mirror of
https://github.com/AgentSeal/codeburn.git
synced 2026-08-23 23:45:12 +00:00
4ca2d4824b
vitest's default glob reached the Electron app's specs under app/, which carry their own vitest config and their own jsdom in app/node_modules. From a root install that fails with ERR_MODULE_NOT_FOUND: jsdom, so the command CONTRIBUTING documents and the one RELEASING.md names as the pre-release gate both error out. Move the scoping CI already applies into package.json: test runs tests/ minus the parallelism-sensitive cache-refresh-lock suites, test:locks runs those three serially, test:watch keeps watch mode at the same scope. The first two are byte-identical to the invocations .github/workflows/tests.yml spells out, so the workflow can be pointed at the scripts to stop the two drifting apart again; that edit is left out of this PR so it needs no workflow permissions. test plus test:locks together still cover all 192 files under tests/. Scoping the script changes what a trailing path argument means: vitest ORs positional filters, so 'npm test -- tests/providers/hermes.test.ts' would no longer narrow to that file, it would run the whole suite. Rewrite those to 'npx vitest run <path>' everywhere they appear - four provider guides and the MCP design plan, thirteen lines in all. Also refresh the stale test docs: 42 files/568 tests (now 192 under tests/), the per-directory counts, the line claiming vitest does not run in CI which stopped being true when tests.yml landed, and the provider test-gap list, which still named antigravity and gemini after both gained test files. Record the cache-refresh-lock naming convention in CONTRIBUTING, since the split makes it load-bearing: a lock test that misses the prefix runs under the full worker pool and flakes, and one that matches it but is absent from test:locks never runs at all.
88 lines
3.8 KiB
Markdown
88 lines
3.8 KiB
Markdown
# LingTai TUI
|
|
|
|
LingTai TUI per-agent token ledger integration.
|
|
|
|
- **Source:** `src/providers/lingtai-tui.ts`
|
|
- **Loading:** eager (`src/providers/index.ts`)
|
|
- **Test:** `tests/providers/lingtai-tui.test.ts`
|
|
|
|
## Where it reads from
|
|
|
|
| Source | Path |
|
|
|---|---|
|
|
| Explicit LingTai homes | `$LINGTAI_HOME` or `$LINGTAI_TUI_HOME` if set; path-list values are supported |
|
|
| Default LingTai home | `~/.lingtai` |
|
|
| Project LingTai homes | `<project>/.lingtai` for projects registered in `~/.lingtai-tui/registry.jsonl` and `~/.lingtai-tui/brief/projects/*/meta.json` |
|
|
| Current worktree home | `.lingtai` in the current directory or any parent directory |
|
|
| Agent ledgers | `<lingtai-home>/<agent>/logs/token_ledger.jsonl` |
|
|
|
|
Daemon ledgers nested under `<agent>/daemons/...` are deliberately not discovered during normal scanning. LingTai mirrors daemon usage into the parent agent ledger with `source`, `em_id`, and `run_id` tags, so reading nested ledgers too would double count spend.
|
|
|
|
## Storage format
|
|
|
|
Append-only JSONL. Each valid ledger line may include:
|
|
|
|
- `source`
|
|
- `em_id`
|
|
- `run_id`
|
|
- `ts`
|
|
- `input`
|
|
- `output`
|
|
- `thinking`
|
|
- `cached`
|
|
- `model`
|
|
- `endpoint`
|
|
|
|
Malformed lines and zero-token entries are skipped. Missing `model` falls back to the agent `.agent.json` `llm.model`, then `unknown`.
|
|
|
|
## Parser
|
|
|
|
CodeBurn emits one parsed call per ledger entry. LingTai records provider-normalized total input plus a separate `cached` counter, so the provider maps:
|
|
|
|
- `input - cached` -> fresh input tokens
|
|
- `cached` -> cache-read tokens
|
|
- `output` -> output tokens
|
|
- `thinking` -> reasoning tokens
|
|
|
|
Costs are calculated from CodeBurn's normal model pricing table.
|
|
|
|
## Activity mapping
|
|
|
|
LingTai's token ledger is an accounting source, not full chat history, so it does not include the original user prompt or per-tool transcript. CodeBurn maps the ledger `source` field conservatively:
|
|
|
|
| LingTai `source` | CodeBurn activity |
|
|
|---|---|
|
|
| `main` and unknown sources | Conversation |
|
|
| `tc_wake` and other task-coordinator wake sources | Delegation |
|
|
| `daemon` | Delegation |
|
|
| `summarize_apriori` | Planning |
|
|
|
|
This keeps the menubar and dashboard **By Activity** view from collapsing all LingTai usage into Conversation while avoiding invented feature/debug/refactor semantics that the ledger cannot prove.
|
|
|
|
## Project grouping
|
|
|
|
Discovery reads `<agent>/.agent.json` and groups by `nickname`, `agent_name`, `address`, then the directory name. Project-local homes are prefixed with the project directory name, for example `sample-project-Project Agent`, so same-named agents from different LingTai projects do not collapse together. The parsed call also carries the agent directory as `projectPath`.
|
|
|
|
## Caching
|
|
|
|
The shared session cache fingerprints each `token_ledger.jsonl`. `LINGTAI_HOME`, `LINGTAI_TUI_HOME`, and `LINGTAI_TUI_GLOBAL_DIR` are part of the provider environment fingerprint so changing homes invalidates stale cached results.
|
|
|
|
## Deduplication
|
|
|
|
Dedup keys include provider name, ledger path, line number, timestamp, model, endpoint, LingTai source tags, and token counts:
|
|
|
|
`lingtai-tui:<ledger-path>:<line>:<timestamp>:<model>:...`
|
|
|
|
The ledger is append-only, so line number is stable for normal operation.
|
|
|
|
## Quirks
|
|
|
|
- Tool calls are not reconstructed from chat history. The token ledger is the stable accounting source and does not include tool metadata.
|
|
- Older ledger entries may not include `source`; those are labeled `main`.
|
|
- `cached` is treated as cache read. LingTai does not expose a separate cache creation counter in the ledger.
|
|
|
|
## When fixing a bug here
|
|
|
|
1. Prefer a minimal redacted `token_ledger.jsonl` fixture over full `chat_history.jsonl`.
|
|
2. Check whether a daemon entry is already mirrored into the parent ledger before adding new discovery paths.
|
|
3. Run `npx vitest run tests/providers/lingtai-tui.test.ts`.
|