* fix(#2402): honor response_language across orchestrator output + UAT checkpoint renderer Replays the in-flight bot branch fix/2402-response-language-orchestrator-coverage (seven commits, never pushed) onto current origin/next as a single squashed commit. The original work was substantial and correct; this commit preserves its full scope, trimmed where rebase conflicts + workflow size budgets required it. Three independent layers where response_language was being dropped are closed: Layer 1 — orchestrator-facing directives across workflows. Adds the strong "All user-facing output in this workflow MUST be presented in {response_language}; technical terms, code, paths, and subagent prompts stay in English" directive to ~40 workflows that previously either lacked it entirely (verify-work, new-project, new-milestone, quick, manager, and ~35 more) or carried only the weak subagent-prompt-only form (plan-phase, execute-phase). The directive covers narration between tool calls and banner output, not just the AskUserQuestion prompts. Layer 2 — UAT checkpoint renderer (src/uat.cts). buildCheckpoint now accepts an optional responseLanguage parameter and renders the frame strings ("CHECKPOINT: Verification Required", "Type `pass` or describe what's wrong.") in any of 9 languages (English/Spanish/French/German/Portuguese/Japanese/ Chinese/Korean/Italian) with an alias table covering ~30 input variants (en, es, español, ja, 日本語, etc.). cmdRenderCheckpoint reads config.response_language via loadConfig(cwd) and passes it through, so the byte-for-byte block verify-work.md reprints verbatim is already localized when written — preserving the anti-injection hygiene rule at verify-work.md (the model is forbidden to translate after the fact). CJK display width is computed by East Asian Width property ranges (W/F) so the right ║ border of the banner stays aligned for full-width characters. English fallback is byte-identical to the pre-fix behavior when response_language is unset or unrecognized. Layer 3 — literal English report templates in execute-phase. The top-of- workflow directive covers all template sites (templates are a structural source, not literal output). Inline render-language notes that previously sat at each template site were removed during the squash because they pushed execute-phase.md over its frozen pre-phase-6 byte ceiling (93600 — ADR-857 Phase 6 capstone). The single top directive covers the same surface with fewer bytes. Also extends src/docs.cts and src/init.cts to propagate response_language into the init JSON bundle of the additional workflows so the directive can read it. Tests added: - tests/uat.test.cjs: buildCheckpoint with unset/unrecognized language falls back to English default; recognized language swaps only the two frame strings while structural lines stay untouched; CJK display-width regression (independent recomputation of East Asian Width W/F ranges). - tests/workspace.test.cjs, tests/docs-update.test.cjs: response_language wiring through docs.cts/init.cts. References: #2402; reporter's three-layer triage + Layer-4 follow-up; the byte-for-byte anti-injection hygiene rule at verify-work.md (the reason Layer 2 must be renderer-side, not model-translated). This is a squash of the in-flight bot branch — seven commits representing the original implementation plus its subsequent fix/CJK-padding/test/ changeset/regen cycles, none of which were ever pushed or PR'd. The squash captures the final coherent state. * chore(#2402): backfill pr:2457 in .changeset/2402-response-language-orchestrator-coverage.md * chore(#2402): regen golden + size baseline after rebase against #2315 (PR #2451) Rebase conflicts were entirely in generated artifacts (golden-install-parity fixtures + workflow-size-baseline.json). After taking theirs during rebase, regenerated cleanly against the merged source tree.
16 KiB
This command is deliberately separate from /gsd:settings (workflow toggles)
and any /gsd-settings-advanced tuning surface. It exists because API keys and
cross-tool routing are connectivity concerns, not workflow or tuning knobs.
- Masking convention:
****<last-4>(e.g.sk-abc123def456→****f456). Strings shorter than 8 characters render as****with no tail so a short secret does not leak a meaningful fraction of its bytes. Unset values render as(unset). - Plaintext is never echoed by AskUserQuestion descriptions, confirmation
tables, or any log line. It is not written to any file under
.planning/other thanconfig.jsonitself. config-setoutput is masked for keys in the secret set (brave_search,firecrawl,exa_search) — seegsd-core/bin/lib/secrets.cjs.- Agent-type and CLI slug validation.
agent_skills.<agent-type>andreview.models.<cli>keys are matched against^[a-zA-Z0-9_-]+$. Inputs containing path separators (/,\,..), whitespace, or shell metacharacters are rejected. This closes off skill-injection attacks.
