mirror of
https://github.com/basnijholt/adaptive-lighting.git
synced 2026-09-15 16:24:04 +02:00
Scaffold CDiT fork: planning artifacts and tooling
- openspec/ — three changes scoped:
• cdit-config-redesign: full artifact set (proposal + design + specs +
tasks), strict-validate green. Prunes 21 fields from the upstream
options flow, switches sun timing to entity-driven sources, hardcodes
a tanh curve, and breaks compat with upstream config entries.
• add-runtime-range-controls: proposal stub for promoting the 4
brightness/color-temp ranges to live number entities.
• house-mode-modes: proposal stub for per-AL house-mode behavior matrix
driving the runtime switches.
- .claude/ — opsx slash commands and openspec skill bundles for driving
the artifact-driven workflow.
- CLAUDE.md — fork orientation, remote topology, dev commands, and the
active change pointer.
This commit is contained in:
Casey
parent
ddaf851be3
commit
80f99db16f
31 changed files with 4569 additions and 0 deletions
152
.claude/commands/opsx/apply.md
Normal file
152
.claude/commands/opsx/apply.md
Normal file
|
|
@ -0,0 +1,152 @@
|
|||
---
|
||||
name: "OPSX: Apply"
|
||||
description: Implement tasks from an OpenSpec change (Experimental)
|
||||
category: Workflow
|
||||
tags: [workflow, artifacts, experimental]
|
||||
---
|
||||
|
||||
Implement tasks from an OpenSpec change.
|
||||
|
||||
**Input**: Optionally specify a change name (e.g., `/opsx:apply add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
|
||||
|
||||
**Steps**
|
||||
|
||||
1. **Select the change**
|
||||
|
||||
If a name is provided, use it. Otherwise:
|
||||
- Infer from conversation context if the user mentioned a change
|
||||
- Auto-select if only one active change exists
|
||||
- If ambiguous, run `openspec list --json` to get available changes and use the **AskUserQuestion tool** to let the user select
|
||||
|
||||
Always announce: "Using change: <name>" and how to override (e.g., `/opsx:apply <other>`).
|
||||
|
||||
2. **Check status to understand the schema**
|
||||
```bash
|
||||
openspec status --change "<name>" --json
|
||||
```
|
||||
Parse the JSON to understand:
|
||||
- `schemaName`: The workflow being used (e.g., "spec-driven")
|
||||
- Which artifact contains the tasks (typically "tasks" for spec-driven, check status for others)
|
||||
|
||||
3. **Get apply instructions**
|
||||
|
||||
```bash
|
||||
openspec instructions apply --change "<name>" --json
|
||||
```
|
||||
|
||||
This returns:
|
||||
- `contextFiles`: artifact ID -> array of concrete file paths (varies by schema)
|
||||
- Progress (total, complete, remaining)
|
||||
- Task list with status
|
||||
- Dynamic instruction based on current state
|
||||
|
||||
**Handle states:**
|
||||
- If `state: "blocked"` (missing artifacts): show message, suggest using `/opsx:continue`
|
||||
- If `state: "all_done"`: congratulate, suggest archive
|
||||
- Otherwise: proceed to implementation
|
||||
|
||||
4. **Read context files**
|
||||
|
||||
Read every file path listed under `contextFiles` from the apply instructions output.
