test(parity): shared server scenario conformance corpus + Python reference runner#62
Merged
Conversation
…rence runner Promotes conformance from message-shape (fixtures.json) to full server BEHAVIOR: spec/conformance/scenarios/*.json are language-neutral scenarios (mockLlmScript + inbound frames + expected outbound event stream) that every native server runs identically. Deterministic across languages because each server drives the same MockLlmProvider script. python/server/tests/test_scenario_parity.py is the ~80-line reference runner — port it into the TS/Go/C#/Rust server suites for full parity. Seed scenarios: basic-streaming-turn, unknown-session-error (both green vs the Python server). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01U7Mn93HpqhSgEmX6tRdPAv
|
brentrager
added a commit
that referenced
this pull request
Jun 24, 2026
… shared parity corpus (#69) The TS/Python/Go servers landed (#59/#60/#61) and all five now run the shared spec/conformance/scenarios corpus (#62-#67) — tested protocol parity. Updates the servers row + tests section from 'in progress' to the real state. Claude-Session: https://claude.ai/code/session_01U7Mn93HpqhSgEmX6tRdPAv Co-authored-by: Claude Opus 4.8 (1M context) <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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Promotes conformance from message-shape to full server behavior — the parity oracle for the polyglot servers.
spec/conformance/scenarios/*.json— language-neutral scenarios (mockLlmScript + inbound frames + expected outbound event stream). Every native server runs the same corpus and must produce identical normalized output. Deterministic because each server drives the same engineMockLlmProviderscript — no live model.python/server/tests/test_scenario_parity.py— the ~80-line reference runner (a state machine over the corpus). Port it into the TS/Go/C#/Rust server suites; when all five run green, the servers are at protocol parity.basic-streaming-turn(create → ack → stream → eventual, with token reassembly) +unknown-session-error(cleanerror/SESSION_NOT_FOUND). Both verified green against the Python server.Next: port the runner into the other four server suites (TS/Go/C#/Rust) + grow the corpus (multi-turn, tool-call/HITL, citations, auth, graceful-drain).
🤖 Generated with Claude Code