chore: release v1.47.0

.claude-plugin/marketplace.json

@@ -9,7 +9,7 @@
       "source": {
         "source": "npm",
         "package": "@copilotkit/aimock",
-        "version": "^1.46.0"
+        "version": "^1.47.0"
       },
       "description": "Fixture authoring skill for @copilotkit/aimock — LLM, multimedia (image/TTS/transcription/video), MCP, A2A, AG-UI, vector, embeddings, structured output, sequential responses, streaming physics, record/replay, agent loop patterns, and debugging"
     }

.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "aimock",
-  "version": "1.46.0",
+  "version": "1.47.0",
   "description": "Fixture authoring guidance for @copilotkit/aimock — LLM, multimedia, MCP, A2A, AG-UI, vector, and service mocking",
   "author": {
     "name": "CopilotKit"

CHANGELOG.md

@@ -1,28 +1,17 @@
 # @copilotkit/aimock
 
-## [Unreleased]
+## [1.47.0] - 2026-10-26
 
 ### Added
 
-- Fixture `citations` serve OpenAI Responses `url_citation` annotations; fixture `files` serve Gemini `inlineData` parts (#550 by @abhiaiyer91)
-- Fixture `citations` also serve Chat Completions `url_citation` annotations (`message.annotations`, one streamed `delta.annotations` chunk), Anthropic `web_search_result_location` citations on text blocks (`citations_delta` when streaming), and Gemini `groundingMetadata` (`groundingChunks` + `groundingSupports`, byte offsets). A citation with `type: "file"` (`fileId`, `filename`, optional `index`, which defaults to the end of the text) serves an OpenAI Responses `file_citation` annotation on `output_text`, streamed through `response.output_text.annotation.added`; Chat Completions, Anthropic and Gemini skip it. Closes #547.
-- Fixture `files` serve OpenAI Responses `image_generation_call` output items (`result` holds the base64 bytes), streamed with the `response.image_generation_call.*` events. Chat Completions and Anthropic Messages reject a fixture with `files` with a 500 carrying `aimock_unsupported_generated_file` (new `UnsupportedGeneratedFileError`). Closes #548.
-- Malformed fixture `citations` or `files` (not an array, a missing or mistyped field, a non-integer offset, an offset outside the text, or citations on a turn with no text: tool calls only, `blocks` with no text block, or empty content) answer a 500 before any content is written: `aimock_invalid_fixture_citation` or `aimock_invalid_fixture_file`. A non-`image/*` file on the OpenAI Responses API answers a 500 with `aimock_unsupported_generated_file`. This is the same on every wire that reads these keys, with or without a misbehavior fault: the fixture is checked on its original turn before any fault applies (only an invalid misbehavior config answers its own 400 or 501 first). A valid fixture under a fault that changes the reply text is served without its `citations`. Only Chat Completions, Anthropic Messages, Gemini and OpenAI Responses read these keys; other wires ignore them.
-- Fixture load validation warns about malformed `citations` and `files`, with the same problem description the 500 carries (the 500 message adds an `aimock: invalid fixture` prefix; the warning adds which 500 the requests answer). The fixture still loads.
-- `InvalidFixtureOutputError` (the error behind `aimock_invalid_fixture_citation` and `aimock_invalid_fixture_file`) is exported from `@copilotkit/aimock`.
-- Opt-in fixture `nonStreamingTimingAllProviders: true` delays non-streaming replies on OpenAI chat, Anthropic, Responses, Gemini/Vertex, Gemini Interactions, Cohere, Bedrock invoke/converse and Ollama; `nonStreamingTiming` is unchanged (OpenAI chat only); error replies are never delayed. On the OpenAI Responses API the wait also counts the stream frames that fixture `citations` and generated `files` add
-- Raw passthrough fixtures: a `raw` response (`wire`, `events`, `json`, optional `status`, `headers`, and `done` on `openai-chat`) sends provider events or JSON exactly as written, with only the named wire's framing, on the HTTP LLM wires (OpenAI Responses and Chat Completions, Anthropic, Gemini/Vertex, Gemini Interactions, Cohere, Ollama `/api/chat` as `ollama` and `/api/generate` as `ollama-generate`, Bedrock invoke and converse). A raw fixture matches only its own wire. A request whose mode has no body answers that wire's 500 with `aimock_raw_mode_unavailable`; an invalid raw fixture added in code answers a 500 with `aimock_raw_fixture_invalid`, and `--validate-on-load` reports it at load. Streaming timing, truncation, disconnects and chaos apply; misbehavior faults skip raw fixtures. A non-streaming raw reply follows `nonStreamingTiming` like a typed fixture: `nonStreamingTiming: true` delays it on OpenAI Chat Completions only, `nonStreamingTimingAllProviders: true` on every provider; a raw reply with status 400 or above is never delayed, and with a `json` it answers JSON even to a streaming request. WebSocket Responses answers a raw fixture with an error event with the code `aimock_raw_mode_unavailable`. New exported types `RawResponse`, `RawWireId` and `WireId` ([#549](https://github.com/CopilotKit/aimock/issues/549))
+- Fixture `citations` serve sources on Responses, Chat Completions, Claude and Gemini (#550, #578)
+- Fixture `files` serve generated images on Gemini and OpenAI Responses (#550, #578)
+- Raw passthrough fixtures send provider SSE events or JSON exactly as written (#580)
+- Opt-in `nonStreamingTimingAllProviders` delays non-streaming replies on every provider (#579)
 
