@arnilo/prism 0.1.3 → 0.1.5

package/docs/provider-conformance.md

@@ -17,7 +17,7 @@ Exported from `@arnilo/prism/testing/provider-conformance`:
 
 ## When to use it
 
-Use these helpers in provider package tests to check event order, terminal events, abort propagation via `ProviderRequest.signal`, streamed tool-call deltas, usage/cache accounting, request body content preservation, protected header ownership, and secret redaction. Do not treat deprecated `ProviderRequestOptions.timeoutMs`/`maxRetries`/`maxRetryDelayMs` as conformance requirements; first-party providers use runtime abort signals and `AgentConfig.retry`/`RunOptions.retry` instead.
+Use these helpers in provider package tests to check event order, terminal events, abort propagation via `ProviderRequest.signal`, streamed tool-call deltas, usage/cache accounting, request body content preservation, protected header ownership, and secret redaction. Provider-level timeout/retry hints were removed in 0.1.5; first-party providers use runtime abort signals and `AgentConfig.retry`/`RunOptions.retry` instead.
 
 Do not use them as a live integration runner, provider simulator, retry framework, credential loader, or test framework replacement.
 
@@ -65,7 +65,7 @@ Helpers accept normal `AIProvider`, `ProviderRequest`, `ProviderEvent`, `Usage`,
 
 - `collectProviderEvents()` returns provider events in stream order.
 - `assertProviderStreamConforms()` returns collected events after verifying the stream ends with `done` or `error`, terminal events are last, and optional text/usage expectations match.
-- `assertAbortIsObserved()` passes an already-aborted signal and expects provider generation to reject. This is the supported timeout primitive; use a host abort controller or `RunOptions.signal` rather than deprecated provider-level `timeoutMs`.
+- `assertAbortIsObserved()` passes an already-aborted signal and expects provider generation to reject. This is the supported timeout primitive; use a host abort controller or `RunOptions.signal`.
 - `assertToolCallDeltasReconstruct()` rebuilds streamed `tool_call_delta` fragments into tool calls and validates expected id/name/arguments. Malformed JSON with id+name present yields `argumentsError` (no throw); missing id/name throws typed `incomplete_delta`. The runtime uses the same reconstruction before tool execution when a provider streams deltas.
 - `assertUsageAccounting()` finds `usage` or `done.usage` and checks selected token fields including `cacheReadTokens` and `cacheWriteTokens`. This is the provider-neutral check for normalized cache read/write token extraction; every first-party provider package exercises it against server-specific fields (`cached_tokens`, `cache_read_input_tokens`, etc.).
 - `assertSerializedRequestCoversContent()` scans a serialized provider request body for primitive canaries from each Prism content block and fails if any supported block type is silently dropped. Provider-valid transcripts place assistant `tool_call` messages before matching role `tool` `tool_result` messages; runtime, cache-aware input layout, and observational-memory worker loops preserve that order before serialization.

package/docs/provider-layer.md

@@ -129,7 +129,7 @@ const agent = createAgent({ model: { provider: own.id, model: "demo" }, provider
 - Provider event helpers return plain `ProviderEvent` objects.
 - `providerError()` converts unknown errors to redacted `ErrorInfo` through `errorToErrorInfo()` and preserves safe string/number `code` fields for retry classification.
 - `createMockProvider()` returns an `AIProvider` whose `generate()` yields the scripted events in order and checks `request.signal?.aborted` before each event.
-- The agent/session runtime passes its per-run abort signal as `ProviderRequest.signal`. `ProviderRequestOptions.structuredOutput` requests provider-native JSON-schema output when the model declares `capabilities.structuredOutput`; unsupported models fail before fetch. `ProviderRequestOptions.timeoutMs`, `maxRetries`, and `maxRetryDelayMs` are deprecated inert hints in first-party providers; use `RunOptions.signal`/host abort controllers for timeouts and `AgentConfig.retry`/`RunOptions.retry` for retry.
+- The agent/session runtime passes its per-run abort signal as `ProviderRequest.signal`. `ProviderRequestOptions.structuredOutput` requests provider-native JSON-schema output when the model declares `capabilities.structuredOutput`; unsupported models fail before fetch. Timeouts are host-owned: pass `RunOptions.signal`/host abort controllers; retries are runtime-owned via `AgentConfig.retry`/`RunOptions.retry`. Provider-level timeout/retry hints were removed in 0.1.5.
 
