Repository navigation
Sync main into v1.2.6 with conflict fixes - #728
Merged
Merged
Conversation
The OpenAI-compatible provider defaulted to a 120s request timeout, which caused frequent timeouts during evaluation runs where model responses legitimately take longer. Raise the default to 300s. The MEMMY_AGENT_OPENAI_COMPAT_TIMEOUT_S env override is unchanged; only the fallback default changes. Update the two default-timeout assertions accordingly. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
…ations Expose OpenAI Completions/Responses and Custom providers in the model workspace, persist thinking/image capability on Custom presets, and send thinking fields through the chat turn so the backend can map them onto reasoningEffort. Co-authored-by: Cursor <cursoragent@cursor.com>
…ponses. Settings can save those protocols for both memory roles, and the memory runtime now sends the matching request instead of rejecting the assignment or falling through to chat completions. Co-authored-by: Cursor <cursoragent@cursor.com>
GPT-6, Claude Opus 5.5, Gemini 3.8 Flash, and DeepSeek V4.1 Flash were missing from the picker table, so the composer had no effort control for those model ids. Co-authored-by: Cursor <cursoragent@cursor.com>
The label and switch already identify the control, and the icon crowded the composer action bar. Co-authored-by: Cursor <cursoragent@cursor.com>
The thinking and image checkboxes did not say what they change, and the checkbox itself did not show a pointer. Co-authored-by: Cursor <cursoragent@cursor.com>
…ng client. Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
…t Completions. Co-authored-by: Cursor <cursoragent@cursor.com>
…and warn Custom users to turn it off. Co-authored-by: Cursor <cursoragent@cursor.com>
…soning models are called with tools. Co-authored-by: Cursor <cursoragent@cursor.com>
…s model with tools, including Custom when thinking is off. Co-authored-by: Cursor <cursoragent@cursor.com>
…t, and show 自定义 for that provider in Chinese. Co-authored-by: Cursor <cursoragent@cursor.com>
… with the OpenAI logo. Co-authored-by: Cursor <cursoragent@cursor.com>
merge main into zy_npm_1008
…into zy_npm_1008
Zy npm 1008
fix(providers): raise default model call timeout to 300s
…opy-v1.2.2 fix(chat): 修复多轮对话中历史助手回复缺少复制按钮 #666
…tion fix(release): avoid paginated PR metadata lookup
fix(release): retry commit PR API with curl
…otes-isolated docs(release): translate v1.2.4 notes to English
syzsunshine219
changed the title
Memtensor-AI
added
area:app
area:docs
area:memory
status:in-progress
and removed
status:needs-triage
labels
Collaborator
Author
|
Project Harness review handoff marker. Only reviews submitted strictly after this GitHub timestamp qualify. |
syzsunshine219
marked this pull request as ready for review
October 23, 2026 11:55
syzsunshine219
requested review from
Wang-Daoji,
ZongYue99,
hijzy and
wustzdy
as code owners
October 23, 2026 11:55
Collaborator
🤖 Open Code ReviewTarget: PR #728 ✅ OpenCodeReview: Review skipped: no items were selected. Generated by cloud-assistant via Open Code Review. |
Collaborator
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Synchronizes
main@74b26fc78ebd14a784981ba8e83bebf878c20865intov1.2.6@b04f5c88c2000a1c7a936230a70401178aca4842as an independent Draft candidate for #720. Final source head:dc597e071e3962fff2c029cb83d1fa4297b5013f.The merge preserves the target's consolidated
Memory/AgentSourceCorereader layout and scan lifecycle alongside main's OpenCode V2 behavior, thinking contracts, and final-answer controls for every completed turn. It excludes interrupted drafts followed by activity, preserves explicit OpenCode removal when memory is cleared, prevents a pending automatic refresh after clearing begins, and accepts both recognized Linux Gateway startup responses while rejecting unrelated upstream HTTP 503 responses.The expanded verification fixes also retain the existing BYOK credential assertions while awaiting both catalog persistence phases, add controlled assignment-publication navigation regressions, and keep real adapter I/O active under a test clock that still checks the original 10ms startup and 100ms recurring deadlines. No production latency budget or test timeout was increased.
Windows validation now checks out and verifies the exact source SHA, runs both native Go modules and the existing History/platform/packaging checks, and uploads a machine-generated provider receipt only after the required Windows job steps succeed. Its scope explicitly excludes live capture and signed-installer acceptance.
Validation on the final source:
120365344219, actual checkoutdc597e071e3962fff2c029cb83d1fa4297b5013f, both native Go modules and every required step successful. Authenticated artifact12495201575, ZIP SHA-25689ca6bc76b2354321d7a13afdec763de43d4dbde7320ebcd50791a74c2923105; the original receipt was downloaded without modification and its repository/run/attempt/source identity verified.run-1792751746567-6e50d795-1106-41ad-81b9-44293974dc57; source and delivery stayed unchanged during execution. Gate:needs_review, verification passed and ready for handoff; independent approval remains required.This remains a Draft for review. Full verification is complete; independent approval has not been recorded. No main/target branch was changed, no force push was used, and no PR was merged.