fix: force streaming for GitHub Copilot non-GPT-5 models - #744
Merged
Colin Francis (colifran) merged 3 commits intoAug 28, 2026
Merged
Conversation
The Copilot API rejects or returns empty responses for non-streaming requests when using Claude and Gemini models. DeepAgents makes non-streaming .invoke() calls internally during repository worker steps, so without streaming: true those workers exit immediately without ever calling submit_plan or submit_page. Extend providerUsesStreaming to return true for the copilot provider, applying the same streaming: true override used by openai-chatgpt. For GPT-5 models that already route through the Responses API, the flag is redundant but harmless. Fixes langchain-ai#731 Signed-off-by: Christian-Sidak <61099993+Christian-Sidak@users.noreply.github.com>
🦋 Changeset detectedLatest commit: 7e12b85 The changes in this PR will be included in the next version bump. This PR includes changesets to release 1 package
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
Colin Francis (colifran)
approved these changes
Aug 28, 2026
Colin Francis (colifran)
left a comment
Colin Francis (colifran)
left a comment
Collaborator
There was a problem hiding this comment.
Thanks, Christian Sidak (@Christian-Sidak)!
Brad Huffman (ppsplus-bradh)
added a commit
to ppsplus-bradh/openwiki
that referenced
this pull request
Aug 28, 2026
Pick up 4 upstream fixes (unrecognized-language rejection langchain-ai#761, GitHub Copilot non-GPT-5 streaming langchain-ai#744, Bedrock maxTokens langchain-ai#743, docs langchain-ai#759). One conflict, in beginRepositoryRun (src/generation/repository-run.ts): upstream langchain-ai#761 now resolves and rejects an unrecognized language before touching the repository, right where the feature computes its skipRepoSetup guard and noopScope. Kept both — the language rejection runs first, then the recursive repo-setup guard and the subproject no-op scope. Full suite: 3680 passed / 3 skipped. Co-Authored-By: Claude <noreply@anthropic.com>
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
2 participants
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.
Summary
.invoke()calls internally during repository worker steps (planner and page workers).streaming: true, those internal calls return empty and the workers exit without callingsubmit_planorsubmit_page, producing the error "Repository planning worker exited without submit_plan."providerUsesStreamingto returntruefor thecopilotprovider. This applies the samestreaming: trueoverride used byopenai-chatgptfor the Codex backend. For GPT-5 Copilot models that already use the Responses API, the flag is redundant but harmless.Test plan
test/config/copilot-provider.test.ts: new test verifyingproviderUsesStreaming("copilot")returnstruetest/config/constants.test.ts: updated "never applies to other providers" test to remove copilot, added copilot-specific testtest/agent/create-model.test.ts: new tests verifyingstreaming: trueis set on theChatOpenAIinstance for both Claude and GPT-5 Copilot modelsNote:
test/visualize/client-interaction.test.ts,evals/ledger/run/evaluator-e2e.test.ts, andtest/integrations/session-manager.test.tshave pre-existing failures onmainunrelated to this change.Fixes #731