|
||||
The files depend on the schema being used:
|
||||
- **spec-driven**: proposal, specs, design, tasks
|
||||
- Other schemas: follow the contextFiles from CLI output
|
||||
|
||||
5. **Show current progress**
|
||||
|
||||
Display:
|
||||
- Schema being used
|
||||
- Progress: "N/M tasks complete"
|
||||
- Remaining tasks overview
|
||||
- Dynamic instruction from CLI
|
||||
|
||||
6. **Implement tasks (loop until done or blocked)**
|
||||
|
||||
For each pending task:
|
||||
- Show which task is being worked on
|
||||
- Make the code changes required
|
||||
- Keep changes minimal and focused
|
||||
- Mark task complete in the tasks file: `- [ ]` → `- [x]`
|
||||
- Continue to next task
|
||||
|
||||
**Pause if:**
|
||||
- Task is unclear → ask for clarification
|
||||
- Implementation reveals a design issue → suggest updating artifacts
|
||||
- Error or blocker encountered → report and wait for guidance
|
||||
- User interrupts
|
||||
|
||||
7. **On completion or pause, show status**
|
||||
|
||||
Display:
|
||||
- Tasks completed this session
|
||||
- Overall progress: "N/M tasks complete"
|
||||
- If all done: suggest archive
|
||||
- If paused: explain why and wait for guidance
|
||||
|
||||
**Output During Implementation**
|
||||
|
||||
```
|
||||
## Implementing: <change-name> (schema: <schema-name>)
|
||||
|
||||
Working on task 3/7: <task description>
|
||||
[...implementation happening...]
|
||||
✓ Task complete
|
||||
|
||||
Working on task 4/7: <task description>
|
||||
[...implementation happening...]
|
||||
✓ Task complete
|
||||
```
|
||||
|
||||
**Output On Completion**
|
||||
|
||||
```
|
||||
## Implementation Complete
|
||||
|
||||
**Change:** <change-name>
|
||||
**Schema:** <schema-name>
|
||||
**Progress:** 7/7 tasks complete ✓
|
||||
|
||||
### Completed This Session
|
||||
- [x] Task 1
|
||||
- [x] Task 2
|
||||
...
|
||||
|
||||
All tasks complete! You can archive this change with `/opsx:archive`.
|
||||
```
|
||||
|
||||
**Output On Pause (Issue Encountered)**
|
||||
|
||||
```
|
||||
## Implementation Paused
|
||||
|
||||
**Change:** <change-name>
|
||||
**Schema:** <schema-name>
|
||||
**Progress:** 4/7 tasks complete
|
||||
|
||||
### Issue Encountered
|
||||
<description of the issue>
|
||||
|
||||
**Options:**
|
||||
1. <option 1>
|
||||
2. <option 2>
|
||||
3. Other approach
|
||||
|
||||
What would you like to do?
|
||||
```
|
||||
|
||||
**Guardrails**
|
||||
- Keep going through tasks until done or blocked
|
||||
- Always read context files before starting (from the apply instructions output)
|
||||
- If task is ambiguous, pause and ask before implementing
|
||||
- If implementation reveals issues, pause and suggest artifact updates
|
||||
- Keep code changes minimal and scoped to each task
|
||||
- Update task checkbox immediately after completing each task
|
||||
- Pause on errors, blockers, or unclear requirements - don't guess
|
||||
- Use contextFiles from CLI output, don't assume specific file names
|
||||
|
||||
**Fluid Workflow Integration**
|
||||
|
||||
This skill supports the "actions on a change" model:
|
||||
|
||||
- **Can be invoked anytime**: Before all artifacts are done (if tasks exist), after partial implementation, interleaved with other actions
|
||||
- **Allows artifact updates**: If implementation reveals design issues, suggest updating artifacts - not phase-locked, work fluidly
|
||||
157
.claude/commands/opsx/archive.md
Normal file
157
.claude/commands/opsx/archive.md
Normal file
|
|
@ -0,0 +1,157 @@
|
|||
---
|
||||
name: "OPSX: Archive"
|
||||
description: Archive a completed change in the experimental workflow
|
||||
category: Workflow
|
||||
tags: [workflow, archive, experimental]
|
||||
---
|
||||
|
||||
Archive a completed change in the experimental workflow.
|
||||
|
||||
**Input**: Optionally specify a change name after `/opsx:archive` (e.g., `/opsx:archive add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
|
||||
|
||||
**Steps**
|
||||
|
||||
1. **If no change name provided, prompt for selection**
|
||||
|
||||
Run `openspec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
|
||||
|
||||
Show only active changes (not already archived).