 ## Request/response example
 

package/docs/provider-packages.md

@@ -68,7 +68,7 @@ api.registerSystemPromptContribution({ id: "demo-prompt", source: "package", mod
 
 Hosts decide which credential resolvers, env objects, OAuth stores, request policies, and prompt contributions become active. Request policies can set generic `ProviderRequest.options` such as `sessionId`, `cacheRetention`, `headers`, `compat`, and opaque `extra`; provider adapters decide how to map those options to provider payloads. Caller headers are extension headers only: provider adapters must apply provider-owned headers (auth, content type, session/cache/security, attribution) after caller headers so requests cannot override credentials or provider policy.
 
-Deprecated provider request options: `timeoutMs`, `maxRetries`, and `maxRetryDelayMs` are inert in first-party providers. Use `RunOptions.signal`/host abort controllers for timeouts and `AgentConfig.retry`/`RunOptions.retry` for retry. Provider packages should not add provider-specific retry loops unless the vendor protocol requires it and runtime retry cannot cover the failure mode.
+Provider request options: `ProviderRequestOptions` carries session/cache/header/compat/extra hints only. Timeouts are host-owned (`RunOptions.signal`/host abort controllers); retries are runtime-owned (`AgentConfig.retry`/`RunOptions.retry`). Provider-level timeout/retry hints were removed in 0.1.5. Provider packages should not add provider-specific retry loops unless the vendor protocol requires it and runtime retry cannot cover the failure mode.
 
 First-party providers map generic `ModelConfig.parameters.maxTokens` to real output-token request fields instead of sending `maxTokens` on the wire: OpenAI Responses uses `max_output_tokens`; OpenRouter, OpenCode Go OpenAI-compatible, OpenCode Go Anthropic-style, Z.AI, Kimi, and NeuralWatt use `max_tokens`. Other `model.parameters` values pass through unchanged unless the provider docs say otherwise.
 

package/docs/provider-primitives.md

@@ -33,7 +33,7 @@ Static scan of root `src/providers/` and `packages/provider-*/src/` before Plan
 | Surface | Owner | Behavior today |
 | --- | --- | --- |
 | Runtime retry | `@arnilo/prism` `AgentConfig.retry` / `RunOptions.retry` | Classifies `ErrorInfo.code`; provider packages set numeric HTTP `code` on errors |
-| `ProviderRequestOptions.maxRetries` / `timeoutMs` | Contracts | **Deprecated / inert** in first-party providers |
+| `ProviderRequestOptions.maxRetries` / `timeoutMs` | Contracts | **Removed in 0.1.5**; use `RunOptions.signal` / `AgentConfig.retry` / `RunOptions.retry` |
 | NeuralWatt `classifyNeuralWattError` | `packages/provider-neuralwatt` | Parses `Retry-After`, `error.retry_after`, `retry_strategy`; no extra network calls |
 | Quota endpoint throttling | `packages/provider-neuralwatt/quota.ts` | Documents 1 rps limit; caller-owned cache |
 

