9 Commits

Author SHA1 Message Date
YuJitang
9892a7d468
fix: bucket subagent token usage into parent run totals (#2838)
* fix: bucket subagent token usage into RunRow.subagent_tokens

Add caller-bucketed token tracking to RunJournal so subagent and
middleware LLM calls are written to the correct RunRow columns instead
of all falling into lead_agent_tokens (default 0).

- RunJournal: accumulate _lead_agent_tokens / _subagent_tokens /
  _middleware_tokens in on_llm_end, deduped by langchain run_id.
  Add record_external_llm_usage_records() for external sources
  (respects track_token_usage flag). Return caller buckets from
  get_completion_data().
- SubagentTokenCollector: new lightweight callback handler that
  collects LLM usage within subagent execution.
- SubagentExecutor: wire collector into subagent run_config and sync
  records to SubagentResult on every chunk (timeout/cancel safe).
- SubagentResult: add token_usage_records and usage_reported fields.
- task_tool: report subagent usage to parent RunJournal on every
  terminal status (COMPLETED/FAILED/CANCELLED/TIMED_OUT), including
  the CancelledError path, guarded against double-reporting.

No DB migration needed — RunRow columns already exist.

* Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* fix: address token usage review feedback

* Address review follow-ups

---------

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
2026-05-10 22:47:30 +08:00
YuJitang
5127f08e1a
enable token usage by default (#2841) 2026-05-10 22:00:57 +08:00
YuJitang
417416087b
fix: use backend thread token usage for header total (#2800)
* fix: use backend thread token usage for header total

* Refactor thread token usage fetch
2026-05-09 19:40:32 +08:00
YuJitang
530bda7107
fix: dedupe token usage aggregation by message id (#2770) 2026-05-08 09:54:20 +08:00
Xinmin Zeng
aded753de3
fix(frontend): restore localhost fallback for getGatewayConfig in prod mode (#2705) (#2718)
* fix(frontend): unify gateway-config localhost fallback for prod (#2705)

`getGatewayConfig()` only fell back to localhost defaults when
`NODE_ENV === "development"`, while `next.config.js` always falls back
to `127.0.0.1:8001`. Running `make start` (which sets NODE_ENV=production
via `next start`) without `DEER_FLOW_INTERNAL_GATEWAY_BASE_URL` /
`DEER_FLOW_TRUSTED_ORIGINS` therefore caused zod to throw inside SSR
layouts and surfaced as a 500.

Drop the NODE_ENV gating and use localhost defaults everywhere — the
"force explicit config in prod" intent should be enforced by deployment
templates (docker-compose already sets both vars), not by request-time
crashes. Document the two vars in both .env.example files and add unit
coverage for the dev/prod env-unset paths.

* Potential fix for pull request finding

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

* Update internalGatewayUrl in gateway config tests

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
2026-05-05 16:27:29 +08:00
YuJitang
d02f762ab0
feat: refine token usage display modes (#2329)
* feat: refine token usage display modes

* docs: clarify token usage accounting semantics

* fix: avoid duplicate subtask debug keys

* style: format token usage tests

* chore: address token attribution review feedback

* Update test_token_usage_middleware.py

* Update test_token_usage_middleware.py

* chore: simplify token attribution fallback

* fix token usage metadata follow-up handling

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-05-04 09:56:16 +08:00
Copilot
ef04174194
Fix invalid HTML nesting in reasoning trigger during complex task rendering (#2382)
* Initial plan

* fix(frontend): avoid invalid paragraph nesting in reasoning trigger

Agent-Logs-Url: https://github.com/bytedance/deer-flow/sessions/4c9eb0c2-ff29-4629-a61c-4e33d736d918

Co-authored-by: WillemJiang <219644+WillemJiang@users.noreply.github.com>

* test(frontend): strengthen reasoning trigger DOM nesting assertion

Agent-Logs-Url: https://github.com/bytedance/deer-flow/sessions/4c9eb0c2-ff29-4629-a61c-4e33d736d918

Co-authored-by: WillemJiang <219644+WillemJiang@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: WillemJiang <219644+WillemJiang@users.noreply.github.com>
2026-04-21 09:41:28 +08:00
Xun
7c87dc5bca
fix(reasoning): prevent LLM-hallucinated HTML tags from rendering as DOM elements (#2321)
* fix

* add test

* fix
2026-04-19 19:27:34 +08:00
yangzheli
4efc8d404f
feat(frontend): set up Vitest frontend testing infrastructure with CI workflow (#2147)
* feat: set up Vitest frontend testing infrastructure with CI workflow

Migrate existing 4 frontend test files from Node.js native test runner
(node:test + node:assert/strict) to Vitest, reorganize test directory
structure under tests/unit/ mirroring src/ layout, and add a dedicated
CI workflow for frontend unit tests.

- Add vitest as devDependency, remove tsx
- Create vitest.config.ts with @/ path alias
- Migrate tests to Vitest API (test/expect/vi)
- Rename .mjs test files to .ts
- Move tests from src/ to tests/unit/ (mirrors src/ layout)
- Add frontend/Makefile `test` target
- Add .github/workflows/frontend-unit-tests.yml (parallel to backend)
- Update CONTRIBUTING.md, README.md, AGENTS.md, CLAUDE.md

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* style: fix the lint error

* style: fix the lint error

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-04-12 18:00:43 +08:00