<required_reading> Read all files referenced by the invoking prompt's execution_context before starting. </required_reading>
Ensure config exists and resolve the active config path (flat vs workstream, #2282):_GSD_SHIM_NAME="gsd-tools.cjs"; _GSD_RUNTIME_ROOT="${RUNTIME_DIR:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}"; GSD_TOOLS="${_GSD_RUNTIME_ROOT}/gsd-core/bin/${_GSD_SHIM_NAME}"; if [ -f "$GSD_TOOLS" ]; then gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${_GSD_RUNTIME_ROOT}/.claude/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${_GSD_RUNTIME_ROOT}/.claude/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${_GSD_RUNTIME_ROOT}/.codex/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${_GSD_RUNTIME_ROOT}/.codex/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif command -v gsd-tools >/dev/null 2>&1; then GSD_TOOLS="$(command -v gsd-tools)"; gsd_run() { "$GSD_TOOLS" "$@"; }; elif [ -f "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CLAUDE_CONFIG_DIR:-$HOME/.claude}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${HERMES_HOME:-$HOME/.hermes}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${HERMES_HOME:-$HOME/.hermes}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CURSOR_CONFIG_DIR:-$HOME/.cursor}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CURSOR_CONFIG_DIR:-$HOME/.cursor}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CODEX_HOME:-$HOME/.codex}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CODEX_HOME:-$HOME/.codex}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${GEMINI_CONFIG_DIR:-$HOME/.gemini}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${GEMINI_CONFIG_DIR:-$HOME/.gemini}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${COPILOT_CONFIG_DIR:-$HOME/.copilot}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${COPILOT_CONFIG_DIR:-$HOME/.copilot}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${WINDSURF_CONFIG_DIR:-$HOME/.codeium/windsurf}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${WINDSURF_CONFIG_DIR:-$HOME/.codeium/windsurf}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${AUGMENT_CONFIG_DIR:-$HOME/.augment}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${AUGMENT_CONFIG_DIR:-$HOME/.augment}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${TRAE_CONFIG_DIR:-$HOME/.trae}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${TRAE_CONFIG_DIR:-$HOME/.trae}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${QWEN_CONFIG_DIR:-$HOME/.qwen}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${QWEN_CONFIG_DIR:-$HOME/.qwen}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CODEBUDDY_CONFIG_DIR:-$HOME/.codebuddy}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CODEBUDDY_CONFIG_DIR:-$HOME/.codebuddy}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${CLINE_CONFIG_DIR:-$HOME/.cline}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${CLINE_CONFIG_DIR:-$HOME/.cline}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${GROK_AGENTS_HOME:-$HOME/.agents}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${GROK_AGENTS_HOME:-$HOME/.agents}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${ANTIGRAVITY_CONFIG_DIR:-$HOME/.gemini/antigravity}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${ANTIGRAVITY_CONFIG_DIR:-$HOME/.gemini/antigravity}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${OPENCODE_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/opencode}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${OPENCODE_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/opencode}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; elif [ -f "${KILO_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/kilo}/gsd-core/bin/${_GSD_SHIM_NAME}" ]; then GSD_TOOLS="${KILO_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/kilo}/gsd-core/bin/${_GSD_SHIM_NAME}"; gsd_run() { node "$GSD_TOOLS" "$@"; }; else echo "ERROR: gsd-tools.cjs not found at $GSD_TOOLS and gsd-tools is not on PATH. Run: npx -y @opengsd/gsd-core@latest --claude --local" >&2; exit 1; fi; if [ -n "${CLAUDE_ENV_FILE:-}" ] && [ -n "${GSD_TOOLS:-}" ]; then printf "export PATH='%s':\"\$PATH\"\n" "${GSD_TOOLS%/*}" >> "$CLAUDE_ENV_FILE" 2>/dev/null || true; fi
RESPONSE_LANGUAGE=$(gsd_run query config-get response_language --default "" 2>/dev/null || echo "")
gsd_run query config-ensure-section
if [[ -z "${GSD_CONFIG_PATH:-}" ]]; then
if [[ -f .planning/active-workstream ]]; then
WS=$(tr -d '\n\r' < .planning/active-workstream)
GSD_CONFIG_PATH=".planning/workstreams/${WS}/config.json"
else
GSD_CONFIG_PATH=".planning/config.json"
fi
fi
If response_language is set: All user-facing questions, prompts, and explanations in this workflow MUST be presented in {response_language}. Technical terms, code, file paths, and subagent prompts stay in English — only user-facing output is translated.
