Commit Graph

Select branches

Hide Pull Requests

main

Mono Color

• 465845b2a1 feat(advisor-comparison): add 相比上次运行 panel to report detail page main wangweiandCopilot 2026-07-02 17:03:02 +08:00
• f4016a1f09 feat(advisor-comparison): wire build_advisor_comparison into report_builder wangweiandCopilot 2026-07-02 17:00:07 +08:00
• 86e3aef7d5 feat(advisor-comparison): add build_advisor_comparison diagnosis diffing wangweiandCopilot 2026-07-02 16:56:24 +08:00
• 001fbb0b58 feat(advisor-comparison): add find_previous_run same-scenario lookup wangweiandCopilot 2026-07-02 16:41:36 +08:00
• 9987573e02 feat(advisor-comparison): add AdvisorComparison models and ReportData field wangweiandCopilot 2026-07-02 16:39:21 +08:00
• 8ebf554989 docs: add advisor comparison implementation plan wangweiandCopilot 2026-07-02 16:37:38 +08:00
• 81996f8aa1 docs: add advisor comparison design spec wangweiandCopilot 2026-07-02 16:28:13 +08:00
• 6bad007cd9 feat(token-tracking): add Token usage panel to the report detail page wangweiandCopilot 2026-07-02 15:40:37 +08:00
• 4bb1952348 feat(token-tracking): surface token_usage in ReportData wangweiandCopilot 2026-07-02 15:14:11 +08:00
• 8245c7f9c3 feat(token-tracking): accumulate token usage across session_async calls wangweiandCopilot 2026-07-02 15:09:30 +08:00
• 6a2bbf8239 feat(token-tracking): capture token usage in /api/score/async job runs wangweiandCopilot 2026-07-02 15:03:25 +08:00
• 5494840431 feat(token-tracking): wrap CLI evaluator metric scoring in track_token_usage wangweiandCopilot 2026-07-02 14:57:19 +08:00
• cd044c8416 feat(token-tracking): add Token usage section to summary.md wangweiandCopilot 2026-07-02 14:50:07 +08:00
• b50b911de0 feat(token-tracking): add EvaluationResult.token_usage and persist to metadata.json wangweiandCopilot 2026-07-02 14:45:58 +08:00
• 29e76d021c feat(token-tracking): attach usage hook to advisor's self-created LLM client wangweiandCopilot 2026-07-02 14:39:13 +08:00
• 613d167e81 feat(token-tracking): add HTTP response hook and attach_usage_hook, wire into build_models wangweiandCopilot 2026-07-02 14:36:59 +08:00
• 8b896e4e7f feat(token-tracking): add TokenUsageTracker with context-scoped activation wangweiandCopilot 2026-07-02 14:31:43 +08:00
• 54cc58e157 docs: add token usage tracking design spec wangweiandCopilot 2026-07-02 14:05:05 +08:00
• 1dec4c8372 Add INFO/DEBUG logging to factory: log resolved base_url per model wangweiandCopilot 2026-07-01 21:24:59 +08:00
• f6e10145cd Fix: build_models resolves separate AsyncOpenAI clients for judge and embedding models wangweiandCopilot 2026-07-01 21:15:09 +08:00
• 3a82d8c487 Update API docs: document judge_language in all score endpoints wangweiandCopilot 2026-07-01 20:21:04 +08:00
• 24a8688a34 Add committed zh judge-prompt cache + enable in Siemens scenarios + docs wangweiandCopilot 2026-07-01 18:15:53 +08:00
• 065b0e0f1a Add judge-prompt cache bootstrap script wangweiandCopilot 2026-07-01 18:04:27 +08:00
• 31fe71eb94 Forward judge_language through score, async, and session endpoints wangweiandCopilot 2026-07-01 18:02:13 +08:00
• bd5658c3ac Wire judge-prompt localization into factory and inline scorer wangweiandCopilot 2026-07-01 17:58:43 +08:00
• 555328cb3b Add judge-prompt localizer with graceful fallback and drift detection wangweiandCopilot 2026-07-01 17:55:26 +08:00
• 4e74e1b247 update for ragas wangwei 2026-07-01 17:53:00 +08:00
• 2bb804b059 Extract shared build_metric_registry factory (DRY) wangweiandCopilot 2026-07-01 17:52:55 +08:00
• 4a646b6b9c Add judge_language config plumbing (settings + scenario + ScoreRequest) wangweiandCopilot 2026-07-01 17:47:21 +08:00
• 03e682b89c docs: add Chinese judge-prompt adaptation design spec wangweiandCopilot 2026-07-01 17:32:22 +08:00
• 9828b1d44c update wangwei 2026-06-27 14:31:45 +08:00
• 1df4010acc fix(llm): resolve score runtime config from saved profiles wangweiandCopilot 2026-06-26 20:34:01 +08:00
