Files
msd-core/gsd-core/workflows/smart-entry.md
Tom Boucher b6e6a22fce fix(#2402): honor response_language across orchestrator output + UAT checkpoint renderer (#2457)
* 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.
2026-07-20 14:22:27 -04:00

11 KiB

GSD smart entry — the state-aware front door. Detect the current project situation via `gsd-tools smart-entry --json`, present a short menu of the right next actions, and dispatch to exactly one existing GSD command. This is a launcher/router only; it never does the work itself.

This is a menu front door, not a second router. For in-project forward motion (planning → executing → verify-pending) the recommended action is /gsd:progress --next, which delegates to the single gated advancement engine (workflows/next.md: Route 0 resume-incomplete-phase + Gates 1-3). smart-entry adds value only where --next cannot reach: pre-project, remediation (paused/blocked/verify-failed), and lifecycle exits (idle-stranded/complete). See docs/adr/1787-gsd-next-smart-entry.md.

<required_reading> Read all files referenced by the invoking prompt's execution_context before starting. </required_reading>

**TEXT_MODE handling (non-Claude runtimes).**

Set TEXT_MODE=true if --text is present in $ARGUMENTS OR text_mode from init JSON is true. When TEXT_MODE is active, replace every AskUserQuestion call with a plain-text numbered list and ask the user to type their choice number. This is required for non-Claude runtimes (OpenAI Codex, Gemini CLI, etc.) where AskUserQuestion is not available.

**Resolve the gsd_run shim.**

Run this resolver block exactly. It locates gsd-tools.cjs across every supported runtime home and defines a gsd_run function. If it cannot find the tool, it prints the standard install hint and exits non-zero.

**Detect the situation.**
_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 "")
SNAPSHOT=$(gsd_run smart-entry --json 2>/dev/null)

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.

Parse SNAPSHOT as JSON. It has the shape:

{
  "situation": "executing",
  "recommended": "progress-next",
  "summary": "Phase 2 of 5 · 60% · executing",
  "signals": { "...": "..." },
  "actions": [
    { "id": "progress-next", "label": "Advance to the next step", "command": "/gsd:progress --next", "recommended": true },
    { "id": "execute-phase", "label": "Continue executing phase 2", "command": "/gsd:execute-phase", "recommended": false }
  ]
}

situation is one of: no-project, paused, blocked, verify-failed, needs-first-phase, planning, executing, verify-pending, idle-stranded, complete, unknown.

Fallback (never strand the user): smart-entry --json can fail for two reasons, and each has a different recovery. Parse SNAPSHOT; if it is empty, not valid JSON, or missing actions, apply the first matching recovery below — do NOT error.

  1. gsd-tools itself is broken (the failure is a Cannot find module ... / Node crash, not just an empty result). Probe by running gsd_run state-snapshot — if THAT also errors, the whole tool layer is down and routing to /gsd:progress would dead-end too (it also needs gsd-tools). Recover by reading state directly:

    • Read .planning/STATE.md (frontmatter + body) with the Read tool. Extract: status (frontmatter status: or body **Status:**), Phase: from the body, total_phases/percent from a nested progress: frontmatter object if present, and any ## Blockers items.
    • Synthesize a minimal result: situation = your best guess from the status text (executing/verifying/planning/complete/paused), summary = a one-line read ("Phase N of M · status"), and an actions list built from status (e.g. verifying → /gsd:verify-work, executing → /gsd:execute-phase, else /gsd:progress), always including /gsd:quick and /gsd:help.
    • Print one line first: smart-entry unavailable (gsd-tools error) — reading state directly. The gsd-tools layer may need a rebuild (rm tsconfig.build.tsbuildinfo && npm run build).
    • Proceed to the present step with this synthesized result.
  2. Only smart-entry is unavailable (e.g. older gsd-core without the subcommand; state-snapshot still works). Run /gsd:progress and stop. Print one line first: smart-entry unavailable — showing progress.

**Present the menu.**

Show the summary line to orient the user, then offer the actions.

If TEXT_MODE is false: call AskUserQuestion with:

  • header: a short label derived from situation (e.g. executing → "Continue work", blocked → "Unblock", no-project → "Get started", complete → "What next?").
  • question: the summary line, then "What would you like to do?"
  • options: the first 4 entries of actions[] in order. For each, label = the action's label, description = the action's command. The recommended action is already first; surface it as the first option. The user may also type a custom command (handled automatically).

If TEXT_MODE is true: print the summary, then a numbered list of ALL actions[] (not capped to 4 — text has no limit), then ask the user to type the number of their choice:

{summary}

  1. {actions[0].label}  ({actions[0].command})
  2. {actions[1].label}  ({actions[1].command})
  ...

Type a number, or describe what you want to do.

Wait for the user's response before continuing. Map the chosen number to the corresponding action.

**Show the routing decision.**
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 GSD ► SMART ENTRY
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

**Situation:** {situation}
**Routing to:** {chosen command}
**Dispatch and stop.**

Invoke the chosen action's command. If the user typed a free-form response instead of picking an action, treat it as freeform intent and route via /gsd:progress --do "<their text>".

After invoking the command, stop. The dispatched command owns everything from here. Do not continue, do not chain, do not re-enter this workflow.

<success_criteria>

  • Situation detected via gsd_run smart-entry --json
  • Summary shown to orient the user
  • Menu offered (AskUserQuestion, or numbered list under TEXT_MODE)
  • Routing decision displayed before dispatch
  • Exactly one command dispatched
  • Any detection failure falls back to /gsd:progress (never strands the user)
  • No work done directly — launcher only </success_criteria>