoint_for_plane("persona", "10.100.10.50")


-class TestGetMe:
-    """docs/contracts/issues/2.contract.md FN get_me (slice: capabilities+me)."""
-
-    @respx.mock
-    async def test_happy_authenticated(self) -> None:
-        """happy_authenticated [happy,tracer]: 200 → parsed identity dict verbatim."""
-        respx.get("https://w.example/me").mock(
-            return_value=httpx.Response(
-                200,
-                json={
-                    "user_id": "alice",
-                    "scopes": ["conversations.read", "conversations.write"],
-                    "tier": "user",
-                    "key_id": "a1b2c3d4",
-                    "key_label": "alice phone",
-                },
-            )
-        )
-        async with httpx.AsyncClient(base_url="https://w.example") as client:
-            me = await get_me(client)
-        assert me["user_id"] == "alice"
-        assert me["tier"] == "user"
-        assert me["key_id"] == "a1b2c3d4"
-        assert me["scopes"] == ["conversations.read", "conversations.write"]
-
-    @respx.mock
-    async def test_anonymous_dev_mode(self) -> None:
-        """anonymous_dev_mode: 200 anonymous shape → dict with tier=anonymous."""
-        respx.get("https://w.example/me").mock(
-            return_value=httpx.Response(
-                200,
-                json={
-                    "user_id": "anonymous",
-                    "scopes": ["conversations.read"],
-                    "tier": "anonymous",
-                },
-            )
-        )
-        async with httpx.AsyncClient(base_url="https://w.example") as client:
-            me = await get_me(client)
-        assert me["tier"] == "anonymous"
-        assert "key_id" not in me  # optional fields omitted, not null
-
-    @respx.mock
-    async def test_401_raises_session_api_failed(self) -> None:
-        """401_raises [error]: bad/absent key → SessionApiFailed(status=401)."""
-        respx.get("https://w.example/me").mock(
-            return_value=httpx.Response(401, json={"detail": "auth_invalid"})
-        )
-        async with httpx.AsyncClient(base_url="https://w.example") as client:
-            with pytest.raises(SessionApiFailed) as exc:
-                await get_me(client)
-        assert exc.value.status == 401
-
-
-class TestGetCapabilities:
-    """docs/contracts/issues/2.contract.md FN get_capabilities (slice: capabilities+me)."""
-
-    @respx.mock
-    async def test_happy(self) -> None:
-        """happy [happy]: 200 → ephemeral_templates dict verbatim."""
-        respx.get("https://w.example/capabilities").mock(
-            return_value=httpx.Response(
-                200,
-                json={
-                    "ephemeral_templates": {
-                        "echo": {
-                            "allowed_models": ["glm5-turbo", "glm4.7"],
-                            "default_model": "glm5-turbo",
-                            "system_prompt_max_bytes": 32768,
-                        }
-                    }
-                },
-            )
-        )
-        async with httpx.AsyncClient(base_url="https://w.example") as client:
-            caps = await get_capabilities(client)
-        echo = caps["ephemeral_templates"]["echo"]
-        assert echo["default_model"] == "glm5-turbo"
-        assert echo["system_prompt_max_bytes"] == 32768
-
-    @respx.mock
-    async def test_non_200_raises(self) -> None:
-        """non_200_raises [error]: 500 → SessionApiFailed(status=500)."""
-        respx.get("https://w.example/capabilities").mock(
-            return_value=httpx.Response(500, content=b"boom")
-        )
-        async with httpx.AsyncClient(base_url="https://w.example") as client:
-            with pytest.raises(SessionApiFailed) as exc:
-                await get_capabilities(client)
-        assert exc.value.status == 500
-
-
 class TestGetSessionBifrost:
    """#2 contract — get_session_bifrost (GET /admin/sessions/{id}/bifrost, #176)."""

@@ -191,59 +92,3 @@ class TestGetSessionBifrost:
            with pytest.raises(AssertionError):
                await get_session_bifrost(client, "s1", admin_key="")
        assert route.call_count == 0
-
-
-class TestTransientCharacters:
-    """docs/contracts/issues/2.contract.md — transient-character wrappers (#161)."""
-
-    @respx.mock
-    async def test_list_models(self) -> None:
-        """list_models [happy,tracer]: 200 → {items:[...]} verbatim."""