package/docs/public-contracts.md

@@ -117,7 +117,7 @@ Important request shapes:
 | `PromptCacheHints` / `PromptCacheBreakpoint` | Structured provider cache intent and reusable prompt anchors. See [Provider caching](provider-caching.md). |
 | `ProviderPackage` | Inert provider package definition with docs metadata and explicit `setup(api)` registration. |
 | `ProviderRequest` | Normalized provider input: `model`, `messages`, optional `tools`, `context`, generic `options`, `metadata`, and `signal`. |
-| `ProviderRequestOptions` | Generic provider adapter hints: session id, legacy `cacheKey`/`cacheRetention`, structured `cache?: PromptCacheHints`, headers, compat, and opaque `extra`; `timeoutMs`, `maxRetries`, and `maxRetryDelayMs` are deprecated inert hints in first-party providers. |
+| `ProviderRequestOptions` | Generic provider adapter hints: session id, legacy `cacheKey`/`cacheRetention`, structured `cache?: PromptCacheHints`, headers, compat, and opaque `extra`. Provider-level timeout/retry hints were removed in 0.1.5; timeouts are host-owned (`RunOptions.signal`) and retries are runtime-owned (`AgentConfig.retry`/`RunOptions.retry`). |
 | `ProviderRequestPolicy` | Ordered pre-provider hook that can patch the request and return exact secrets for provider-error redaction. |
 | `ToolRegistry` | Host active tool registry shape: `register()`, `get()`, `resolve()`, and `list()`. |
 | `ToolExecutionContext` | Host tool execution context: session/run ids, tool call id, optional abort signal, metadata, and progress callback. |
@@ -131,7 +131,7 @@ Important request shapes:
 | `CredentialRequest` | Credential lookup request: credential `name`, optional provider id, and metadata. |
 | `OAuthProvider` | Host/package OAuth callbacks for login, optional refresh, and conversion to a `Credential`. |
 | `AgentSessionConfig` | Session creation input: optional id, agent, store, leaf id, and metadata. |
-| `RunOptions` | Per-run overrides: optional abort signal, model, input layout, max tool rounds, provider options/request policies, system prompt layers, compaction, retry, metadata, skill selection, validate, redactor, and loop. |
+| `RunOptions` | Per-run overrides: optional abort signal, model, input layout, run limits (incl. `limits.maxToolRounds`), provider options/request policies, system prompt layers, compaction, retry, metadata, skill selection, validate, redactor, and loop. |
 | `SubscribeOptions` / `SubscriberOverflowPolicy` | Live `AgentEvent` subscriber queue limit and overflow policy: `maxQueuedEvents`, `overflow: "close" \| "drop_oldest" \| "drop_newest"`. |
 | `resumeAgentRunStream` / `AgentRunResumeStreamOptions` | One durable-run event stream: existing checkpoint/resume options plus `signal` and bounded subscriber options. `AgentRunLifecycle.resumeStream()` adds host capability resolution; no protocol types enter core. |
 | `AgentConfig.loop` / `RunOptions.loop` | Replaceable per-run control loop: `singleShotLoop` default, `generate-validate-revise` options, or a custom `AgentLoopStrategy`. `RunOptions.loop` wins. See [Agent loops](agent-loops.md). |
@@ -417,6 +417,8 @@ void credentials;
 
 ## Extension and configuration notes
 
+**Internal file structure (0.1.4).** Since 0.1.4 the contract declarations are spread across sibling modules behind the `src/contracts.ts` barrel: `src/contracts-core.ts` (JSON/content/core agent contracts plus the `SESSION_ENTRY_KINDS`/`session-store` values), `src/contracts-run-state.ts` (run-state and agent-session contracts including `AgentRunStatus` through `AgentSession`, decision/steer constants, and the error classes), and `src/contracts-protocol.ts` (pure protocol-payload types). The 295-name public surface is unchanged; this page groups the frozen contract by functionality rather than source file.
+
 - Contracts are host-owned and package-friendly. External packages can implement `AIProvider`, `ToolDefinition`, `CommandDefinition`, `AgentDefinition`, `InputBuilder`, `PromptBuilder`, `Middleware`, `ContextProvider`, `Skill`, `Extension`, config providers, data-only manifests, compaction strategies, store factories, resource loaders, settings providers, and credential resolvers.
 - `ExtensionAPI` is implemented by the extension kernel. It exposes explicit registries, ordered middleware registration, ordered event subscription/emission, and registration methods for Phase 2 contribution categories.
 - `AgentConfig.provider` can hold a direct provider instance for simple host wiring. Hosts that need config-driven selection should use `ModelConfig.provider` with explicit `createProviderRegistry()` / `createModelRegistry()` objects; Prism does not create a hidden global provider registry.

package/docs/release-and-install.md

@@ -274,6 +274,70 @@ git push origin v0.1.2        # tag push triggers release.yml publish job (prove
 
 **Rollback notes.** `release:publish --version 0.1.2 --resume --report release-artifacts/publish-report.json` resumes an interrupted publication and skips only registry versions whose internal dependency fingerprint matches the local manifest. A failed package aborts the run with its status written to the report; re-run after fixing the cause. npm cannot unpublish the `0.1.2` line after 72 hours — a post-publication defect ships as a `0.1.x` patch (additive-only compat promise, `release:gate` enforced), or as a documented break in the next line with a `docs/migration.md` entry. `0.1.2` is store-compatible with `0.1.1` in **both directions** (no migration ran — same checksum-protected contract), so an operator may defer or roll back the patch without a database rollback.
 