 ### Fixed
 
-- Misbehavior faults on Chat Completions, Anthropic Messages, Gemini and the OpenAI Responses API (HTTP and WebSocket): a fixture the wire rejects (generated `files` on Chat Completions or Anthropic, a non-`image/*` file on Responses, malformed `citations` or `files`) is never faulted. It takes the normal path, is journaled as a 500 that keeps its fixture, and consumes no fault `times` budget or seed ordinal; `aimock_misbehavior_total` does not count it. A non-stream Chat Completions fault is journaled before its timing wait.
-- Journal accuracy: a client that hangs up during the timing wait of any non-stream Chat Completions reply (faulted or not) is journaled as interrupted, not as served.
-- Client disconnects stop delivery (no more chunks or waits) on OpenAI chat, Anthropic, Responses, Gemini/Vertex, Gemini Interactions, Cohere, Bedrock, Ollama, transcription streams and the Responses, Realtime and Gemini Live WebSockets
-- Client disconnects on those surfaces are journaled as `interrupted` with `interruptReason: "client aborted"` (HTTP `status: 0` when nothing was sent); aimock-caused teardowns record `"disconnect"`. Journal snapshots of hung-up requests now carry these fields
-- WebSocket: a client TCP FIN without a close frame now closes the connection at once (1006) and ends the turn
-- Daily drift: the OpenAI Responses K9 reasoning-exhaustion probes (HTTP and WebSocket) request `gpt-5.4-mini`. OpenAI retired `o4-mini` on 2026-10-23 (its `/v1/models` `shutdown_date`), and it has answered `404 model_not_found` since. The probe model is one constant, `OPENAI_K9_PROBE_MODEL`. The usage check accepts `output_tokens` equal to `output_tokens_details.reasoning_tokens` (gpt-5.4-mini spends the 32-token cap on reasoning; o4-mini reported 0). The event-order check is unchanged, and the retained o4-mini replay fixtures are still graded against o4-mini. Drift harness only; aimock behavior is unchanged (#584).
-- Daily drift: a preflight checks every model the live drift probes pin (`src/__tests__/drift/probe-models.ts`) against the provider's own retirement data before the run. A retired model fails the run with `probe model X retired on DATE — update <constant>` instead of looking like API drift; a shutdown date within 30 days is a warning in the job summary and in Slack. The Gemini embeddings canary now probes `gemini-embedding-001`; `text-embedding-004` answers 404. Drift harness only; aimock behavior is unchanged.
-- Docker image: the base image is pinned to `node:22.23.4-alpine` by digest. Node 22.23.4 fixes CVE-2026-111497 (Brotli decompression memory bug); the 1.46.0 image shipped Node 22.23.3.
+- Client disconnects stop and journal every LLM reply; Docker image on Node 22.23.4 (#579, #576)
 
