@arnilo/prism 0.5.0 → 0.5.2

package/CHANGELOG.md

@@ -1,3 +1,16 @@
+## [0.5.2] - 2026-09-08
+
+### Fixed
+- **Stream tokens no longer persist as one content block per SSE delta.** Adjacent `text`/`thinking` deltas merge on persist (`text += delta`); `message_delta` events stay per-token. Replay serializers join those parts with `""` instead of `"\n"`, so multi-turn tool loops stop poisoning the next request into one token per line. Lockstep `0.5.1` → `0.5.2` with internal ranges `^0.5.1` → `^0.5.2`.
+
+## [0.5.1] - 2026-09-07 (plan 066)
+
+### Changed
+- **Prism constructs valid provider requests on every owned generate site (plan 066, additive):** new `applyDefaultProviderRequestOptions(request, { sessionId, thinkingLevel? })` fills missing `options.sessionId` (from the kernel session id) and `options.cacheKey` (from that id) with host values always winning; new `AgentConfig.thinkingLevel` / `RunOptions.thinkingLevel` session intent (run overrides agent) reaches the wire through the existing `applyThinkingLevelForModel` snap/merge; cache-control and explicit-breakpoint models now get default `{ system_prompt, last_stable_message }` breakpoints with `cacheRetention: "short"` unless the host sets `cache.mode: "off"`, `cacheRetention: "none"`, or explicit breakpoints — implicit/host-owned providers (Azure, Bedrock, Vertex, AI SDK) emit nothing new. Host request policies (`createSessionCachePolicy` and friends) remain overlays and are never required for request success.
+- **Observational memory derives its own correlation id** (`om:{session.id}`, shared across observer/reflector/dropper) fully separate from the agent session (workers may use a different model); **LLM compaction reuses the agent session id** so summaries hit the same prompt cache.
+- **OpenCode Go fails closed before fetch:** a raw `provider.generate()` without resolvable `sessionId`/`cacheKey` throws the new typed `ProviderRequirementError` (`ERR_PRISM_PROVIDER_REQUIREMENT`, redacted message naming requirement + provider id) instead of an opaque upstream HTTP 400.
+- **Lockstep 0.5.1 bump:** all 10 publishable manifests `0.5.0` → `0.5.1` with internal ranges `^0.5.0` → `^0.5.1`. New exports: `applyDefaultProviderRequestOptions`, `ProviderRequirementError`, `ApplyDefaultProviderRequestOptionsContext`. Contract rewrite in `docs/provider-packages.md` and `docs/provider-request-policies.md`; additive 0.5.1 section in `docs/migrate-to-0.5.md`; each provider page documents its P1 session wire, mandatory flag, and P2 default cache behavior.
+
 ## [0.5.0] - 2026-09-06 (plans 055-065)
 
 ### Changed

package/README.md

@@ -162,16 +162,16 @@ printf '{"id":"1","command":"prompt","params":{"input":"Hi"}}\n' \
 
 | package | version | notes |
 | --- | --- | --- |
-| `@arnilo/prism` | 0.5.0 | core — runtime, CLI/RPC, templates, docs |
-| `@arnilo/prism-coding-tools` | 0.5.0 | family — /agent, /security, /document-reader, /openapi, /computer-use-linux, /dev, /caveman, /ponytail, /impeccable subpaths |
-| `@arnilo/prism-core` | 0.5.0 | family — /runtime, /sessions, /governance, /credentials, /enterprise, /work, /validation subpaths |
-| `@arnilo/prism-providers` | 0.5.0 | family — all provider adapters as `/<adapter>` subpaths |
-| `@arnilo/prism-acp-agent` | 0.5.0 | capability — ACP adapter |
-| `@arnilo/prism-ag-ui` | 0.5.0 | capability — AG-UI/A2A/A2UI adapter |
-| `@arnilo/prism-mcp` | 0.5.0 | capability — MCP client/server/OAuth interop |
-| `@arnilo/prism-memory` | 0.5.0 | capability — memory plus /rag, /compaction/*, /graft, /wiki subpaths |
-| `@arnilo/prism-office` | 0.5.0 | capability — /documents, /sheets, /diagrams subpaths |
-| `@arnilo/prism-web-tools` | 0.5.0 | capability — Brave/Exa/Firecrawl plus peer-gated /browser and /obscura subpaths |
+| `@arnilo/prism` | 0.5.2 | core — runtime, CLI/RPC, templates, docs |
+| `@arnilo/prism-coding-tools` | 0.5.2 | family — /agent, /security, /document-reader, /openapi, /computer-use-linux, /dev, /caveman, /ponytail, /impeccable subpaths |
+| `@arnilo/prism-core` | 0.5.2 | family — /runtime, /sessions, /governance, /credentials, /enterprise, /work, /validation subpaths |
+| `@arnilo/prism-providers` | 0.5.2 | family — all provider adapters as `/<adapter>` subpaths |
+| `@arnilo/prism-acp-agent` | 0.5.2 | capability — ACP adapter |
+| `@arnilo/prism-ag-ui` | 0.5.2 | capability — AG-UI/A2A/A2UI adapter |
+| `@arnilo/prism-mcp` | 0.5.2 | capability — MCP client/server/OAuth interop |
+| `@arnilo/prism-memory` | 0.5.2 | capability — memory plus /rag, /compaction/*, /graft, /wiki subpaths |
+| `@arnilo/prism-office` | 0.5.2 | capability — /documents, /sheets, /diagrams subpaths |
+| `@arnilo/prism-web-tools` | 0.5.2 | capability — Brave/Exa/Firecrawl plus peer-gated /browser and /obscura subpaths |
 <!-- generated:package-truth:inventory end -->
 
 ## Scripts

package/dist/agent-session/session/provider-round.js

@@ -5,6 +5,22 @@ import { providerToolCallDeltaContent } from "../../provider-events.js";
 import { errorToErrorInfo, redactRunLedgerRecord, redactSecrets } from "../../redaction.js";
 import { createDefaultRetryPolicy, waitForRetry } from "../../retry.js";
 import { bridgeAbort, errorFromInfo, isSteerSoftInterrupt, jsonBytes, mergeRetry, ProviderTurnFailure, providerContent, randomId, reconstructMissingToolCalls, SteerSoftInterrupt, throwIfAborted, } from "../helpers.js";
+function pushCoalescedContent(content, block) {
+    const last = content.at(-1);
+    if (last?.type === "text" && block.type === "text") {
+        content[content.length - 1] = { type: "text", text: last.text + block.text };
+        return;
+    }
+    if (last?.type === "thinking" && block.type === "thinking") {
+        content[content.length - 1] = {
+            type: "thinking",
+            text: last.text + block.text,
+            ...((block.signature ?? last.signature) ? { signature: block.signature ?? last.signature } : {}),
+        };
+        return;
+    }
+    content.push(block);
+}
 /**
  * Plan 062: price usage through the host's {@link CostCatalog} when the provider
  * did not report a cost itself. Stale/unknown quotes, catalog failures, or
@@ -156,7 +172,7 @@ export async function generateProviderTurn(session, request, runId, signal, secr
                     continue;
                 }
                 const block = providerContent(event);
-                content.push(block);
+                pushCoalescedContent(content, block);
                 if (block.type === "tool_call")
                     calls.push(block);
                 emitOutput({ type: "message_delta", sessionId: session.id, runId, content: block });

package/dist/agent-session/session.js

@@ -3,7 +3,7 @@ import { policyList } from "../agent-tool-dispatch.js";
 import { createDefaultCompactionStrategy, isCompactionEntryData } from "../compaction.js";
 import { DEFAULT_MAX_PENDING_STEER_BYTES, DEFAULT_MAX_PENDING_STEERS } from "../contracts.js";
 import { GuardrailError, runGuardrails } from "../guardrails.js";
-import { createProviderRequestPolicyChain, normalizeProviderRequestPolicyResult } from "../provider-request-policy.js";
+import { applyDefaultProviderRequestOptions, createProviderRequestPolicyChain, normalizeProviderRequestPolicyResult, } from "../provider-request-policy.js";
 import { redactAgentEvent, redactProviderRequest, redactRunLedgerRecord, redactSecrets, redactSessionEntry } from "../redaction.js";
 import { createMemorySessionStore, createSessionEntry, getSessionBranchEntries, rebuildSessionContext } from "../session-stores.js";
 import { createLoadedSkillSet } from "../skill-disclosure.js";
@@ -370,10 +370,20 @@ export class RuntimeAgentSession {
         return true;
     }
     async applyProviderRequestPolicies(request, runId, options, metadata, signal) {
+        const stamped = applyDefaultProviderRequestOptions(request, {
+            sessionId: this.id,
+            thinkingLevel: options.thinkingLevel ?? this.agent.config.thinkingLevel,
+        });
         const policies = [...policyList(this.agent.config.providerRequestPolicies), ...policyList(options.providerRequestPolicies)];
         if (policies.length === 0)
-            return { request, secrets: [] };
-        const result = await createProviderRequestPolicyChain(policies).apply({ request, sessionId: this.id, runId, metadata, signal });
+            return { request: stamped, secrets: [] };
+        const result = await createProviderRequestPolicyChain(policies).apply({
+            request: stamped,
+            sessionId: this.id,
+            runId,
+            metadata,
+            signal,
+        });
         return normalizeProviderRequestPolicyResult(result);
     }
     async appendMessage(message, runId) {

package/dist/contracts-core/agent.d.ts

@@ -73,6 +73,8 @@ export interface AgentConfig {
     /** Optional trust check for tool and resource targets. */
     readonly trust?: TrustPolicy;
     readonly providerOptions?: ProviderRequestOptions;
+    /** Portable thinking intent. Snapped per model; run value overrides. */
+    readonly thinkingLevel?: string;
     readonly providerRequestPolicies?: ProviderRequestPolicy | readonly ProviderRequestPolicy[];
     readonly systemPrompt?: SystemPromptConfig;
     readonly redactor?: SecretRedactor;

