feat: raw SSE/JSON passthrough fixtures for LLM endpoints

CHANGELOG.md

@@ -11,6 +11,7 @@
 - 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))
 
 ### Fixed
 

docs/aws-bedrock/index.html

@@ -55,6 +55,11 @@ <h1>AWS Bedrock</h1>
           against the Bedrock-format requests, returning responses in the authentic Bedrock format
           including AWS Event Stream binary framing for streaming.
         </p>
+        <p>
+          To send events or fields aimock does not model yet, use a
+          <a href="/raw-passthrough">raw passthrough fixture</a> with
+          <code>wire: "bedrock-invoke"</code> or <code>wire: "bedrock-converse"</code>.
+        </p>
 
         <h2>How It Works</h2>
         <p>

docs/chat-completions/index.html

@@ -54,6 +54,11 @@ <h1>OpenAI Chat Completions</h1>
           non-streaming JSON responses, including text content and tool calls. This is the most
           commonly used endpoint.
         </p>
+        <p>
+          To send events or fields aimock does not model yet, use a
+          <a href="/raw-passthrough">raw passthrough fixture</a> with
+          <code>wire: "openai-chat"</code>.
+        </p>
 
         <h2>Endpoint</h2>
         <table class="endpoint-table">

docs/claude-messages/index.html

@@ -54,6 +54,11 @@ <h1>Anthropic Claude Messages API</h1>
           streaming SSE using <code>event:</code> + <code>data:</code> format, including content
           blocks for text and tool use.
         </p>
+        <p>
+          To send events or fields aimock does not model yet, use a
+          <a href="/raw-passthrough">raw passthrough fixture</a> with
+          <code>wire: "anthropic"</code>.
+        </p>
 
         <h2>Endpoint</h2>
         <table class="endpoint-table">

docs/cohere/index.html

@@ -54,6 +54,10 @@ <h1>Cohere v2 Chat API</h1>
           streaming events and dual usage tracking (<code>billed_units</code> and
           <code>tokens</code>).
         </p>
+        <p>
+          To send events or fields aimock does not model yet, use a
+          <a href="/raw-passthrough">raw passthrough fixture</a> with <code>wire: "cohere"</code>.
+        </p>
 
         <h2>Endpoint</h2>
         <table class="endpoint-table">

docs/fixtures/index.html

@@ -451,6 +451,14 @@ <h2>Response Types</h2>
                 usage envelopes
               </td>
             </tr>
+            <tr>
+              <td>Raw</td>
+              <td>raw.wire, raw.events?, raw.json?, raw.status?, raw.headers?, raw.done?</td>
+              <td>
+                Provider events or JSON sent as written, framed for one wire. See
+                <a href="/raw-passthrough">Raw Passthrough Fixtures</a>.
+              </td>
+            </tr>
           </tbody>
         </table>
 

docs/gemini-interactions/index.html

@@ -56,6 +56,11 @@ <h1>Gemini Interactions API</h1>
           <code>outputs[]</code> instead of nested <code>candidates[].content.parts[]</code>, and
           typed SSE events with an <code>event_type</code> field inside each JSON payload.
         </p>
+        <p>
+          To send events or fields aimock does not model yet, use a
+          <a href="/raw-passthrough">raw passthrough fixture</a> with
+          <code>wire: "gemini-interactions"</code>.
+        </p>
 
         <h2>Endpoint</h2>
         <table class="endpoint-table">

docs/gemini/index.html

@@ -54,6 +54,10 @@ <h1>Google Gemini</h1>
           <code>streamGenerateContent</code> (SSE) endpoints, plus Gemini Live over WebSocket. The
           same fixtures drive all three transports.
         </p>
+        <p>
+          To send events or fields aimock does not model yet, use a
+          <a href="/raw-passthrough">raw passthrough fixture</a> with <code>wire: "gemini"</code>.
+        </p>
 
         <h2>Endpoints</h2>
         <table class="endpoint-table">

docs/ollama/index.html

@@ -54,6 +54,12 @@ <h1>Ollama</h1>
           <code>/api/tags</code> endpoints with NDJSON streaming, matching Ollama's wire format
           including its key differences from OpenAI.
         </p>
+        <p>
+          To send events or fields aimock does not model yet, use a
+          <a href="/raw-passthrough">raw passthrough fixture</a> with
+          <code>wire: "ollama"</code> for <code>/api/chat</code> or
+          <code>wire: "ollama-generate"</code> for <code>/api/generate</code>.
+        </p>
 
         <h2>Endpoints</h2>
         <table class="endpoint-table">

docs/openrouter-chat/index.html

@@ -59,6 +59,11 @@ <h1>OpenRouter Chat &amp; Router</h1>
           <code>cost</code>. Callers on the plain OpenAI base (<code>/v1/&hellip;</code>) are left
           byte-for-byte unchanged.
         </p>
+        <p>
+          To send events or fields aimock does not model yet, use a
+          <a href="/raw-passthrough">raw passthrough fixture</a> with
+          <code>wire: "openai-chat"</code>.
+        </p>
 
         <div class="info-box">
           <p>