• 754a30ad59 feat(session-async): add /api/score/session_async with incremental session report aggregation wangweiandCopilot 2026-06-26 16:09:33 +08:00
• e1751447df feat(advisor): add 0.85 advisory threshold triggering LLM suggestions wangweiandCopilot 2026-06-25 11:35:49 +08:00
• 4fd515d2d9 feat: async score jobs — POST /api/score/async + 评分记录 page wangweiandCopilot 2026-06-24 17:24:22 +08:00
• abcd61ec8f docs: add async score jobs implementation plan wangwei 2026-06-24 17:08:01 +08:00
• 363e8b0f27 docs: add async score jobs design spec wangwei 2026-06-24 17:04:06 +08:00
• b870ed8730 feat: make contexts optional in /api/score wangweiandCopilot 2026-06-24 14:42:03 +08:00
• 791738bb07 feat: rename project to 'Siemens RAGAS 评估平台' in frontend wangweiandCopilot 2026-06-24 10:20:23 +08:00
• 630b70cc2a docs: add project-overview.html — full project documentation wangweiandCopilot 2026-06-24 10:17:08 +08:00
• a781ba1e4a config: set default judge_model=gpt-5, embedding_model=text-embedding-3-small wangweiandCopilot 2026-06-23 15:29:01 +08:00
• 2ad2c1ea9d docs: update /api/score example to use gpt-5.4 and text-embedding-3-small wangweiandCopilot 2026-06-23 15:11:34 +08:00
• f8e308b7dc fix: use max_tokens=8 for chat model connectivity test wangweiandCopilot 2026-06-23 15:03:27 +08:00
• fb420656ec fix: use /embeddings endpoint for embedding models in connectivity test wangweiandCopilot 2026-06-23 14:53:32 +08:00
• 05419db1f9 fix: support max_completion_tokens for newer models (gpt-5.x) in connectivity test wangweiandCopilot 2026-06-23 14:51:28 +08:00
• 1dc7ab9727 fix: restore LLM profile test connectivity buttons (lost from git) wangweiandCopilot 2026-06-23 13:58:43 +08:00
• 7cc3aff95a fix: hide #view-apidocs when [hidden] attribute is set wangweiandCopilot 2026-06-23 13:34:24 +08:00
• ad2651ce27 feat: configure full logging in webmain.py — all API logs to file + console wangweiandCopilot 2026-06-23 11:46:34 +08:00
• fb42116616 fix: add setuptools package discovery config to pyproject.toml wangweiandCopilot 2026-06-23 11:29:35 +08:00
• a629bd516c chore: add .gitattributes to enforce LF for shell scripts and Python files wangweiandCopilot 2026-06-23 11:22:24 +08:00
• ac410e7a5d feat: add detailed logging to all API routes and global access log middleware wangweiandCopilot 2026-06-23 10:35:00 +08:00
• 1304fec1c4 fix: change ScoreRequest json_schema_extra from examples list to example dict wangweiandCopilot 2026-06-23 10:03:46 +08:00
• 5ced129ff7 feat: add detailed request logging to /api/score and global 422 handler wangweiandCopilot 2026-06-22 18:14:01 +08:00
• ebf1fc7be8 docs: enhance /api/score OpenAPI docs with full Chinese docstring and response example wangweiandCopilot 2026-06-22 15:52:30 +08:00
• 1bcb208f92 feat: Dify score API complete — add SCORE_API_TOKEN to .env.example wangweiandCopilot 2026-06-22 15:28:20 +08:00
• a03a24be4e feat: add POST /api/score endpoint for Dify real-time scoring wangweiandCopilot 2026-06-22 15:14:19 +08:00
• e4d4e4968b feat: add InlineScorer service with LLM client caching wangweiandCopilot 2026-06-22 15:03:43 +08:00
• 761faf9c42 feat: add ScoreRequest/ScoreResponse models and SCORE_API_TOKEN setting wangweiandCopilot 2026-06-22 15:00:05 +08:00
• 9ad6ad4ebc docs: add Dify score API implementation plan wangwei 2026-06-22 14:55:43 +08:00
• eee96eb158 docs: add Dify score API integration design spec wangweiandCopilot 2026-06-22 14:51:52 +08:00
• ccf25eb1f9 feat: add Linux deployment scripts (deploy/start/stop/run_eval) wangweiandCopilot 2026-06-22 14:28:44 +08:00
• 199b3af611 docs: add Linux deploy script design spec wangweiandCopilot 2026-06-22 14:18:14 +08:00
• f9e3ba0f64 feat: add weight config panel to 新建评估 and weighted_score card to report wangweiandCopilot 2026-06-18 17:28:15 +08:00