|
||||
Include the schema used for each change if available.
|
||||
|
||||
**IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
|
||||
|
||||
2. **Check artifact completion status**
|
||||
|
||||
Run `openspec status --change "<name>" --json` to check artifact completion.
|
||||
|
||||
Parse the JSON to understand:
|
||||
- `schemaName`: The workflow being used
|
||||
- `artifacts`: List of artifacts with their status (`done` or other)
|
||||
|
||||
**If any artifacts are not `done`:**
|
||||
- Display warning listing incomplete artifacts
|
||||
- Prompt user for confirmation to continue
|
||||
- Proceed if user confirms
|
||||
|
||||
3. **Check task completion status**
|
||||
|
||||
Read the tasks file (typically `tasks.md`) to check for incomplete tasks.
|
||||
|
||||
Count tasks marked with `- [ ]` (incomplete) vs `- [x]` (complete).
|
||||
|
||||
**If incomplete tasks found:**
|
||||
- Display warning showing count of incomplete tasks
|
||||
- Prompt user for confirmation to continue
|
||||
- Proceed if user confirms
|
||||
|
||||
**If no tasks file exists:** Proceed without task-related warning.
|
||||
|
||||
4. **Assess delta spec sync state**
|
||||
|
||||
Check for delta specs at `openspec/changes/<name>/specs/`. If none exist, proceed without sync prompt.
|
||||
|
||||
**If delta specs exist:**
|
||||
- Compare each delta spec with its corresponding main spec at `openspec/specs/<capability>/spec.md`
|
||||
- Determine what changes would be applied (adds, modifications, removals, renames)
|
||||
- Show a combined summary before prompting
|
||||
|
||||
**Prompt options:**
|
||||
- If changes needed: "Sync now (recommended)", "Archive without syncing"
|
||||
- If already synced: "Archive now", "Sync anyway", "Cancel"
|
||||
|
||||
If user chooses sync, use Task tool (subagent_type: "general-purpose", prompt: "Use Skill tool to invoke openspec-sync-specs for change '<name>'. Delta spec analysis: <include the analyzed delta spec summary>"). Proceed to archive regardless of choice.
|
||||
|
||||
5. **Perform the archive**
|
||||
|
||||
Create the archive directory if it doesn't exist:
|
||||
```bash
|
||||
mkdir -p openspec/changes/archive
|
||||
```
|
||||
|
||||
Generate target name using current date: `YYYY-MM-DD-<change-name>`
|
||||
|
||||
**Check if target already exists:**
|
||||
- If yes: Fail with error, suggest renaming existing archive or using different date
|
||||
- If no: Move the change directory to archive
|
||||
|
||||
```bash
|
||||
mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
|
||||
```
|
||||
|
||||
6. **Display summary**
|
||||
|
||||
Show archive completion summary including:
|
||||
- Change name
|
||||
- Schema that was used
|
||||
- Archive location
|
||||
- Spec sync status (synced / sync skipped / no delta specs)
|
||||
- Note about any warnings (incomplete artifacts/tasks)
|
||||
|
||||
**Output On Success**
|
||||
|
||||
```
|
||||
## Archive Complete
|
||||
|
||||
**Change:** <change-name>
|
||||
**Schema:** <schema-name>
|
||||
**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
|
||||
**Specs:** ✓ Synced to main specs
|
||||
|
||||
All artifacts complete. All tasks complete.
|
||||
```
|
||||
|
||||
**Output On Success (No Delta Specs)**
|
||||
|
||||
```
|
||||
## Archive Complete
|
||||
|
||||
**Change:** <change-name>
|
||||
**Schema:** <schema-name>
|
||||
**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
|
||||
**Specs:** No delta specs
|
||||
|
||||
All artifacts complete. All tasks complete.
