Commit graph

1323 commits

Author SHA1 Message Date
Yiorgis Gozadinos
24275d2ef9
Fixes 2026-03-12 12:19:21 +02:00
Yiorgis Gozadinos
c785a54f5f
Respect config.prompts.qa in evaluations benchmark and optimization 2026-03-12 12:05:51 +02:00
Yiorgis Gozadinos
e7f19c4d42
Compactify tuning.md 2026-03-12 12:05:50 +02:00
Yiorgis Gozadinos
6812435ba0
cleanup 2026-03-12 12:05:50 +02:00
Yiorgis Gozadinos
7c399d1ff1
Remove evaluation ceremony from gepa judge 2026-03-12 12:05:50 +02:00
Yiorgis Gozadinos
8bac8b4104
Properly choose training/eval set 2026-03-12 12:05:50 +02:00
Yiorgis Gozadinos
66f88f7872
Test evaluations 2026-03-12 12:05:50 +02:00
Yiorgis Gozadinos
10abfbe3d8
docs 2026-03-12 12:05:49 +02:00
Yiorgis Gozadinos
45f7ac8d1b
run_optimization should be sync 2026-03-12 12:05:25 +02:00
Yiorgis Gozadinos
8f39ccf29c
Fix precommit to use uv installed ruff 2026-03-12 12:05:25 +02:00
Yiorgis Gozadinos
adc83e5f81
Tests for gepa 2026-03-12 12:05:25 +02:00
Yiorgis Gozadinos
60b1d3c013
Add GEPA prompt optimization for QA evaluations 2026-03-12 12:05:25 +02:00
Yiorgis Gozadinos
e31b692124
Merge pull request #306 from ggozad/fix/read-only-inits-on-empty-folder
Prevent read-only mode from creating tables in empty directories
2026-03-12 11:50:13 +02:00
Yiorgis Gozadinos
b8c377da1e
Prevent read-only mode from creating tables in empty directories 2026-03-12 11:42:04 +02:00
Yiorgis Gozadinos
8d6617d63f
vb 2026-03-11 17:08:22 +02:00
Yiorgis Gozadinos
f07a4b70ed
Merge pull request #304 from ggozad/chore/speed
Cap QA search iterations and tune defaults for faster responses
2026-03-11 13:49:48 +02:00
Yiorgis Gozadinos
45e94ec67a
Set search limit to 10 2026-03-11 12:26:41 +02:00
Yiorgis Gozadinos
bf8eec68e3
Use dict-keyed counter for concurrent-safe search cap 2026-03-11 12:19:19 +02:00
Yiorgis Gozadinos
e2749ad2a6
Cap QA agent search iterations to reduce response time 2026-03-11 12:13:43 +02:00
Yiorgis Gozadinos
f366aea905
vb 2026-03-06 11:12:54 +02:00
Yiorgis Gozadinos
1382d0aebe
Merge pull request #303 from ggozad/feat/param-tune
Set appropriate temperature and max_tokens defaults
2026-03-05 15:56:50 +02:00
Yiorgis Gozadinos
5a0430857f
Enable thinking by default for QA agent 2026-03-05 15:48:08 +02:00
Yiorgis Gozadinos
40ff54eac0
Set params for evaluations judge 2026-03-05 13:59:20 +02:00
Yiorgis Gozadinos
3cc2d5e19e
Set appropriate temperature and max_tokens defaults 2026-03-05 13:23:50 +02:00
Yiorgis Gozadinos
75642c8074
Merge pull request #302 from ggozad/chore/deps-update
Dependencies update
2026-03-05 13:12:18 +02:00
Yiorgis Gozadinos
d460d553f3
Set repeat_table_header=False to match docling serve 2026-03-05 13:02:18 +02:00
Yiorgis Gozadinos
30ebd6694b
Update dependencies 2026-03-05 13:01:53 +02:00
Yiorgis Gozadinos
24de604678
Merge pull request #301 from ggozad/chore/test-cleanup
Test suite cleanup & parallelization
2026-03-05 12:31:14 +02:00
Yiorgis Gozadinos
58959b9249
enable parallel test run 2026-03-05 12:23:22 +02:00
Yiorgis Gozadinos
5e99b84308
Prevent HuggingFace network access during tests 2026-03-05 12:10:07 +02:00
Yiorgis Gozadinos
c7b03eb9ab
Strengthen weak assertions in context enhancement and converter tests
- Add doc_item_refs and headings assertions to test_expand_context_docling_merges_metadata
- Add page count and markdown content assertions to test_convert_pdf_with_ocr_engine