+### 0.1.5 publish handoff (plan 017 Task 4)
+
+**Decision: GO when the operator prerequisites below are recorded.** Release **0.1.5** (plan 017) is the **documented breaking cut** on the frozen 0.1.x line — deprecated-option removal, with the removed-symbols list, replacements, before/after examples, dynamic-config refusal behavior, store compatibility, and rollback in the top `docs/migration.md` `0.1.4 → 0.1.5` section. Removed: `ProviderRequestOptions.timeoutMs`/`maxRetries`/`maxRetryDelayMs` (inert in first-party providers; abort/retry lives at the host layer — replacements `RunOptions.signal`/`AgentConfig.retry`/`RunOptions.retry`), `RunOptions.maxToolRounds` (→ `limits.maxToolRounds`; CLI `--max-tool-rounds` unchanged), `ObservationalMemorySettingsInput` pre-0.0.19 flat keys and top-level `workerProvider`/`workerModel` aliases (→ nested `observation`/`reflection`/`dropper` configs; `sessionModel` fallback unchanged), `ReadToolOptions.autoResizeImages` (→ `transformImage`), and `INIT_PROVIDERS` (→ `listInitProviders()`). Every removal **fails closed** for untyped callers with a `TypeError` naming the replacement before any provider call, tool call, filesystem access, compaction, or session append. Compat baselines were regenerated only after the reviewed `--allow-break` break report: `arnilo__prism.txt` (removed `INIT_PROVIDERS` const + `maxToolRounds`/provider-knob member lines — interface members are not baseline text, so the delta is the `INIT_PROVIDERS` line), `arnilo__prism-coding-agent.txt` (`autoResizeImages` is an interface member — baseline delta limited to statement/re-export text if any), `arnilo__prism-compaction-observational-memory.txt` (flat keys and worker aliases are interface members — no baseline line delta expected). Publishable graph stays **49** manifests (root + 48 workspace) at exact **0.1.5**. Store compatibility with 0.1.4: **compatible, no migration** (removed options were inert aliases; nested replacements resolve to the same active values; `DEFAULT_RUN_LIMITS.maxToolRounds` 8 / hard cap 64 unchanged); zero new dependencies (lockfile name-set unchanged).
+
+```bash
+# Operator prerequisites (each a named blocked gate — none may be skipped):
+#  1. protected live-canary matrix green (live-canaries.yml, canary-report.json retained)
+#  2. PostgreSQL + keychain protected suites green (test:postgres, keychain suite)
+#  3. CodeQL SAST green on the release commit (security.yml / release.yml codeql-release)
+#  4. npm OIDC trusted publishing identity authenticated (NPM_TOKEN with id-token, provenance)
+
+git diff --check
+npm ci
+npm run sdk:ready            # includes typecheck, lint, format, full test, coverage, pack, release:gate
+npm run security:threat-suites
+PRISM_TEST_POSTGRES_URL="$DATABASE_URL" npm run test:postgres   # Phase 7 + Phase 12 restart-recovery
+npm audit --audit-level=moderate
+npm run release:check -- --version 0.1.5 --report /tmp/prism-0.1.5-preflight.json
+npm run release:publish -- --version 0.1.5 --dry-run --allow-dirty --allow-untagged --report /tmp/prism-0.1.5-dry-run.json
+#   run the dry-run twice and diff the reports: deterministic, byte-identical
+
+# Sign the release on the clean tagged tree (operator GPG key):
+git tag -s v0.1.5 -m "Prism 0.1.5 — documented breaking cut: deprecated-option removal"
+git verify-tag v0.1.5
+git push origin v0.1.5        # tag push triggers release.yml publish job (provenance, attestations)
+
+# Real publication never bypasses the gates: release.mjs refuses
+# --allow-dirty/--allow-untagged without --dry-run.
+```
+
+**Rollback notes.** `release:publish --version 0.1.5 --resume --report release-artifacts/publish-report.json` resumes an interrupted publication and skips only registry versions whose internal dependency fingerprint matches the local manifest. A failed package aborts the run with its status written to the report; re-run after fixing the cause. npm cannot unpublish the `0.1.5` line after 72 hours — a post-publication defect ships as a `0.1.x` patch (additive-only compat promise, `release:gate` enforced), or as a documented break in the next line with a `docs/migration.md` entry. `0.1.5` is store-compatible with `0.1.4` in **both directions** (no migration ran — same checksum-protected contract), so an operator may defer or roll back the cut without a database rollback; code/config using removed keys must be migrated first (removed keys fail closed on 0.1.5).
