Cover the composable helpers extracted from deriveStateFromDb:
reconcileDiskToDb, buildCompletenessSet, buildRegistryAndFindActive,
handleNoActiveMilestone, resolveSliceDependencies, reconcileSliceTasks,
detectBlockers, checkReplanTrigger, checkInterruptedWork, and queue
order sorting.
Extracts the monolithic deriveStateFromDb function into distinct,
composable helper functions (reconcileDiskToDb, resolveSliceDependencies,
detectBlockers, etc.) inside state.ts.
Resolves technical debt identified during the code quality audit by
drastically reducing cyclomatic complexity while preserving the exact
type signature and logical behavior.
Also removes duplicate disk->DB reconciliation that could overwrite
milestone statuses.
Implements file-level advisory locking via proper-lockfile to ensure
atomic read-modify-write sequences in:
- compactMilestoneEvents (event-log.jsonl)
- custom-workflow-engine reconcile (GRAPH.yaml)
Fixes silent data loss when concurrent auto-mode or dashboard
sessions overlap in these operations.
This fixes an issue where MCP workflow tools (e.g. gsd_plan_slice) would return error details in their JSON response, but without setting the 'isError: true' flag at the top level of the tool response payload. This caused MCP clients (like Claude Code) to interpret failed validations (like empty tasks arrays) as successes and get stuck in infinite validation failure loops.
The depth verification gate and multi-milestone readiness gate
unconditionally referenced ask_user_questions. On transports where
structuredQuestionsAvailable is false, this would trap the flow in
re-ask loops.
Add {{structuredQuestionsAvailable}} conditionals to:
- Depth verification (true: ask_user_questions, false: plain text)
- Multi-milestone Phase 3 readiness gate
- Per-milestone technical assumption verification
The discuss.md prompt (used for /gsd new project creation) only asked
"What's the vision?" once and relied on LLM judgment for follow-ups.
This led to the agent asking a single question then jumping straight
to planning without gathering enough context.
Add explicit Question Rounds section with:
- 1-3 questions per round structure
- Conditional ask_user_questions vs plain text support
- Incremental persistence (CONTEXT-DRAFT save every 2 rounds)
- Depth-matching rule (1-2 rounds for simple, 4+ for large visions)
- Round cadence that drives toward the depth enforcement checklist
Thread structuredQuestionsAvailable through buildDiscussPrompt() and
prepareAndBuildDiscussPrompt() so the template variable resolves
correctly at runtime.
Closes#3976
resolvePreferredModelConfig now skips routing-ceiling synthesis when
isAutoMode=false, preventing interactive dispatches from silently switching
to the tier_models.heavy model. The auto-start banner now reflects
effective routing state by checking flat-rate provider suppression and
using the actual ceiling from tier_models.heavy when configured.
Dynamic routing silently downgraded models in interactive commands (guided-flow),
overriding the user's /model selection. Now routing only applies in auto-mode where
cost optimization is expected. Model downgrade notifications always fire regardless
of verbose setting, and auto-mode shows routing status upfront on start.
Convert resource-loader import path to file URL via pathToFileURL() to
fix Windows ERR_UNSUPPORTED_ESM_URL_SCHEME. Update existing regression
test to validate the GSD_PKG_ROOT + pathToFileURL contract.
Auto-mode resume crashed with "Cannot find module" because the relative
import ../../../resource-loader.js only works from the source tree, not
from the deployed path at ~/.gsd/agent/extensions/gsd/auto.js.
Expose GSD_PKG_ROOT from loader.ts and use it in auto.ts to construct
an absolute path to dist/resource-loader.js that works in both contexts.
Delete the Anthropic OAuth module, remove it from the built-in provider
registry, strip the OAuth client branch from the Anthropic streaming
provider, and replace the daemon orchestrator's token refresh with a
simple ANTHROPIC_API_KEY requirement.
Anthropic access is now API key or local Claude Code CLI only.
Closes#3952
When running inside a cmux terminal, GSD now automatically enables cmux
in project preferences instead of showing a manual enable prompt. Users
who explicitly disabled cmux (enabled: false) are still respected.
Closesgsd-build/gsd-2#3947
.agents/, .bg-shell/, .idea/, venv/, target/, .cache/, and tmp/ were
missing from DEFAULT_EXCLUDES. This caused /gsd-new-project to scan
skill and agent definition files as project code, confusing researcher
agents during project initialization.
Aligns the exclude list with the gitignore patterns in gitignore.ts.
Addresses Codex adversarial review findings — the ADR-005 registries
and filters were built but not connected to the actual model selection
and provider adapter paths.
Fix 1+2: Tool filtering applied after model selection
- selectAndApplyModel() now calls adjustToolSet() after pi.setModel()
- Incompatible tools are removed via pi.setActiveTools()
- adjust_tool_set hook fires to allow extension overrides
- Verbose output reports filtered tools with provider context
Fix 3: ProviderSwitchReport wired through all 6 provider adapters
- New transformMessagesWithReport() convenience wrapper creates report,
passes it to transformMessages(), and logs non-empty reports to stderr
when GSD_VERBOSE=1 or PI_VERBOSE=1
- All adapters updated: anthropic, google, openai-responses,
openai-completions, mistral, bedrock
Close three remaining gaps from ADR-004:
1. Add modelOverrides to GSDPreferences type — removes unsafe type cast
in auto-model-selection.ts, enables TypeScript validation for user
capability override config.
2. Add profile completeness lint test — two tests in capability-router
that fail if MODEL_CAPABILITY_TIER and MODEL_CAPABILITY_PROFILES
drift out of sync (catches stale profiles on new model additions).
3. Add capability profiles for all 24 missing tier-mapped models — goes
from 9 to 33 profiles, organized by provider. Values reflect each
model family's known strengths (o-series high reasoning, nano/spark
high speed, codex variants high coding).
Closes#2659
