Commit Graph

15 Commits

Author SHA1 Message Date
Lex Christopherson
60ccba9446 feat: add Brave Search integration for researchers
- Add `websearch` command to gsd-tools.js for Brave API
- Detect BRAVE_API_KEY env var or ~/.gsd/brave_api_key file
- Persist brave_search setting to config.json on project init
- Update researcher agents to check config before calling

Graceful degradation: if brave_search is false, agents use
built-in WebSearch without wasted Bash calls.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-08 10:36:26 -06:00
TÂCHES
246d542c65 feat(gsd-tools): add compound init commands and update workflows (#468)
* feat(gsd-tools): add compound init commands for workflow setup

Adds 8 compound commands that return all context a workflow needs in
one JSON blob, replacing 5-10 atomic calls per workflow:

- init execute-phase: models, config, phase info, plan inventory
- init plan-phase: models, workflow flags, existing artifacts
- init new-project: models, brownfield detection, state checks
- init new-milestone: models, milestone info
- init quick: models, next task number, timestamps
- init resume: file existence, interrupted agent
- init verify-work: models, phase info
- init phase-op: generic phase context

Updated 8 workflows to use compound commands:
- execute-phase, plan-phase, new-project, quick
- resume-project, verify-work, discuss-phase

Token savings: ~200 lines of bash setup replaced with single init calls.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* feat(gsd-tools): add 4 new init commands and update files to use compound commands

Add new compound init commands:
- init todos - context for todo workflows
- init milestone-op - context for milestone operations
- init map-codebase - context for codebase mapping
- init progress - context for progress workflow

Update 24 files to use compound init commands instead of atomic calls:
- 4 phase operation workflows (add-phase, insert-phase, remove-phase, verify-phase)
- 5 todo/milestone workflows (add-todo, check-todos, audit-milestone, complete-milestone, new-milestone)
- 6 misc workflows (execute-plan, map-codebase, pause-work, progress, set-profile, settings)
- 6 agent files (gsd-executor, gsd-planner, gsd-phase-researcher, gsd-plan-checker, gsd-debugger, gsd-research-synthesizer)
- 2 command files (debug, research-phase)
- 1 reference file (planning-config)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix(gsd-tools): add init to help output

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix(verify-phase): correct expected init fields

The workflow was referencing plans/summaries from init phase-op,
but those fields come from ls command. Updated to reference
has_plans and plan_count which are actually in phase-op output.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-07 22:09:07 -06:00
TÂCHES
d44c7dcc9b refactor: update commands, workflows, agents for gsd-tools integration
Commands (15): audit-milestone, complete-milestone, debug, execute-phase,
help, insert-phase, new-milestone, new-project, plan-milestone-gaps,
plan-phase, progress, quick, remove-phase, research-phase, verify-work

Workflows (22): execute-plan (69% reduction), verify-phase (55%), others
Agents (14): All updated for new workflow structure

Total token savings: ~22k chars (75.6% in affected sections)

Ported from: get-shit-done-v2@d1fb2d5, 7f79a9b
2026-02-07 11:25:35 -06:00
Lex Christopherson
cc3c6aca56 revert: remove GSD Memory system (not ready for release)
Reverts af7a057 "feat: add GSD Memory cross-project knowledge system"

The memory system needs more work before shipping:
- Workflow integration is incomplete (writes but doesn't query)
- UX requires too much manual intervention
- Setup friction exceeds value for most users

Preserved on branch `memory-wip` for continued development.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-06 09:48:09 -06:00
Lex Christopherson
af7a057294 feat: add GSD Memory cross-project knowledge system
Implements MCP server for semantic search across GSD projects:

MCP Tools:
- gsd_memory_search: Search across all registered projects
- gsd_memory_decisions: Find decisions from SUMMARY/PROJECT.md
- gsd_memory_patterns: Find patterns from SUMMARY.md
- gsd_memory_pitfalls: Find pitfalls from RESEARCH.md
- gsd_memory_stack: Find tech stack entries
- gsd_memory_register: Register project with memory
- gsd_memory_index: Trigger indexing/update
- gsd_memory_status: Show system status

Architecture:
- QMD wrapper with grep fallback when QMD unavailable
- YAML frontmatter extractors for GSD document types
- Project registry at ~/.gsd/projects.json
- Auto-install via bin/install.js for Claude Code

Workflow integrations:
- new-project: Registers project with memory
- plan-phase: Indexes after planning
- execute-phase: Indexes after execution
- complete-milestone: Indexes milestone completion
- Researcher agents query memory before Context7

Tests: 117 passing (66 unit + 51 integration)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-05 13:13:22 -06:00
Solvely-Colin
161aa61137 fix: researcher agent always writes RESEARCH.md regardless of commit_docs
Fixes #343

The agent was misinterpreting commit_docs=false as 'skip file write'
when it should only skip git commit operations.

Changes:
- Explicitly state Write tool is mandatory in Step 5
- Clarify commit_docs only affects git operations, not file writes
- Rename Step 6 to indicate it's optional
- Make the file-write-then-commit order explicit
2026-02-03 11:10:57 -06:00
TÂCHES
ecbc692bc9 fix(#326): enforce context fidelity in planning pipeline (#391)
* prompt(001): map dependencies for new-project command

* fix(#326): enforce context fidelity in planning pipeline

Root cause: User decisions from CONTEXT.md were available but not
enforced throughout the RESEARCH → PLAN → VERIFY chain.

Changes:
- gsd-planner: Add <context_fidelity> section requiring agents to
  parse and honor user decisions BEFORE creating tasks. Includes
  self-check checklist and conflict handling guidance.

- gsd-phase-researcher: Add User Constraints as FIRST section in
  downstream consumer table. Require researcher to copy CONTEXT.md
  decisions verbatim to RESEARCH.md so planner sees them even if
  it only skims.