+
+### 0.1.4 publish handoff (plan 016 Task 6)
+
+**Decision: GO when the operator prerequisites below are recorded.** Release **0.1.4** (plan 016) is the internal god-module split, compat-preserving on the frozen 0.1.x line: `src/agents.ts` and `src/contracts.ts` reorganized by concern behind barrel re-exports (`contracts-core`/`contracts-run-state`/`contracts-protocol`; `agent-session`/`agent-run-lifecycle`/`agent-approval`/`agent-tool-dispatch` reusing `agent-run-state`/`agent-loops`/`compaction`) with a **byte-identical public entry surface** (0 added/0 removed/0 changed vs the 0.1.3 baseline; the 14 additive union-surface helpers are internal cross-module exports, not consumer-importable — deviation #1), measured tree-shaking improvement (111,049 → 982 B `dist/agents.js`, 9,420 → 418 B `dist/contracts.js`, module count 64 → 70; evidence in `scripts/phase16-baseline.json`), and additive **`@arnilo/prism-browser` Chrome DevTools Protocol capabilities** (Tasks 4-5): `browser_evaluate`, `browser_observe`, `block_urls`/`unblock_urls`/`throttle`/`emulate` act actions, and `{ css }`/`{ xpath }` targets on Chromium hosts — 41 added / 0 removed / 18 changed declaration texts (15 re-export-statement artifacts + 3 optional-member/signature widenings), the documented deviation #2 carve-out; root `arnilo__prism.txt` regenerated with zero breaking deltas. Publishable graph stays **49** manifests (root + 48 workspace) at exact **0.1.4**. Store compatibility with 0.1.3: **compatible, no migration**; zero new dependencies (lockfile name-set unchanged).
+
+```bash
+# Operator prerequisites (each a named blocked gate — none may be skipped):
+#  1. protected live-canary matrix green (live-canaries.yml, canary-report.json retained)
+#  2. PostgreSQL + keychain protected suites green (test:postgres, keychain suite)
+#  3. CodeQL SAST green on the release commit (security.yml / release.yml codeql-release)
+#  4. npm OIDC trusted publishing identity authenticated (NPM_TOKEN with id-token, provenance)
+
+git diff --check
+npm ci
+npm run sdk:ready            # includes typecheck, lint, format, full test, coverage, pack, release:gate
+npm run security:threat-suites
+PRISM_TEST_POSTGRES_URL="$DATABASE_URL" npm run test:postgres   # Phase 7 + Phase 12 restart-recovery
+npm audit --audit-level=moderate
+npm run release:check -- --version 0.1.4 --report /tmp/prism-0.1.4-preflight.json
+npm run release:publish -- --version 0.1.4 --dry-run --allow-dirty --allow-untagged --report /tmp/prism-0.1.4-dry-run.json
+#   run the dry-run twice and diff the reports: deterministic, byte-identical
+
+# Sign the release on the clean tagged tree (operator GPG key):
+git tag -s v0.1.4 -m "Prism 0.1.4"
+git verify-tag v0.1.4
+git push origin v0.1.4        # tag push triggers release.yml publish job (provenance, attestations)
+
+# Real publication never bypasses the gates: release.mjs refuses
+# --allow-dirty/--allow-untagged without --dry-run.
+```
+
+**Rollback notes.** `release:publish --version 0.1.4 --resume --report release-artifacts/publish-report.json` resumes an interrupted publication and skips only registry versions whose internal dependency fingerprint matches the local manifest. A failed package aborts the run with its status written to the report; re-run after fixing the cause. npm cannot unpublish the `0.1.4` line after 72 hours — a post-publication defect ships as a `0.1.x` patch (additive-only compat promise, `release:gate` enforced), or as a documented break in the next line with a `docs/migration.md` entry. `0.1.4` is store-compatible with `0.1.3` in **both directions** (no migration ran — same checksum-protected contract), so an operator may defer or roll back the patch without a database rollback. The next line, **0.1.5**, is the documented breaking cut (deprecated-option removal) with its removed-symbols list landing in `docs/migration.md`.
+
 ### 0.1.3 publish handoff (plan 015 Task 5)
 