-        respx.get("https://w.example/models/available-for-characters").mock(
-            return_value=httpx.Response(200, json={"items": [{"name": "fast", "thinking": False}]})
-        )
-        async with httpx.AsyncClient(base_url="https://w.example") as client:
-            models = await list_character_models(client)
-        assert models["items"][0]["name"] == "fast"
-
-    @respx.mock
-    async def test_create_body_and_response(self) -> None:
-        """create [happy]: body is {character, state}; 201 → {character_id, ttl_expires_at}."""
-        import json as _json
-
-        route = respx.post("https://w.example/characters").mock(
-            return_value=httpx.Response(201, json={"character_id": "char_x", "ttl_expires_at": "t"})
-        )
-        async with httpx.AsyncClient(base_url="https://w.example") as client:
-            out = await create_character(client, {"schema_version": "1", "name": "H"})
-        assert out["character_id"] == "char_x"
-        body = _json.loads(route.calls[0].request.content)
-        assert body == {"character": {"schema_version": "1", "name": "H"}, "state": None}
-
-    @respx.mock
-    async def test_get_state(self) -> None:
-        """get_state [happy]: 200 → live PAD/emotions snapshot."""
-        respx.get("https://w.example/characters/char_x/state").mock(
-            return_value=httpx.Response(200, json={"schema_version": "1", "pad": [0.4, 0.1, -0.2]})
-        )
-        async with httpx.AsyncClient(base_url="https://w.example") as client:
-            state = await get_character_state(client, "char_x")
-        assert state["pad"] == [0.4, 0.1, -0.2]
-
-    @respx.mock
-    async def test_delete_204(self) -> None:
-        """delete [happy]: 204 → None."""
-        respx.delete("https://w.example/characters/char_x").mock(return_value=httpx.Response(204))
-        async with httpx.AsyncClient(base_url="https://w.example") as client:
-            assert await delete_character(client, "char_x") is None
-
-    @respx.mock
-    async def test_create_403_scope(self) -> None:
-        """create_403 [error]: key lacks character.write → SessionApiFailed(403)."""
-        respx.post("https://w.example/characters").mock(
-            return_value=httpx.Response(403, json={"error_code": "auth_scope_denied"})
-        )
-        async with httpx.AsyncClient(base_url="https://w.example") as client:
-            with pytest.raises(SessionApiFailed) as exc:
-                await create_character(client, {"name": "H"})
-        assert exc.value.status == 403
@@ -235,3 +235,52 @@ class TestCli:
        err = capsys.readouterr().err
        assert rc == 10
        assert "[usage_error]" in err
+
+    @respx.mock
+    def test_cli_define_partial_response_degrades(
+        self,
+        capsys: pytest.CaptureFixture[str],
+        monkeypatch: pytest.MonkeyPatch,
+        _isolated_local_agents: "Path",
+    ) -> None:
+        """cli_define_partial [error]: a 201 missing `role` + a NULL system_prompt
+        degrades (role '?', description-safe) and exits 0 — never a KeyError/
+        AttributeError traceback (heid-bug-hunt open-world invariant)."""
+        from ratatoskr.local_agents import load_local_agents
+
+        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={
+                "agent_id": "ratatoskr:wizard", "agent_name": "wizard",
+                "system_prompt": None,  # present-but-null: .get(...,'') would NOT default
+            })
+        )
+        rc = main([
+            "define", "--name", "wizard", "--system-prompt", "x", "--role", "m",
+        ])
+        out = capsys.readouterr()
+        assert rc == 0
+        assert out.out.strip() == "defined ratatoskr:wizard (?)"
+        # Well-formed identity → still indexed (role degraded to '?').
+        entries = load_local_agents()
+        assert len(entries) == 1
+        assert entries[0].role == "?"
+
+    @respx.mock
+    def test_cli_define_no_agent_id_is_api_failure(
+        self, capsys: pytest.CaptureFixture[str], monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        """cli_define_no_agent_id [error]: a 2xx with no usable agent_id → [api_failed]
+        + exit 20 (controlled), not an uncaught traceback."""
+        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={"role": "m"})  # no agent_id
+        )
+        rc = main([
+            "define", "--name", "wizard", "--system-prompt", "x", "--role", "m",
+        ])
+        err = capsys.readouterr().err
+        assert rc == 20
+        assert "[api_failed]" in err
@@ -132,6 +132,57 @@ class TestAgentsEndpoint:
        # Upstream entry wins (it's first in the merge); local is deduped
        assert body[0]["name"] == "Sindra-from-server"

+    @respx.mock
+    def test_malformed_upstream_items_degrade_not_500(self, monkeypatch, tmp_path) -> None:
+        """malformed_upstream [error]: a non-mapping / agent_id-less upstream item is
+        dropped, not crashed on — the endpoint degrades to the well-formed + local
+        merge (heid-bug-hunt: open-world reads degrade, never crash)."""
