5 Commits

Author	SHA1	Message	Date
m4	470cf75722	merge: bring upstream v0.3.0 (72 commits) into Ai4Sci fork ... Merged upstream/main (418abca, release v0.3.0) into our fork on a dedicated branch. 21 conflicting files resolved; main worktree untouched. Resolution policy and key decisions: - Keep Ai4Sci runtime endpoints, durable dispatch, workspace scopes and the HITL/DynamicReview approval chain (approval path is product-critical). - Adopt upstream model registry (llm/registry.py): our 136 model entries are a strict subset of upstream's 180, so dropping our inline table loses nothing and gains 44 new models. - Adopt upstream native EvoChatDeepSeek; drop our obsolete _patch_deepseek_reasoning_passback monkey patch. - Keep our six patches.py additions, ported onto upstream's new _OpenAICompatContent class: stable tool-call ids, tool-history sanitization, drop_reasoning_metadata, empty-SSE keepalive, extracted-document-text patch, _has_assistant_tool_protocol. - Keep our skill-budget middleware path (skills=None) instead of passing skills through, to avoid double loading. - Keep sanitized error labels (_safe_error_label) while adopting upstream's injected MiddlewareEventSink for fallback narration. - Keep port 3076 and the LANGGRAPH_SERVER_URL override; adopt upstream's host/probe-host handling and CONFIG_DRIFT_SINCE_LAUNCH. - Adopt upstream dependency stack: deepagents 0.7.6, langchain-quickjs 0.3.7, langgraph-api 0.14; keep our extra deps (rfc8785, pillow, firecrawl-anydoc, nest-asyncio). - Align call sites with upstream APIs: create_tool_selector_middleware now takes events= instead of track_stream_selection=.	2026-09-13 16:07:27 +08:00
jfilipiuk	3d6cc959e3	fix: cut deployed-graph rebuild from 15s to <1s by deferring observation-index reads (#427) ... * fix: defer eager observation-index build to first model call * fix: add mtime-keyed cache to list_observation_documents to avoid re-parsing unchanged files * fix: return a copy of the cached document list and strengthen the deletion test * fix: copy cached document list on read and write to prevent caller mutations * fix: split global and project cache to avoid duplicate parsing and cross-project invalidation * fix: bump mtime explicitly in cache modification test for Windows NTFS resolution * fix: bound project observation cache with LRU eviction * fix: deduplicate path logic and strengthen cache typing * fix: group cache tests under TestObservationCache with autouse fixture and fix f-string interpolation * fix: reject non-positive observation cache cap in config validation * fix: cache resolved observation docs and config cap to avoid repeated work * fix: use st_mtime_ns and st_size in cache signature for NTFS reliability * test: clear EVOSCIENTIST_MAX_CACHED_PROJECTS in test env cleanup fixtures * test: cover per-file observation cache semantics * fix: replace layered observation caches with per-file parse cache * fix: serialize observation parse cache transactions	2026-08-21 06:49:32 +00:00
m4	5a581c78a2	feat: add scoped model runtime configuration ... Introduce provider, model, and invocation contracts with encrypted configuration persistence. Add web runtime fencing, route fallback, recovery middleware, workspace scoping, and comprehensive tests.	2026-08-14 22:03:04 +08:00
dinos	2b244888ec	feat(memory): autoskills (#319)	2026-07-03 11:16:33 +02:00
dinos	f2f010a350	feat(memory): observation linking (#307) ... * refactor(gateway): create module for launching async/bg agents * refactor(memory): refactor worker launch around source context & output deltas * refactor(gateway): generalize async/bg module * refactor(memory): revamp worker launching * feat(memory): add observation linking * test(memory): remove redundant test branches * fix(memory): make 'supersedes' relation directional * fix(memory): don't create empty project observation dirs * fix(memory): schedule direct observations for linking * fix(cli): wait for observation linker before shutdown * fix(memory): block arbitrary writes to /memories * fix(linker): remove `linked_by` attribute from frontmatter * refactor(linker): rename base relationship to `comlpements` * fix(cli): bump worker wait to 2m * feat(tools): catch malformed tool calls & retry * feat(status): add linking result to statusbar * fix(linker): don't launch linker when observations are disabled * fix(memory): use posix paths * fix(watcher): call abort hook on error status * fix(watcher): delete thread on failed run creation * fix(watcher): preserve url * fix(observation): record session_id, drop unused fields * fix(memory): reject unsupported worker source types * refactor(backends): shared memory backend builder * fix(scheduler): resolve linker inputs outside lock * fix(memory): dont launch workers / record observations without thread_id * feat(memory): include related observations in tool results * fix(memory): skip malformed observation frontmatter * revert(tools): drop tool error handling changes from this PR * fix(memory): serialize observation link writes * fix(memory): queue observations written by aborted workers * fix(memory): track observation linker launch handoff * fix(memory): resolve cross-project related observations * fix(status): avoid recounting reason-only link updates * fix(memory): avoid rereading file for content * fix(linker): use neutral prose for bidirectional reasons * test(memory): coverage for aborted/failed launches * test(memory): cleanup & helpers * feat(linker): add observations index hint	2026-06-26 22:20:52 +01:00