Commit graph

134 commits

Author SHA1 Message Date
Yiorgis Gozadinos
b01c649684
surface picture image bytes in SearchResult and emit multimodal ToolReturn from the agent search tool 2026-04-30 12:43:05 +03:00
Yiorgis Gozadinos
206c4ffcf2
address review: top-level AnalysisRunDeps import, asserts, e2e tests
- Move AnalysisRunDeps to the module-level import in _tools.py.
- Swap the RuntimeError guards in _require_rag and execute_code for
  plain asserts with the same diagnostic messages. Apply the same
  treatment to the ty-reachability guard in Sandbox._ensure_initialized.
- Add end-to-end lifespan tests for both skills that drive _run_skill
  with TestModel, covering the sub-agent entry path that the existing
  tool-level tests bypass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-22 15:04:24 +03:00
Yiorgis Gozadinos
4a9dd9b49a
persist sandbox variables across execute_code calls within one invocation 2026-04-22 13:30:38 +03:00
Yiorgis Gozadinos
af7731f4e1
bulk-fetch items.jsonl via lazy cache to avoid per-document query timeout 2026-04-20 14:25:16 +03:00
Yiorgis Gozadinos
cd0c21c996
remove cited_chunks from analysis agent, hoist _deny_write out of loop 2026-04-20 14:05:10 +03:00
Yiorgis Gozadinos
579e609ae1
revert REPL persistence: fresh sandbox per execute_code call 2026-04-20 12:48:05 +03:00
Yiorgis Gozadinos
167c837514
repository methods, module-level executor, read-only VFS 2026-04-20 11:57:39 +03:00
Yiorgis Gozadinos
4d75943df5
use MontyRepl for persistent variables across execute_code calls 2026-04-20 10:47:50 +03:00
Yiorgis Gozadinos
7d98d0ec57
add citation support to analysis agent 2026-04-17 18:35:16 +03:00
Yiorgis Gozadinos
a45820dbf7
add document virtual filesystem to analysis sandbox
Replace get_document() and get_docling_document() with a VFS at
/documents/{id}/ with metadata.json (eager), content.txt (lazy),
and items.jsonl (lazy). Keep search(), list_documents() (now returns
all), and llm() as external functions.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-17 18:35:16 +03:00
Yiorgis Gozadinos
bacc21b38b
expose doc_item_refs and labels in sandbox search results 2026-04-17 18:35:16 +03:00
Yiorgis Gozadinos
4118533db1
fold context expansion into sandbox search and remove get_context 2026-04-17 18:35:16 +03:00
Yiorgis Gozadinos
44fd0c9906
add get_context() to analysis sandbox and improve prompt 2026-04-17 18:32:45 +03:00
Yiorgis Gozadinos
d2b3ba1b59
rename RLM agent to analysis throughout the codebase 2026-04-17 18:32:01 +03:00
Yiorgis Gozadinos
75c84805b4
Improve judge prompt, QA prompt, and raise max_searches to 5 2026-04-16 12:12:23 +03:00
Yiorgis Gozadinos
e4dc60c4f1
Update core dependencies 2026-04-03 10:14:27 +03:00
Yiorgis Gozadinos
aa9fdf051d
Remove support for structured output 2026-03-24 14:11:43 +02:00
Yiorgis Gozadinos
713e9087cc
Bump pydantic-monty to 0.0.8, remove regex external functions, update skill 2026-03-12 17:24:01 +02:00
Yiorgis Gozadinos
8c7eec8a8d
Strengthen cited chunk structured output description 2026-03-12 14:00:24 +02:00
Yiorgis Gozadinos
90fe624fa7
improve QA citation reliability via prompt and ID normalization 2026-03-12 11:50:46 +02:00
Yiorgis Gozadinos
e2749ad2a6
Cap QA agent search iterations to reduce response time 2026-03-11 12:13:43 +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
034ee27daf
Use ToolOutput for structured output. 2026-03-03 16:14:45 +02:00
Yiorgis Gozadinos
6759a2e0a5
Give regex to monty as externals 2026-02-24 13:12:56 +02:00
Yiorgis Gozadinos
1ee9747551
Catch MontyRuntimeError from Monty() constructor 2026-02-24 12:11:20 +02:00
Yiorgis Gozadinos
380fc6c930
Consolidate prompt 2026-02-24 12:09:11 +02:00
Yiorgis Gozadinos
459fdfca71
Add get_docling_document external function to sandbox 2026-02-24 11:51:43 +02:00
Yiorgis Gozadinos
d3c6322481
Simplify sandbox with run_monty_async, replace manual ThreadPoolExecutor start/resume loop 2026-02-24 11:35:39 +02:00
Yiorgis Gozadinos
b9fa1a061f
Update monty 2026-02-24 09:55:45 +02:00
Yiorgis Gozadinos
017712c9b1
Update prompts & docs. Remove docker sandbox workflow 2026-02-24 09:55:45 +02:00
Yiorgis Gozadinos
c61ded1271
Replace Docker sandbox with pydantic-monty 2026-02-24 09:55:40 +02:00
Yiorgis Gozadinos
69083c8cb4
Fix stale docs 2026-02-20 16:59:58 +02:00
Yiorgis Gozadinos
37f28ea8de
Clean up stale references and dead code 2026-02-20 16:37:15 +02:00
Yiorgis Gozadinos
eb9436eb2a
Remove unused conversational output mode from research graph 2026-02-20 16:36:50 +02:00
Yiorgis Gozadinos
8176103eb0
Remove agents/chat/ 2026-02-20 16:36:48 +02:00
Yiorgis Gozadinos
ed89ff0fc9
Simplify tools/ — remove AG-UI state machinery, keep core toolsets 2026-02-20 16:36:48 +02:00
Yiorgis Gozadinos
8c76897af2
Update tui and app to use the toolkit 2026-02-16 12:54:44 +02:00
Yiorgis Gozadinos
72c8f6e1b1
Additional tests 2026-02-13 18:08:46 +02:00
Yiorgis Gozadinos
84c48e1541
Add preamble parameter to chat agent and citations_history to ChatSessionState 2026-02-13 16:59:21 +02:00
Yiorgis Gozadinos
c0ed93da2d
Expand tests 2026-02-13 14:34:24 +02:00
Yiorgis Gozadinos
f5c562db9b
Fix double summarization, cleanup 2026-02-13 12:16:23 +02:00
Yiorgis Gozadinos
d9acdfba9d
prompt builder 2026-02-13 11:21:09 +02:00
Yiorgis Gozadinos
5f6d9e9812
handle state_key duplication between deps and ToolContext 2026-02-13 10:23:12 +02:00
Yiorgis Gozadinos
a5b8e3be7e
Add AgentDeps and prepare_context for custom agent DX 2026-02-12 17:37:37 +02:00
Yiorgis Gozadinos
8f180f707b
Decouple QA toolset from chat agent, add ToolContext state methods 2026-02-12 17:27:47 +02:00
Yiorgis Gozadinos
0c6d73409d
Move SessionContext from agents/chat/state.py to tools/session.py, change QASessionState.session_context to use it 2026-02-12 17:13:01 +02:00
Yiorgis Gozadinos
05ebd781d4
Move client and tool_context from toolset factories to RunContext.deps 2026-02-12 15:50:46 +02:00
Yiorgis Gozadinos
51f1d9cf13
Issue a full state snapshot from ask() tool to preserve server side background context 2026-02-11 17:49:09 +02:00
Yiorgis Gozadinos
58c2bd49ea
Clean up server vs client session setting priorities 2026-02-11 16:54:00 +02:00