package/dist/contracts-protocol.d.ts

@@ -75,6 +75,8 @@ export interface RunOptions {
     /** Run-scoped ceilings. When an agent config also sets limits, these can only narrow it. */
     readonly limits?: RunLimits;
     readonly providerOptions?: ProviderRequestOptions;
+    /** Portable thinking intent for this run. Overrides `AgentConfig.thinkingLevel`. */
+    readonly thinkingLevel?: string;
     readonly providerRequestPolicies?: ProviderRequestPolicy | readonly ProviderRequestPolicy[];
     readonly systemPrompt?: SystemPromptConfig;
     readonly compaction?: false | CompactionOptions;

package/dist/index.d.ts

@@ -73,8 +73,8 @@ export { createMemoryPersistenceLifecycle, DEFAULT_LIFECYCLE_PAGE_SIZE, DEFAULT_
 export { boundResponse, defaultResolver, isLoopbackAddress, isLoopbackHostname, normalizeHostname, type PinnedFetchOptions, pinnedFetch, raceAbort, requestPinned, resolvePinnedAddress, } from "./pinned-fetch.js";
 export { providerContentDelta, providerContinuationRequired, providerDone, providerError, providerTextDelta, providerThinkingDelta, providerToolCall, providerToolCallDelta, providerUsage, toolCallContent, toolCallFromArgumentsText, } from "./provider-events.js";
 export { authMethodKey, defineProviderPackage, systemPromptContributionKey } from "./provider-packages.js";
-export type { SessionCachePolicyOptions } from "./provider-request-policy.js";
-export { createProviderRequestPolicyChain, createSessionCachePolicy, mergeProviderRequestOptions } from "./provider-request-policy.js";
+export type { ApplyDefaultProviderRequestOptionsContext, SessionCachePolicyOptions } from "./provider-request-policy.js";
+export { applyDefaultProviderRequestOptions, createProviderRequestPolicyChain, createSessionCachePolicy, mergeProviderRequestOptions, ProviderRequirementError, } from "./provider-request-policy.js";
 export { canonicalizeJsonSchema } from "./providers/schema.js";
 export type { ProviderRegistry, ProviderRegistryOptions } from "./providers.js";
 export { createProviderRegistry, createProviderResolver } from "./providers.js";
@@ -119,5 +119,5 @@ export { trimTrailingSlashes } from "./trim-trailing-slashes.js";
 export type { ResolvedUseCaseModel, ResolveUseCaseModelInput, UseCaseModelBinding, } from "./use-case-model.js";
 export { resolveUseCaseModel, resolveUseCaseModelBinding, useCaseCredentialProviderId, } from "./use-case-model.js";
 export declare const name = "prism";
-export declare const version = "0.5.0";
+export declare const version = "0.5.2";
 export declare const description = "Agent harness for AI providers, agents, sessions, and tools.";

package/dist/index.js

@@ -40,7 +40,7 @@ export { createMemoryPersistenceLifecycle, DEFAULT_LIFECYCLE_PAGE_SIZE, DEFAULT_
 export { boundResponse, defaultResolver, isLoopbackAddress, isLoopbackHostname, normalizeHostname, pinnedFetch, raceAbort, requestPinned, resolvePinnedAddress, } from "./pinned-fetch.js";
 export { providerContentDelta, providerContinuationRequired, providerDone, providerError, providerTextDelta, providerThinkingDelta, providerToolCall, providerToolCallDelta, providerUsage, toolCallContent, toolCallFromArgumentsText, } from "./provider-events.js";
 export { authMethodKey, defineProviderPackage, systemPromptContributionKey } from "./provider-packages.js";
-export { createProviderRequestPolicyChain, createSessionCachePolicy, mergeProviderRequestOptions } from "./provider-request-policy.js";
+export { applyDefaultProviderRequestOptions, createProviderRequestPolicyChain, createSessionCachePolicy, mergeProviderRequestOptions, ProviderRequirementError, } from "./provider-request-policy.js";
 export { canonicalizeJsonSchema } from "./providers/schema.js";
 export { createProviderRegistry, createProviderResolver } from "./providers.js";
 export { createSecretRedactor, errorToErrorInfo, redactAgentEvent, redactMessage, redactProviderRequest, redactRunLedgerRecord, redactSecrets, redactSessionEntry, resolveRedactor, } from "./redaction.js";
@@ -66,6 +66,6 @@ export { createToolParameterValidator, createToolRegistry, dispatchToolCall, fil
 export { trimTrailingSlashes } from "./trim-trailing-slashes.js";
 export { resolveUseCaseModel, resolveUseCaseModelBinding, useCaseCredentialProviderId, } from "./use-case-model.js";
 export const name = "prism";
-export const version = "0.5.0";
+export const version = "0.5.2";
 export const description = "Agent harness for AI providers, agents, sessions, and tools.";
 //# sourceMappingURL=index.js.map

package/dist/input.js

@@ -1,6 +1,7 @@
 import { assertMessagesSupportModelCapabilities } from "./content.js";
 import { applyContextBudget, CONTEXT_BUDGET_REPORT_METADATA_KEY } from "./context-budget.js";
 import { runInstructionInjectors } from "./instruction-injection.js";
+import { applyDefaultProviderRequestOptions } from "./provider-request-policy.js";
 import { redactMessage } from "./redaction.js";
 import { loadTextResource } from "./resources.js";
 import { skillMessages as buildSkillMessages } from "./skill-disclosure.js";
@@ -200,7 +201,7 @@ export async function assembleProviderInput(options) {
     const providerMessages = await promptBuilder.build({ ...promptRequest, inputLayout: layout, tools, model: options.model });
     assertMessagesSupportModelCapabilities(options.model, providerMessages);
     const metadata = budgetReport ? { ...options.metadata, [CONTEXT_BUDGET_REPORT_METADATA_KEY]: budgetReport } : options.metadata;
-    return {
+    return applyDefaultProviderRequestOptions({
         model: options.model,
         messages: providerMessages,
         tools,
@@ -208,7 +209,7 @@ export async function assembleProviderInput(options) {
         options: options.providerOptions,
         metadata,
         signal: options.signal,
-    };
+    }, { sessionId: options.sessionId });
 }
 async function buildDefaultInputMessageGroups(input, context) {
     return {

package/dist/provider-request-policy.d.ts

@@ -3,6 +3,21 @@ export interface SessionCachePolicyOptions {
     readonly retention?: CacheRetention;
     readonly cacheKey?: string;
 }
+export interface ApplyDefaultProviderRequestOptionsContext {
+    readonly sessionId?: string;
+    readonly thinkingLevel?: string;
+}
+export declare class ProviderRequirementError extends Error {
+    readonly code: "ERR_PRISM_PROVIDER_REQUIREMENT";
+    readonly requirement: string;
+    readonly providerId?: string;
+    constructor(message: string, options: {
+        readonly requirement: string;
+        readonly providerId?: string;
+    });
+}
+/** Fill-if-missing `sessionId` / `cacheKey` / cache defaults from `model.cache`. Host values win. Thinking intent patches after. */
+export declare function applyDefaultProviderRequestOptions(request: ProviderRequest, ctx?: ApplyDefaultProviderRequestOptionsContext): ProviderRequest;
 export declare function createProviderRequestPolicyChain(policies: readonly ProviderRequestPolicy[]): ProviderRequestPolicy;
 export declare function createSessionCachePolicy(options?: SessionCachePolicyOptions): ProviderRequestPolicy;
 export declare function mergeProviderRequestOptions(base: ProviderRequestOptions | undefined, patch: ProviderRequestOptions | undefined): ProviderRequestOptions | undefined;

package/dist/provider-request-policy.js

@@ -1,3 +1,55 @@
+import { applyThinkingLevelForModel } from "./thinking.js";
+export class ProviderRequirementError extends Error {
+    code = "ERR_PRISM_PROVIDER_REQUIREMENT";
+    requirement;
+    providerId;
+    constructor(message, options) {
+        super(message);
+        this.name = "ProviderRequirementError";
+        this.requirement = options.requirement;
+        this.providerId = options.providerId;
+    }
+}
+function present(value) {
+    return value ? value : undefined;
+}
+const DEFAULT_CACHE_BREAKPOINTS = [
+    { location: "system_prompt" },
+    { location: "last_stable_message" },
+];
+function defaultCacheOptions(request) {
+    const cache = request.model.cache;
+    if (!cache || (cache.kind !== "cache_control" && cache.explicitBreakpoints !== true))
+        return undefined;
+    const options = request.options;
+    if (options?.cache?.mode === "off" || options?.cacheRetention === "none" || options?.cache?.breakpoints?.length) {
+        return undefined;
+    }
+    return {
+        ...(options?.cacheRetention ? {} : { cacheRetention: "short" }),
+        cache: { breakpoints: DEFAULT_CACHE_BREAKPOINTS },
+    };
+}
+/** Fill-if-missing `sessionId` / `cacheKey` / cache defaults from `model.cache`. Host values win. Thinking intent patches after. */
+export function applyDefaultProviderRequestOptions(request, ctx = {}) {
+    const sessionId = present(request.options?.sessionId) ?? present(ctx.sessionId);
+    const cacheKey = present(request.options?.cacheKey) ?? sessionId;
+    const cachePatch = defaultCacheOptions(request);
+    const thinkingLevel = present(ctx.thinkingLevel);
+    if (sessionId === present(request.options?.sessionId) &&
+        cacheKey === present(request.options?.cacheKey) &&
+        !cachePatch &&
+        !thinkingLevel) {
+        return request;
+    }
+    const merged = mergeProviderRequestOptions(request.options, {
+        ...(sessionId !== undefined ? { sessionId } : {}),
+        ...(cacheKey !== undefined ? { cacheKey } : {}),
+        ...cachePatch,
+    });
+    const options = thinkingLevel ? applyThinkingLevelForModel(merged, thinkingLevel, request.model) : merged;
+    return { ...request, options };
+}
 export function createProviderRequestPolicyChain(policies) {
     return {
         name: "provider-request-policy-chain",

package/dist/providers/openai-primitives.js

@@ -66,7 +66,7 @@ export function serializeOpenAIChatMessage(message, capabilities = {}) {
         if (toolCalls.length > 0) {
             return {
                 role: "assistant",
-                content: textParts.map((part) => part.text).join("\n") || null,
+                content: textParts.map((part) => part.text).join("") || null,
                 tool_calls: toolCalls.map((call) => ({
                     id: call.id,
                     type: "function",

package/docs/0.1.0-readiness.md

@@ -1,6 +1,6 @@
 # 0.1.0 / 1.0 Readiness Gates
 
-Status: **0.5.0** is the current release line (dead-export removal cut: 10 active packages, family subpaths, `^0.5.0` peers); **0.3.3** was the terminal 0.3.x cut; **0.1.7** was the terminal 0.1.x baseline; **1.0** readiness remains operator-gated, not automatic.
+Status: **0.5.2** is the current release line (10 active packages, family subpaths, `^0.5.2` peers); **0.3.3** was the terminal 0.3.x cut; **0.1.7** was the terminal 0.1.x baseline; **1.0** readiness remains operator-gated, not automatic.
 