+        monkeypatch.setenv("RATATOSKR_LOCAL_AGENTS", str(tmp_path / "local_agents.json"))
+        respx.get("https://w.example/agents").mock(
+            return_value=httpx.Response(
+                200,
+                json=[
+                    {"agent_id": "mimir", "name": "Mimir", "description": "k"},
+                    {},                       # no agent_id — dropped
+                    {"name": "Ghost"},        # no agent_id — dropped
+                    "not-a-mapping",          # non-mapping — dropped
+                    {"agent_id": 123},        # non-str agent_id — dropped
+                ],
+            )
+        )
+        from ratatoskr.local_agents import LocalAgentEntry, add_local_agent
+        add_local_agent(LocalAgentEntry(
+            agent_id="ratatoskr:local", agent_name="local", role="m",
+            description="d", defined_at="t",
+        ))
+        from ratatoskr.web.server import create_app
+        app = create_app(_mock_client_factory())
+        resp = TestClient(app).get("/api/agents")
+        assert resp.status_code == 200
+        ids = {a["agent_id"] for a in resp.json()}
+        # Only the one well-formed upstream item + the local entry survive.
+        assert ids == {"mimir", "ratatoskr:local"}
+
+    @respx.mock
+    def test_non_list_upstream_falls_back_to_local(self, monkeypatch, tmp_path) -> None:
+        """non_list_upstream [error]: an envelope (non-list) upstream body degrades to
+        the local-only list rather than iterating dict keys into a crash."""
+        monkeypatch.setenv("RATATOSKR_LOCAL_AGENTS", str(tmp_path / "local_agents.json"))
+        respx.get("https://w.example/agents").mock(
+            return_value=httpx.Response(200, json={"items": [{"agent_id": "mimir"}]})
+        )
+        from ratatoskr.local_agents import LocalAgentEntry, add_local_agent
+        add_local_agent(LocalAgentEntry(
+            agent_id="ratatoskr:local", agent_name="local", role="m",
+            description="d", defined_at="t",
+        ))
+        from ratatoskr.web.server import create_app
+        app = create_app(_mock_client_factory())
+        resp = TestClient(app).get("/api/agents")
+        assert resp.status_code == 200
+        ids = {a["agent_id"] for a in resp.json()}
+        assert ids == {"ratatoskr:local"}
+

 _CREATE_OK = {
    "session_id": "s-1",
@@ -53,13 +53,19 @@ from ratatoskr.wt import (
    SessionApiFailed,
    build_client,
    cancel_turn,
+    create_character,
    create_session,
    define_agent,
    delete_agent,
+    delete_character,
+    get_capabilities,
+    get_character_state,
+    get_me,
    get_persona_state,
    get_session_messages,
    get_session_tools,
    list_agents,
+    list_character_models,
    list_sessions,
    patch_agent,
    set_persona_state,
@@ -705,6 +711,16 @@ class TestDefineAgent:
            await define_agent(_wta(fake), agent_name="wizard", system_prompt="x", role="m")
        assert ei.value.field == "valence"

+    async def test_layer_deferred_non_string_field_is_none(self) -> None:
+        # A non-string `field` value collapses to None — the exception surface is
+        # `field: str | None` and the CLI prints it (heid-bug-hunt hardening).
+        fake = _FakeAgents(error=ApiError(
+            "layer_deferred", "no", status=422, body='{"detail": {"field": {"x": 1}}}',
+        ))
+        with pytest.raises(Tier3LayerDeferred) as ei:
+            await define_agent(_wta(fake), agent_name="wizard", system_prompt="x", role="m")
+        assert ei.value.field is None
+
    async def test_403_wrong_code_maps_to_default(self) -> None:
        # Dual-key negative: a 403 whose code is NOT tier3_user_id_unsupported →
        # generic default, not a spurious Tier3UserIdUnsupported (INV-CUT-2).
@@ -839,3 +855,214 @@ class TestDeleteAgent:
        with pytest.raises(SessionApiFailed) as ei:
            await delete_agent(_wta(fake), "ratatoskr:wizard")
        assert ei.value.status == 500
+
+
+# ── slice-5: characters + me/capabilities/models adapter routes ───────────────
+# One canned result / error per fake (each slice-5 adapter fn touches exactly one
+# sub-resource method), recorded by qualified name so the test can assert the route.
