fix(hindsight): make cloud client timeout configurable#9882
Closed
konsisumer wants to merge 4 commits into
Closed
Conversation
977e8e5 to
a716796
Compare
The Hindsight cloud client was hardcoded to a 30s timeout, causing hindsight_reflect to fail on LLM synthesis operations that routinely take longer. The timeout is now configurable via config key "timeout" or HINDSIGHT_TIMEOUT env var, defaulting to 120s to match the _run_sync wrapper. Closes NousResearch#9869
…ntials The copilot credential pool entry does not include a base_url, so when resolve_runtime_provider takes the pool path the returned base_url is empty. Add a fallback to DEFAULT_GITHUB_MODELS_BASE_URL, matching how other providers (codex, qwen, openrouter) handle the same scenario. Fixes test_runtime_copilot_uses_gh_cli_token.
…on model conflict The zai provider now has an explicit entry in _PROVIDER_VISION_MODELS (glm-5v-turbo) on main, so the test no longer exercises the prefix-strip fallback path. Switch to deepseek which has no explicit vision model mapping.
The rebase onto main mixed the branch's deepseek config with main's glm-5v-turbo assertion. Restore main's version of this test since main already fixed the assertion.
a716796 to
88356e4
Compare
5 tasks
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
hindsight_reflectto fail on LLM synthesis that routinely exceeds 30s ([Bug]: Hindsight plugin hardcoded 30s timeout causes hindsight_reflect to fail #9869)timeoutorHINDSIGHT_TIMEOUTenv var, defaulting to 120s (matching the_run_syncwrapper timeout)Test plan
hindsight_reflectcalls with slow LLM providers should no longer timeout prematurelyHINDSIGHT_TIMEOUT=60or"timeout": 60in config.json should override the defaultCloses #9869