 This page distills runnable readiness gates into one command-per-gate table.
 The **Last evidence** column records the 0.1.0-tree snapshot (plan 012 Tasks
@@ -20,7 +20,7 @@ Historical release lines (0.0.16 floor → 0.0.27 Phase 10 ACP interop → 0.1.0
 keep their per-phase evidence in the pages above; this page records the 0.2.6
 snapshot (plan 026) with the 0.1.x tables below as the historical record.
 
-## Current line (0.5.0)
+## Current line (0.5.2)
 
 | Item | Status |
 |---|---|

package/docs/agent-session-runtime.md

@@ -49,7 +49,7 @@ string | Message | readonly Message[]
 
 `AgentConfig.limits` sets run ceilings; `RunOptions.limits` may only narrow configured agent values. Limits cover turns, provider attempts, tool rounds/calls, wall time, request/response bytes, tokens, and optional single-currency cost. A breach emits one `run_limit_exceeded` event and throws `AgentRunError` with `result.limit`; see [Runs and usage ledger](runs-and-usage.md#run-limits).
 
-`RunOptions.model` can override the request model for a run. Model overrides append a `model_change` entry. `AgentConfig.inputLayout` selects the default input assembly layout (`"cache_aware"` by default, or opt-in `"legacy"`); `RunOptions.inputLayout` wins for one run. `AgentConfig.providerOptions`/`RunOptions.providerOptions` supply generic provider request options (session/cache/header/compat/extra hints only — provider-level timeout/retry hints were removed in 0.1.5). Use `RunOptions.signal`/host abort controllers for timeouts and `AgentConfig.retry`/`RunOptions.retry` for retry. `AgentConfig.providerRequestPolicies`/`RunOptions.providerRequestPolicies` run before `AIProvider.generate()` and before `provider_request` middleware. `AgentConfig.systemPrompt` and `RunOptions.systemPrompt` add explicit layered system prompt contributions; `RunOptions.systemPrompt: false` disables configured prompt layers for that run while keeping `AgentConfig.instructions` as the base path. `RunOptions.compaction` can enable auto-compaction for that run or use `false` to disable configured auto-compaction. `RunOptions.retry` can enable provider-turn retry for that run or use `false` to disable configured retry. `RunOptions.metadata` is merged with agent/session metadata for assembly, provider requests, and tool contexts. Run tool-round limits via `RunOptions.limits.maxToolRounds`. `RunOptions.signal` is bridged into the per-run abort signal passed to assembly, providers, tools, auto-compaction, and retry backoff.
+`RunOptions.model` can override the request model for a run. Model overrides append a `model_change` entry. `AgentConfig.inputLayout` selects the default input assembly layout (`"cache_aware"` by default, or opt-in `"legacy"`); `RunOptions.inputLayout` wins for one run. `AgentConfig.thinkingLevel` / `RunOptions.thinkingLevel` (run wins) is the session thinking intent — Prism snaps it onto the request after host `providerOptions`. `AgentConfig.providerOptions`/`RunOptions.providerOptions` supply generic provider request options (session/cache/header/compat/extra hints only — provider-level timeout/retry hints were removed in 0.1.5). Kernel construction always stamps `options.sessionId`/`cacheKey` from `session.id` when missing; `createSessionCachePolicy` is an overlay, not required. Use `RunOptions.signal`/host abort controllers for timeouts and `AgentConfig.retry`/`RunOptions.retry` for retry. `AgentConfig.providerRequestPolicies`/`RunOptions.providerRequestPolicies` run before `AIProvider.generate()` and before `provider_request` middleware. `AgentConfig.systemPrompt` and `RunOptions.systemPrompt` add explicit layered system prompt contributions; `RunOptions.systemPrompt: false` disables configured prompt layers for that run while keeping `AgentConfig.instructions` as the base path. `RunOptions.compaction` can enable auto-compaction for that run or use `false` to disable configured auto-compaction. `RunOptions.retry` can enable provider-turn retry for that run or use `false` to disable configured retry. `RunOptions.metadata` is merged with agent/session metadata for assembly, provider requests, and tool contexts. Run tool-round limits via `RunOptions.limits.maxToolRounds`. `RunOptions.signal` is bridged into the per-run abort signal passed to assembly, providers, tools, auto-compaction, and retry backoff.
 
 `RunOptions.activeSkills` selects named skills from a configured `SkillRegistry`; `RunOptions.skills` replaces a plain `Skill[]` config for one run. When `AgentConfig.skills` is a registry and neither is set, **no skills activate** unless `activateAllSkills: true` (run or agent). `skillsDisclosure` (`"progressive"` default, `"eager"` opt-in; run wins) controls catalog vs full instruction bodies; the session-owned `LoadedSkillSet` is populated by `load_skill` when the host registers `createLoadSkillTool`. `toolResultFold` (off unless the host supplies `summarize`) optionally folds aged large tool results in provider input only. See [Context and skills](context-and-skills.md).
 
@@ -117,6 +117,7 @@ const agent = createAgent({
   provider: createMockProvider([providerTextDelta("Hello"), providerDone()]),
   tools: [echo],
   store,
+  thinkingLevel: "low",
 });
 
 const session = agent.createSession({ id: "s1" });

package/docs/compaction-llm.md

@@ -32,6 +32,7 @@ Key exports:
 | `providerRequestPolicies` | Optional Prism provider request policies applied before the summary call. |
 | `customInstructions` | Additional summary focus appended to prompts. |
 | `thinkingLevel` | Mapped into `ProviderRequest.options.compat` via `applyThinkingLevel` / `thinkingFamilyForModel` (not inert `extra.thinkingLevel`). See [Thinking and reasoning](thinking-and-reasoning.md). |
+| session correlation | Summary `provider.generate` uses the **agent** `context.sessionId` (same cache key as the chat session). Kernel stamps `sessionId`/`cacheKey` even with no `providerRequestPolicies`. |
 | `reserveTokens` | Output budget basis; defaults to `16384`, hard cap `131072`. |
 | `keepRecentTokens` | Approximate recent-token budget; defaults to `20000`. |
 | `maxSummaryTokens` / `maxOutputTokens` | Summary retention/request ceiling; default `16384`, hard cap `131072`. `maxSummaryTokens` wins over the compatibility alias. The finite value is written to `model.parameters.maxTokens`; first-party providers map it to their wire field. |
@@ -132,6 +133,7 @@ The strategy makes only the needed provider call(s): one history summary plus on
 
 - [Use-case model selection](use-case-model-selection.md): `summaryModel` vs session `model` fallback.
 - [Thinking and reasoning](thinking-and-reasoning.md): `thinkingLevel` → `compat`.
+- [Provider request policies](provider-request-policies.md): kernel stamps agent `sessionId` on summary requests.
 - [Compaction and retry policies](compaction-and-retry.md): replaceable compaction strategy boundary and core compaction strategy surface.
 - [Observational memory compaction package](compaction-observational-memory.md): source-backed memory workers with the same use-case binding pattern.
 - [Agent/session runtime](agent-session-runtime.md): `AgentSession.compact()` and opt-in auto-compaction.

package/docs/compaction-observational-memory.md

@@ -156,6 +156,8 @@ Observer/reflector/dropper may use separate providers, models, instructions, thi
 
 Token counting uses `estimateEntryTokens()` / `estimateMessageTokens()`.
 
+Worker `provider.generate` calls use a **derived** correlation id `om:{session.id}` (shared by observer/reflector/dropper of that attach; adapters sanitize via `sanitizeCacheKey`). This is fully separate from the agent session id so OM cache does not collide with chat. Host `providerOptions.sessionId` still wins. Workers may use a different model than the session.
+
 The runtime requires host-supplied `session`, an `appendEntry` callback bound to that session's owning store/branch, and at least one worker provider (`observation.provider` / `reflection.provider` / `dropper.provider`). Model selection uses [use-case model selection](use-case-model-selection.md): pass per-worker `model` (or settings `observation.model` / `reflection.model` / `dropper.model`) to override, and `sessionModel: agent.config.model` so workers fall back to the session model when no worker model is configured. `requireExplicitModel: true` restores the historical `missing_model` skip when no explicit worker model is set. It no longer accepts a separate `store` option because mismatched session/store pairs can append memory entries outside the active branch. After each memory append, the runtime checks the appended entry is visible at the session leaf and fails closed/restores the previous checkout if the callback points elsewhere. Optional credential resolution is explicit; missing requested credentials skip worker execution. Default credential requests use the **resolved** model's provider id.
 
 `createObservationalMemoryCompactionStrategy()` keeps recent message entries like the default compaction strategy, renders existing observations/reflections as the summary, and returns a standard Prism compaction entry. Its `data` includes `throughEntryId`, `keepEntryIds`, `strategy`, `trigger`, and `memory: { type: "om.folded", version: 1, fullFold, observations, reflections, droppedObservationIds }`. When active observations exceed `context.observationsPoolMaxTokens`, it performs a full fold and synchronously trims lowest-relevance observations until the folded payload fits hard byte/token caps (or throws a typed error).
@@ -230,6 +232,7 @@ Ownership: funnel only within the `OwnershipScope` already on the parent agent/s
 
 - [Use-case model selection](use-case-model-selection.md): session vs worker model binding and `resolveUseCaseModel`.
 - [Thinking and reasoning](thinking-and-reasoning.md): `thinkingLevel` → provider `compat`.
+- [Provider request policies](provider-request-policies.md): derived `om:{session.id}` on worker generate.
 - [Compaction and retry policies](compaction-and-retry.md): replaceable compaction strategy boundary.
 - [LLM compaction package](compaction-llm.md): existing optional compaction-package pattern.
 - [Session stores and branching](session-stores-and-branching.md): branch entries that observational memory reads and appends to.

package/docs/index.md

@@ -2,9 +2,11 @@
 
 Prism is a TypeScript/Node.js agent harness. Host apps and extension packages own providers, tools, resources, credentials, storage, UI, and business behavior. Prism supplies contracts, registries, streaming events, and replaceable runtime primitives.
 