+
+
+class _FakeMe:
+    def __init__(self, rec: _FakeMisc) -> None:
+        self._rec = rec
+
+    async def get(self, *a: Any, **k: Any) -> Any:
+        return await self._rec._dispatch("me.get", *a, **k)
+
+
+class _FakeCapabilities:
+    def __init__(self, rec: _FakeMisc) -> None:
+        self._rec = rec
+
+    async def get(self, *a: Any, **k: Any) -> Any:
+        return await self._rec._dispatch("capabilities.get", *a, **k)
+
+
+class _FakeModels:
+    def __init__(self, rec: _FakeMisc) -> None:
+        self._rec = rec
+
+    async def available_for_characters(self, *a: Any, **k: Any) -> Any:
+        return await self._rec._dispatch("models.available_for_characters", *a, **k)
+
+
+class _FakeCharacters:
+    def __init__(self, rec: _FakeMisc) -> None:
+        self._rec = rec
+
+    async def create(self, *a: Any, **k: Any) -> Any:
+        return await self._rec._dispatch("characters.create", *a, **k)
+
+    async def state(self, *a: Any, **k: Any) -> Any:
+        return await self._rec._dispatch("characters.state", *a, **k)
+
+    async def delete(self, *a: Any, **k: Any) -> Any:
+        return await self._rec._dispatch("characters.delete", *a, **k)
+
+
+class _FakeMisc:
+    """Stand-in for the slice-5 client surface — exposes `.me` / `.capabilities` /
+    `.models` / `.characters`, recording each call under its qualified name and
+    returning a canned result or raising a canned error (same shape as `_FakeSessions`
+    / `_FakeAgents`)."""
+
+    def __init__(self, *, result: Any = None, error: BaseException | None = None) -> None:
+        self._result = result
+        self._error = error
+        self.calls: list[tuple[str, tuple[Any, ...], dict[str, Any]]] = []
+        self.me = _FakeMe(self)
+        self.capabilities = _FakeCapabilities(self)
+        self.models = _FakeModels(self)
+        self.characters = _FakeCharacters(self)
+
+    async def _dispatch(self, name: str, *args: Any, **kwargs: Any) -> Any:
+        self.calls.append((name, args, kwargs))
+        if self._error is not None:
+            raise self._error
+        return self._result
+
+
+def _wtm(misc: _FakeMisc) -> WorldtreeClient:
+    """Cast the slice-5 misc-surface fake (me/capabilities/models/characters) to the
+    nominal client type the route functions are typed against."""
+    return cast(WorldtreeClient, misc)
+
+
+class TestGetMe:
+    """slice-5: get_me → SDK me.get(); open-world dict verbatim."""
+
+    async def test_happy_returns_dict_verbatim(self) -> None:
+        me = {"user_id": "alice", "scopes": ["conversations.read"], "tier": "user"}
+        fake = _FakeMisc(result=me)
+        out = await get_me(_wtm(fake))
+        assert out is me
+        assert fake.calls[-1][0] == "me.get"
+
+    async def test_401_maps_to_session_api_failed(self) -> None:
+        fake = _FakeMisc(error=ApiError("auth_invalid", "no", status=401))
+        with pytest.raises(SessionApiFailed) as ei:
+            await get_me(_wtm(fake))
+        assert ei.value.status == 401
+
+
+class TestGetCapabilities:
+    """slice-5: get_capabilities → SDK capabilities.get(); open-world verbatim."""
+
+    async def test_happy_returns_dict_verbatim(self) -> None:
+        caps = {"ephemeral_templates": {"echo": {"default_role": "echo"}}}
+        fake = _FakeMisc(result=caps)
+        out = await get_capabilities(_wtm(fake))
+        assert out is caps
+        assert fake.calls[-1][0] == "capabilities.get"
+
+    async def test_error_maps_to_session_api_failed(self) -> None:
+        fake = _FakeMisc(error=ApiError("upstream", "boom", status=500))
+        with pytest.raises(SessionApiFailed) as ei:
+            await get_capabilities(_wtm(fake))
+        assert ei.value.status == 500
+
+
+class TestListCharacterModels:
+    """slice-5: list_character_models → SDK models.available_for_characters()."""