 **Decision: GO when the operator prerequisites below are recorded.** Release **0.1.3** (plan 015) is the dead-code and deprecation hygiene patch on the frozen 0.1.x line: one parameterized benchmark runner `scripts/benchmark.mjs --scenario <name>` replaces the per-version runners (16 orphaned `benchmark-0.0.{8..16}` runner/test files removed, evidence JSON kept; the CI schema leg runs `scripts/benchmark.test.mjs`), the 12 `docs/review-coverage-2026-07-*.md` evidence files moved to the tarball-excluded `docs/_evidence/` archive, a non-blocking unused-code sweep (`npm run sweep:unused` — tsc `noUnusedLocals`/`noUnusedParameters` over core + all workspace tsconfigs plus a zero-dep dead-export scan; always exits 0, report to `scripts/unused-sweep-report.txt`), and opt-in checkpoint persistence (`persistSessionState: true` on durable run/resume options — loaded-skill name catalog ≤64 names rides the run-state checkpoint and restores on resume, bodies re-resolve from the live registry; `createReadPathSetPersistence` in `@arnilo/prism-coding-agent` persists the read-before-write path set through the host `CheckpointStore`, ≤1024 paths, ownership-scoped). Publishable graph stays **49** manifests (root + 48 workspace) at exact **0.1.3**. Store compatibility with 0.1.2: **compatible, no migration**; declaration surface additive-only vs the frozen 0.1.x contract (`scripts/compat-baseline` regenerated at 0.1.3 with zero breaking deltas).

