transcript-grep

1# Transcript Grep
2 
3Find where a pattern appears in a session transcript and show the matches in context.
4 
5## Input
6 
7The user provides: **$ARGUMENTS**
8 
9Interpreted as a session reference plus a search pattern, e.g.
10`<session-id> "rate limit"` or `latest TypeError`. Parsing rules:
11- The session reference is the first token if it looks like an id, or the words
12  `latest`/`last` (most recently updated session).
13- The remainder is the search pattern (string or regex, quoted if it contains spaces).
14- If no session is given, default to the most recent session.
15 
16## Data Sources
17 
18| Endpoint | Returns |
19|----------|---------|
20| `GET /api/sessions?limit=N` | session list to resolve `latest`/`last` and to confirm the id exists |
21| `GET /api/sessions/:id/transcript` | the ordered transcript messages (role, content, tool calls/results, timestamps) for the session |
22 
23## Report Sections
24 
25### 1. Resolve the session
26If `latest`/`last` (or no id), call `GET /api/sessions?limit=1`. Otherwise verify
27the id with `GET /api/sessions?limit=1000` (or `GET /api/sessions/:id`). Report
28the resolved id, status, and model before searching.
29 
30### 2. Fetch and search
31Call `GET /api/sessions/:id/transcript`. Walk the messages in order and match the
32pattern against message text, tool_name, and tool input/output content.
33Case-insensitive by default; treat the pattern as a regex if it contains regex
34metacharacters, otherwise as a literal substring.
35 
36### 3. Matches with context
37For each match show:
38 
39```
40…