-## Current line (0.4)
+## Current line (0.5.2)
 
-- **10 publishable packages**: consolidated family packages use explicit subpaths and changed packages publish independently under Decision B.
+- **Stream token coalesce**: adjacent `text`/`thinking` deltas merge on persist; replay serializers join with `""` so multi-turn tool loops do not grow interstitial newlines.
+- **Provider request construction**: Prism stamps `sessionId`/`cacheKey` on every owned generate site, default cache breakpoints on `cache_control` / explicit-breakpoint models, and `thinkingLevel` on `AgentConfig` / `RunOptions`. Host policies are overlays. OpenCode Go missing session fails closed with `ProviderRequirementError` before fetch.
+- **10 publishable packages**: lockstep `0.5.2` (plans 055–066); family packages use explicit subpaths.
 - **Linux desktop control**: optional `@arnilo/prism-coding-tools/computer-use-linux` wraps a host-owned `computer-use-linux` MCP binary; DeviceAdapter admission is deny-by-default and the package is omitted from umbrellas.
 - **Coding/ACP closeouts**: `read.findText`, visible fuzzy edit outcomes and miss context, ACP editor-buffer operations, per-session spawnable coding registries, and delete/move projections.
 
@@ -36,8 +38,8 @@ Prism is a TypeScript/Node.js agent harness. Host apps and extension packages ow
 
 ## Compaction/session memory
 - [Compaction and retry policies](compaction-and-retry.md): summarize branch history and retry transient provider failures with host-replaceable policies. Task-boundary `session.compact()` fails closed during an active run (`Error("Agent session already has an active run")`).
-- [LLM compaction subpath](compaction-llm.md): optional provider-backed strategy with finite summary/reserve/error caps, bounded redacted streaming retention, mandatory finite post-policy `model.parameters.maxTokens`, and `createCodingCompactionStrategy()` for coding handoff focus.
-- [Observational memory compaction subpath](compaction-observational-memory.md): optional source-backed memory with explicit `attach()` lifecycle — **Recent exact messages**, **Observation log**, **Reflections**, **Raw-source retrieval** (exact-id recall + cursor paging); dual coverage, **nested-only settings** (pre-0.0.19 flat keys and top-level `workerProvider`/`workerModel` aliases removed in 0.1.5; removed keys fail closed naming the nested replacement), branch-isolated `appendEntry`, secrets redaction, inert import/extension, and an opt-in cross-session recall pattern (host-composed store funnel; default remains per-session).
+- [LLM compaction subpath](compaction-llm.md): optional provider-backed strategy with finite summary/reserve/error caps, bounded redacted streaming retention, mandatory finite post-policy `model.parameters.maxTokens`, and `createCodingCompactionStrategy()` for coding handoff focus. Summary generate uses the **agent session id** so it can hit the same prompt cache.
+- [Observational memory compaction subpath](compaction-observational-memory.md): optional source-backed memory with explicit `attach()` lifecycle — **Recent exact messages**, **Observation log**, **Reflections**, **Raw-source retrieval** (exact-id recall + cursor paging); dual coverage, **nested-only settings** (pre-0.0.19 flat keys and top-level `workerProvider`/`workerModel` aliases removed in 0.1.5; removed keys fail closed naming the nested replacement), branch-isolated `appendEntry`, secrets redaction, inert import/extension, and an opt-in cross-session recall pattern (host-composed store funnel; default remains per-session). Worker generate uses derived `om:{session.id}`, separate from the agent session.
 - [Working and semantic memory](working-and-semantic-memory.md): optional `@arnilo/prism-memory` working-memory store, semantic recall with opt-in composite recency/importance scoring (sum-normalized weights, component-exposing hits), finite Embedder/VectorStore contracts (incl. embedder identity + generation pointers), PostgreSQL/pgvector path (`createPostgresVectorStore` standalone, HNSW/fts DDL on the host knowledge database), consent lifecycle, identity-bound redacted export, and resumable bounded rebuild.
 - [Session stores](session-stores.md): `SessionStore` contract, `SessionAppendOptions`, `SessionAppendConflictError`, branch handles, `readBranchPath`, optional bounded `searchSessions` / `SessionIndex` (memory linear|unsupported), and dev-vs-production branch reads — start here for session persistence.
 - [Conversations](conversations.md): durable user-scoped conversation threads (create/list/continue/branch/archive/export/delete) on session + event-ledger seams, thread-bound reconnectable replay, frozen caps, atomic metadata via version/CAS (`metadata_conflict` on stale writes), and legal-hold-aware deletion.
@@ -61,10 +63,10 @@ Prism is a TypeScript/Node.js agent harness. Host apps and extension packages ow
 - [Provider layer](provider-layer.md): register and resolve host-owned providers/models, choose replace-or-error duplicate policy, create provider events, stream/reconstruct tool-call deltas, use generic provider request options, and test with the mock provider; deprecated provider-level timeout/retry hints point to runtime abort/retry.
 - [Model registry](model-registry.md): register and resolve `ModelConfig` records with capabilities, limits, cost, cache support metadata, compat data, and duplicate policy.
 - [Provider caching](provider-caching.md): use `PromptCacheHints`, `PromptCacheBreakpoint`, `ModelCacheCapabilities`, cache-aware stable-prefix guidance, and shared cache diagnostics helpers; includes the complete per-provider explicit/implicit cache matrix plus no-Prism-cache entries (including Anthropic, Google, Alibaba, Ollama, cloud adapters, and host-owned AI SDK); cache hints are best-effort and cache keys are never secrets; `createCacheTelemetry()` aggregates per-provider/model hit rate and cache-token totals from the `usage` event stream for tuning the `cache_aware` layout — the `__overflow__` bucket reports requests/token totals only, never mixed-model cost.
-- [Thinking and reasoning](thinking-and-reasoning.md): model-aware effort adapter (`applyThinkingLevelForModel`) resolves the compat family, snaps the level to the model's declared `capabilities.thinkingLevels`, and merges the patch — with new `google` and `output_config_effort` families, per-provider legality in the coverage evidence matrix (`docs/_evidence/thinking-coverage-2026-09-05.md`), and per-provider declared-level tables.
+- [Thinking and reasoning](thinking-and-reasoning.md): session entry point is `AgentConfig.thinkingLevel` / `RunOptions.thinkingLevel`; `applyThinkingLevelForModel` snaps the level to the model's declared `capabilities.thinkingLevels` and merges the patch — with `google` and `output_config_effort` families, per-provider legality in the coverage evidence matrix (`docs/_evidence/thinking-coverage-2026-09-05.md`), and per-provider declared-level tables.
 - [Use-case model selection](use-case-model-selection.md): bind `{ model?, provider?, thinkingLevel? }` for observational memory, LLM compaction, and other non-session LLM jobs with explicit session-model fallback via `resolveUseCaseModel`.
-- [Provider request policies](provider-request-policies.md): chain `ProviderRequestPolicy` hooks, use `createSessionCachePolicy`, and merge legacy/structured cache options safely.
-- [Provider packages](provider-packages.md): all provider adapters ship as `@arnilo/prism-providers/<adapter>` subpaths (importing one adapter never evaluates another); define explicit provider packages, model metadata, auth descriptors, request/cache policies, provider-owned header precedence, the provider-authorized OAuth matrix, and the Phase 10 first-party compatibility matrix without package discovery or provider-specific core behavior; includes a cache behavior summary and **caller-gated on-demand model discovery** (`list*Models`, setup zero-fetch).
+- [Provider request policies](provider-request-policies.md): kernel `applyDefaultProviderRequestOptions` constructs session/cache/thinking; `createSessionCachePolicy` and other `ProviderRequestPolicy` hooks are overlays; merge legacy/structured cache options safely.
+- [Provider packages](provider-packages.md): all provider adapters ship as `@arnilo/prism-providers/<adapter>` subpaths (importing one adapter never evaluates another); define explicit provider packages, model metadata, auth descriptors, request/cache overlays, provider-owned header precedence, the provider-authorized OAuth matrix, and the Phase 10 first-party compatibility matrix without package discovery or provider-specific core behavior. Prism constructs valid requests (session correlation, cache defaults, thinking intent); hosts own credentials/OAuth/env/overlays. Includes a cache behavior summary and **caller-gated on-demand model discovery** (`list*Models`, setup zero-fetch).
   - Phase 12 package workspaces: [`@arnilo/prism-providers/openai`](providers/openai.md) (Responses hosted-tool attribution, bounded continuation, Realtime session seam), [`@arnilo/prism-providers/anthropic`](providers/anthropic.md) (native Messages, `cache_control`, thinking, caller-gated `listAnthropicModels`), [`@arnilo/prism-providers/google`](providers/google.md) (native Gemini `generateContent` SSE, caller-gated `listGoogleModels`), [`@arnilo/prism-providers/opencode-go`](providers/opencode-go.md) (official Go open models, dual-route Anthropic/OpenAI, caller-gated `listOpenCodeGoModels`, `reasoning_content`/thinking preserve), [`@arnilo/prism-providers/openrouter`](providers/openrouter.md) (app-controlled catalog, caller-gated `listOpenRouterModels`, `reasoning` merge/preserve, `cache_control` + sticky `session_id`), [`@arnilo/prism-providers/zai`](providers/zai.md) (official `thinking`/`reasoning_effort`/`tool_stream`, implicit cache, caller-gated `listZaiModels`), [`@arnilo/prism-providers/deepseek`](providers/deepseek.md) (official `thinking` + `reasoning_effort`, implicit prefix cache, caller-gated `listDeepSeekModels`), [`@arnilo/prism-providers/xai`](providers/xai.md) (Grok Completions, `x-grok-conv-id`, SuperGrok device-code OAuth, caller-gated `listXaiModels`), [`@arnilo/prism-providers/clinepass`](providers/clinepass.md) (stream-only `cline-pass/*` catalog, implicit cache, no WorkOS), [`@arnilo/prism-providers/hyper`](providers/hyper.md) (Charm Hyper, dual-route Anthropic/OpenAI plus explicit `/v1/responses` pass-through, `reasoning_effort`, caller-gated `listHyperModels`, Hypercredit cost telemetry, `402` billing semantics), [`@arnilo/prism-providers/commandcode`](providers/commandcode.md) (Command Code Provider API, server-enforced dual-route Anthropic/OpenAI, optional ZDR, caller-gated `listCommandCodeModels`, off-peak/deal pricing caveats), [`@arnilo/prism-providers/kimi`](providers/kimi.md), [`@arnilo/prism-providers/alibaba`](providers/alibaba.md) (Alibaba Cloud Model Studio / DashScope + Coding Plan, OpenAI-compatible, caller-gated `listAlibabaModels`, implicit + explicit `cache_control` caching, Qwen `enable_thinking`), [`@arnilo/prism-providers/ollama`](providers/ollama.md) (Ollama Cloud + local, OpenAI-compatible, caller-gated `listOllamaModels`, implicit-only caching, `reasoning_effort`), and [`@arnilo/prism-providers/neuralwatt`](providers/neuralwatt.md) with implicit vLLM prefix caching, reasoning controls (`reasoning_effort`/`thinking_token_budget`/`enable_thinking`/`preserve_thinking`/`clear_thinking`), reasoning preservation, OpenAI-style tool-call loop, quota, telemetry, and retry classification helpers, plus the cross-vendor `@arnilo/prism-providers/model-discovery` model-list/capability discovery adapters (OpenAI-compatible + Google, provenance + TTL cache, see model-registry.md).
   - Phase 8 enterprise cloud (workload identity; separate from consumer Anthropic/Google): [`@arnilo/prism-providers/azure`](providers/azure.md) (Entra / Foundry, credential once per request), [`@arnilo/prism-providers/bedrock`](providers/bedrock.md) (IAM/IRSA + region/PrivateLink, duplicate-case-safe SigV4 signing), [`@arnilo/prism-providers/vertex`](providers/vertex.md) (ADC / Vertex OpenAPI, credential once per request).
   - Optional AI SDK adapter: [`@arnilo/prism-providers/ai-sdk`](providers/ai-sdk.md) maps host-owned pinned `LanguageModelV4` models onto Prism `AIProvider` streams (offline-tested `@ai-sdk/provider` version matrix; no Prism catalog; maps metadata/tool authority/`finish.usage` cache tokens; reasoning is host-model-owned).
@@ -161,8 +163,8 @@ Prism is a TypeScript/Node.js agent harness. Host apps and extension packages ow
 - [Impeccable behavior integration](impeccable.md): optional `@arnilo/prism-coding-tools/impeccable` — host `upstreamPath` to compiled Impeccable `SKILL.md`, skill + `/impeccable` → `load_skill`; no detector CLI, no live browser, not in code/sdk/all.
 