 ## [1.46.0] - 2026-10-20
 

README.md

@@ -92,13 +92,16 @@ Run them all on one port with `npx @copilotkit/aimock --config aimock.json`, or
 - **[Native model catalogs and token counts](https://aimock.copilotkit.dev/claude-messages#model-catalog)** — Anthropic `GET /v1/models` (selected by `anthropic-version`, or `x-api-key` without `Authorization`; the list route needs `policy.modelCatalog: "native"` and otherwise stays the OpenAI list) and Gemini `GET /v1beta/models` list and detail routes with provider paging, built from fixture model IDs with synthetic metadata; `POST /v1/messages/count_tokens` and Gemini `:countTokens` return a deterministic estimate of about 1 token per 4 characters of messages (plus tool definitions), minimum 1. These routes never proxy or record
 - **Context-Based Fixture Routing** — `X-AIMock-Context` header scopes fixtures per integration; fixtures with `match.context` only match requests carrying that context, fixtures without it remain shared
 - **[Drift Detection](https://aimock.copilotkit.dev/drift-detection)** — Daily CI validation against real APIs
-- **[Streaming Physics](https://aimock.copilotkit.dev/streaming-physics)** — Configurable `ttft`, `tps`, and `jitter`
+- **[Streaming Physics](https://aimock.copilotkit.dev/streaming-physics)** — Configurable `ttft`, `tps`, and `jitter`; opt in with `nonStreamingTimingAllProviders: true` to give non-streaming replies the same timing on every LLM provider
+- **[Client Disconnects](https://aimock.copilotkit.dev/error-injection#client-disconnects)** — When the client hangs up, every LLM provider (HTTP and WebSocket) stops sending and journals the request as `interrupted`, so you can test cancel and abort paths
 - **[WebSocket APIs](https://aimock.copilotkit.dev/websocket)** — OpenAI Realtime (GA protocol with models: gpt-realtime, gpt-realtime-2, gpt-realtime-1.5, gpt-realtime-mini; transcription/translation via gpt-4o-transcribe, gpt-4o-mini-transcribe, whisper-1; image input; commentary phase), Responses WS, Gemini Live
 - **[GPT-Live](https://aimock.copilotkit.dev/websocket#openai-live)** — Mock, record, and replay primary WebSocket sessions at `/v1/live/sessions` in client and managed modes, with fixture-backed audio and backend tool continuation. Saved fixtures replay offline; aimock does not synthesize speech. This voice surface is separate from OpenAI text-model family support; WebRTC/SDP and sideband connections are outside this scope.
 - **[Prometheus Metrics](https://aimock.copilotkit.dev/metrics)** — Request counts, latencies, fixture match rates
 - **[Docker + Helm](https://aimock.copilotkit.dev/docker)** — Container image and Helm chart for CI/CD
 - **[Vitest & Jest Plugins](https://aimock.copilotkit.dev/test-plugins)** — Zero-config `useAimock()` with auto lifecycle and env patching
 - **[Response Overrides](https://aimock.copilotkit.dev/fixtures)** — Control `id`, `model`, `usage`, `finishReason` in fixture responses
+- **[Citations and Generated Files](https://aimock.copilotkit.dev/fixtures#citations-and-files)** — Fixture `citations` serve source citations on OpenAI Responses (URL and file), Chat Completions, Claude and Gemini; fixture `files` serve generated images on the Responses API and Gemini. Each uses the provider's own format, streaming and non-streaming
+- **[Raw Passthrough](https://aimock.copilotkit.dev/raw-passthrough)** — A `raw` fixture sends provider SSE events or JSON exactly as written on any HTTP LLM wire, for fields aimock does not model yet; timing, chaos and disconnects still apply
 - **[Ordered Blocks](https://aimock.copilotkit.dev/fixtures#ordered-blocks)** — A `blocks` array streams text and tool calls in any order (tool-first or interleaved); blocks-only fixtures are first-class, and the recorder captures order from genuinely tool-first/interleaved streams
 - **[Namespaced and Custom Tool Calls](https://aimock.copilotkit.dev/responses-api#namespaced-and-custom-tool-calls)** — Responses API fixtures can return namespaced function calls and custom tool calls (`custom_tool_call`) over HTTP streaming, non-streaming and WebSocket, and can match on `toolNamespace`. This lets you script OpenAI Codex CLI's namespaced MCP and sub-agent tools and its freeform `apply_patch` tool (with the `responsesTools: "extended"` server option)
 - **[Streaming Usage Chunks](https://aimock.copilotkit.dev/streaming-physics)** — `stream_options.include_usage` support emits a final chunk with token counts, matching OpenAI's streaming usage protocol

charts/aimock/Chart.yaml

@@ -3,4 +3,4 @@ name: aimock
 description: Mock infrastructure for AI application testing (OpenAI, Anthropic, Gemini, MCP, A2A, vector)
 type: application
 version: 0.1.0
-appVersion: "1.46.0"
+appVersion: "1.47.0"

docs/chat-completions/index.html

@@ -59,6 +59,11 @@ <h1>OpenAI Chat Completions</h1>
           <a href="/raw-passthrough">raw passthrough fixture</a> with
           <code>wire: "openai-chat"</code>.
         </p>
+        <p>
+          Fixture <code>citations</code> serve <code>url_citation</code> annotations. A fixture with
+          generated <code>files</code> answers a 500, because Chat Completions has no place for
+          them. See <a href="/fixtures#citations-and-files">Citations and generated files</a>.
+        </p>
 