+
+    async def test_happy_returns_dict_verbatim(self) -> None:
+        models = {"items": [{"name": "fast", "thinking": False}]}
+        fake = _FakeMisc(result=models)
+        out = await list_character_models(_wtm(fake))
+        assert out is models
+        assert fake.calls[-1][0] == "models.available_for_characters"
+
+    async def test_error_maps_to_session_api_failed(self) -> None:
+        fake = _FakeMisc(error=ApiError("auth_scope_denied", "no", status=403))
+        with pytest.raises(SessionApiFailed) as ei:
+            await list_character_models(_wtm(fake))
+        assert ei.value.status == 403
+
+
+class TestCreateCharacter:
+    """slice-5: create_character → SDK characters.create(body); body-building + parity."""
+
+    async def test_happy_omits_state_when_none(self) -> None:
+        # SDK-idiomatic body: {character} only — no redundant explicit state:null.
+        created = {"character_id": "char_x", "ttl_expires_at": "t"}
+        fake = _FakeMisc(result=created)
+        out = await create_character(_wtm(fake), {"schema_version": "1", "name": "H"})
+        assert out is created
+        name, args, _ = fake.calls[-1]
+        assert name == "characters.create"
+        assert args[0] == {"character": {"schema_version": "1", "name": "H"}}
+
+    async def test_includes_state_when_supplied(self) -> None:
+        fake = _FakeMisc(result={"character_id": "c1"})
+        await create_character(
+            _wtm(fake), {"name": "H"}, state={"mood": "calm"}
+        )
+        assert fake.calls[-1][1][0] == {
+            "character": {"name": "H"},
+            "state": {"mood": "calm"},
+        }
+
+    async def test_empty_character_asserts_no_call(self) -> None:
+        fake = _FakeMisc(result={})
+        with pytest.raises(AssertionError):
+            await create_character(_wtm(fake), {})
+        assert fake.calls == []
+
+    async def test_403_maps_to_session_api_failed(self) -> None:
+        fake = _FakeMisc(error=ApiError("auth_scope_denied", "no", status=403))
+        with pytest.raises(SessionApiFailed) as ei:
+            await create_character(_wtm(fake), {"name": "H"})
+        assert ei.value.status == 403
+
+
+class TestGetCharacterState:
+    """slice-5: get_character_state → SDK characters.state(id); open-world verbatim."""
+
+    async def test_happy_returns_dict_verbatim(self) -> None:
+        state = {"schema_version": "1", "pad": [0.4, 0.1, -0.2]}
+        fake = _FakeMisc(result=state)
+        out = await get_character_state(_wtm(fake), "char_x")
+        assert out is state
+        assert fake.calls[-1] == ("characters.state", ("char_x",), {})
+
+    async def test_empty_id_asserts_no_call(self) -> None:
+        fake = _FakeMisc(result={})
+        with pytest.raises(AssertionError):
+            await get_character_state(_wtm(fake), "")
+        assert fake.calls == []
+
+    async def test_error_maps_to_session_api_failed(self) -> None:
+        fake = _FakeMisc(error=ApiError("not_found", "no", status=404))
+        with pytest.raises(SessionApiFailed) as ei:
+            await get_character_state(_wtm(fake), "char_x")
+        assert ei.value.status == 404
+
+
+class TestDeleteCharacter:
+    """slice-5: delete_character → SDK characters.delete(id); open ack verbatim."""
+
+    async def test_returns_ack_verbatim(self) -> None:
+        # Worldtree returns an open ack body here (not 204) — passed through, NOT
+        # normalized to None (parity posture).
+        ack = {"deleted": True, "character_id": "char_x"}
+        fake = _FakeMisc(result=ack)
+        out = await delete_character(_wtm(fake), "char_x")
+        assert out is ack
+        assert fake.calls[-1] == ("characters.delete", ("char_x",), {})
+
+    async def test_none_on_204(self) -> None:
+        # A 204 no-content yields None from the SDK — passed through unchanged.
