Spaces:
Running
Running
Commit History
-
Add local H100 scientist eval tooling
a29a83d
-
Add 12 scoring & environment improvements with full test coverage
- LLM judge integration via OpenRouter with config toggle and deterministic fallback - Communication bonus scoring (action diversity, responsiveness, substantiveness) - Per-domain scoring weight profiles (math, ML, finance) - Adaptive reward shaping (later rounds carry heavier penalties) - Richer fidelity matching with bigram overlap and substring fuzzy matching - Cross-dimension feasibility tradeoffs in Lab Manager policy - Mid-episode judge feedback hints at negotiation midpoint - Scenario consistency validation (budget, equipment, reagent checks) - Cached substitution index per episode in environment - Docker HEALTHCHECK directive for container orchestration - .dockerignore security hardening for .env files - Fix circular import in judge_policy via lazy import - 25 new tests (integration + LLM judge mock tests), 514 total passing Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>2b98daa
-
Add model-driven local runtime and dynamic demo flow
4ea916a -
Finalize demo flow and training assets
b878f5b -
Add MOD 08 schema tests, V2 training stack, and close MOD 08/JDG 07/API 01/OBS 02
- MOD 08: 70 comprehensive unit tests for all Pydantic models (Kian lane 100% done) - V2 training: GRPO, SFT, evaluation, metrics, plots, CLI, corpus, datasets modules - TRN 01/02/14: Notebook skeleton, install cell, model selection - JDG 07/API 01/OBS 02: Verified and closed in trackers (already implemented) - 409 tests pass, 92/152 tasks complete (60.53%)685783a -
Recover env judge training stack and sync project tracking
13ae015 -
Recover env server client stack and deployment tracking
8b157ab -
Add AGT 04/05/07 implementations, server integration, and doc updates
- AGT 04: build_baseline_scientist_action with domain inference - AGT 05: check_feasibility with per-dimension checks - AGT 07: compose_lab_manager_response with action type selection - Server: real Lab Manager pipeline replaces hardcoded stub responses - Tests: AGT 04/05/07 test coverage - Docs: task completion tracking and model selection notes Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>7c2246c -
Add future improvements doc, import FND 09 and MOD 01-03 completions
- Add docs/future_improvements.md with domain-agnostic normalized scenario layer design, impact analysis, and 6 planned work items - Import completed FND 09 (openenv.yaml), MOD 01 (ScientistAction validators), MOD 02 (LabManagerAction validators), MOD 03 (typed ConversationEntry and Protocol models) - Update task tracking docs, completion tracker, and Kian task lists - Add model validation tests and uv.lock Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>db07024 -
Rename owner docs to kian max kush and update mappings
038da92 -
Complete FND 02 FND 05 FND 06 FND 07 foundation setup bundle
3f69f35 -
Add FND 08 contract, model updates, task docs, and completion tracking
- Add frozen JSON contract (docs/fnd08_frozen_json_contract.md) - Update models.py with base model assumptions and field refinements - Add per-person task docs (Person A, C, D breakdowns and lists) - Update completion tracker with FND 04/08 status - Add project management rules and AGENTS.md - Update comprehensive task division with model selection notes Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>ad13149 -
Add model selection and architecture notes
- Qwen3-4B as primary trainable Scientist, Qwen3-8B as H100 stretch - Deterministic rubric remains sole training reward - Hosted frontier evaluator for optional explanation and demo audit only - Lab Manager stays rule-based for MVP - Future model-backed Lab Manager added to stretch backlog and risk register - Updated Person B docs with base-model rationale and reward notes80aa0ec -
Refine task breakdown execution order and dependency details
5f5a3f4
-
Fix task list and breakdown to align with source of truth
- Correct totals to 29 tasks, 21.5h - Remove blueprint-based assumptions for early starts - All tasks correctly marked as blocked per task division - Keep AGT 11 and TRN 14 as separate tracked tasksa6e3459 -
Add Person B task list and execution breakdown
fb99880