@superbased/observer 1.4.28 → 1.4.30

package/README.md

@@ -6,8 +6,9 @@
 
 **Capture, normalize, compress, and analyze every AI coding tool call you
 run** — across Claude Code, Codex, Cursor, Cline / Roo Code, GitHub
-Copilot, OpenCode, OpenClaw, and Pi — in one local single-binary
-tool. No telemetry, no cloud, no data leaves your machine.
+Copilot, OpenCode, OpenClaw, Pi, Google Antigravity, and Gemini CLI —
+in one local single-binary tool. No telemetry, no cloud, no data
+leaves your machine.
 
 ```
   ┌──────────────┐    ┌──────────────────────────────────┐
@@ -132,6 +133,8 @@ env var that matches your client(s); both can coexist on one machine.
 | **OpenCode** ([opencode.ai](https://opencode.ai/)) | (no proxy yet)                     | SQLite — actual install path is `~/.local/share/opencode/opencode.db` (XDG). Captures **token counts + model + cost** per assistant message from OpenCode's InfoData (`tokens.input/output/reasoning/cache.{read,write}` + `cost`); **subtask** parts → `spawn_subagent` actions; **todo** table → `todo_update` actions; tool-name coverage extended to webfetch/websearch/task/todowrite/todoread/multiedit. Tagged `Source=jsonl, Reliability=approximate`. |
 | **OpenClaw** ([openclaw.ai](https://openclaw.ai/)) | (no proxy yet)                     | JSONL + sqlite — `~/.openclaw/tasks/runs.sqlite` + `~/.openclaw/agents/<agent>/sessions/sessions.json` |
 | **Pi** ([pi.dev](https://pi.dev/)) | (no proxy yet)                                       | JSONL — `~/.pi/agent/sessions/--<path>--/*.jsonl` (per upstream `docs/session-format.md` v3). Captures user / assistant / toolResult / `bashExecution` message roles; `usage.cost.total` → per-message USD; terminal `stopReason` (stop/length/error/aborted) → `task_complete` with `success=false` for failures (mid-turn `toolUse` is correctly skipped); `thinking` blocks surface as preceding reasoning. Tagged `Source=jsonl, Reliability=approximate`. |
+| **Google Antigravity** | (no proxy yet) | Encrypted protobuf — `~/.gemini/antigravity/conversations/*.pb` (Linux-native) and the matching Windows-side path on WSL2. Observer ships a per-OS Chromium-pattern `oscrypt` key fetcher (macOS Keychain / libsecret / DPAPI / WSL2-via-PowerShell helper) and a multi-cipher try-loop for local decryption. Sessions whose ciphers don't validate locally fall back to the language_server's `GetCascadeTrajectory` gRPC endpoint via a built-in helper (`antigravity-bridge.exe` on WSL2 / native gRPC elsewhere) — extracts model + per-turn token counts + Tier 0–6 ToolEvents (file views, artifact edits/writes, user prompts, assistant text, run_command terminal snapshots, structured plan steps, final summaries). State index + per-conversation title/workspace URI read from `state.vscdb` + `state.vscdb.backup`. Tagged `Source=jsonl, Reliability=approximate`. |
+| **Gemini CLI** | (no proxy yet) | JSONL or single-object JSON — `~/.gemini/tmp/<hash>/chats/session-*.{json,jsonl}`. Dual-format dispatch: legacy single-object JSON (size-based cursor, cline-style) and proposed JSONL event records (byte-offset cursor, issue [#15292](https://github.com/google-gemini/gemini-cli/issues/15292)). Action mapping covers `read_file` / `write_file` / `edit_file` / `run_command` / `search_files` / `web_fetch` and arbitrary MCP tool calls. Project root falls back through tool-call `cwd` → `~/.gemini/history/<hash>/.git/config` worktree pointer → synthetic `[gemini-cli:<hash>]` key (promoted via ON CONFLICT DO UPDATE on `sessions.project_id` once a future scan supplies a real cwd). Tagged `Source=jsonl, Reliability=approximate`. |
 
 **JSONL-only** clients are captured passively by the watcher (always-on,
 no setup beyond `observer init`). You won't see real-time cost numbers
@@ -140,8 +143,9 @@ call shows up on Sessions / Actions / Discovery / Tools / Patterns and
 the JSONL-derived token counts feed the Cost tab. Reliability tagging
 is per-adapter: Claude Code emits `unreliable` (the JSONL stream uses
 streaming-time placeholder counts per spec §24); Codex / Cline / Pi /
-OpenCode / OpenClaw emit `approximate` (provider-reported usage that
-hasn't been reconciled against an upstream invoice).
+OpenCode / OpenClaw / Antigravity / Gemini CLI emit `approximate`