 ## Release and install
-- [Release and install](release-and-install.md): current **0.5.0** package graph — generated inventory in the [package-inventory section](#package-inventory) and the release page — plan 041-044 changed-package cut (progressive tool loading with `search_tools` disclosure, `@arnilo/prism-prompts` initial cut with run-ledger `promptVersion` provenance (persistence schema 9), trace-to-dataset curation in `@arnilo/prism-evals`, and composite memory-recall scoring in `@arnilo/prism-memory@0.3.2`) and independent `^0.3.0` publication; plan 050 changed-package cut (clay-integration-findings fixes + OKF v0.2 wiki bundles) and independent `^0.3.0` publication; plan 030 last-lockstep cut and independent `^0.3.0` publication; plan 029 **0.2.9** provider adoption (DeepSeek, xAI SuperGrok OAuth, ClinePass), `@arnilo/prism-impeccable`, Ponytail 4.9.0, Caveman v2.1 extras; then plan 028 **0.2.8** ACP adoption fixes; then plan 026 the fully-featured coding-agent-readiness cut: **host-selected PTY** (`pty: true` delegates only to the host `ptyBackend`, fails closed as unsupported when absent, bounded resize/TERM/attach caps), **indexed code search** (host-owned incremental index seam with explicit `indexed_literal`/`semantic` modes, literal remains the default, stale/failed/untrusted indexes fail closed `ERR_PRISM_INDEX_*`, results labeled `untrusted_index`), **coding workspaces** (`createCodingWorkspaceLifecycle`: durable CheckpointStore CAS records + LeaseStore fencing, locked worktrees, credential-free fingerprints, cleanup refusal matrix), **durable recovery** (process intent/ACP `activeRun` refs over Postgres/SQLite stores with attach-if-attested `recover()` and durable fence-checked cancellation, never fabricated exits), **patch review and diagnostics** (`createCodingPatchReviewManifest` + `assertCodingPatchAccepted` with pending/accepted/rejected/superseded bound to digest + revision + identity, opt-in LSP `syncDocument`/`diagnosticDelta`), and the **protected real coding journey** (packed consumer through real provider/Docker/Postgres/GitHub/Playwright/PTY services with retained evidence report; forge breadth GitLab/Bitbucket stays demand-gated); then plan 025 the maintainability-and-bounded-performance cut: **god-module splits** (the six remaining implementation monoliths — `src/contracts-core.ts` 1,719 L, `src/agent-session.ts` 2,049 L, `workflows/src/run.ts` 1,227 L, `server/src/handler.ts` 1,005 L, `coding-agent/src/repository.ts` 974 L, `ag-ui/src/acp/agent.ts` 836 L — split into cohesive family files behind preserved barrels, compat-preserving with zero breaking deltas, no `exports`-map subpath, `RuntimeAgentSession` kept as one class with a recorded reason), **persistence-mechanics dedup** (21 pure ownership/cursor/checkpoint/lifecycle/search helpers moved into the dependency-free `session-store-codecs`; postgres/sqlite adapters shrank 273 lines; SQL dialect stays per-adapter; no schema/shape change; cross-store conformance green), **bounded accumulation removed** (per-push `Buffer.concat` in language framing + tar parsing → chunk-array readers; framing ~100–200× faster at 4,000 chunks, tar linear at 8 MiB, caps fail-closed byte-identical; CLI `collectOutput` audited already linear), **dead-code cleanup internal-only** (62 candidates triaged: 2 internal removals + 60 allow-listed in `docs/_evidence/phase25-dead-exports-triage.md`), and **coverage close** (76 behavior-backed regressions; core 90.53/84.20/90.54 → 91.43/84.80/91.60); additive-only compat (105 helper exports), no migration; then plan 024 the package-documentation-and-compatibility-truth cut: **umbrella wording matches manifests** (`@arnilo/prism-providers` installs 11 of 14 provider adapters — Azure/Bedrock/Vertex are added separately by `prism-all`; `prism-all` installs 20 direct / 43 transitive packages and omits document-reader, OpenAPI tools, NATS, Caveman, Ponytail; membership unchanged in 0.2.x), **manifest-derived package truth** (`scripts/package-truth.mjs` → `scripts/package-truth.json` is the single source for counts, provider membership, and closures; docs literals regenerate from it and drift fails the gates), **peer-version policy Decision A** (exact `@arnilo/prism: 0.2.4` pins, atomic-upgrade rule, ERESOLVE refusal for partial upgrades, `^1.0.0` widening at 1.x), and **current-line truth** (`docs/0.1.0-readiness.md` at the 0.2.x line with 0.1.7 as the terminal 0.1.x baseline); no runtime contract delta (compat gate at 0.2.4: version literal only), no migration; then plan 023 the build-coverage-and-release-evidence-integrity cut: **build serialization** (dependency-free `scripts/with-build-lock.mjs` — one O_EXCL lockfile at `node_modules/.prism-build.lock` serializing every emit/test leaf so concurrent compilers can never expose a partial live `dist/`, stale-PID reclaim, env-overridable `PRISM_BUILD_LOCK_TIMEOUT_MS`, fail-closed; documented direct-`tsc` caveat), **corrected workspace coverage denominators** (package-local `--test-coverage-include=dist/**` so imported core `dist` no longer pollutes workspace rows — `mcp` 45.47→90.25, `rag` 19.70→94.82; evidence-based per-package thresholds in `scripts/coverage-thresholds.json` with `protectedException` for durable-leg packages shown separately, machine-readable `scripts/coverage-summary.json`), **machine-auditable release skip manifest** (`scripts/release-skip-manifest.mjs` → `scripts/release-evidence.json`: every surface recorded `pass`/`skip`/`blocked`/`protected` with reason and required env; the 33 protected/live skips named; a required surface without evidence records `blocked` and fails the release gate fail-closed — missing credentials/services can never convert into a green release), and **stabilized quality gates** (Biome 2.x `preset` config migration with zero lint diagnostics, the racy 150ms MCP bridge timing assert replaced by a deterministic barrier, load-sensitive guards carry documented `ponytail:` ceilings, machine-readable `lint-report.sarif` + `unused-report.json` retained by CI); no runtime contract delta (compat gate at 0.2.3: version literal only), no migration; then plan 022 the concurrent-state-and-durability-integrity cut: atomic model-budget reservation (`ModelRouterStateStore.reserveBudget`/`commitBudget`/`releaseBudget` with fencing tokens, `reservationTtlMs` expiry and unknown-usage reconciliation, rate/budget key-map caps with LRU eviction that never drops a held reservation), atomic conversation metadata (`SessionRecord.version` + `appendSession` `expectedVersion` CAS across Postgres/SQLite — create-only `0`, exact-version `N>0`, legacy last-write-wins when omitted; `SessionMetadataConflictError` `metadata_conflict` with versions only, HTTP 409; concurrent create/branch/archive single-statement with branch caps inside the CAS, archive wins, deleted rows never resurrect), single-consumer `EventMultiplexer` (`EventMultiplexerError` `ERR_PRISM_EVENT_MULTIPLEXER_SINGLE_CONSUMER` instead of silent queue sharing), restart-stable NATS durable consumer identity (`prism_<hmac16>` with no random suffix — crash-resumed subscribe continues from the last ack, orphaned 0.2.1 consumers reclaimed on clean stop), and bounded non-durable active-run registries (sweep + fail-closed 512 cap `ERR_PRISM_WORKFLOW_RUN_REGISTRY_OVERFLOW`); new regression surface `scripts/phase22-security.test.mjs` (4 blockers + gate accounting over built public entrypoints) + packed plain-JS `security22.mjs` consumer + the `@arnilo/prism/testing/state-concurrency-conformance` harness (7 probes across memory/Postgres/SQLite/NATS legs, no timing-only sleeps) + the `scripts/phase22-conformance.test.mjs` gate; additive-only compat (new exports only, no removals); forward-only migrations 008 (`prism_sessions.version`) and 003 (`prism_model_router_budgets.reservations`); migration `0.2.1 → 0.2.2`; then plan 021 the provider-completion-and-outbound-trust-boundaries cut: strict stream completion is the shared OpenAI-compatible default (truncated streams fail `incomplete_delta`, explicit `strictCompletion: false` opt-out), bounded success bodies via `readBoundedResponseJson` on all discovery/quota/embeddings/upload/OAuth JSON endpoints (65,536-byte ceiling, depth/property/shape caps), DNS-pinned OIDC JWKS/OPA/content fetches through the core `pinnedFetch` primitive with 3xx redirects rejected outright (private/metadata answers fail closed `ssrf_denied`), shared bounded OAuth device/token polling (`pollDeviceCodeToken`) across provider-openai and credentials-node, and the four edge fixes (Azure/Vertex credential-once, Bedrock duplicate-case/repeated-query SigV4 canonicalization, OpenAI upload failed-DELETE retention, cache `__overflow__` tokens-only); public-entrypoint threat-suite `scripts/phase21-security.test.mjs` + packed plain-JS consumer; additive-only compat (MCP transport helpers re-exported from core, no removals); migration `0.2.0 → 0.2.1`; then plan 020 the fail-closed runtime-and-sandbox-security cut on the 0.2.x review-remediation line: durable-resume decision validation in core (`assertValidAgentRunResume` — unknown decisions/malformed batches fail closed with `ERR_PRISM_DECISION_*` before any state claim, checkpoint write, or tool execution; server parser remains defense in depth), isolated work-tool subprocess environments (`@arnilo/prism-work-tools` — fixed base allow-list + explicit env + forced HOME/telemetry + late-bound per-identity tokens, 64-name/64-KiB caps, absolute binary/configDir, linear output capture), and explicit sandbox capabilities (`@arnilo/prism-coding-security` — `SandboxAdapter.capabilities` with omission-is-false fail-closed resolution, `SandboxCodingComposition.capabilities` from verified wiring, `containmentClaim` deprecated as the conservative projection; Docker reports only verified controls, native reports filesystem/process/privilege `false`); public-entrypoint security conformance (`scripts/phase20-security.test.mjs`, wired into `security:threat-suites`), packed plain-JS consumer regressions, and the sandbox-browser workflow's fail-loud Docker/native capability evidence gate — 0.2.0 never ships while a blocker is skipped; migration and rollback notes in `docs/migration.md` `0.1.7 → 0.2.0`, store-compatible with 0.1.7 in both directions; 0.1.7 was the performance-and-DX patch — dependency-free `createCacheTelemetry()` per-provider/model cache hit/miss aggregator (bounded cardinality with `__overflow__`, token counters/rates only, host-activated), host-configurable `ModelRouterSelectionPolicy` on `createModelRouter` with the reference `createCostLatencySelection` (ModelCost rank then in-memory latency EMA, default ordered behavior byte-identical), `prism providers add <name>` OpenAI-compatible provider scaffold (manifest/provider/models/cache/conformance test/docs stub, npm-name + traversal + symlink-escape validation, placeholders only), and the async `AgUiProjection` verification closeout (plan 009 Task 15 evidence recorded, no new code); plan 017 the documented breaking cut — deprecated-option removal with `docs/migration.md` `0.1.4 → 0.1.5` section and reviewed compat-baseline regeneration via `--allow-break` then `--update-baseline`: the inert provider request knobs, `RunOptions.maxToolRounds`, observational-memory flat settings keys + top-level worker aliases, `ReadToolOptions.autoResizeImages`, `INIT_PROVIDERS`; all removals fail closed naming their replacement; plan 016 internal god-module split — `agents.ts`/`contracts.ts` reorganized behind barrel re-exports with a byte-identical public entry surface, measured tree-shaking improvement in `scripts/phase16-baseline.json`, and additive `@arnilo/prism-browser` Chrome DevTools Protocol capabilities — `browser_evaluate`/`browser_observe` and `block_urls`/`unblock_urls`/`throttle`/`emulate` act actions; plan 015 dead-code and deprecation hygiene on the frozen 0.1.x line — parameterized benchmark runner `scripts/benchmark.mjs` absorbing the per-version runners, archived review-coverage evidence in `docs/_evidence/`, non-blocking unused-code sweep `npm run sweep:unused`, opt-in checkpoint persistence for loaded-skill names and read-path sets; plan 014 Alibaba provider enrichment — embeddings, video input, verified compatible-mode surface decision table; plan 013 post-release hardening — build single-flight, MCP SSE relay test, combined coverage summary, canonical manifest-count narrative, ACP modes/config persistence guidance; Phase 12 release-candidate hardening; plan 012 — freeze manifest, compatibility matrix, upgrade matrix, packed-install e2e journeys, restart-recovery evidence, capacity envelopes, security policy), exact-peer/install/tarball rules, deterministic resumable publication and publish dry-run, frozen 0.1.x compatibility and support matrix (Node/PostgreSQL/platform/provider/protocol pins and unsupported combinations, machine-checked against `scripts/phase12-freeze-manifest.json`), protected PostgreSQL gate, pinned supply-chain gates, offline tests, the 0.0.15 provider/AI-SDK/RAG/memory protected live-canary matrix, and sandbox-browser Docker/Playwright gates. 0.2.6 (plan 026 Task 7) adds the protected coding journey: `scripts/phase26-coding-journey.test.mjs` runs a packed consumer through real provider calls, a digest-pinned Docker sandbox, the durable Postgres worktree lifecycle, provider-driven ACP edits with policy approval, named checks with `diagnosticDelta`, patch review over the server ArtifactService, cross-replica process recovery, durable cancellation, real GitHub PR push/reconcile/cleanup, host Playwright inspection, and the host PTY adapter (frozen profile) — the retained `scripts/phase26-coding-journey-report.json` gates release evidence (pass/blocked/protected, never a passing skip).
-- [Migrate 0.4 to 0.5](migrate-to-0.5.md): the complete 0.5.0 migration guide (plans 055–065) — new Hyper/CommandCode adapters, tenant-scoped store factories + child env allow-list, the 27 removed unused exports with replacements, dependency majors (pdf-parse 2.4, better-sqlite3 13, keyring 2), the MCP SDK v2 module move, the CLI real-provider contract, and model-aware thinking effort (Anthropic `output_config.effort`, xAI `reasoning_effort`, snapping, Azure/Vertex/Bedrock compat forwarding) — plus rollback.