package/docs/tool-execution-primitives.md

@@ -91,7 +91,7 @@ Blocked reasons today: `unknown_tool`, `tool_denied`, `invalid_arguments`, `perm
 | Surface | Location | Behavior today |
 | --- | --- | --- |
 | `singleShotLoop` | `src/agent-loops.ts` | Sequential `for (const call of calls) await dispatchToolCall(call)` per provider turn |
-| `maxToolRounds` | `AgentConfig` / `RunOptions` → `LoopContext` | Default `1` in `RuntimeAgentSession.run()` |
+| `maxToolRounds` | `AgentConfig.limits` / `RunOptions.limits` → `LoopContext` | Default `1` in `RuntimeAgentSession.run()` |
 | Transcript ordering | `src/agent-loops.ts` | Tool results appended in call order (Plan 053 R-002 fix shipped) |
 | Parallelism | — | **None** — models may emit multiple calls; runtime executes one at a time |
 
@@ -290,11 +290,11 @@ export type TransformImage = (input: TransformImageInput) => Promise<Buffer>;
 export interface ReadToolOptions {
   readonly maxImageBytes?: number; // default DEFAULT_MAX_IMAGE_BYTES
   readonly transformImage?: TransformImage;
-  /** @deprecated Use transformImage instead; ignored when transformImage is absent. */
-  readonly autoResizeImages?: boolean;
 }
 ```
 
+`autoResizeImages` was removed in 0.1.5; the supported `transformImage` callback is the only resize path. Untyped callers passing the old key fail closed before any filesystem access.
+
 Reject oversize images by `stat` before full read where possible; re-check `buffer.length` after read and after `transformImage`. MIME from magic bytes only (existing behavior). `transformImage` is host-owned; base package stays free of image-processing deps. Implemented in `packages/coding-agent/src/read.ts`.
 
 ## Conformance and threat-model matrix

package/docs/tools.md

@@ -161,7 +161,7 @@ Need different tools for one request? Build a short-lived agent/session with a n
 
 ### Artifact-loop tools
 
-`generate-validate-revise` treats provider tools as inert by default. Set `loop.toolCalls: "bounded"` and `RunOptions.maxToolRounds` only when an artifact needs a host-owned lookup before its next candidate. Each response with one-or-more calls consumes one shared round, dispatches calls sequentially through this exact `dispatchToolCall()` path, persists assistant-call then result transcript rows, and skips artifact parsing/validation for that response. A post-limit call executes nothing; the loop emits `artifact_failed` with `metadata.reason: "tool_round_limit"`. Tools do not consume `maxRevisions`, and tool schemas/context never grant authority.
+`generate-validate-revise` treats provider tools as inert by default. Set `loop.toolCalls: "bounded"` and `RunOptions.limits.maxToolRounds` only when an artifact needs a host-owned lookup before its next candidate. Each response with one-or-more calls consumes one shared round, dispatches calls sequentially through this exact `dispatchToolCall()` path, persists assistant-call then result transcript rows, and skips artifact parsing/validation for that response. A post-limit call executes nothing; the loop emits `artifact_failed` with `metadata.reason: "tool_round_limit"`. Tools do not consume `maxRevisions`, and tool schemas/context never grant authority.
 
 ### Runtime-supplied validators
 
@@ -220,7 +220,7 @@ Opt in through `loop.toolConcurrency` on `AgentConfig` / `RunOptions` (single-sh
 
 ```ts
 await session.run(input, {
-  maxToolRounds: 3,
+  limits: { maxToolRounds: 3 },
   loop: { strategy: "single-shot", toolConcurrency: 4 },
 });
 ```

package/docs/use-case-model-selection.md

@@ -24,11 +24,11 @@ Prism separates the **session chat model** (`AgentConfig.model` / `RunOptions.mo
 ```ts
 import { resolveUseCaseModel, applyThinkingLevel, thinkingFamilyForModel } from "@arnilo/prism";
 
-// Prefer an explicit worker; otherwise inherit the session/agent model.
+// Prefer an explicit worker model; otherwise inherit the session/agent model.
 const resolved = resolveUseCaseModel({
-  configured: settings.workerModel,       // optional use-case ModelConfig
-  sessionModel: agent.config.model,       // host-supplied; AgentSession does not expose agent
-  thinkingLevel: settings.thinkingLevel,
+  configured: settings.observation?.model,  // optional per-worker ModelConfig
+  sessionModel: agent.config.model,         // host-supplied; AgentSession does not expose agent
+  thinkingLevel: settings.observation?.thinkingLevel,
 });
 if (!resolved) {
   // skip — neither configured nor session model (or requireExplicitModel)
@@ -52,7 +52,7 @@ Resolution is O(1) and network-free. It does not mutate session history.
 
