@arnilo/prism 0.1.4 → 0.1.6

package/docs/release-and-install.md

@@ -2,11 +2,11 @@
 
 ## What it does
 
-Prism is published as **49 publishable manifests**: the root `@arnilo/prism` core package plus **48 workspace packages** — 14 provider adapters, 9 `prism-*` family/profile packages, and 25 capability packages. (Regenerate the counts: `ls packages/*/package.json | wc -l` = 48 workspace; `ls -d packages/provider-*/ | wc -l` = 14; `ls -d packages/prism-*/ | wc -l` = 9; capability = 48 − 14 − 9 = 25; publishable = root + 48 = 49.) This page describes how they are packed, what each tarball contains, how to install them, the required `@arnilo/prism` peer dependency, the release workflow, and the offline test budget. The measurable 1.0 readiness gates (command-per-gate) live in [`0.1.0-readiness.md`](./0.1.0-readiness.md).
+Prism is published as **50 publishable manifests**: the root `@arnilo/prism` core package plus **49 workspace packages** — 14 provider adapters, 9 `prism-*` family/profile packages, and 26 capability packages. (Regenerate the counts: `ls packages/*/package.json | wc -l` = 49 workspace; `ls -d packages/provider-*/ | wc -l` = 14; `ls -d packages/prism-*/ | wc -l` = 9; capability = 49 − 14 − 9 = 26; publishable = root + 49 = 50.) The 50th manifest is the 0.1.6 plan 018 optional `@arnilo/prism-document-reader` package (bounded PDF/Office literal-text extraction for the coding read tool; ships only because its `doc-reader` closeout is demanded — a deferred closeout keeps the graph at 49). This page describes how they are packed, what each tarball contains, how to install them, the required `@arnilo/prism` peer dependency, the release workflow, and the offline test budget. The measurable 1.0 readiness gates (command-per-gate) live in [`0.1.0-readiness.md`](./0.1.0-readiness.md).
 
 Core `@arnilo/prism` ships runtime, CLI, templates, and docs. Every code package has a required `@arnilo/prism@0.1.0` peer; profiles are pure manifests. Installation activates no provider, listener, database, browser, credential, or tool capability.
 
-Current **49** publishable manifests (root + 48 workspace packages):
+Current **50** publishable manifests (root + 49 workspace packages):
 
 `@arnilo/prism`, `@arnilo/prism-ag-ui`, `@arnilo/prism-browser`, `@arnilo/prism-coding-agent`, `@arnilo/prism-coding-security`, `@arnilo/prism-compaction-llm`
 `@arnilo/prism-compaction-observational-memory`, `@arnilo/prism-credentials-node`, `@arnilo/prism-enterprise-postgres`, `@arnilo/prism-evals`, `@arnilo/prism-mcp`, `@arnilo/prism-memory`
@@ -15,7 +15,7 @@ Current **49** publishable manifests (root + 48 workspace packages):
 `@arnilo/prism-provider-alibaba`, `@arnilo/prism-provider-anthropic`, `@arnilo/prism-provider-azure`, `@arnilo/prism-provider-bedrock`, `@arnilo/prism-provider-google`, `@arnilo/prism-provider-kimi`
 `@arnilo/prism-provider-neuralwatt`, `@arnilo/prism-provider-ollama`, `@arnilo/prism-provider-openai`, `@arnilo/prism-provider-opencode-go`, `@arnilo/prism-provider-openrouter`, `@arnilo/prism-provider-vertex`
 `@arnilo/prism-provider-zai`, `@arnilo/prism-rag`, `@arnilo/prism-server`, `@arnilo/prism-session-store-codecs`, `@arnilo/prism-session-store-nats`, `@arnilo/prism-session-store-postgres`, `@arnilo/prism-session-store-sqlite`
-`@arnilo/prism-openapi-tools`, `@arnilo/prism-supervisor`, `@arnilo/prism-tool-validator-json-schema`, `@arnilo/prism-web-tools`, `@arnilo/prism-work-tools`, `@arnilo/prism-workflows`
+`@arnilo/prism-openapi-tools`, `@arnilo/prism-supervisor`, `@arnilo/prism-tool-validator-json-schema`, `@arnilo/prism-web-tools`, `@arnilo/prism-work-tools`, `@arnilo/prism-workflows`, `@arnilo/prism-document-reader`
 
 Core ships `dist`, docs, templates, and `CHANGELOG.md`; code packages ship compiled output, README, license, and changelog. Family/profile packages ship manifest, README, and changelog. `@arnilo/prism-providers` includes all eleven `@arnilo/prism-provider-*` packages.
 
@@ -178,7 +178,7 @@ PRISM_LIVE_PROVIDER_TESTS=1 npm run test --workspaces --if-present
 
