Dom bb1ea42318 feat(tools): add 7 wired+bench utility scripts (A+B classification) ...

- A (wired, imports project modules): e2e_map_roles, anonymize_demo, grounding_e2e_resolve_engine
- B (orphan projection, standalone benches): enrichment_eval_multi, extract_easily_bench_cases, extract_record_bench_cases, grounding_eval_multi

2026-07-02 13:27:04 +02:00

..

_bench_t2a_out

backup: snapshot post-démo GHT 2026-05-19

2026-05-19 14:55:06 +02:00

analyze_bench_results.py

backup: snapshot post-démo GHT 2026-05-19

2026-05-19 14:55:06 +02:00

anonymize_demo.py

feat(tools): add 7 wired+bench utility scripts (A+B classification)

2026-07-02 13:27:04 +02:00

append_excel_steps_interop.py

backup: snapshot post-démo GHT 2026-05-19

2026-05-19 14:55:06 +02:00

bench_safety_checks_models.py

feat(qw4): bench rigoureux LLM safety_checks → gemma4:latest par défaut

2026-05-06 09:23:09 +02:00

bench_t2a_post_fix.py

backup: snapshot post-démo GHT 2026-05-19

2026-05-19 14:55:06 +02:00

benchmark_grounding.py

feat(grounding): pipeline centralisé + serveur UI-TARS transformers + nettoyage code mort

2026-04-25 17:48:18 +02:00

benchmark_medgemma_demo.py

backup: snapshot post-démo GHT 2026-05-19

2026-05-19 14:55:06 +02:00

competence_validator.py

feat(competences): extract batch candidates

2026-05-29 11:25:00 +02:00

duplicate_demo_urgence_2_interop.py

backup: snapshot post-démo GHT 2026-05-19

2026-05-19 14:55:06 +02:00

duplicate_demo_urgence_3_db.py

backup: snapshot post-démo GHT 2026-05-19

2026-05-19 14:55:06 +02:00

e2e_map_roles.py

feat(tools): add 7 wired+bench utility scripts (A+B classification)

2026-07-02 13:27:04 +02:00

enrichment_eval_multi.py

feat(tools): add 7 wired+bench utility scripts (A+B classification)

2026-07-02 13:27:04 +02:00

extract_competences_from_session.py

feat(competences): extract batch candidates

2026-05-29 11:25:00 +02:00

extract_easily_bench_cases.py

feat(tools): add 7 wired+bench utility scripts (A+B classification)

2026-07-02 13:27:04 +02:00

extract_record_bench_cases.py

feat(tools): add 7 wired+bench utility scripts (A+B classification)

2026-07-02 13:27:04 +02:00

generate_ollama_inventory_v2.py

feat(vwb): add dashboard competence testing and health tools

2026-06-02 16:27:19 +02:00

grounding_e2e_resolve_engine.py

feat(tools): add 7 wired+bench utility scripts (A+B classification)

2026-07-02 13:27:04 +02:00

grounding_eval_multi.py

feat(tools): add 7 wired+bench utility scripts (A+B classification)

2026-07-02 13:27:04 +02:00

lea_bench_ollama.py

feat(evaluation): add local Ollama LeaBench adapter

2026-05-24 21:58:06 +02:00

lea_bench_openai_compat.py

feat(p1y-alpha): add OpenAI-compatible LeaBench adapter (benchmark only)

2026-06-04 16:49:53 +02:00

lea_bench.py

feat(evaluation): add LeaBench computer-use scorer

2026-05-24 21:21:17 +02:00

lea_healthcheck.py

feat(vwb): add dashboard competence testing and health tools

2026-06-02 16:27:19 +02:00

lea_micro_preflight.py

feat(vwb): add dashboard competence testing and health tools

2026-06-02 16:27:19 +02:00

probe_qwen3vl_processor.py

backup: snapshot post-démo GHT 2026-05-19

2026-05-19 14:55:06 +02:00

run_session_cleaner.sh

feat: session_cleaner — outil leger de nettoyage de sessions avant replay

2026-04-12 11:35:31 +02:00

session_cleaner.py

feat(vwb): add dashboard competence testing and health tools

2026-06-02 16:27:19 +02:00

start_grounding_server.sh

feat(grounding): pipeline centralisé + serveur UI-TARS transformers + nettoyage code mort

2026-04-25 17:48:18 +02:00

test_instruction.sh

chore: sauvegarde pré-stabilisation — audit 66/66 tests OK

2026-04-23 09:14:56 +02:00

test_replay_e2e.py

test(e2e): harness replay reproductible — mock client Léa V1 contre serveur réel

2026-05-07 22:11:07 +02:00