 | Site | How hosts bind | Session fallback |
 | --- | --- | --- |
-| Observational memory | `workerModel` / settings `workerModel` + runtime `sessionModel` | Yes — pass `sessionModel: agent.config.model`; `requireExplicitModel` restores skip |
+| Observational memory | `observation.model` / `reflection.model` / `dropper.model` + runtime `sessionModel` | Yes — pass `sessionModel: agent.config.model`; `requireExplicitModel` restores skip |
 | LLM compaction | `summaryModel` with `model` as fallback slot | Yes — `resolveUseCaseModel({ configured: summaryModel, sessionModel: model })` |
 | `RunOptions.model` | Per-run override on the **session** | N/A — this *is* the session/run model (writes `model_change`) |
 | Declarative `AgentDefinition` | Definition `model` / registry resolve | Definition-scoped (independent agent) |
@@ -67,17 +67,18 @@ Resolution is O(1) and network-free. It does not mutate session history.
 createObservationalMemoryRuntime({
   session,
   appendEntry: (entry) => store.append(entry),
-  workerProvider,
-  sessionModel: agent.config.model, // enables fallback when workerModel unset
-  // workerModel: { provider: "neuralwatt", model: "glm-5.2-fast" }, // optional override
-  overrides: { thinkingLevel: "low", observeAfterTokens: 1 },
+  observation: { provider: workerProvider }, // optional per-worker model override below
+  sessionModel: agent.config.model, // enables fallback when no worker model is configured
+  // observation: { provider: workerProvider, model: { provider: "neuralwatt", model: "glm-5.2-fast" } },
+  overrides: { observation: { thinkingLevel: "low", messageTokens: 1 } },
 });
 ```
 
-- Default: no `workerModel` + `sessionModel` set → workers use the session model.
-- Explicit `workerModel` (or settings `workerModel`) always wins.
+- Default: no worker `model` + `sessionModel` set → workers use the session model.
+- Explicit per-worker `model` (or settings `observation.model` / `reflection.model` / `dropper.model`) always wins.
 - `requireExplicitModel: true` (runtime or settings) → `skipped: "missing_model"` when no worker model, even if `sessionModel` is set.
 - Neither worker nor session model → `skipped: "missing_model"`.
+- Top-level `workerProvider` / `workerModel` aliases were removed in 0.1.5; workers resolve only from the nested `observation` / `reflection` / `dropper` configs.
 - Default credential request uses the **resolved** model's `provider` id.
 
 ## LLM compaction

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@arnilo/prism",
-  "version": "0.1.3",
+  "version": "0.1.5",
   "description": "Agent harness for AI providers, agents, sessions, and tools.",
   "type": "module",
   "main": "./dist/index.js",
@@ -142,7 +142,7 @@
     "build": "npm run build:core && npm run build --workspaces --if-present",
     "typecheck": "npm run build && npm run typecheck --workspaces --if-present && tsc -p examples --noEmit",
     "sweep:unused": "node scripts/sweep-unused.mjs",
-    "test": "npm run build && node --test dist/__tests__/*.test.js && node --test scripts/release-gate.test.mjs scripts/tooling-gate.test.mjs scripts/budget-gate.test.mjs scripts/phase8-conformance.test.mjs scripts/phase9-conformance.test.mjs scripts/phase10-conformance.test.mjs scripts/phase11-conformance.test.mjs scripts/phase11-freeze.test.mjs scripts/phase12-freeze.test.mjs scripts/phase13-freeze.test.mjs scripts/phase14-freeze.test.mjs scripts/phase15-freeze.test.mjs scripts/benchmark-0.1.0.test.mjs scripts/sweep-unused.test.mjs scripts/e2e-enterprise-journey.test.mjs scripts/e2e-coding-journey.test.mjs && npm run test --workspaces --if-present",
+    "test": "npm run build && node --test dist/__tests__/*.test.js && node --test scripts/release-gate.test.mjs scripts/tooling-gate.test.mjs scripts/budget-gate.test.mjs scripts/phase8-conformance.test.mjs scripts/phase9-conformance.test.mjs scripts/phase10-conformance.test.mjs scripts/phase11-conformance.test.mjs scripts/phase11-freeze.test.mjs scripts/phase12-freeze.test.mjs scripts/phase13-freeze.test.mjs scripts/phase14-freeze.test.mjs scripts/phase15-freeze.test.mjs scripts/phase16-freeze.test.mjs scripts/phase17-freeze.test.mjs scripts/benchmark-0.1.0.test.mjs scripts/sweep-unused.test.mjs scripts/e2e-enterprise-journey.test.mjs scripts/e2e-coding-journey.test.mjs && npm run test --workspaces --if-present",
     "test:coverage": "node --test --experimental-test-coverage --test-coverage-lines=60 --test-coverage-functions=70 --test-coverage-branches=75 --test-coverage-exclude='**/__tests__/**' --test-coverage-exclude='**/node_modules/**' --test-coverage-exclude='**/scripts/**' --test-coverage-exclude='**/packages/**' --test-coverage-exclude='**/examples/**' dist/__tests__/*.test.js && node scripts/coverage-summary.mjs",
     "coverage:summary": "node scripts/coverage-summary.mjs",
     "lint": "biome lint .",