|
||||
```
|
||||
|
||||
**Output On Success With Warnings**
|
||||
|
||||
```
|
||||
## Archive Complete (with warnings)
|
||||
|
||||
**Change:** <change-name>
|
||||
**Schema:** <schema-name>
|
||||
**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
|
||||
**Specs:** Sync skipped (user chose to skip)
|
||||
|
||||
**Warnings:**
|
||||
- Archived with 2 incomplete artifacts
|
||||
- Archived with 3 incomplete tasks
|
||||
- Delta spec sync was skipped (user chose to skip)
|
||||
|
||||
Review the archive if this was not intentional.
|
||||
```
|
||||
|
||||
**Output On Error (Archive Exists)**
|
||||
|
||||
```
|
||||
## Archive Failed
|
||||
|
||||
**Change:** <change-name>
|
||||
**Target:** openspec/changes/archive/YYYY-MM-DD-<name>/
|
||||
|
||||
Target archive directory already exists.
|
||||
|
||||
**Options:**
|
||||
1. Rename the existing archive
|
||||
2. Delete the existing archive if it's a duplicate
|
||||
3. Wait until a different date to archive
|
||||
```
|
||||
|
||||
**Guardrails**
|
||||
- Always prompt for change selection if not provided
|
||||
- Use artifact graph (openspec status --json) for completion checking
|
||||
- Don't block archive on warnings - just inform and confirm
|
||||
- Preserve .openspec.yaml when moving to archive (it moves with the directory)
|
||||
- Show clear summary of what happened
|
||||
- If sync is requested, use the Skill tool to invoke `openspec-sync-specs` (agent-driven)
|
||||
- If delta specs exist, always run the sync assessment and show the combined summary before prompting
|
||||
242
.claude/commands/opsx/bulk-archive.md
Normal file
242
.claude/commands/opsx/bulk-archive.md
Normal file
|
|
@ -0,0 +1,242 @@
|
|||
---
|
||||
name: "OPSX: Bulk Archive"
|
||||
description: Archive multiple completed changes at once
|
||||
category: Workflow
|
||||
tags: [workflow, archive, experimental, bulk]
|
||||
---
|
||||
|
||||
Archive multiple completed changes in a single operation.
|
||||
|
||||
This skill allows you to batch-archive changes, handling spec conflicts intelligently by checking the codebase to determine what's actually implemented.
|
||||
|
||||
**Input**: None required (prompts for selection)
|
||||
|
||||
**Steps**
|
||||
|
||||
1. **Get active changes**
|
||||
|
||||
Run `openspec list --json` to get all active changes.
|
||||
|
||||
If no active changes exist, inform user and stop.
|
||||
|
||||
2. **Prompt for change selection**
|
||||
|
||||
Use **AskUserQuestion tool** with multi-select to let user choose changes:
|
||||
- Show each change with its schema
|
||||
- Include an option for "All changes"
|
||||
- Allow any number of selections (1+ works, 2+ is the typical use case)
|
||||
|
||||
**IMPORTANT**: Do NOT auto-select. Always let the user choose.
|
||||
|
||||
3. **Batch validation - gather status for all selected changes**
|
||||
|
||||
For each selected change, collect:
|
||||
|
||||
a. **Artifact status** - Run `openspec status --change "<name>" --json`
|
||||
- Parse `schemaName` and `artifacts` list
|
||||
- Note which artifacts are `done` vs other states
|
||||
|
||||
b. **Task completion** - Read `openspec/changes/<name>/tasks.md`
|
||||
- Count `- [ ]` (incomplete) vs `- [x]` (complete)
|
||||
- If no tasks file exists, note as "No tasks"
|
||||
|
||||
c. **Delta specs** - Check `openspec/changes/<name>/specs/` directory
|
||||
- List which capability specs exist
|
||||
- For each, extract requirement names (lines matching `### Requirement: <name>`)
|
||||
|
||||
4. **Detect spec conflicts**
|
||||
|
||||
Build a map of `capability -> [changes that touch it]`:
|
||||
|
||||
```
|
||||
auth -> [change-a, change-b] <- CONFLICT (2+ changes)
|
||||
api -> [change-c] <- OK (only 1 change)
|
||||
```
|
||||
|
||||
A conflict exists when 2+ selected changes have delta specs for the same capability.
