feat(i18n): add response_language config for cross-phase language consistency (#1412)

* feat(i18n): add response_language config for cross-phase language consistency

Adds `response_language` config key that propagates through all init
outputs via withProjectRoot(). Workflows read this field and instruct
agents to present user-facing questions in the configured language,
solving the problem of language preference resetting at phase boundaries.

Usage: gsd-tools config-set response_language "Portuguese"

Closes #1399

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* test(security): allowlist discuss-phase.md for size threshold

discuss-phase.md legitimately exceeds 50K chars due to power mode
and i18n directives — not prompt stuffing.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

get-shit-done/bin/lib/config.cjs

@@ -29,6 +29,7 @@ const VALID_CONFIG_KEYS = new Set([
   'hooks.context_warnings',
   'project_code', 'phase_naming',
   'manager.flags.discuss', 'manager.flags.plan', 'manager.flags.execute',
+  'response_language',
 ]);
 
 /**

get-shit-done/bin/lib/core.cjs

@@ -357,6 +357,7 @@ function loadConfig(cwd) {
       model_overrides: parsed.model_overrides || null,
       agent_skills: parsed.agent_skills || {},
       manager: parsed.manager || {},
+      response_language: get('response_language') || null,
     };
   } catch {
     return defaults;

get-shit-done/bin/lib/init.cjs

@@ -37,6 +37,13 @@ function withProjectRoot(cwd, result) {
   const agentStatus = checkAgentsInstalled();
   result.agents_installed = agentStatus.agents_installed;
   result.missing_agents = agentStatus.missing_agents;
+  // Inject response_language into all init outputs (#1399).
+  // Workflows propagate this to subagent prompts so user-facing questions
+  // stay in the configured language across phase boundaries.
+  const config = loadConfig(cwd);
+  if (config.response_language) {
+    result.response_language = config.response_language;
+  }
   return result;
 }
 

get-shit-done/references/planning-config.md

@@ -38,6 +38,7 @@ Configuration options for `.planning/` directory behavior.
 | `manager.flags.discuss` | `""` | Flags passed to `/gsd:discuss-phase` when dispatched from manager (e.g. `"--auto --analyze"`) |
 | `manager.flags.plan` | `""` | Flags passed to plan workflow when dispatched from manager |
 | `manager.flags.execute` | `""` | Flags passed to execute workflow when dispatched from manager |
+| `response_language` | `null` | Language for user-facing questions and prompts across all phases/subagents (e.g. `"Portuguese"`, `"Japanese"`, `"Spanish"`). When set, all spawned agents include a directive to respond in this language. |
 </config_schema>
 
 <commit_docs_behavior>

get-shit-done/workflows/discuss-phase.md

@@ -137,7 +137,9 @@ if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
 AGENT_SKILLS_ADVISOR=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" agent-skills gsd-advisor 2>/dev/null)
 ```
 
-Parse JSON for: `commit_docs`, `phase_found`, `phase_dir`, `phase_number`, `phase_name`, `phase_slug`, `padded_phase`, `has_research`, `has_context`, `has_plans`, `has_verification`, `plan_count`, `roadmap_exists`, `planning_exists`.
+Parse JSON for: `commit_docs`, `phase_found`, `phase_dir`, `phase_number`, `phase_name`, `phase_slug`, `padded_phase`, `has_research`, `has_context`, `has_plans`, `has_verification`, `plan_count`, `roadmap_exists`, `planning_exists`, `response_language`.
+
+**If `response_language` is set:** All user-facing questions, prompts, and explanations in this workflow MUST be presented in `{response_language}`. This includes AskUserQuestion labels, option text, gray area descriptions, and discussion summaries. Technical terms, code, and file paths remain in English. Subagent prompts stay in English — only user-facing output is translated.
 
 **If `phase_found` is false:**
 ```

get-shit-done/workflows/execute-phase.md

@@ -66,7 +66,9 @@ if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
 AGENT_SKILLS=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" agent-skills gsd-executor 2>/dev/null)
 ```
 
-Parse JSON for: `executor_model`, `verifier_model`, `commit_docs`, `parallelization`, `branching_strategy`, `branch_name`, `phase_found`, `phase_dir`, `phase_number`, `phase_name`, `phase_slug`, `plans`, `incomplete_plans`, `plan_count`, `incomplete_count`, `state_exists`, `roadmap_exists`, `phase_req_ids`.
+Parse JSON for: `executor_model`, `verifier_model`, `commit_docs`, `parallelization`, `branching_strategy`, `branch_name`, `phase_found`, `phase_dir`, `phase_number`, `phase_name`, `phase_slug`, `plans`, `incomplete_plans`, `plan_count`, `incomplete_count`, `state_exists`, `roadmap_exists`, `phase_req_ids`, `response_language`.
+
+**If `response_language` is set:** Include `response_language: {value}` in all spawned subagent prompts so any user-facing output stays in the configured language.
 
 Read worktree config:
 

get-shit-done/workflows/plan-phase.md

@@ -32,7 +32,9 @@ CONTEXT_WINDOW=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" config-get
 
 When `CONTEXT_WINDOW >= 500000`, the planner prompt includes prior phase CONTEXT.md files so cross-phase decisions are consistent (e.g., "use library X for all data fetching" from Phase 2 is visible to Phase 5's planner).
 
-Parse JSON for: `researcher_model`, `planner_model`, `checker_model`, `research_enabled`, `plan_checker_enabled`, `nyquist_validation_enabled`, `commit_docs`, `text_mode`, `phase_found`, `phase_dir`, `phase_number`, `phase_name`, `phase_slug`, `padded_phase`, `has_research`, `has_context`, `has_reviews`, `has_plans`, `plan_count`, `planning_exists`, `roadmap_exists`, `phase_req_ids`.
+Parse JSON for: `researcher_model`, `planner_model`, `checker_model`, `research_enabled`, `plan_checker_enabled`, `nyquist_validation_enabled`, `commit_docs`, `text_mode`, `phase_found`, `phase_dir`, `phase_number`, `phase_name`, `phase_slug`, `padded_phase`, `has_research`, `has_context`, `has_reviews`, `has_plans`, `plan_count`, `planning_exists`, `roadmap_exists`, `phase_req_ids`, `response_language`.
+
+**If `response_language` is set:** Include `response_language: {value}` in all spawned subagent prompts so any user-facing output stays in the configured language.
 
 **File paths (for <files_to_read> blocks):** `state_path`, `roadmap_path`, `requirements_path`, `context_path`, `research_path`, `verification_path`, `uat_path`, `reviews_path`. These are null if files don't exist.