test(crew): premise validation harness + live integration test - #123
Merged
Merged
Conversation
|
crim doesn't review pull requests automatically here. Comment |
Premise-first validation of the code-first crew core (per its new CONTEXT.md): - test_crew_premise_e2e.py: in-process, deterministic, fake LLM. Covers the seams and edge cases — LLM turn -> generate_response chunks, speak-only-when-running, failing turn surfaces a fatal error and still closes, barge-in survival, background node observes silently, event-codec wire round-trip, imports resolve. - test_crew_integration_live.py: live-gated (ANTHROPIC_API_KEY, -m integration). A real crew node with a real OpenAIClient against Anthropic streams a real turn. - crew/CONTEXT.md: premise, domain vocabulary, seams, invariants, edge cases.
abhishekmishragithub
force-pushed
the
crew-premise-validation
branch
from
September 22, 2026 00:39
48e64a2 to
fa81f91
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Premise-first validation of the agent-crew core, the thing that matters most before adding features.
-m integration, skips withoutANTHROPIC_API_KEY): a real crew node + real OpenAIClient against Anthropic streams a real turn. Verified passing live.No crew defects found during validation; the premise holds. mypy + ruff clean.