|
||||
|
||||
5. **Resolve conflicts agentically**
|
||||
|
||||
**For each conflict**, investigate the codebase:
|
||||
|
||||
a. **Read the delta specs** from each conflicting change to understand what each claims to add/modify
|
||||
|
||||
b. **Search the codebase** for implementation evidence:
|
||||
- Look for code implementing requirements from each delta spec
|
||||
- Check for related files, functions, or tests
|
||||
|
||||
c. **Determine resolution**:
|
||||
- If only one change is actually implemented -> sync that one's specs
|
||||
- If both implemented -> apply in chronological order (older first, newer overwrites)
|
||||
- If neither implemented -> skip spec sync, warn user
|
||||
|
||||
d. **Record resolution** for each conflict:
|
||||
- Which change's specs to apply
|
||||
- In what order (if both)
|
||||
- Rationale (what was found in codebase)
|
||||
|
||||
6. **Show consolidated status table**
|
||||
|
||||
Display a table summarizing all changes:
|
||||
|
||||
```
|
||||
| Change | Artifacts | Tasks | Specs | Conflicts | Status |
|
||||
|---------------------|-----------|-------|---------|-----------|--------|
|
||||
| schema-management | Done | 5/5 | 2 delta | None | Ready |
|
||||
| project-config | Done | 3/3 | 1 delta | None | Ready |
|
||||
| add-oauth | Done | 4/4 | 1 delta | auth (!) | Ready* |
|
||||
| add-verify-skill | 1 left | 2/5 | None | None | Warn |
|
||||
```
|
||||
|
||||
For conflicts, show the resolution:
|
||||
```
|
||||
* Conflict resolution:
|
||||
- auth spec: Will apply add-oauth then add-jwt (both implemented, chronological order)
|
||||
```
|
||||
|
||||
For incomplete changes, show warnings:
|
||||
```
|
||||
Warnings:
|
||||
- add-verify-skill: 1 incomplete artifact, 3 incomplete tasks
|
||||
```
|
||||
|
||||
7. **Confirm batch operation**
|
||||
|
||||
Use **AskUserQuestion tool** with a single confirmation:
|
||||
|
||||
- "Archive N changes?" with options based on status
|
||||
- Options might include:
|
||||
- "Archive all N changes"
|
||||
- "Archive only N ready changes (skip incomplete)"
|
||||
- "Cancel"
|
||||
|
||||
If there are incomplete changes, make clear they'll be archived with warnings.
|
||||
|
||||
8. **Execute archive for each confirmed change**
|
||||
|
||||
Process changes in the determined order (respecting conflict resolution):
|
||||
|
||||
a. **Sync specs** if delta specs exist:
|
||||
- Use the openspec-sync-specs approach (agent-driven intelligent merge)
|
||||
- For conflicts, apply in resolved order
|
||||
- Track if sync was done
|
||||
|
||||
b. **Perform the archive**:
|
||||
```bash
|
||||
mkdir -p openspec/changes/archive
|
||||
mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
|
||||
```
|
||||
|
||||
c. **Track outcome** for each change:
|
||||
- Success: archived successfully
|
||||
- Failed: error during archive (record error)
|
||||
- Skipped: user chose not to archive (if applicable)
|
||||
|
||||
9. **Display summary**
|
||||
|
||||
Show final results:
|
||||
|
||||
```
|
||||
## Bulk Archive Complete
|
||||
|
||||
Archived 3 changes:
|
||||
- schema-management-cli -> archive/2026-01-19-schema-management-cli/
|
||||
- project-config -> archive/2026-01-19-project-config/
|
||||
- add-oauth -> archive/2026-01-19-add-oauth/
|
||||
|
||||
Skipped 1 change:
|
||||
- add-verify-skill (user chose not to archive incomplete)
|
||||
|
||||
Spec sync summary:
|
||||
- 4 delta specs synced to main specs
|
||||
- 1 conflict resolved (auth: applied both in chronological order)
|
||||
```
|
||||
|
||||
If any failures:
|
||||
```
|
||||
Failed 1 change:
|
||||
- some-change: Archive directory already exists
|
||||
```
|
||||
|
||||
**Conflict Resolution Examples**
|
||||
|
||||
Example 1: Only one implemented
|
||||
```
|
||||
Conflict: specs/auth/spec.md touched by [add-oauth, add-jwt]
|
||||
|
||||
Checking add-oauth:
|
||||
- Delta adds "OAuth Provider Integration" requirement
|
||||
- Searching codebase... found src/auth/oauth.ts implementing OAuth flow
|
||||
|
||||
Checking add-jwt:
|
||||
- Delta adds "JWT Token Handling" requirement
|
||||
- Searching codebase... no JWT implementation found
|
||||
|
||||
Resolution: Only add-oauth is implemented. Will sync add-oauth specs only.
