mirror of
https://github.com/AgentSeal/codeburn.git
synced 2026-07-29 19:05:30 +00:00
e0051fc403
* feat(providers): add coder/mux as a datasource Reads coder/mux session data from ~/.mux/sessions/<workspaceId>/chat.jsonl and normalizes per-assistant-message token usage into ParsedProviderCall. Discovery resolves project names from config.json; the token decomposition matches mux's own inclusive input/output accounting, and cost is recomputed via LiteLLM. Includes unit tests and a provider doc. Change-Id: Ie6ce9d41254d8bf05ff0965b443328dfa7b598de Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Signed-off-by: Thomas Kosiewski <tk@coder.com> * fix(providers): discover mux sub-agent transcripts discoverSessions only globbed sessions/<id>/chat.jsonl and skipped each spawned sub-agent's transcript at sessions/<id>/subagent-transcripts/<childTaskId>/chat.jsonl. Against a real ~/.mux (629 workspaces) those nested files are 5,889 sessions and ~51% of all assistant messages, so sub-agent spend was silently dropped: total mux usage went from $17,113 to $21,564 (+26%) once counted. Walk the subagent-transcripts dir per workspace and attribute each child session to the parent's project. Dedup is unaffected: the parser keys off the <childTaskId> dir name, which is disjoint from every workspace id, so each call is still counted once. Cross-checked parsed per-model token totals against mux's sibling session-usage.json. Also corrects the provider doc, which wrongly claimed sub-agents get their own top-level sessions/<id>/chat.jsonl, and documents the Google reasoning>output decomposition edge case. Change-Id: I1d43f26eec7c9c6c523e5ea541e2ff8d0c3aa07e Signed-off-by: Thomas Kosiewski <tk@coder.com> Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Signed-off-by: Thomas Kosiewski <tk@coder.com> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| antigravity.md | ||
| claude.md | ||
| cline.md | ||
| codex.md | ||
| copilot.md | ||
| crush.md | ||
| cursor-agent.md | ||
| cursor.md | ||
| droid.md | ||
| forge.md | ||
| gemini.md | ||
| goose.md | ||
| ibm-bob.md | ||
| kilo-code.md | ||
| kimi.md | ||
| kiro.md | ||
| mistral-vibe.md | ||
| mux.md | ||
| omp.md | ||
| openclaw.md | ||
| opencode.md | ||
| pi.md | ||
| qwen.md | ||
| README.md | ||
| roo-code.md | ||
| vscode-cline-parser.md | ||
| warp.md | ||
Provider Docs
One file per provider integration. If you are fixing a bug or adding a feature scoped to a single provider, read the file for that provider first; it tells you which file to edit, where on disk the source data lives, and what edge cases the test suite already covers.
For the architectural picture, see ../architecture.md.
Provider Index
Eager (always loaded)
| Provider | Storage | Source | Test |
|---|---|---|---|
| Claude | JSONL (no parser) | src/providers/claude.ts |
none (covered indirectly) |
| Cline | JSON | src/providers/cline.ts |
tests/providers/cline.test.ts |
| Codex | JSONL | src/providers/codex.ts |
tests/providers/codex.test.ts |
| Copilot | JSONL | src/providers/copilot.ts |
tests/providers/copilot.test.ts |
| Droid | JSONL | src/providers/droid.ts |
tests/providers/droid.test.ts |
| Gemini | JSON / JSONL | src/providers/gemini.ts |
none |
| IBM Bob | JSON | src/providers/ibm-bob.ts |
tests/providers/ibm-bob.test.ts |
| KiloCode | JSON | src/providers/kilo-code.ts |
tests/providers/kilo-code.test.ts |
| Kiro | JSON | src/providers/kiro.ts |
tests/providers/kiro.test.ts |
| Kimi | JSONL | src/providers/kimi.ts |
tests/providers/kimi.test.ts |
| Mistral Vibe | JSON / JSONL | src/providers/mistral-vibe.ts |
tests/providers/mistral-vibe.test.ts |
| OpenClaw | JSONL | src/providers/openclaw.ts |
tests/providers/openclaw.test.ts |
| Pi | JSONL | src/providers/pi.ts |
tests/providers/pi.test.ts |
| OMP | JSONL | src/providers/pi.ts |
tests/providers/omp.test.ts |
| Qwen | JSONL | src/providers/qwen.ts |
none |
| Roo Code | JSON | src/providers/roo-code.ts |
tests/providers/roo-code.test.ts |
Lazy (loaded on first call)
| Provider | Storage | Source | Test |
|---|---|---|---|
| Antigravity | protobuf over RPC | src/providers/antigravity.ts |
none |
| Crush | SQLite (per-project) | src/providers/crush.ts |
tests/providers/crush.test.ts |
| Forge | SQLite | src/providers/forge.ts |
tests/providers/forge.test.ts |
| Cursor | SQLite | src/providers/cursor.ts |
tests/providers/cursor.test.ts |
| Cursor Agent | text / JSONL | src/providers/cursor-agent.ts |
tests/providers/cursor-agent.test.ts |
| Goose | SQLite | src/providers/goose.ts |
none |
| OpenCode | SQLite | src/providers/opencode.ts |
tests/providers/opencode.test.ts |
| Warp | SQLite | src/providers/warp.ts |
tests/providers/warp.test.ts |
Shared
| Helper | Used by | Source |
|---|---|---|
| vscode-cline-parser | cline, ibm-bob, kilo-code, roo-code |
src/providers/vscode-cline-parser.ts |
File Format
Each provider doc has the same structure:
- One-line summary of what the provider integrates.
- Where it reads from on disk (or over RPC).
- Storage format and validation rules.
- Caching (which cache layer, if any).
- Deduplication key so you understand cross-provider dedup.
- Quirks that have bitten us before.
- When fixing a bug here as a checklist.
If you add a new provider, copy claude.md as a template and fill in your provider's specifics. Update this index, and prefer adding a real test fixture under tests/providers/.