+- [Release and install](release-and-install.md): current **0.5.2** package graph — generated inventory in the [package-inventory section](#package-inventory) and the release page — plan 041-044 changed-package cut (progressive tool loading with `search_tools` disclosure, `@arnilo/prism-prompts` initial cut with run-ledger `promptVersion` provenance (persistence schema 9), trace-to-dataset curation in `@arnilo/prism-evals`, and composite memory-recall scoring in `@arnilo/prism-memory@0.3.2`) and independent `^0.3.0` publication; plan 050 changed-package cut (clay-integration-findings fixes + OKF v0.2 wiki bundles) and independent `^0.3.0` publication; plan 030 last-lockstep cut and independent `^0.3.0` publication; plan 029 **0.2.9** provider adoption (DeepSeek, xAI SuperGrok OAuth, ClinePass), `@arnilo/prism-impeccable`, Ponytail 4.9.0, Caveman v2.1 extras; then plan 028 **0.2.8** ACP adoption fixes; then plan 026 the fully-featured coding-agent-readiness cut: **host-selected PTY** (`pty: true` delegates only to the host `ptyBackend`, fails closed as unsupported when absent, bounded resize/TERM/attach caps), **indexed code search** (host-owned incremental index seam with explicit `indexed_literal`/`semantic` modes, literal remains the default, stale/failed/untrusted indexes fail closed `ERR_PRISM_INDEX_*`, results labeled `untrusted_index`), **coding workspaces** (`createCodingWorkspaceLifecycle`: durable CheckpointStore CAS records + LeaseStore fencing, locked worktrees, credential-free fingerprints, cleanup refusal matrix), **durable recovery** (process intent/ACP `activeRun` refs over Postgres/SQLite stores with attach-if-attested `recover()` and durable fence-checked cancellation, never fabricated exits), **patch review and diagnostics** (`createCodingPatchReviewManifest` + `assertCodingPatchAccepted` with pending/accepted/rejected/superseded bound to digest + revision + identity, opt-in LSP `syncDocument`/`diagnosticDelta`), and the **protected real coding journey** (packed consumer through real provider/Docker/Postgres/GitHub/Playwright/PTY services with retained evidence report; forge breadth GitLab/Bitbucket stays demand-gated); then plan 025 the maintainability-and-bounded-performance cut: **god-module splits** (the six remaining implementation monoliths — `src/contracts-core.ts` 1,719 L, `src/agent-session.ts` 2,049 L, `workflows/src/run.ts` 1,227 L, `server/src/handler.ts` 1,005 L, `coding-agent/src/repository.ts` 974 L, `ag-ui/src/acp/agent.ts` 836 L — split into cohesive family files behind preserved barrels, compat-preserving with zero breaking deltas, no `exports`-map subpath, `RuntimeAgentSession` kept as one class with a recorded reason), **persistence-mechanics dedup** (21 pure ownership/cursor/checkpoint/lifecycle/search helpers moved into the dependency-free `session-store-codecs`; postgres/sqlite adapters shrank 273 lines; SQL dialect stays per-adapter; no schema/shape change; cross-store conformance green), **bounded accumulation removed** (per-push `Buffer.concat` in language framing + tar parsing → chunk-array readers; framing ~100–200× faster at 4,000 chunks, tar linear at 8 MiB, caps fail-closed byte-identical; CLI `collectOutput` audited already linear), **dead-code cleanup internal-only** (62 candidates triaged: 2 internal removals + 60 allow-listed in `docs/_evidence/phase25-dead-exports-triage.md`), and **coverage close** (76 behavior-backed regressions; core 90.53/84.20/90.54 → 91.43/84.80/91.60); additive-only compat (105 helper exports), no migration; then plan 024 the package-documentation-and-compatibility-truth cut: **umbrella wording matches manifests** (`@arnilo/prism-providers` installs 11 of 14 provider adapters — Azure/Bedrock/Vertex are added separately by `prism-all`; `prism-all` installs 20 direct / 43 transitive packages and omits document-reader, OpenAPI tools, NATS, Caveman, Ponytail; membership unchanged in 0.2.x), **manifest-derived package truth** (`scripts/package-truth.mjs` → `scripts/package-truth.json` is the single source for counts, provider membership, and closures; docs literals regenerate from it and drift fails the gates), **peer-version policy Decision A** (exact `@arnilo/prism: 0.2.4` pins, atomic-upgrade rule, ERESOLVE refusal for partial upgrades, `^1.0.0` widening at 1.x), and **current-line truth** (`docs/0.1.0-readiness.md` at the 0.2.x line with 0.1.7 as the terminal 0.1.x baseline); no runtime contract delta (compat gate at 0.2.4: version literal only), no migration; then plan 023 the build-coverage-and-release-evidence-integrity cut: **build serialization** (dependency-free `scripts/with-build-lock.mjs` — one O_EXCL lockfile at `node_modules/.prism-build.lock` serializing every emit/test leaf so concurrent compilers can never expose a partial live `dist/`, stale-PID reclaim, env-overridable `PRISM_BUILD_LOCK_TIMEOUT_MS`, fail-closed; documented direct-`tsc` caveat), **corrected workspace coverage denominators** (package-local `--test-coverage-include=dist/**` so imported core `dist` no longer pollutes workspace rows — `mcp` 45.47→90.25, `rag` 19.70→94.82; evidence-based per-package thresholds in `scripts/coverage-thresholds.json` with `protectedException` for durable-leg packages shown separately, machine-readable `scripts/coverage-summary.json`), **machine-auditable release skip manifest** (`scripts/release-skip-manifest.mjs` → `scripts/release-evidence.json`: every surface recorded `pass`/`skip`/`blocked`/`protected` with reason and required env; the 33 protected/live skips named; a required surface without evidence records `blocked` and fails the release gate fail-closed — missing credentials/services can never convert into a green release), and **stabilized quality gates** (Biome 2.x `preset` config migration with zero lint diagnostics, the racy 150ms MCP bridge timing assert replaced by a deterministic barrier, load-sensitive guards carry documented `ponytail:` ceilings, machine-readable `lint-report.sarif` + `unused-report.json` retained by CI); no runtime contract delta (compat gate at 0.2.3: version literal only), no migration; then plan 022 the concurrent-state-and-durability-integrity cut: atomic model-budget reservation (`ModelRouterStateStore.reserveBudget`/`commitBudget`/`releaseBudget` with fencing tokens, `reservationTtlMs` expiry and unknown-usage reconciliation, rate/budget key-map caps with LRU eviction that never drops a held reservation), atomic conversation metadata (`SessionRecord.version` + `appendSession` `expectedVersion` CAS across Postgres/SQLite — create-only `0`, exact-version `N>0`, legacy last-write-wins when omitted; `SessionMetadataConflictError` `metadata_conflict` with versions only, HTTP 409; concurrent create/branch/archive single-statement with branch caps inside the CAS, archive wins, deleted rows never resurrect), single-consumer `EventMultiplexer` (`EventMultiplexerError` `ERR_PRISM_EVENT_MULTIPLEXER_SINGLE_CONSUMER` instead of silent queue sharing), restart-stable NATS durable consumer identity (`prism_<hmac16>` with no random suffix — crash-resumed subscribe continues from the last ack, orphaned 0.2.1 consumers reclaimed on clean stop), and bounded non-durable active-run registries (sweep + fail-closed 512 cap `ERR_PRISM_WORKFLOW_RUN_REGISTRY_OVERFLOW`); new regression surface `scripts/phase22-security.test.mjs` (4 blockers + gate accounting over built public entrypoints) + packed plain-JS `security22.mjs` consumer + the `@arnilo/prism/testing/state-concurrency-conformance` harness (7 probes across memory/Postgres/SQLite/NATS legs, no timing-only sleeps) + the `scripts/phase22-conformance.test.mjs` gate; additive-only compat (new exports only, no removals); forward-only migrations 008 (`prism_sessions.version`) and 003 (`prism_model_router_budgets.reservations`); migration `0.2.1 → 0.2.2`; then plan 021 the provider-completion-and-outbound-trust-boundaries cut: strict stream completion is the shared OpenAI-compatible default (truncated streams fail `incomplete_delta`, explicit `strictCompletion: false` opt-out), bounded success bodies via `readBoundedResponseJson` on all discovery/quota/embeddings/upload/OAuth JSON endpoints (65,536-byte ceiling, depth/property/shape caps), DNS-pinned OIDC JWKS/OPA/content fetches through the core `pinnedFetch` primitive with 3xx redirects rejected outright (private/metadata answers fail closed `ssrf_denied`), shared bounded OAuth device/token polling (`pollDeviceCodeToken`) across provider-openai and credentials-node, and the four edge fixes (Azure/Vertex credential-once, Bedrock duplicate-case/repeated-query SigV4 canonicalization, OpenAI upload failed-DELETE retention, cache `__overflow__` tokens-only); public-entrypoint threat-suite `scripts/phase21-security.test.mjs` + packed plain-JS consumer; additive-only compat (MCP transport helpers re-exported from core, no removals); migration `0.2.0 → 0.2.1`; then plan 020 the fail-closed runtime-and-sandbox-security cut on the 0.2.x review-remediation line: durable-resume decision validation in core (`assertValidAgentRunResume` — unknown decisions/malformed batches fail closed with `ERR_PRISM_DECISION_*` before any state claim, checkpoint write, or tool execution; server parser remains defense in depth), isolated work-tool subprocess environments (`@arnilo/prism-work-tools` — fixed base allow-list + explicit env + forced HOME/telemetry + late-bound per-identity tokens, 64-name/64-KiB caps, absolute binary/configDir, linear output capture), and explicit sandbox capabilities (`@arnilo/prism-coding-security` — `SandboxAdapter.capabilities` with omission-is-false fail-closed resolution, `SandboxCodingComposition.capabilities` from verified wiring, `containmentClaim` deprecated as the conservative projection; Docker reports only verified controls, native reports filesystem/process/privilege `false`); public-entrypoint security conformance (`scripts/phase20-security.test.mjs`, wired into `security:threat-suites`), packed plain-JS consumer regressions, and the sandbox-browser workflow's fail-loud Docker/native capability evidence gate — 0.2.0 never ships while a blocker is skipped; migration and rollback notes in `docs/migration.md` `0.1.7 → 0.2.0`, store-compatible with 0.1.7 in both directions; 0.1.7 was the performance-and-DX patch — dependency-free `createCacheTelemetry()` per-provider/model cache hit/miss aggregator (bounded cardinality with `__overflow__`, token counters/rates only, host-activated), host-configurable `ModelRouterSelectionPolicy` on `createModelRouter` with the reference `createCostLatencySelection` (ModelCost rank then in-memory latency EMA, default ordered behavior byte-identical), `prism providers add <name>` OpenAI-compatible provider scaffold (manifest/provider/models/cache/conformance test/docs stub, npm-name + traversal + symlink-escape validation, placeholders only), and the async `AgUiProjection` verification closeout (plan 009 Task 15 evidence recorded, no new code); plan 017 the documented breaking cut — deprecated-option removal with `docs/migration.md` `0.1.4 → 0.1.5` section and reviewed compat-baseline regeneration via `--allow-break` then `--update-baseline`: the inert provider request knobs, `RunOptions.maxToolRounds`, observational-memory flat settings keys + top-level worker aliases, `ReadToolOptions.autoResizeImages`, `INIT_PROVIDERS`; all removals fail closed naming their replacement; plan 016 internal god-module split — `agents.ts`/`contracts.ts` reorganized behind barrel re-exports with a byte-identical public entry surface, measured tree-shaking improvement in `scripts/phase16-baseline.json`, and additive `@arnilo/prism-browser` Chrome DevTools Protocol capabilities — `browser_evaluate`/`browser_observe` and `block_urls`/`unblock_urls`/`throttle`/`emulate` act actions; plan 015 dead-code and deprecation hygiene on the frozen 0.1.x line — parameterized benchmark runner `scripts/benchmark.mjs` absorbing the per-version runners, archived review-coverage evidence in `docs/_evidence/`, non-blocking unused-code sweep `npm run sweep:unused`, opt-in checkpoint persistence for loaded-skill names and read-path sets; plan 014 Alibaba provider enrichment — embeddings, video input, verified compatible-mode surface decision table; plan 013 post-release hardening — build single-flight, MCP SSE relay test, combined coverage summary, canonical manifest-count narrative, ACP modes/config persistence guidance; Phase 12 release-candidate hardening; plan 012 — freeze manifest, compatibility matrix, upgrade matrix, packed-install e2e journeys, restart-recovery evidence, capacity envelopes, security policy), exact-peer/install/tarball rules, deterministic resumable publication and publish dry-run, frozen 0.1.x compatibility and support matrix (Node/PostgreSQL/platform/provider/protocol pins and unsupported combinations, machine-checked against `scripts/phase12-freeze-manifest.json`), protected PostgreSQL gate, pinned supply-chain gates, offline tests, the 0.0.15 provider/AI-SDK/RAG/memory protected live-canary matrix, and sandbox-browser Docker/Playwright gates. 0.2.6 (plan 026 Task 7) adds the protected coding journey: `scripts/phase26-coding-journey.test.mjs` runs a packed consumer through real provider calls, a digest-pinned Docker sandbox, the durable Postgres worktree lifecycle, provider-driven ACP edits with policy approval, named checks with `diagnosticDelta`, patch review over the server ArtifactService, cross-replica process recovery, durable cancellation, real GitHub PR push/reconcile/cleanup, host Playwright inspection, and the host PTY adapter (frozen profile) — the retained `scripts/phase26-coding-journey-report.json` gates release evidence (pass/blocked/protected, never a passing skip).
+- [Migrate 0.4 to 0.5](migrate-to-0.5.md): the complete 0.5.x migration guide (plans 055–066) — 0.5.0 lockstep plus **0.5.1** additive request construction (`thinkingLevel` field, kernel session/cache defaults, OpenCode Go `ProviderRequirementError`) — plus rollback.
 - [Migrate legacy 0.3 packages to 0.4](migrate-to-0.4.md): complete breaking package-reorganization guide — all retired package/import mappings, profile replacements, optional peers and host binaries, security boundaries, rollback, and npm `legacy`/deprecation lifecycle.
 - [0.1.0 / 1.0 readiness gates](0.1.0-readiness.md): command-per-gate 1.0 readiness table — frozen API surface + compat gate, migration/docs tripwires, budget table, live-suite matrix, security matrix, current-line status (**0.2.5** current line; 0.1.7 terminal 0.1.x baseline), signed-publication/live-canary prerequisites for 1.0, and Phase 12 demand-evidence entry criteria.
 - [Review coverage archive](_evidence/): per-phase evidence freezes (plans 067–079, releases 0.0.4–0.0.16, 0.2.7 ERP evidence) — traceability matrices, provider validation, capability/primitive/limit matrices, benchmark budgets, and artifact-diet findings; tarball-excluded, kept in-repo for audit.
@@ -177,15 +179,15 @@ The generated inventory below derives from [`scripts/package-truth.json`](../scr
 