|
||||
```
|
||||
|
||||
Example 2: Both implemented
|
||||
```
|
||||
Conflict: specs/api/spec.md touched by [add-rest-api, add-graphql]
|
||||
|
||||
Checking add-rest-api (created 2026-01-10):
|
||||
- Delta adds "REST Endpoints" requirement
|
||||
- Searching codebase... found src/api/rest.ts
|
||||
|
||||
Checking add-graphql (created 2026-01-15):
|
||||
- Delta adds "GraphQL Schema" requirement
|
||||
- Searching codebase... found src/api/graphql.ts
|
||||
|
||||
Resolution: Both implemented. Will apply add-rest-api specs first,
|
||||
then add-graphql specs (chronological order, newer takes precedence).
|
||||
```
|
||||
|
||||
**Output On Success**
|
||||
|
||||
```
|
||||
## Bulk Archive Complete
|
||||
|
||||
Archived N changes:
|
||||
- <change-1> -> archive/YYYY-MM-DD-<change-1>/
|
||||
- <change-2> -> archive/YYYY-MM-DD-<change-2>/
|
||||
|
||||
Spec sync summary:
|
||||
- N delta specs synced to main specs
|
||||
- No conflicts (or: M conflicts resolved)
|
||||
```
|
||||
|
||||
**Output On Partial Success**
|
||||
|
||||
```
|
||||
## Bulk Archive Complete (partial)
|
||||
|
||||
Archived N changes:
|
||||
- <change-1> -> archive/YYYY-MM-DD-<change-1>/
|
||||
|
||||
Skipped M changes:
|
||||
- <change-2> (user chose not to archive incomplete)
|
||||
|
||||
Failed K changes:
|
||||
- <change-3>: Archive directory already exists
|
||||
```
|
||||
|
||||
**Output When No Changes**
|
||||
|
||||
```
|
||||
## No Changes to Archive
|
||||
|
||||
No active changes found. Create a new change to get started.
|
||||
```
|
||||
|
||||
**Guardrails**
|
||||
- Allow any number of changes (1+ is fine, 2+ is the typical use case)
|
||||
- Always prompt for selection, never auto-select
|
||||
- Detect spec conflicts early and resolve by checking codebase
|
||||
- When both changes are implemented, apply specs in chronological order
|
||||
- Skip spec sync only when implementation is missing (warn user)
|
||||
- Show clear per-change status before confirming
|
||||
- Use single confirmation for entire batch
|
||||
- Track and report all outcomes (success/skip/fail)
|
||||
- Preserve .openspec.yaml when moving to archive
|
||||
- Archive directory target uses current date: YYYY-MM-DD-<name>
|
||||
- If archive target exists, fail that change but continue with others
|
||||
114
.claude/commands/opsx/continue.md
Normal file
114
.claude/commands/opsx/continue.md
Normal file
|
|
@ -0,0 +1,114 @@
|
|||
---
|
||||
name: "OPSX: Continue"
|
||||
description: Continue working on a change - create the next artifact (Experimental)
|
||||
category: Workflow
|
||||
tags: [workflow, artifacts, experimental]
|
||||
---
|
||||
|
||||
Continue working on a change by creating the next artifact.
