Handle Gemini assistant message events in JSONL parser (#5143)

## Thinking Path

> - Paperclip orchestrates AI agents for zero-human companies, including
agents
>   running the Gemini CLI (`gemini-local` adapter)
> - The Gemini CLI emits a JSONL event stream during a run that the
adapter
> parses to extract the assistant's response text, tool results, and
usage
> - Recent versions of the Gemini CLI emit assistant responses as
> `{ "type": "message", "role": "assistant", "content": ... }` events in
>   addition to the previously-handled event shapes
> - The parser was not handling the new event type, so the assistant's
actual
> response text was being silently dropped from parsed output. Callers
ended
>   up with empty assistant messages even when Gemini had successfully
>   responded
> - This PR teaches the parser to recognize `{type: "message", role:
>   "assistant"}` events and extract their content text via the same
>   `collectMessageText` helper used for other message-shaped events
> - The benefit is that Gemini runs surface the assistant's real
response in
> downstream consumers (issue comments, run logs, downstream agent
context)
>   instead of vanishing

## What Changed

- `packages/adapters/gemini-local/src/server/parse.ts`: in
`parseGeminiJsonl(...)`, add a branch for `event.type === "message"`
with
  `role === "assistant"` that calls
  `messages.push(...collectMessageText(event.content))`.
- `packages/adapters/gemini-local/src/server/parse.test.ts`: ~19 lines
of
  coverage for the new branch.

## Verification

- `pnpm --filter @paperclipai/adapter-gemini-local test -- parse`
- Manual QA: run a Gemini agent on an issue, confirm the assistant's
response
appears as the issue comment / run output. Before this fix the comment
was
  empty even when the run completed successfully.

## Risks

- Tightly scoped: 8 lines of production code in one parser branch. No
effect
  on existing event shapes or other adapters.
- If the Gemini CLI changes its event schema again, this branch may need
to be
  revisited — but adding it is strictly additive over current behaviour.

## Model Used

- OpenAI GPT-5.4 (reasoning effort: high) via Codex CLI
- Provider: OpenAI
- Used to author the code changes in this PR

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [ ] If this change affects the UI, I have included before/after
screenshots — N/A
- [ ] I have updated relevant documentation to reflect my changes — N/A
- [x] I have considered and documented any risks above
- [x] I will address all Greptile and reviewer comments before
requesting merge

packages/adapters/gemini-local/src/server/parse.test.ts

@@ -0,0 +1,46 @@
+import { describe, expect, it } from "vitest";
+import { parseGeminiJsonl } from "./parse.js";
+
+describe("parseGeminiJsonl", () => {
+  it("collects assistant text from message events with string content", () => {
+    const stdout = [
+      '{"type":"init","session_id":"session-1"}',
+      '{"type":"message","role":"user","content":"Respond with hello."}',
+      '{"type":"message","role":"assistant","content":"hello","delta":true}',
+      '{"type":"result","status":"success"}',
+    ].join("\n");
+
+    const parsed = parseGeminiJsonl(stdout);
+
+    expect(parsed.sessionId).toBe("session-1");
+    expect(parsed.summary).toBe("hello");
+    expect(parsed.errorMessage).toBeNull();
+  });
+
+  it("collects assistant text from message events with structured object content", () => {
+    const stdout = [
+      '{"type":"init","session_id":"session-2"}',
+      '{"type":"message","role":"assistant","content":{"content":[{"type":"text","text":"first part"},{"type":"text","text":"second part"}]}}',
+      '{"type":"result","status":"success"}',
+    ].join("\n");
+
+    const parsed = parseGeminiJsonl(stdout);
+
+    expect(parsed.sessionId).toBe("session-2");
+    expect(parsed.summary).toBe("first part\n\nsecond part");
+    expect(parsed.errorMessage).toBeNull();
+  });
+
+  it("ignores non-assistant message events", () => {
+    const stdout = [
+      '{"type":"message","role":"user","content":"hidden user input"}',
+      '{"type":"message","role":"system","content":"hidden system note"}',
+      '{"type":"message","role":"assistant","content":"visible response"}',
+      '{"type":"result","status":"success"}',
+    ].join("\n");
+
+    const parsed = parseGeminiJsonl(stdout);
+
+    expect(parsed.summary).toBe("visible response");
+  });
+});

packages/adapters/gemini-local/src/server/parse.ts

@@ -121,6 +121,19 @@ export function parseGeminiJsonl(stdout: string) {
       continue;
     }
 
+    if (type === "message") {
+      const role = asString(event.role, "").trim().toLowerCase();
+      if (role === "assistant") {
+        // Mirror the assistant-event handling above: collect every assistant
+        // message including deltas. Gemini CLI emits these as discrete final
+        // messages (one per assistant turn), not as cumulative streaming
+        // tokens, so collecting all of them produces the expected concatenated
+        // turn-by-turn summary rather than duplicated text.
+        messages.push(...collectMessageText(event.content));
+      }
+      continue;
+    }
+
     if (type === "result") {
       resultEvent = event;
       accumulateUsage(usage, event.usage ?? event.usageMetadata);