• 36e5506e2a feat: report_builder uses weighted means; ReportData gains weighted_score_mean wangweiandCopilot 2026-06-18 17:16:09 +08:00
• 835614189e feat: ScenarioInfo exposes metric_weights and doc_weights from YAML wangweiandCopilot 2026-06-18 17:05:26 +08:00
• ce0d2291b0 feat: yaml_patcher and ProfileApplyRequest support metric_weights and doc_weights wangweiandCopilot 2026-06-18 17:02:21 +08:00
• 480f6d66ea feat: use weighted metric means and add weighted_score row to summary.md wangweiandCopilot 2026-06-18 16:59:56 +08:00
• d371ef7d24 feat: add weighted_score and sample_weight columns to score rows wangweiandCopilot 2026-06-18 16:53:45 +08:00
• 8617eaa5aa feat: add metric_weights and doc_weights to Scenario schema and dataclass wangweiandCopilot 2026-06-18 16:50:33 +08:00
• e0b064587f feat: add metric/doc weight computation module (weights.py) wangweiandCopilot 2026-06-18 16:47:47 +08:00
• 078097af00 docs: add metric/doc weights implementation plan wangwei 2026-06-18 16:43:08 +08:00
• ca586bf9bb docs: add metric and doc weights feature design spec wangweiandCopilot 2026-06-18 16:37:18 +08:00
• 9ad2daff73 feat: restore API文档 nav item (iframe /docs) without touching other 4 modules wangwei 2026-06-17 11:24:16 +08:00
• e8af5b906c chore: remove API docs iframe nav item, rename title to RAGAS 评估控制台 wangwei 2026-06-17 11:18:01 +08:00
• 8ea2b9c7d2 feat: add API文档 nav item with embedded Swagger UI iframe wangwei 2026-06-17 11:09:55 +08:00
• 074800b741 feat: add history report switcher dropdown in report detail view wangwei 2026-06-17 10:35:56 +08:00
• 3019390592 feat: add export-to-PDF via browser print with @media print CSS wangwei 2026-06-17 10:28:01 +08:00
• 24956bbf75 更新 wangwei 2026-06-16 18:12:33 +08:00
• ca01e44ad2 feat(webapp): add session persistence via URL hash routing + sessionStorage wangweiandClaude 2026-06-16 17:55:07 +08:00
• 1a2cc534b8 feat(webapp): add optimization advice section to report UI wangweiandClaude 2026-06-16 17:26:37 +08:00
• 91c0dab4f9 fix(advisor): fix LLM API call, wire advice_markdown to webapp, update .env.example timeouts wangweiandClaude 2026-06-16 17:12:32 +08:00
• f5c2dce64a feat(advisor): add optimization advisor module wangweiandClaude 2026-06-16 17:06:19 +08:00
• d68399d39b chore: update startup scripts and .env.example for LLM profile feature wangwei 2026-06-16 17:03:25 +08:00
• 719c3b4ca4 test: ensure test package structure and all webapp tests pass wangwei 2026-06-16 16:27:54 +08:00
• 5b60ed12ea feat: add LLM role-assignment panel to 新建评估 view wangwei 2026-06-16 16:27:00 +08:00
• dc8baf8662 feat: add LLM配置 management page (profiles view) wangwei 2026-06-16 16:25:20 +08:00
• e329f59139 feat: add yaml_patcher service to apply LLM profiles to scenario YAML wangwei 2026-06-16 16:21:19 +08:00
• b19054bd66 feat: add /api/llm-profiles CRUD router wangwei 2026-06-16 16:18:40 +08:00
• 5d09deb420 feat: add ProfileManager service with JSON persistence wangwei 2026-06-16 16:14:31 +08:00
• b98af29449 feat: add LLMProfile pydantic models wangwei 2026-06-16 16:10:37 +08:00
• 4173a40d93 feat(scripts): add run_eval.bat / run_eval.ps1 evaluation launcher scripts wangweiandClaude 2026-06-16 11:16:53 +08:00
• 629304aa6d feat(logging): add structured evaluation logs for metric-level debugging wangweiandClaude 2026-06-16 10:48:41 +08:00
• 1ff4a3943a feat(dataset-builder): add retry logic and ASCII-safe logging for Siemens PDF pipeline wangweiandClaude Opus 4 2026-06-15 23:06:33 +08:00
• 75ae7927ad Add Siemens CT document evaluation scenario (three-step pipeline) wangweiandClaude Sonnet 4 2026-06-15 17:00:52 +08:00
• 1288a366d1 Fix start.bat (ASCII-only, guaranteed window stays open) + add start.ps1 wangweiandClaude Sonnet 4 2026-06-15 16:14:53 +08:00
• e89695e490 Add RAGAS evaluation web console (FastAPI + vanilla JS) wangweiandClaude Sonnet 4 2026-06-15 15:53:57 +08:00
• 9cbdc1d95d first commit Guangfei.Zhao 2026-06-12 14:02:15 +08:00