Store $GSD_CONFIG_PATH. Every subsequent read/write uses it.
(unset)— field is null / missing****<last-4>— secret field that is populated (plaintext never shown)<value>— non-secret routing/skill string, shown as-is
BRAVE=$(gsd_run query config-get brave_search --default null)
FIRECRAWL=$(gsd_run query config-get firecrawl --default null)
EXA=$(gsd_run query config-get exa_search --default null)
SEARCH_GITIGNORED=$(gsd_run query config-get search_gitignored --default false)
For each secret key (brave_search, firecrawl, exa_search) the displayed
value is ****<last-4> when set, never the raw string. Never echo the
plaintext to stdout, stderr, or any log.
Text mode (workflow.text_mode: true or --text flag): Set
TEXT_MODE=true and replace every AskUserQuestion call with a plain-text
numbered list. Required for non-Claude runtimes.
Ask the user what they want to do for each search API key. For keys that are
already set, show **** already set and offer Leave / Replace / Clear. For
unset keys, offer Skip / Set.
AskUserQuestion([
{
question: "Brave Search API key — used for web research during plan/discuss phases",
header: "Brave",
multiSelect: false,
options: [
// When already set:
{ label: "Leave (**** already set)", description: "Keep current value" },
{ label: "Replace", description: "Enter a new API key" },
{ label: "Clear", description: "Remove the stored key" }
// When unset, use the two-option shape: Skip / Set.
]
},
{
question: "Firecrawl API key — used for deep-crawl scraping",
header: "Firecrawl",
multiSelect: false,
options: [ /* same Leave/Replace/Clear or Skip/Set */ ]
},
{
question: "Exa Search API key — used for semantic search",
header: "Exa",
multiSelect: false,
options: [ /* same Leave/Replace/Clear or Skip/Set */ ]
},
{
question: "Include gitignored files in local code searches?",
header: "Gitignored",
multiSelect: false,
options: [
{ label: "No (Recommended)", description: "Respect .gitignore. Safer — excludes secrets, node_modules, build artifacts." },
{ label: "Yes", description: "Include gitignored files. Useful when secrets/artifacts genuinely contain searchable intent." }
]
}
])
For each "Set" or "Replace", follow with a text-input prompt that asks for the key value. The answer must not be echoed back in subsequent question descriptions or confirmation text. Write the value via:
gsd_run query config-set brave_search "<value>" # masked in output
gsd_run query config-set firecrawl "<value>" # masked in output
gsd_run query config-set exa_search "<value>" # masked in output
gsd_run query config-set search_gitignored true|false
For "Clear", write null:
gsd_run query config-set brave_search null
review.models.<cli> is a map that tells the code-review workflow which
shell command to invoke for a given reviewer flavor. Supported flavors:
claude, codex, gemini, opencode.
