test(python): pin the minimal composition's model-visible surface
The Python lane never compared what the minimal composition shows the model: the mock model only asserted system-role messages, and the advanced snapshot tokenizes the assembled system prompt and tool schemas. The sdk-minimal scenario now records model-visible.json — every model request's advertised tool schemas verbatim and its message list, with system and user text kept and assistant/tool payloads reduced to call identity so the expected output replays on macOS and Linux. It excludes the dynamic runtime-context snapshot, which the same composition emits on macOS and not on Linux (#2488). AGENTS.md and the testing policy name both SDKs as independent projections of the agent loop, session lifecycle, and SessionEventMap.
This commit is contained in:
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"AGENTS.md": 1900,
|
||||
"AGENTS.md": 1950,
|
||||
"docs/AGENTS.md": 1320,
|
||||
"docs/architecture.md": 2400,
|
||||
"docs/cordis-primer.md": 600,
|
||||
|
||||
Reference in New Issue
Block a user