Index Cursor, opencode and Gemini CLI sessions

.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "agsearch",
-  "description": "Search your past Claude Code and Codex sessions from inside Claude",
+  "description": "Search your past Claude Code, Codex, Cursor, opencode and Gemini CLI sessions from inside Claude",
   "version": "0.1.0",
   "author": { "name": "Dev Dalia" },
   "homepage": "https://github.com/devcodes9/agsearch",

CHANGELOG.md

@@ -11,8 +11,33 @@ migration in the same line.
 
 ## [Unreleased]
 
+### Added
+
+- **Cursor, opencode and Gemini CLI sessions are indexed, searched and resumed** alongside
+  Claude Code and Codex, labelled `cu`, `oc` and `gm`. Cursor keeps each chat as a SQLite store under
+  `~/.cursor/chats/`, opened read-only, reading message records and skipping the binary and
+  image blobs beside them; it resumes with `cursor-agent --resume <id>`. Gemini keeps one JSON
+  object per session under `~/.gemini/tmp/`, and resumes with `gemini --session-file <path>`
+  because its `--resume` takes a project-scoped index number rather than a stable id.
+  opencode keeps every session in one database, so it also resumes by id
+  (`opencode run --session <id>`) but is read as a whole.
+  On a 852-session corpus, adding 101 Cursor sessions moved held-out ranking by +0.004, so
+  existing searches are unaffected.
+- **A transcript file may now hold more than one session.** The indexer took the first row's
+  id as the id for the entire file, which is right for a file per session and wrong for a
+  harness that keeps them all in one database: every session but the first was unreachable.
+  It now registers each session a file contains, and reading one filters to it. No change for
+  Claude Code, Codex, Cursor or Gemini, which write one session per file.
+
 ### Changed
 
+- **Harnesses are described by one source table instead of a ternary in five places.** Adding
+  an agent was supposed to be one line, but the file extension, the parser used for preview,
+  the row label, the preview label and the resume command each decided for themselves what a
+  source was, and two of them had already drifted (`codex` against `cx`). They now read one
+  record per harness, so a new agent is a parser plus one entry. Behaviour for Claude Code and
+  Codex is unchanged; the cache format bumps to 7 and reindexes once on first run.
+
 - **Piped output is shaped for the program reading it.** `-n` and `read` are what a coding
   agent sees, and an agent pays per character for what a terminal gets free. Behind the same
   not-a-terminal test the colour seam already uses: session ids shorten to the shortest prefix

README.md

@@ -7,7 +7,7 @@
 
 <p align="center">
   Ranked full-text search across the coding-agent sessions already on your machine.<br>
-  <strong>Claude Code</strong> and <strong>Codex CLI</strong> today, more next.
+  <strong>Claude Code</strong>, <strong>Codex</strong>, <strong>Cursor</strong>, <strong>opencode</strong> and <strong>Gemini CLI</strong>.
 </p>
 
 <p align="center">
@@ -16,8 +16,8 @@
 </p>
 
 agsearch indexes the local transcripts your coding agents already write. Search them in one
-ranked list, preview the matching lines, and resume the original Claude Code or Codex session.
-Everything stays on your machine.
+ranked list, preview the matching lines, and resume the original session in the tool it came
+from. Everything stays on your machine.
 
 <p align="center"><img src="https://raw.githubusercontent.com/devcodes9/agsearch/main/docs/demo.gif" alt="Searching 52 sessions; the second query is misspelled and still lands on the right one" width="100%"></p>
 
@@ -42,10 +42,9 @@ uvx agsearch -n "stripe tax id"
 
 - **Full-conversation search.** Search user prompts and assistant replies, not only titles and
   session metadata.
-- **One list for both tools.** Claude Code and Codex sessions appear together, labelled `cc`
-  and `cx`. Adding another agent is a parser plus a source entry, with no change to search or
-  ranking — [Gemini CLI and opencode](https://github.com/devcodes9/agsearch/issues/40) are the
-  tracked candidates.
+- **One list for every tool.** Sessions from all five agents appear together, labelled `cc`,
+  `cx`, `cu`, `oc` and `gm`. Adding another agent is a parser plus one entry in the source
+  table, with no change to search or ranking.
 - **Ranked results.** BM25 ranking favors focused sessions and shows matching lines in context.
 - **Preview, read, or resume.** Inspect a match, open the transcript in a pager, or return to the
   original session.
@@ -156,8 +155,8 @@ Either way it needs the `agsearch` binary, which the installation section above
 | <kbd>Ctrl-Y</kbd> | Copy the resume command |
 | <kbd>Ctrl-/</kbd> | Toggle the preview pane |
 
-Selecting a result starts `claude --resume` or `codex resume` from the session's project
-directory. The current query is copied to the clipboard so you can find the same text after
+Selecting a result resumes the session in the tool that created it, from that session's
+project directory. The current query is copied to the clipboard so you can find the same text after
 resuming.
 
 For a global shortcut, see the
@@ -189,8 +188,17 @@ words, and the first result is not guaranteed to be the session you intended.
 
 agsearch reads:
 
-- `~/.claude/projects/**/*.jsonl`
-- `~/.codex/sessions/**/*.jsonl`
+| Agent | Read from | Resumed with |
+| --- | --- | --- |
+| Claude Code | `~/.claude/projects/**/*.jsonl` | `claude --resume <id>` |
+| Codex | `~/.codex/sessions/**/*.jsonl` | `codex resume <id>` |
+| Cursor | `~/.cursor/chats/**/store.db` | `cursor-agent --resume <id>` |
+| opencode | `~/.local/share/opencode/opencode.db` | `opencode run --session <id>` |
+| Gemini CLI | `~/.gemini/tmp/**/chats/*.json` | `gemini --session-file <path>` |
+
+Cursor and opencode keep sessions in SQLite; agsearch opens those read-only and reads message
+records only. Gemini's `--resume` takes a project-scoped index number rather than a stable
+id, so resume goes through the transcript file instead.
 
 Its cache lives under `~/.cache/agsearch/`. Transcript parsing and ranking happen locally, and
 only changed files are reparsed.