+        fake = _FakeMisc(result=None)
+        assert await delete_character(_wtm(fake), "char_x") is None
+
+    async def test_empty_id_asserts_no_call(self) -> None:
+        fake = _FakeMisc(result=None)
+        with pytest.raises(AssertionError):
+            await delete_character(_wtm(fake), "")
+        assert fake.calls == []
+
+    async def test_error_maps_to_session_api_failed(self) -> None:
+        fake = _FakeMisc(error=ApiError("upstream", "oops", status=500))
+        with pytest.raises(SessionApiFailed) as ei:
+            await delete_character(_wtm(fake), "char_x")
+        assert ei.value.status == 500
@@ -472,7 +472,7 @@ wheels = [

 [[package]]
 name = "ratatoskr"
-version = "0.21.14"
+version = "0.21.18"
 source = { editable = "." }
 dependencies = [
    { name = "httpx" },
Author	SHA1	Message	Date
vh	4e20030229	fix(#20 ): heid-bug-hunt fixups — CLI open-world container-type hardening (slice-5) Panel (Gróa + Hulda + Regin, source-verified by Heid): adapter/route-map/ ConnectFailed-at-call-sites sound against the declared invariants; 4 real robustness findings, all in the CLI open-world presenter/probe paths — the container-type layer BELOW the null/element holes the code-review already fixed. Fixed (findings 1-3): - `_format_whoami` (`cli.py`): a non-iterable `scopes`/`allowed_roles` scalar (`{"scopes": 123}`) made `x or []` yield `123` → `for s in 123` TypeError. New `_display_seq` helper degrades any non-list (scalar / bare string / null / absent) to empty; applied to both `scopes` and `allowed_roles`. - `_characters_probe` (`cli.py`): same class on the model catalog `items` (`{"items": 123}`) — now guards `models` is a Mapping and `items` is a list before iterating. - `_characters_probe`: the top-level open-world reads `created` / `state` are now `isinstance(_, Mapping)`-guarded before any `.get` — a non-mapping SDK passthrough (`created=[...]`) aborts cleanly (exit 20) / renders `pad=None` instead of an AttributeError. Accepted (finding 4, documented in contract § slice-5 notes): the `--characters` probe leaks its transient character on a mid-lifecycle failure. PRE-EXISTING (the retired probe had the identical linear no-`finally` structure — cutover did not worsen it), TTL-bounded, one-shot diagnostic; a `try/finally` would swallow a happy-path delete-failure (delete is both teardown and a tested step). Gróa + Heid concur accept is defensible. Dismissed (finding 5): Hulda flagged `sessions.py` dropping `get_me`/etc. as a caller-contract break — it is the intended DEC-3 no-backwards-compat migration (all in-repo callers rewired same-diff); Heid labels it intended-surface-change. Added CLI tests for the three hardened paths (scalar scopes/roles; scalar items + non-mapping state; non-mapping create abort). Suite 488 green; ruff clean; live smoke re-run clean (identical happy-path output). Patch bump 0.21.17 → 0.21.18.	2026-07-19 11:29:10 -07:00
vh	d86d6df147	fix(#20 ): heid-code-review fixups — CLI presenter degrade-not-crash (slice-5) Panel: Gróa + Regin returned zero (adapter/route-map/error-map faithful); Hulda flagged two source-confirmed open-world-presenter crash holes — the same class the slice-4 bug-hunt found in the agents presenters. Both fixed: - `_format_whoami` scopes (`cli.py`): `', '.join(me.get('scopes', []))` crashes on a present-null `scopes` (`.get(k, [])` returns None, not the default) or a non-string element. Now `', '.join(str(s) for s in (me.get('scopes') or []))` — matching the `allowed_roles` hardening on the same function. The contract names `_format_whoami` as the degrade-not-crash exemplar (contract:144-146); the cited exemplar had an un-hardened line. - `_characters_probe` model items (`cli.py`): the slice-5 `or []` guarded the list-level null but not each entry — `[None]` / `["x"]` / `[{"name":123}]` would raise. Now guards each item is a dict and str-coerces `name` (element-level completion of the list-level guard). Hulda #3 (live-smoke not in the reviewed file set) → accept: the smoke WAS run and is recorded in `deab762` + coverage-map (artifact-only review couldn't see it). Added CLI tests for both hardened paths (present-null/non-string scopes; malformed model items). Suite 485 green; ruff clean; live smoke re-run clean (identical happy-path output). Patch bump 0.21.16 → 0.21.17.	2026-07-19 11:11:12 -07:00