 | package | version | notes |
 | --- | --- | --- |
-| `@arnilo/prism` | 0.5.0 | core — runtime, CLI/RPC, templates, docs |
-| `@arnilo/prism-coding-tools` | 0.5.0 | family — /agent, /security, /document-reader, /openapi, /computer-use-linux, /dev, /caveman, /ponytail, /impeccable subpaths |
-| `@arnilo/prism-core` | 0.5.0 | family — /runtime, /sessions, /governance, /credentials, /enterprise, /work, /validation subpaths |
-| `@arnilo/prism-providers` | 0.5.0 | family — all provider adapters as `/<adapter>` subpaths |
-| `@arnilo/prism-acp-agent` | 0.5.0 | capability — ACP adapter |
-| `@arnilo/prism-ag-ui` | 0.5.0 | capability — AG-UI/A2A/A2UI adapter |
-| `@arnilo/prism-mcp` | 0.5.0 | capability — MCP client/server/OAuth interop |
-| `@arnilo/prism-memory` | 0.5.0 | capability — memory plus /rag, /compaction/*, /graft, /wiki subpaths |
-| `@arnilo/prism-office` | 0.5.0 | capability — /documents, /sheets, /diagrams subpaths |
-| `@arnilo/prism-web-tools` | 0.5.0 | capability — Brave/Exa/Firecrawl plus peer-gated /browser and /obscura subpaths |
+| `@arnilo/prism` | 0.5.2 | core — runtime, CLI/RPC, templates, docs |
+| `@arnilo/prism-coding-tools` | 0.5.2 | family — /agent, /security, /document-reader, /openapi, /computer-use-linux, /dev, /caveman, /ponytail, /impeccable subpaths |
+| `@arnilo/prism-core` | 0.5.2 | family — /runtime, /sessions, /governance, /credentials, /enterprise, /work, /validation subpaths |
+| `@arnilo/prism-providers` | 0.5.2 | family — all provider adapters as `/<adapter>` subpaths |
+| `@arnilo/prism-acp-agent` | 0.5.2 | capability — ACP adapter |
+| `@arnilo/prism-ag-ui` | 0.5.2 | capability — AG-UI/A2A/A2UI adapter |
+| `@arnilo/prism-mcp` | 0.5.2 | capability — MCP client/server/OAuth interop |
+| `@arnilo/prism-memory` | 0.5.2 | capability — memory plus /rag, /compaction/*, /graft, /wiki subpaths |
+| `@arnilo/prism-office` | 0.5.2 | capability — /documents, /sheets, /diagrams subpaths |
+| `@arnilo/prism-web-tools` | 0.5.2 | capability — Brave/Exa/Firecrawl plus peer-gated /browser and /obscura subpaths |
 <!-- generated:package-truth:inventory end -->
 