 ### 0.1.0 publish handoff (plan 012 Task 7)
 
-**Decision: GO when the operator prerequisites below are recorded.** Release **0.1.0** (Phase 12, plan 012) is the release-candidate hardening cut of the **0.0.28** graph: no new packages, public exports, schema migrations, or runtime dependencies (freeze manifest `scripts/phase12-freeze-manifest.json`). Publishable graph stays **49** publishable manifests (root + 48 workspace packages) at exact **0.1.0**. Store compatibility with 0.0.28: **compatible, no migration** ([migration](migration.md) `0.0.28 → 0.1.0`); the full `0.0.17 → 0.1.0` upgrade matrix is in the same page. All evidence for the tree under publication is recorded in [0.1.0 readiness](0.1.0-readiness.md) (capacity envelopes, restart-recovery, e2e journeys, threat-suites leg, audit at moderate).
+**Decision: GO when the operator prerequisites below are recorded.** Release **0.1.0** (Phase 12, plan 012) is the release-candidate hardening cut of the **0.0.28** graph: no new packages, public exports, schema migrations, or runtime dependencies (freeze manifest `scripts/phase12-freeze-manifest.json`). At this line the canonical statement read **49 publishable manifests**: the root `@arnilo/prism` core package plus **48 workspace packages** — 14 provider adapters, 9 `prism-*` family/profile packages, and 25 capability packages. Publishable graph stays **49** publishable manifests (root + 48 workspace packages) at exact **0.1.0**. Store compatibility with 0.0.28: **compatible, no migration** ([migration](migration.md) `0.0.28 → 0.1.0`); the full `0.0.17 → 0.1.0` upgrade matrix is in the same page. All evidence for the tree under publication is recorded in [0.1.0 readiness](0.1.0-readiness.md) (capacity envelopes, restart-recovery, e2e journeys, threat-suites leg, audit at moderate).
 
 ```bash
 # Operator prerequisites (each a named blocked gate — none may be skipped):
@@ -274,6 +274,64 @@ 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.
 
+### 0.1.6 publish handoff (plan 018 Task 7)
+
+**Decision: GO when the operator prerequisites below are recorded.** Release **0.1.6** (plan 018) is the coding-agent capability-closeouts patch on the frozen 0.1.x line — **additive-only** vs 0.1.5 (plain compat gate at 0.1.6 passed with 0 breaking declaration deltas; the baseline text was regenerated with `--update-baseline` for the version literal only, no `--allow-break` anywhere). Five demand-gated closeouts shipped, each flipped to `demanded` by named demand evidence (operator `arn` for native-sandbox/doc-reader/delete-glob/checkpoint-bodies, user `Clay` for acp-session-store) before its task landed; the demand-gate registry (`scripts/phase18-freeze-manifest.json`) machine-checks demanded ⇒ implemented, deferred ⇒ untouched. Shipped: (1) **durable ACP session store** — `@arnilo/prism-ag-ui` `AcpSessionStore` host seam (`save`/`loadAll`/`evict`), persisted `{sessionId, ownership, modeId, configValues, cwd, additionalDirectories, updatedAt}`, lazy ownership-scoped restore, fail-closed drops, absent seam = 0.1.5 behavior; (2) **network-free native sandbox** — `createNativeSandbox` in `@arnilo/prism-coding-security` (fresh netns per command via the OS `unshare` binary, chained ulimits with `|| exit 126`, argv-only exec, cwd containment, process-group kill, env allow-list, Linux-only fail-closed); (3) **bounded PDF/Office document reader** — new optional package `@arnilo/prism-document-reader` (the 50th manifest, graph 49 → 50) with optional `pdf-parse`/`mammoth` peers fail-closed at creation, magic-byte gating, null fall-through, caps + redaction at the adapter boundary; (4) **recursive delete + brace-expanding glob** — per-call `recursive: true` with fan-out cap and symlink-unlink-not-follow, host-selected/per-call `braceExpansion` bounded to 128 alternatives / 4096 expanded bytes, fail-closed on overflow/malformed braces; (5) **checkpoint persistence for loaded-skill bodies** — opt-in `includeSkillBodies` on run + resume options (names-only stays default, 0.1.3 shapes byte-identical), ≤64 bodies / ≤256-char names / ≤262144-byte bodies / ≤1 MiB total, `maxStateBytes` refusal, redacted at rest, registry-independent resume render. Store compatibility with 0.1.5: **compatible, no migration** (additive-only; no persisted-shape change; `docs/migration.md` gains no entries). Exit gate green: npm test core 1,433/1,433 + 190 script gates (incl. phase18-freeze done-phase), `sdk:ready` exit 0, audit 0 moderate, pack dry-run 50/50 twice byte-identical, budget/benchmark gates green; evidence in `scripts/phase18-baseline.json` `exitGate`. Rollback = restore the 0.1.5 manifests/tag.
+
+```bash
+# Operator prerequisites recorded: clean tree at the v0.1.6 tag candidate, GPG key, npm OIDC publisher.
+npm test                                        # core + workspace suites + all script gates
+npm run sdk:ready                               # typecheck, lint, format, test, pack, release:gate
+node scripts/release.mjs gate --version 0.1.6   # plain additive gate, 0 breaking deltas
+npm run pack:dry-run                            # twice; diff reports — deterministic
+npm audit --audit-level=moderate
+npm run release:check -- --version 0.1.6 --report /tmp/prism-0.1.6-preflight.json
+npm run release:publish -- --version 0.1.6 --dry-run --allow-dirty --allow-untagged --report /tmp/prism-0.1.6-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 v0.1.6 -m "Prism 0.1.6 — coding-agent capability closeouts (additive)"
+git verify-tag v0.1.6
+git push origin v0.1.6        # 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 0.1.6 --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 `0.1.6` 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. `0.1.6` is store-compatible with `0.1.5` 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 **0.1.7** continues the frozen 0.1.x additive promise; the 0.2.0 module line (delegated agents, agent-owned persistence, host-owned seam expansions) is the next documented cut.
+
+### 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).

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": "0.1.4",
+  "version": "0.1.6",
   "description": "Agent harness for AI providers, agents, sessions, and tools.",
   "type": "module",
   "main": "./dist/index.js",
@@ -134,6 +134,7 @@
     "packages/enterprise-postgres",
     "packages/browser",
     "packages/ag-ui",
+    "packages/document-reader",
     "packages/prism-*"
   ],
   "scripts": {
@@ -142,7 +143,7 @@
     "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/phase16-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/phase18-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 .",