chore: chunk processing refactoring#202
Open
VinShurik wants to merge 15 commits intointegration-0.7from
Open
Conversation
…hore/refactoring # Conflicts: # src/quickapp/common/__init__.py # src/quickapp/common/_di_types.py # src/quickapp/dial_deployment_tooling/dial_completion_service.py
Collaborator
Author
|
/deploy-review
|
VinShurik
force-pushed
the
chore/chunk_processing_refactoring
branch
from
c00abab to
0790588
Compare
VinShurik
changed the title
Collaborator
Author
|
/deploy-review
|
…ctoring # Conflicts: # src/quickapp/agent/agent_module.py # src/quickapp/agent/assistant_invoker.py # src/quickapp/agent/tool_executor.py
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description of changes
This PR unifies OpenAI-compatible chat completion streaming between the orchestrator and deployment tooling, and cleans up related DI and dead code.
Streaming
ChatCompletionStreamHandlerwith orchestrator vs deployment strategies (config via Pydantic models with callables / arbitrary types where needed).chat_completion_stream(parse,driver,models,stream_result).Choice; propagate thinking/reasoning stages when enabled, including incremental stage deltas (index → stage name cache so content-only chunks still route correctly). Deployment: shallow-mergecustom_content.state, extend attachments, stream toBaseStageWrapperwhen present.ChatStreamHandlerErrorand subclasses) for clearer top-level handling.DI / clients
AsyncAzureOpenAIbindings by use case: orchestrator client vs deployment client (typedAnnotatedaliases), so deployment calls are not pinned to the orchestrator deployment name.Structure / readability
AccumulatedToolCalltocommon/chat_completion_stream/tool_call.pyand removes theagent/_modelspackage.chat_completion_stream/__init__.py(no barrel re-exports); imports use explicit submodules.ChunkProcessorand its unit tests (superseded byChatCompletionStreamHandler).Tests
azure_clientvs staledial_client), and request payload shape (model+extra_body).Checklist
By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.