- research.md template: Add <user_constraints> section that must
  be populated first. Locked decisions, Claude's discretion, and
  deferred ideas copied verbatim from CONTEXT.md.

The command file (commands/gsd/plan-phase.md) already passes
CONTEXT_CONTENT to all agents. These changes add the enforcement
layer in the agent instructions.

Fixes #326, #216, #206

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-03 09:17:17 -06:00
Cristian Uibar
5660b6fc0b fix: Gemini CLI agent loading errors (#347)
* fix: convert agent frontmatter for Gemini CLI compatibility

- Add claudeToGeminiTools mapping (Read→read_file, Bash→run_shell_command, etc.)
- Add convertGeminiToolName() to map tools and filter out mcp__*/Task
- Add convertClaudeToGeminiAgent() to convert agent YAML frontmatter
- Hook conversion into agent copy logic for Gemini installs
- Fixes: tools as YAML array (not string), color field removed, mcp__* excluded

* fix: enable experimental.enableAgents for Gemini CLI installs

* fix: strip HTML <sub> tags for Gemini CLI terminal output

* fix: replace ${VAR} with $VAR in agent templates to avoid Gemini CLI template parsing
2026-01-29 19:43:01 -06:00
dan bachelder
1f18ec8907 feat: add uncommitted planning mode (#107)
* feat: add uncommitted planning mode

Add config option to keep planning docs local-only (not committed to git).
Useful for OSS contributions, client projects, or keeping planning private.

Config options in .planning/config.json:
- planning.commit_docs: true/false (default: true)
- planning.search_gitignored: true/false (default: false)

When commit_docs=false:
- All git operations for .planning/ files are skipped
- User should add .planning/ to .gitignore
- Planning system works normally, just not tracked

Updated files:
- config.json template: added planning section
- execute-plan.md: conditional git commits
- execute-phase.md: conditional git commits
- create-roadmap.md: conditional git commits
- help.md: documented new config options
- planning-config.md: reference doc for config behavior

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* feat: extend commit_docs check to all agents/commands/workflows

Add COMMIT_PLANNING_DOCS config check to all files that commit
.planning/ artifacts, ensuring consistent behavior when
commit_docs=false is set in config.json.

Updated:
- 5 agents (planner, executor, debugger, phase-researcher, synthesizer)
- 8 commands (add-todo, check-todos, execute-phase, new-milestone,
  pause-work, plan-milestone-gaps, remove-phase, research-project)
- 7 workflows (complete-milestone, create-milestone, define-requirements,
  diagnose-issues, discuss-phase, map-codebase, verify-work)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix(progress): use Bash instead of Glob for .planning/ check

Glob respects .gitignore, so projects with gitignored .planning/
directories would fail with "No planning structure found."

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix(new-milestone): integrate full research/requirements/roadmap flow

Previously routed to non-existent /gsd:research-project and
/gsd:define-requirements commands. Now handles the full flow inline
like new-project does:

- Phase 7: Research Decision (spawns 4 milestone-aware researchers)
- Phase 8: Define Requirements (scopes features, creates REQUIREMENTS.md)
- Phase 9: Create Roadmap (continues phase numbering from previous milestone)
- Phase 10: Done

Key adaptations for milestones:
- Research focuses on NEW features only
- Requirements add to existing, don't start fresh
- Phase numbering continues from previous milestone

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-19 16:49:05 -06:00
Lex Christopherson
6ad1d0a318 fix(agents): remove hardcoded 2025 year from search query examples
Researcher agents were using literal "2025" in query template examples,
causing Claude to copy them verbatim instead of using the actual current
year. Changed to [current year] placeholder with explicit instruction to
check today's date.

Fixes #164

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-19 14:40:19 -06:00
Lex Christopherson
a31f730f62 fix: phase directory matching and orphaned references
- Support both zero-padded (05-*) and unpadded (5-*) phase folders
- Delete orphaned research-subagent-prompt.md template
- Update resume-project.md to use Task tool resume parameter

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-16 18:48:43 -06:00
Lex Christopherson
d7463e2f3f fix(researcher): hardcode read for CONTEXT.md
Researcher was only checking if CONTEXT.md exists (ls), not
actually reading it (cat). Added mandatory bash command to
read phase context file in step 1.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-16 13:31:58 -06:00
Lex Christopherson
339e0613d8 fix: consistent zero-padding and file naming across agents
- plan-phase.md: zero-pad phase number in mkdir
- roadmapper: explicit zero-padding instruction with printf
- discuss-phase workflow: use PADDED_PHASE in file paths
- planner: fix {plan}-PLAN.md -> {phase}-{plan}-PLAN.md
- researcher: fix double-path bug in git add command
- researcher: add CONTEXT.md loading from discuss-phase

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-16 13:17:26 -06:00
Lex Christopherson
d1df08cfbc feat(researcher): add upstream CONTEXT.md awareness
Researcher now reads and respects user decisions from discuss-phase:
- Locked decisions constrain research scope
- Claude's discretion areas get options explored
- Deferred ideas ignored

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-16 13:16:06 -06:00
Lex Christopherson
2144960c6c feat: integrate research into plan-phase with specialized agents
Split gsd-researcher into two specialized agents:
- gsd-phase-researcher: tailored for phase research before planning
- gsd-project-researcher: tailored for ecosystem research before roadmap

Updated /gsd:plan-phase to auto-research before planning:
- Research runs if no RESEARCH.md exists (silent use if exists)
- --research flag forces re-research
- --skip-research flag bypasses research entirely
- Researchers commit their output

This enables single-command workflow: /gsd:plan-phase does
research → plan → verify in one orchestrated flow.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-16 10:10:22 -06:00