deepseek-harness/python/development.i18n.yaml

# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
# side as of the last confirmed-consistent state. Both languages carry equal authority;
# after editing either side, bring the other along and re-record with:
#   pnpm run verify-translation-pairing --write python/development.md
development.md: fe62a109f2643afe0b9be1ed51b86be0b9fa731f
development.zh.md: d4ab9850d6c83dc17a740240f97cef89d61faaa0
docs: apply hierarchy across the corpus 2026-08-04 00:54:19 +08:00			`# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each`
			`# side as of the last confirmed-consistent state. Both languages carry equal authority;`
			`# after editing either side, bring the other along and re-record with:`
			`# pnpm run verify-translation-pairing --write python/development.md`
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. 2026-08-13 15:21:45 +08:00			`development.md: fe62a109f2643afe0b9be1ed51b86be0b9fa731f`
			`development.zh.md: d4ab9850d6c83dc17a740240f97cef89d61faaa0`