+(provider-reported usage that hasn't been reconciled against an
+upstream invoice).
 
 ### Persistent setups
 
@@ -175,12 +179,26 @@ Five components running side by side:
 
 ### 1. JSONL adapters (passive ingest)
 
-Watch `~/.claude/projects/`, `~/.codex/sessions/`, etc. for new
+Watch `~/.claude/projects/`, `~/.codex/sessions/`,
+`~/.gemini/tmp/.../chats/`, `~/.gemini/antigravity/conversations/`
+(and the matching Antigravity index `state.vscdb`), etc. for new
 session log lines. Normalize per-client tool names to a shared
 taxonomy (`read_file`, `run_command`, `spawn_subagent`, …) and write
 them into the actions table. **Always-on**, no setup required —
 `observer init` registers the hooks once.
 
+For Antigravity (which stores conversations as encrypted protobufs),
+observer ships a per-OS `oscrypt` key fetcher (Chromium Safe Storage
+pattern: macOS Keychain / Linux libsecret + peanuts fallback / Windows
+DPAPI / WSL2-via-PowerShell helper) plus a `language_server`-aware
+gRPC fallback that calls `GetCascadeTrajectory` through the bundled
+`antigravity-bridge.exe` when local decryption can't validate the
+ciphertext. Tier 0–6 ToolEvents (file views, artifact edits/writes,
+user prompts, assistant text, run_command terminal snapshots,
+structured plan steps, final summaries) are extracted from the
+trajectory's wire format without committing to specific .proto field
+numbers.
+
 What this gets you: every tool call you've ever run, queryable.
 
 ### 2. API reverse proxy (active capture)
@@ -268,11 +286,11 @@ in the help drawer.
 ### Sessions tab
 
 One row per AI-coding session. Each session has a stable ID, a tool
-(claude-code / cursor / codex / cline / copilot), a working-directory
-project, action count, sub-agent action count (when the session
-spawned sub-agents via the `Agent` tool), per-session **Tokens** and
-**Cost** columns, and — if `observer score` has run — quality / errors
-/ redundancy ratios. The `~` suffix on Cost flags rows whose pricing
+(claude-code / cursor / codex / cline / copilot / opencode / openclaw /
+pi / antigravity / gemini-cli), a working-directory project, action
+count, sub-agent action count (when the session spawned sub-agents via
+the `Agent` tool), per-session **Tokens** and **Cost** columns, and —
+if `observer score` has run — quality / errors / redundancy ratios. The `~` suffix on Cost flags rows whose pricing
 was tier-fallback rather than billing-grade ("accurate" reliability).
 
 Click a row to open the session-detail modal:
@@ -629,9 +647,9 @@ dashboard) has the full versions with cross-links.
   changed between reads. Cross-session reads are excluded (a fresh
   session has no memory of a prior session's read).
 - **Tool** — in this dashboard, "tool" means the *AI client*
-  (claude-code, cursor, codex, cline, copilot), not the per-tool
-  name (`read_file`, `run_command`). The latter is "Tool name" on
-  the Actions tab.
+  (claude-code, cursor, codex, cline, copilot, opencode, openclaw,
+  pi, antigravity, gemini-cli), not the per-tool name (`read_file`,
+  `run_command`). The latter is "Tool name" on the Actions tab.
 - **Tool-pair integrity** — Anthropic requires every `tool_result`
   block to have a corresponding `tool_use` block in a preceding
   message. The compression pipeline preserves both sides of every

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@superbased/observer",
-  "version": "1.4.28",
+  "version": "1.4.30",
   "description": "SuperBased Observer — capture, normalize, compress, and analyze AI coding tool activity across Claude Code, Codex, Cursor, Cline/Roo, and Copilot.",
   "keywords": [
     "ai",
@@ -36,11 +36,11 @@
     "LICENSE"
   ],
   "optionalDependencies": {
-    "@superbased/observer-linux-x64": "1.4.28",
-    "@superbased/observer-linux-arm64": "1.4.28",
-    "@superbased/observer-darwin-x64": "1.4.28",
-    "@superbased/observer-darwin-arm64": "1.4.28",
-    "@superbased/observer-win32-x64": "1.4.28"
+    "@superbased/observer-linux-x64": "1.4.30",
+    "@superbased/observer-linux-arm64": "1.4.30",
+    "@superbased/observer-darwin-x64": "1.4.30",
+    "@superbased/observer-darwin-arm64": "1.4.30",
+    "@superbased/observer-win32-x64": "1.4.30"
   },
   "scripts": {
     "test": "node bin/observer.js --version"