package/docs/input-and-prompt-assembly.md

@@ -90,7 +90,7 @@ In cache-aware mode, leading system instructions form the stable boundary before
 - Text attachments and explicit text resources are user messages; inline `audio`/`file`/`document` blocks pass through unchanged on attachments with `content`.
 - Tool results are tool messages containing `tool_result` content; the agent/session runtime uses this to feed dispatched tool results into the next provider turn, placing the assistant `tool_call` and the matching role `tool` `tool_result` before any final assistant content. Cache-aware layout keeps tool results before the current user suffix so it does not split tool transcripts.
 - Middleware runs only when `middleware` is supplied in the context.
-- `assembleProviderInput()` returns a `ProviderRequest` with the caller's model/tools/provider options/metadata/signal and composed messages/context. It also calls `assertMessagesSupportModelCapabilities()` so unsupported `audio`/`file`/`document`/`image` blocks fail with `UnsupportedModalityError` when the model declares `capabilities.input`.
+- `assembleProviderInput()` returns a `ProviderRequest` with the caller's model/tools/provider options/metadata/signal and composed messages/context. It stamps missing `sessionId`/`cacheKey` via `applyDefaultProviderRequestOptions` when `sessionId` is passed (agent sessions always pass `session.id`). It also calls `assertMessagesSupportModelCapabilities()` so unsupported `audio`/`file`/`document`/`image` blocks fail with `UnsupportedModalityError` when the model declares `capabilities.input`.
 - Optional `contextBudget` (at least one of `maxInputTokens` / `maxInputBytes`) runs after default message groups are built and before final flatten. Eviction drops droppable sections first (toolResults → history → summaries → context → skills → attachments; layout-aware). Within `history`, oldest messages drop first. Protected instructions + current user `input` (+ tools catalog) fail closed with `ContextBudgetError` if they alone exceed the budget. When `reportOmissions: true`, attach `ProviderRequest.metadata[CONTEXT_BUDGET_REPORT_METADATA_KEY]` and read via `getContextBudgetReport(request)` (kinds/ids/sizes only — no secrets). Raw session store entries are never deleted.
 - `renderPromptTemplate()` replaces top-level `{{name}}` variables with caller-supplied JSON-compatible values. Strings are inserted directly; numbers, booleans, `null`, arrays, and objects are stringified deterministically with sorted object keys. Missing variables throw by default or stay unchanged with `{ missing: "preserve" }`.
 

package/docs/migrate-to-0.5.md

@@ -1,6 +1,6 @@
 # Migrate Prism 0.4 to 0.5
 
-> **Status: released 2026-09-06** (`v0.5.0` tag). Covers every host-visible change from plan 055 onward: new provider adapters (055), security hardening (056), the dead-export cut (058), dependency majors (062), the MCP 2026-07-28 adoption (063), the CLI real-provider contract (064), and model-aware thinking effort (065).
+> **Status: 0.5.2** (stream-token coalesce, additive on the 2026-09-07 `v0.5.1` tag). 0.5.0 covers plans 055–065. 0.5.1 adds kernel provider-request construction.
 
 ## What changes
 
@@ -105,15 +105,37 @@ What to do:
 
 Contract reference: [`docs/thinking-and-reasoning.md`](thinking-and-reasoning.md); per-provider declared levels + wire fields on each `docs/providers/*.md` page.
 
+## 8. Provider request construction — additive (plan 066 / 0.5.1)
+
+Prism now constructs a valid wire request for every generate site it owns. Hosts pick provider + model + intent. Host request policies are overlays and are never required for success.
+
+Additive surface:
+
+| Change | Behavior |
+| --- | --- |
+| `applyDefaultProviderRequestOptions` | Fill-if-missing `sessionId`/`cacheKey`; default `{ system_prompt, last_stable_message }` + `cacheRetention: "short"` on `cache_control` / `explicitBreakpoints` models |
+| `AgentConfig.thinkingLevel` / `RunOptions.thinkingLevel` | Session thinking intent (run overrides agent); snapped via `applyThinkingLevelForModel` |
+| `ProviderRequirementError` (`ERR_PRISM_PROVIDER_REQUIREMENT`) | OpenCode Go throws **before fetch** when `sessionId`/`cacheKey` is missing — not an opaque upstream 400. Message has no request body. |
+| OM vs compaction ids | Observational-memory workers use derived `om:{session.id}`; LLM compaction uses the agent session id |
+
+What to do:
+
+1. You can drop `createSessionCachePolicy()` from Clay / host agent config if it existed only to inject session correlation.
+2. Prefer `createAgent({ thinkingLevel: "low" })` over hand-merging `providerOptions.compat`.
+3. Raw `provider.generate()` to OpenCode Go without `options.sessionId` now fails closed with `ProviderRequirementError` instead of HTTP 400.
+4. Custom generate sites should call `applyDefaultProviderRequestOptions(request, { sessionId, thinkingLevel })`.
+5. Nothing persisted changes. Session/cache keys are correlation ids, never secrets.
+
 ## Upgrade steps
 
-1. Bump every `@arnilo/*` dependency/peer to `^0.5.0`.
+1. Bump every `@arnilo/*` dependency/peer to `^0.5.1` (0.5.0 hosts: `^0.5.0` still works until you want construction).
 2. Build; if the compiler flags a removed symbol above, apply the replacement from the table.
 3. If you host MCP: move SDK imports to the v2 modular packages (section 5).
 4. If you spawn child processes with ambient env: pass env explicitly (section 2).
 5. If you construct durable stores: pass the tenant scope (section 2).
-6. If you set thinking levels: move to `applyThinkingLevelForModel` (section 7).
+6. If you set thinking levels: prefer `AgentConfig.thinkingLevel` / `RunOptions.thinkingLevel` (section 8); `applyThinkingLevelForModel` remains for custom generate sites (section 7).
 7. Run your suite. No persisted-data migration exists or is needed.
+8. After 0.5.1: drop host-only `createSessionCachePolicy` if it existed only for OpenCode Go / session headers (section 8).
 
 ## Rollback