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-05 11:44:51 +02:00
Yiorgis Gozadinos
3c7d746d57
Strengthen search tests, remove redundant title test, relocate primary label test
- Strengthen test_search_returns_search_result with chunk_id, document_id, and
  non-empty labels assertions
- Remove test_chunks_include_document_title (subsumed by strengthened test) and
  its cassette
- Rename test_chunks_include_document_info to
  test_search_chunk_includes_document_provenance; add document_title is None
  assertion for untitled documents
- Move test_search_result_get_primary_label from test_context_enhancement.py to
  test_search.py; rename, remove unnecessary @pytest.mark.vcr() decorator

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-05 11:39:45 +02:00
Yiorgis Gozadinos
f73d4f4da9
Remove stale cassette, dead vcr_cassette_dir fixtures, and unnecessary VCR decorator 2026-03-05 11:36:22 +02:00
Yiorgis Gozadinos
878423ea2e
vb 2026-03-04 15:02:34 +02:00
Yiorgis Gozadinos
d08d32dd5f
Merge pull request #300 from ggozad/feat/support-native-structured-output
Automatically set structured output mode (tool vs native)
2026-03-04 15:01:47 +02:00
Yiorgis Gozadinos
28e90e5a87
Auto-detect structured output mode from model profile. Remove the structured_output config field from ModelConfig. 2026-03-04 14:51:09 +02:00
Yiorgis Gozadinos
fdd7c21757
Add configurable structured output mode (tool vs native) 2026-03-04 13:35:32 +02:00
Yiorgis Gozadinos
2358c14028
Merge pull request #299 from ggozad/feat/skill-meta
Expose skill state metadata as module-level API
2026-03-04 13:17:52 +02:00
Yiorgis Gozadinos
3f02abbc70
Expose skill state metadata as module-level API 2026-03-04 11:38:00 +02:00
Yiorgis Gozadinos
8a859fbe3c
vb 2026-03-03 17:25:53 +02:00
Yiorgis Gozadinos
1c4beb9970
Merge pull request #295 from ggozad/fix/tool-calls
Use ToolOutput for structured output
2026-03-03 17:19:32 +02:00
Yiorgis Gozadinos
c9f63b9ab6
Re-record RLM vcrs 2026-03-03 16:59:35 +02:00
Yiorgis Gozadinos
034ee27daf
Use ToolOutput for structured output. 2026-03-03 16:14:45 +02:00
Yiorgis Gozadinos
1eca0fc308
Fix AGENT_PREAMBLE 2026-03-03 15:06:58 +02:00
Yiorgis Gozadinos
a92f5fe062
Merge pull request #294 from ggozad/feat/search-citations
Search use in SKILL produces citations.
2026-03-03 15:06:06 +02:00
Yiorgis Gozadinos
9a4cda1d65
Reinforce ask prompt in skill 2026-03-03 14:04:53 +02:00
Yiorgis Gozadinos
ee232ba657
Merge pull request #293 from ggozad/feat/real-time-agui-with-skills
Tool calls within skills are now streamed as real-time AG-UI events
2026-03-03 13:25:20 +02:00
Yiorgis Gozadinos
2566bf1a61
Adapt to haiku.skills streaming sub-agent ag-ui events 2026-03-03 11:16:44 +02:00
Yiorgis Gozadinos
a9583abd76
Merge pull request #292 from ggozad/fix/fix-filter
Remove filter parameter from search and list_documents tools
2026-03-03 11:12:22 +02:00
Yiorgis Gozadinos
1a3ea64aa6
Remove filter parameter from search and list_documents tools 2026-03-03 11:01:58 +02:00