AskUserQuestion([
{
question: "Review model CLI mapping — what next?",
header: "Review",
multiSelect: false,
options: [
{ label: "Configure CLI", description: "Pick a reviewer flavor and set/clear its command" },
{ label: "Done", description: "Finish this section" }
]
}
])
If "Configure CLI" is selected, ask:
AskUserQuestion([
{
question: "Which reviewer CLI do you want to configure?",
header: "CLI",
multiSelect: false,
options: [
{ label: "Claude", description: "review.models.claude — defaults to session model when unset" },
{ label: "Codex", description: "review.models.codex — bare model id injected into --model, e.g. 'gpt-5'" },
{ label: "Gemini", description: "review.models.gemini — bare model id injected into -m, e.g. 'gemini-2.5-pro'" },
{ label: "OpenCode", description: "review.models.opencode — bare model id injected into --model, e.g. 'claude-sonnet-4'" }
]
}
])
For the selected CLI, show the current value (or (unset)) and offer
Leave / Replace / Clear, followed by a text-input prompt for the model id
string. Write via:
gsd_run query config-set review.models.<cli> "<model id>"
After each update, return to the "Review model CLI mapping — what next?" question. Loop until the user selects "Done".
The review.models.<cli> key is validated by the dynamic pattern
^review\.models\.[a-zA-Z0-9_-]+$. Empty CLI slugs and path-containing slugs
are rejected by config-set before any write.
agent_skills.<agent-type> injects extra skill names into an agent's spawn
frontmatter. The slug is user-extensible, so input is free-text validated
against ^[a-zA-Z0-9_-]+$. Inputs with path separators, spaces, or shell
metacharacters are rejected.
AskUserQuestion([
{
question: "Agent skills mapping — what next?",
header: "Agent Skills",
multiSelect: false,
options: [
{ label: "Configure agent", description: "Pick an agent type and set/clear skills" },
{ label: "Done", description: "Finish this section" }
]
}
])
If "Configure agent" is selected, ask:
AskUserQuestion([
{
question: "Configure agent_skills for which agent type?",
header: "Agent Type",
multiSelect: false,
options: [
{ label: "gsd-executor", description: "Skills injected when spawning executor agents" },
{ label: "gsd-planner", description: "Skills injected when spawning planner agents" },
{ label: "gsd-verifier", description: "Skills injected when spawning verifier agents" },
{ label: "Custom…", description: "Enter a custom agent-type slug" }
]
}
])
For "Custom…", prompt for a slug and validate it matches
^[a-zA-Z0-9_-]+$. If it fails validation, print:
Rejected: agent-type '<slug>' must match [a-zA-Z0-9_-]+ (no path separators,
spaces, or shell metacharacters).
and re-prompt.
For a selected slug, prompt for the comma-separated skill list (text input). Show the current value if any, offer Leave / Replace / Clear. Write via:
gsd_run query config-set agent_skills.<slug> "<skill-a,skill-b,skill-c>"
After each update, return to the "Agent skills mapping — what next?" question. Loop until "Done".
Display the masked confirmation table. **No plaintext API keys appear in this output under any circumstance.**━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
GSD ► INTEGRATIONS UPDATED
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Search Integrations
| Field | Value |
|--------------------|-------------------|
| brave_search | ****<last-4> | (or "(unset)")
| firecrawl | ****<last-4> |
| exa_search | ****<last-4> |
| search_gitignored | true | false |
Code Review CLI Routing
| CLI | Command |
|-------------|--------------------------------------|
| claude | <value or (session model default)> |
| codex | <value or (unset)> |
| gemini | <value or (unset)> |
| opencode | <value or (unset)> |
Agent Skills Injection
| Agent Type | Skills |
|------------------|---------------------------|
| <slug> | <skill-a, skill-b> |
| ... | ... |
Notes:
- API keys are stored plaintext in .planning/config.json. The confirmation
table above never displays plaintext — keys appear as ****<last-4>.
- Plaintext is not echoed back by this workflow, not written to any log,
and not displayed in error messages.
Quick commands:
- /gsd:settings — workflow toggles and model profile
- /gsd-set-profile <profile> — switch model profile
<success_criteria>
- Current config read from
$GSD_CONFIG_PATH - User presented with three sections: Search Integrations, Review CLI Routing, Agent Skills Injection
- API keys written plaintext only to
config.json; never echoed, never logged, never displayed - Masked confirmation table uses
****<last-4>for set keys and(unset)for null review.models.<cli>andagent_skills.<agent-type>keys validated against[a-zA-Z0-9_-]+before write- Config merge preserves all keys outside the three sections this workflow owns </success_criteria>