|
||||
|
||||
**Input**: Optionally specify a change name after `/opsx:continue` (e.g., `/opsx:continue add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
|
||||
|
||||
**Steps**
|
||||
|
||||
1. **If no change name provided, prompt for selection**
|
||||
|
||||
Run `openspec list --json` to get available changes sorted by most recently modified. Then use the **AskUserQuestion tool** to let the user select which change to work on.
|
||||
|
||||
Present the top 3-4 most recently modified changes as options, showing:
|
||||
- Change name
|
||||
- Schema (from `schema` field if present, otherwise "spec-driven")
|
||||
- Status (e.g., "0/5 tasks", "complete", "no tasks")
|
||||
- How recently it was modified (from `lastModified` field)
|
||||
|
||||
Mark the most recently modified change as "(Recommended)" since it's likely what the user wants to continue.
|
||||
|
||||
**IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
|
||||
|
||||
2. **Check current status**
|
||||
```bash
|
||||
openspec status --change "<name>" --json
|
||||
```
|
||||
Parse the JSON to understand current state. The response includes:
|
||||
- `schemaName`: The workflow schema being used (e.g., "spec-driven")
|
||||
- `artifacts`: Array of artifacts with their status ("done", "ready", "blocked")
|
||||
- `isComplete`: Boolean indicating if all artifacts are complete
|
||||
|
||||
3. **Act based on status**:
|
||||
|
||||
---
|
||||
|
||||
**If all artifacts are complete (`isComplete: true`)**:
|
||||
- Congratulate the user
|
||||
- Show final status including the schema used
|
||||
- Suggest: "All artifacts created! You can now implement this change with `/opsx:apply` or archive it with `/opsx:archive`."
|
||||
- STOP
|
||||
|
||||
---
|
||||
|
||||
**If artifacts are ready to create** (status shows artifacts with `status: "ready"`):
|
||||
- Pick the FIRST artifact with `status: "ready"` from the status output
|
||||
- Get its instructions:
|
||||
```bash
|
||||
openspec instructions <artifact-id> --change "<name>" --json
|
||||
```
|
||||
- Parse the JSON. The key fields are:
|
||||
- `context`: Project background (constraints for you - do NOT include in output)
|
||||
- `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
|
||||
- `template`: The structure to use for your output file
|
||||
- `instruction`: Schema-specific guidance
|
||||
- `outputPath`: Where to write the artifact
|
||||
- `dependencies`: Completed artifacts to read for context
|
||||
- **Create the artifact file**:
|
||||
- Read any completed dependency files for context
|
||||
- Use `template` as the structure - fill in its sections
|
||||
- Apply `context` and `rules` as constraints when writing - but do NOT copy them into the file
|
||||
- Write to the output path specified in instructions
|
||||
- Show what was created and what's now unlocked
|
||||
- STOP after creating ONE artifact
|
||||
|
||||
---
|
||||
|
||||
**If no artifacts are ready (all blocked)**:
|
||||
- This shouldn't happen with a valid schema
|
||||
- Show status and suggest checking for issues
|
||||
|
||||
4. **After creating an artifact, show progress**
|
||||
```bash
|
||||
openspec status --change "<name>"
|
||||
```
|
||||
|
||||
**Output**
|
||||
|
||||
After each invocation, show:
|
||||
- Which artifact was created
|
||||
- Schema workflow being used
|
||||
- Current progress (N/M complete)
|
||||
- What artifacts are now unlocked
|
||||
- Prompt: "Run `/opsx:continue` to create the next artifact"
|
||||
|
||||
**Artifact Creation Guidelines**
|
||||
|
||||
The artifact types and their purpose depend on the schema. Use the `instruction` field from the instructions output to understand what to create.
