7 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
m4	c683f6e739	feat: prepare EvoScientist 0.3.0 ... Add bounded document ingestion, controlled web search, recoverable session support, subagent timeouts, and the native sandbox runtime contract. Unify package versioning and add release-focused regression coverage.	2026-09-03 06:55:56 +08:00
LinxXu	47c8da3e5b	fix(llm): bound routed reasoning and surface empty truncation (#425) ... * fix(llm): bound routed reasoning and surface empty truncation Default DashScope Qwen 3.8 Max requests to low reasoning effort and forward explicit reasoning controls to custom OpenAI-compatible endpoints. Detect length-limited responses that exhaust their budget during reasoning without producing content or tool calls, and surface a provider-aware error instead of ending the turn silently. Add regression coverage for routed reasoning configuration, truncated empty responses, and valid content/tool-call responses. * fix(middleware): reject empty structured text blocks * fix(llm): address reasoning truncation review feedback * fix(llm): validate DashScope reasoning effort * fix(llm): document DashScope reasoning support	2026-08-18 08:28:19 +01:00
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
m4	3ce5614254	fix: harden tool-call protocol and fallback handling	2026-07-19 12:05:56 +08:00
dinos	05dfffbc73	fix(llm): use native langchain-deepseek SDK (#349)	2026-07-15 17:13:33 +01:00
jfilipiuk	88ac9f5ba1	fix: surface real exception class+message in SSE error events (#315) ... * fix: surface real exception class+message in SSE error events * fix: tighten SSE error patch scope and key redaction * fix: redact base64-style secret suffixes fully * style: remove notes/ reference from the dosctring * fix: rebuild env cache on each error call * fix: route BaseException through serde.default on SSE/webhook paths * fix: distinguish routed providers by request URL host * feat: normalize provider-SDK exceptions via ErrorNormalizationMiddleware * refactor: drop json_dumpb dataclass-bypass wrappers, superseded by middleware * fix: guard _extract_host against SDK properties that raise * refactor: derive provider tag from ModelRequest.model, not the exception * refactor: drop serde.default patch and exception-based inference; ProviderStreamError.model_dump handles the emit * refactor: move envelope helpers from patches.py to errors.py * feat: extend ErrorNormalizationMiddleware coverage to every model-call path * chore: clean up review findings from middleware pivot * fix: pass through all langgraph.errors * fix: move langgraph.errors pass-through into _normalize * fix: pass through ContextOverflowError in _normalize	2026-07-13 14:17:56 +01:00