Skip to content

Conversation

rguan72
Copy link
Contributor

@rguan72 rguan72 commented Sep 25, 2025

  • .
  • .
  • .
  • .
  • Update backend/onyx/evals/tracing.py
  • .
  • .
  • .
  • .
  • .
  • .
  • .
  • .
  • .
  • .
  • .
  • .
  • .
  • .
  • .
  • .

Description

[Provide a brief description of the changes in this PR]

How Has This Been Tested?

[Describe the tests you ran to verify your changes]

Additional Options

  • [Optional] Override Linear Check

Summary by cubic

Introduces a new streaming chat turn pipeline (Simple Agent V2) and a deep-research scratchpad agent, and wires chat processing to the new runner. Adds Braintrust tracing controls and an eval CLI flag to disable log sending.

  • New Features

    • New chat turn infra: OnyxRunner, Emitter, and unified_event_stream for thread-safe, blocking event iteration.
    • fast_chat_turn agent using LiteLLM; process_message now streams via fast_chat_turn and parses agent/reasoning events.
    • Deep-research scratchpad agent with tools (web_search, web_fetch, internal_search), compaction hooks, and a clarification gate.
    • Braintrust updates: configurable masking length (BRAINTRUST_MASKING_LENGTH), tracing processor setup, demo agent, and --no-send-logs flag (propagated through evals).
  • Refactors

    • gather_stream parses unified packet objects and builds responses from streaming deltas.
    • Simplified LLM logging (no-op) and minor DR prompt/CSV cleanup.
    • Temporary change: chat session rename endpoint returns a static placeholder.
    • Eval models/providers accept no_send_logs; added quality classifier scaffold.

Copy link

vercel bot commented Sep 25, 2025

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Preview Comments Updated (UTC)
internal-search Ready Ready Preview Comment Sep 26, 2025 1:11am

Copy link

blacksmith-sh bot commented Sep 25, 2025

9 Jobs Failed:

Run Integration Tests v2 / prepare-build failed on "Generate OpenAPI schema"
[...]
  PERM_SYNC_SHAREPOINT_CERTIFICATE_PASSWORD: ***
  PERM_SYNC_SHAREPOINT_DIRECTORY_ID: ***
  GITHUB_REPO_NAME: ***/onyx
  pythonLocation: /opt/hostedtoolcache/Python/3.11.13/arm64
  PKG_CONFIG_PATH: /opt/hostedtoolcache/Python/3.11.13/arm64/lib/pkgconfig
  Python_ROOT_DIR: /opt/hostedtoolcache/Python/3.11.13/arm64
  Python2_ROOT_DIR: /opt/hostedtoolcache/Python/3.11.13/arm64
  Python3_ROOT_DIR: /opt/hostedtoolcache/Python/3.11.13/arm64
  LD_LIBRARY_PATH: /opt/hostedtoolcache/Python/3.11.13/arm64/lib
  PYTHONPATH: .
Traceback (most recent call last):
  File "/home/runner/_work/onyx/onyx/backend/scripts/onyx_openapi_schema.py", line 11, in <module>
    from onyx.main import app as app_fn
  File "/home/runner/_work/onyx/onyx/backend/onyx/main.py", line 55, in <module>
    from onyx.evals.tracing import setup_braintrust
  File "/home/runner/_work/onyx/onyx/backend/onyx/evals/tracing.py", line 5, in <module>
    from agents import set_trace_processors
ModuleNotFoundError: No module named 'agents'
Error: Process completed with exit code 1.
Run Integration Tests v2 / required failed on "Run actions/github-script@v7"
[...]
  retry-exempt-status-codes: 400,401,403,404,422
env:
  PRIVATE_REGISTRY: experimental-registry.blacksmith.sh:5000
  PRIVATE_REGISTRY_USERNAME: ***
  PRIVATE_REGISTRY_PASSWORD: ***
  OPENAI_API_KEY: ***
  SLACK_BOT_TOKEN: ***
  CONFLUENCE_TEST_SPACE_URL: ***
  CONFLUENCE_USER_NAME: ***
  CONFLUENCE_ACCESS_TOKEN: ***
  JIRA_BASE_URL: ***
  JIRA_USER_EMAIL: ***
  JIRA_API_TOKEN: ***
  PERM_SYNC_SHAREPOINT_CLIENT_ID: ***
  PERM_SYNC_SHAREPOINT_PRIVATE_KEY: ***
  PERM_SYNC_SHAREPOINT_CERTIFICATE_PASSWORD: ***
  PERM_SYNC_SHAREPOINT_DIRECTORY_ID: ***
  GITHUB_REPO_NAME: ***/onyx
Error: One or more upstream jobs failed or were cancelled.

7 jobs failed running on non-Blacksmith runners.


Summary: 2 successful workflows, 7 failed workflows

Last updated: 2025-09-26 01:21:58 UTC

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant