fix: respect conversation language across all harnesses#353
fix: respect conversation language across all harnesses#353masamaru0513 wants to merge 2 commits into
Conversation
|
@raj-jain-aws This is the v2 rebuild of #290 (now closed), reshaped onto the current |
|
Same on the v2 branch with Korean intents. Across 4 independent dry-run fixtures (different intent shapes — greenfield SaaS, a feature add on an existing service, a consumer-app MVP, a local-only full-stack service) the persona-authored artifacts under each intent's Glad to see this PR — happy to test it against the four Korean fixtures once it merges. |
5b12844 to
c53929a
Compare
Add a conversation-language rule to the Mandated section of core/memory/org.md so the framework default — inherited by all four harnesses (claude, codex, kiro, kiro-ide) through the shared memory layer — instructs agents to write every human-readable artifact in the language the human last used. The rule states a principle rather than an enumerated allow-list: anything a person reads or reviews (requirements, stories, plans, specs, reviews, questions, discovered practices, discovered/affirmed rules, evidence, rationale) follows the conversation language, and only machine-parsed/verified content stays English (stable IDs, enum values, code, paths, mermaid keywords, template section headings matched by the required-sections sensor, and machine-read state files). Rule-layer artifacts following an ALWAYS/NEVER directive shape are written in the human's language too; the marker keyword may stay. Verified on the kiro harness end-to-end: ideation through operation artifacts render in Japanese while IDs, code, tool names, template headings, and state/audit files stay English. Bumps version 2.1.1 -> 2.1.2 with matching README badge and CHANGELOG.
|
Update (2026-06-27): Rebased and reworked for the v2-unified architecture (introduced 2026-06-15 in
|
c53929a to
445fd88
Compare
Add a conversation-language rule to the Mandated section of core/memory/org.md so the framework default — inherited by all four harnesses (claude, codex, kiro, kiro-ide) through the shared memory layer — instructs agents to write every human-readable artifact in the language the human last used. The rule states a principle rather than an enumerated allow-list: anything a person reads or reviews (requirements, stories, plans, specs, reviews, questions, discovered practices, discovered/affirmed rules, evidence, rationale) follows the conversation language, and only machine-parsed/verified content stays English (stable IDs, enum values, code, paths, mermaid keywords, template section headings matched by the required-sections sensor, and machine-read state files). Rule-layer artifacts following an ALWAYS/NEVER directive shape are written in the human's language too; the marker keyword may stay. Verified on the kiro harness end-to-end: ideation through operation artifacts render in Japanese while IDs, code, tool names, template headings, and state/audit files stay English. Bumps version 2.1.1 -> 2.1.2 with matching README badge and CHANGELOG.
Add a conversation-language rule to the Mandated section of core/memory/org.md so the framework default — inherited by all four harnesses (claude, codex, kiro, kiro-ide) through the shared memory layer — instructs agents to write every human-readable artifact in the language the human last used. The rule states a principle rather than an enumerated allow-list: anything a person reads or reviews (requirements, stories, plans, specs, reviews, questions, discovered practices, discovered/affirmed rules, evidence, rationale) follows the conversation language, and only machine-parsed/verified content stays English (stable IDs, enum values, code, paths, mermaid keywords, template section headings matched by the required-sections sensor, and machine-read state files). Rule-layer artifacts following an ALWAYS/NEVER directive shape are written in the human's language too; the marker keyword may stay. Verified on the kiro harness end-to-end: ideation through operation artifacts render in Japanese while IDs, code, tool names, template headings, and state/audit files stay English. Bumps version 2.1.1 -> 2.1.2 with matching README badge and CHANGELOG.
445fd88 to
d94506d
Compare
Add a conversation-language rule to the Mandated section of core/memory/org.md so the framework default — inherited by all four harnesses (claude, codex, kiro, kiro-ide) through the shared memory layer — instructs agents to write every human-readable artifact in the language the human last used. The rule states a principle rather than an enumerated allow-list: anything a person reads or reviews (requirements, stories, plans, specs, reviews, questions, discovered practices, discovered/affirmed rules, evidence, rationale) follows the conversation language, and only machine-parsed/verified content stays English (stable IDs, enum values, code, paths, mermaid keywords, template section headings matched by the required-sections sensor, and machine-read state files). Rule-layer artifacts following an ALWAYS/NEVER directive shape are written in the human's language too; the marker keyword may stay. Verified on the kiro harness end-to-end: ideation through operation artifacts render in Japanese while IDs, code, tool names, template headings, and state/audit files stay English. Bumps version 2.1.4 -> 2.1.5 with matching README badge and CHANGELOG.
d94506d to
04d48be
Compare
|
Update (2026-07-01): Rebased onto the latest |
…ntion # Conflicts: # CHANGELOG.md # README.md # core/tools/aidlc-version.ts # dist/claude/.claude/tools/aidlc-version.ts # dist/codex/.codex/tools/aidlc-version.ts # dist/kiro-ide/.kiro/tools/aidlc-version.ts # dist/kiro/.kiro/tools/aidlc-version.ts
Adds a conversation-language rule to
core/memory/org.mdso all harnesses instruct agents to write human-readable artifacts in the user's language. Rebased onto the current v2 architecture (the pre-v2persona-prompt-augment.yamlandconventions/are gone).Fixes #288
Summary
Adds a Conversation language rule to the
## Mandatedsection ofcore/memory/org.md. The rule states a principle: anything a person reads or reviews follows the conversation language; only machine-parsed/verified content stays English (stable IDs, enum values, code, file paths, mermaid keywords, template section headings, state files). One byte-shared source propagates to all four harnesses (claude, codex, kiro, kiro-ide) viabun scripts/package.ts.This is feedforward prose — it does not guarantee 100% enforcement (no sensor checks output language). But in practice the presence or absence of the rule makes a large, consistent difference.
Changes
core/memory/org.md: added conversation-language rule to## Mandatedcore/tools/aidlc-version.ts: version bump 2.1.1 → 2.1.2README.md: version badge updatedCHANGELOG.md: added## [2.1.2]entrydist/(4 harnesses): regenerated viabun scripts/package.tsUser experience
Before (no rule):
interaction-spec,design-system-mapping,accessibility-checklist)After (with this change):
Verification
Ran the same Japanese prompt (
簡単なTODOアプリを作りたい) on clean v2 (no rule) vs this change, on both kiro-cli and Claude Code. The control isolates the rule as the only variable — the before/after table above summarises the results.Checklist
core/, notdist/bun scripts/package.tsand committed regenerateddist/bun scripts/package.ts --checkreports no driftcore/tools/aidlc-version.ts+ README badge + CHANGELOG entry)