vh	deab7627eb	feat(#20 ): characters + me/capabilities/models onto the wt adapter (slice-5) Slice-5 of the worldtree-sdk cutover: migrate the remaining consumer READS + transient-character CRUD off the hand-rolled httpx wrappers onto the `ratatoskr.wt` adapter over the SDK, and delete the retired path. Adapter (`wt.py`): add `get_me` / `get_capabilities` / `list_character_models` / `create_character` / `get_character_state` / `delete_character` over `client.me` / `client.capabilities` / `client.models` / `client.characters.*`. All six are open-world reads/acks returned verbatim; none carries a discriminated SDK error, so each maps any `ApiError` → the `SessionApiFailed` default (INV-CUT-2) — exact parity with the retired path. No new Error-map rows. Decisions (contract § slice-5 notes): `create_character` omits `state` when None (SDK-idiomatic inline literal, server-equivalent to the retired explicit null); `delete_character` returns the SDK's open ACK verbatim (`-> Mapping\|None`, not normalized to None). CLI rewire (`cli.py`): `--whoami` (me + capabilities) and `--characters` (models → create → state → delete) build a `wt.build_client` over the injected probe transport and catch `wt.SessionApiFailed` + `ConnectFailed`. Open-world degrade-not-crash carried (cumulative cutover foot-gun): `_characters_probe` reads `items` null-safe and extracts `character_id` defensively (clean abort, no hard-index KeyError); `_format_whoami` widened to `Mapping`. Deleted the six hand-rolled `sessions.py` wrappers (net -5 mypy no-any-return); `endpoint_for_plane` + `get_session_bifrost` (slice-6) + the exception classes stay. Retired the corresponding `test_sessions.py` classes; added the slice-5 adapter tests + a CLI malformed-create-abort test. LIVE SMOKE (:8081, b128) — INV-CUT-5 / DEC-4 cleared: `--whoami` rendered real identity + capabilities; `--characters` drove the full lifecycle end-to-end (char-rp catalog → created char_8c00006e… → PAD read-back → deleted). Suite 483 green; ruff clean; mypy at the 2 pre-existing baseline errors. Patch bump 0.21.15 → 0.21.16 (the cutover MINOR is deferred to slice-7, DEC-6).	2026-07-19 11:00:41 -07:00
vh	4f74645a00	memory: /snapshot — worldtree-sdk cutover slice-4 complete (c62b4ee→477d98f)	2026-07-19 10:24:35 -07:00
vh	477d98f52e	fix(#20 ): heid-bug-hunt fixups — open-world presenter degrade-not-crash (slice-4) Panel (Gróa+Hulda+Regin, 5/5/5, no false positives) confirmed two 3/3 crash sites where open-world dict reads violate the declared "degrade, never crash the presenter" invariant — the wt adapter tests + the live smoke used full server dicts, so partial/drifted wire responses were never exercised: - FIX (tier3.py _run_define/_run_patch): the CLI hard-indexed the open-world define/patch dicts (`info["agent_id"]` / `["role"]` / `["agent_name"]`), so a partial 2xx → KeyError escaping main()'s exit matrix as a raw traceback (exit 1); and `make_description(info.get("system_prompt", ""))` fed None to .splitlines() on a present-but-null field → AttributeError. Now reads via `_str_field` (absent/ null/non-str → default), degrades role to '?', indexes only a well-formed identity, and maps a no-usable-agent_id 2xx to [api_failed] exit 20 (controlled, not a crash). - FIX (web/server.py _agents_endpoint): the upstream dedup hard-indexed each item (`{a["agent_id"] for a in upstream}` + `_as_dict`), so a malformed item (`[{}]`, `["str"]`, `{"name":…}`, non-str agent_id) or a non-list envelope → 500 before the local fallback merged. Now filters to well-formed mappings first; a non-list upstream degrades to the local-only list. - FIX (wt.py _error_field_from_body): type-check the parsed `field` is a str (the exception surface is `field: str \| None`, the CLI prints it) — restores the retired hand-rolled `_extract_error_field` isinstance guard. Held (triaged, no change): the 429→Tier3QuotaExceeded / bare-404→Tier3AgentNotFound maps are ungated-by-error_code BY CONTRACT DESIGN (§ Error map route+status rows; the SDK's ApiError floor drops Retry-After, so retry_after=0 is canonical) — the arms flagged them spec-free; Heid's source-check confirmed intended. Dual-keying define's 429 for full row consistency is an available tightening (contract amendment), surfaced not applied. The persona-endpoint SessionApiFailed gap the arms also caught was already closed in the prior code-review fixup (`aed9429`). Suite 475 green (+5).	2026-07-19 10:18:36 -07:00