         <h2>Endpoint</h2>
         <table class="endpoint-table">

docs/claude-messages/index.html

@@ -59,6 +59,12 @@ <h1>Anthropic Claude Messages API</h1>
           <a href="/raw-passthrough">raw passthrough fixture</a> with
           <code>wire: "anthropic"</code>.
         </p>
+        <p>
+          Fixture <code>citations</code> serve <code>web_search_result_location</code> citations on
+          text blocks. A fixture with generated <code>files</code> answers a 500, because the
+          Messages API has no place for them. See
+          <a href="/fixtures#citations-and-files">Citations and generated files</a>.
+        </p>
 
         <h2>Endpoint</h2>
         <table class="endpoint-table">

docs/docs/index.html

@@ -262,26 +262,47 @@ <h2>What's New</h2>
 
         <div class="highlight-grid">
           <div class="highlight-card">
-            <span class="highlight-card-title">Model Catalogs &amp; Token Counts</span>
-            <span class="version-note">New in 1.46.0</span>
+            <span class="highlight-card-title">Citations &amp; Generated Images</span>
+            <span class="version-note">New in 1.47.0</span>
             <p class="highlight-card-desc">
-              List and look up Gemini and Anthropic models in their native formats (the Anthropic
-              list is opt-in), and estimate prompt size with <code>count_tokens</code> /
-              <code>countTokens</code>
+              Script source citations on OpenAI, Claude and Gemini replies, and generated images on
+              the Responses API and Gemini, in each provider's own format
             </p>
-            <a href="/claude-messages#model-catalog" class="highlight-card-cta"
+            <a href="/fixtures#citations-and-files" class="highlight-card-cta"
+              >Docs <span>&rarr;</span></a
+            >
+          </div>
+
+          <div class="highlight-card">
+            <span class="highlight-card-title">Raw Passthrough</span>
+            <span class="version-note">New in 1.47.0</span>
+            <p class="highlight-card-desc">
+              Send provider events or JSON exactly as written, for fields aimock does not model yet,
+              with timing, chaos and disconnects still applied
+            </p>
+            <a href="/raw-passthrough" class="highlight-card-cta">Docs <span>&rarr;</span></a>
+          </div>
+
+          <div class="highlight-card">
+            <span class="highlight-card-title">Stream Realism</span>
+            <span class="version-note">New in 1.47.0</span>
+            <p class="highlight-card-desc">
+              Every LLM provider stops sending and journals the request when the client hangs up,
+              and non-streaming replies on every provider can opt in to realistic timing
+            </p>
+            <a href="/error-injection#client-disconnects" class="highlight-card-cta"
               >Docs <span>&rarr;</span></a
             >
           </div>
 
           <div class="highlight-card">
-            <span class="highlight-card-title">Native Auth Errors</span>
+            <span class="highlight-card-title">Native Catalogs &amp; Auth Errors</span>
             <span class="version-note">New in 1.46.0</span>
             <p class="highlight-card-desc">
-              Opt in to provider-native 401 bodies and required-header checks, so you can test how
-              your app handles a bad key or a missing <code>anthropic-version</code>
+              Gemini and Anthropic model lists, token counts, and opt-in provider-native 401s, so
+              you can test model pickers and bad-key handling
             </p>
-            <a href="/claude-messages#authentication-errors" class="highlight-card-cta"
+            <a href="/claude-messages#model-catalog" class="highlight-card-cta"
               >Docs <span>&rarr;</span></a
             >
           </div>
@@ -306,18 +327,6 @@ <h2>What's New</h2>
             >
           </div>
 
-          <div class="highlight-card">
-            <span class="highlight-card-title">Stream Realism</span>
-            <span class="version-note">New in 1.46.0</span>
-            <p class="highlight-card-desc">
-              Anthropic streams stop and journal when the client disconnects, and non-streaming
-              OpenAI replies can opt in to streaming-profile timing
-            </p>
-            <a href="/streaming-physics#non-streaming" class="highlight-card-cta"
-              >Docs <span>&rarr;</span></a
-            >
-          </div>
-
           <div class="highlight-card">
             <span class="highlight-card-title">Responses API Tools</span>
             <p class="highlight-card-desc">
@@ -336,15 +345,6 @@ <h2>What's New</h2>
             </p>
             <a href="/vector-stores" class="highlight-card-cta">Docs <span>&rarr;</span></a>
           </div>
-
-          <div class="highlight-card">
-            <span class="highlight-card-title">GPT-Live Sessions</span>
-            <p class="highlight-card-desc">
-              Mock, record, and replay OpenAI GPT-Live sessions, with message, audio, and lifetime
-              limits
-            </p>
-            <a href="/websocket#openai-live" class="highlight-card-cta">Docs <span>&rarr;</span></a>
-          </div>
         </div>
 
         <!-- ─── The Suite (compact table) ───────────────────────────── -->