|
||||
|
||||
Common artifact patterns:
|
||||
|
||||
**spec-driven schema** (proposal → specs → design → tasks):
|
||||
- **proposal.md**: Ask user about the change if not clear. Fill in Why, What Changes, Capabilities, Impact.
|
||||
- The Capabilities section is critical - each capability listed will need a spec file.
|
||||
- **specs/<capability>/spec.md**: Create one spec per capability listed in the proposal's Capabilities section (use the capability name, not the change name).
|
||||
- **design.md**: Document technical decisions, architecture, and implementation approach.
|
||||
- **tasks.md**: Break down implementation into checkboxed tasks.
|
||||
|
||||
For other schemas, follow the `instruction` field from the CLI output.
|
||||
|
||||
**Guardrails**
|
||||
- Create ONE artifact per invocation
|
||||
- Always read dependency artifacts before creating a new one
|
||||
- Never skip artifacts or create out of order
|
||||
- If context is unclear, ask the user before creating
|
||||
- Verify the artifact file exists after writing before marking progress
|
||||
- Use the schema's artifact sequence, don't assume specific artifact names
|
||||
- **IMPORTANT**: `context` and `rules` are constraints for YOU, not content for the file
|
||||
- Do NOT copy `<context>`, `<rules>`, `<project_context>` blocks into the artifact
|
||||
- These guide what you write, but should never appear in the output
|
||||
173
.claude/commands/opsx/explore.md
Normal file
173
.claude/commands/opsx/explore.md
Normal file
|
|
@ -0,0 +1,173 @@
|
|||
---
|
||||
name: "OPSX: Explore"
|
||||
description: "Enter explore mode - think through ideas, investigate problems, clarify requirements"
|
||||
category: Workflow
|
||||
tags: [workflow, explore, experimental, thinking]
|
||||
---
|
||||
|
||||
Enter explore mode. Think deeply. Visualize freely. Follow the conversation wherever it goes.
|
||||
|
||||
**IMPORTANT: Explore mode is for thinking, not implementing.** You may read files, search code, and investigate the codebase, but you must NEVER write code or implement features. If the user asks you to implement something, remind them to exit explore mode first and create a change proposal. You MAY create OpenSpec artifacts (proposals, designs, specs) if the user asks—that's capturing thinking, not implementing.
|
||||
|
||||
**This is a stance, not a workflow.** There are no fixed steps, no required sequence, no mandatory outputs. You're a thinking partner helping the user explore.
|
||||
|
||||
**Input**: The argument after `/opsx:explore` is whatever the user wants to think about. Could be:
|
||||
- A vague idea: "real-time collaboration"
|
||||
- A specific problem: "the auth system is getting unwieldy"
|
||||
- A change name: "add-dark-mode" (to explore in context of that change)
|
||||
- A comparison: "postgres vs sqlite for this"
|
||||
- Nothing (just enter explore mode)
|
||||
|
||||
---
|
||||
|
||||
## The Stance
|
||||
|
||||
- **Curious, not prescriptive** - Ask questions that emerge naturally, don't follow a script
|
||||
- **Open threads, not interrogations** - Surface multiple interesting directions and let the user follow what resonates. Don't funnel them through a single path of questions.
|
||||
- **Visual** - Use ASCII diagrams liberally when they'd help clarify thinking
|
||||
- **Adaptive** - Follow interesting threads, pivot when new information emerges
|
||||
- **Patient** - Don't rush to conclusions, let the shape of the problem emerge
|
||||
- **Grounded** - Explore the actual codebase when relevant, don't just theorize
|
||||
|
||||
---
|
||||
|
||||
## What You Might Do
|
||||
|
||||
Depending on what the user brings, you might:
|
||||
|
||||
**Explore the problem space**
|
||||
- Ask clarifying questions that emerge from what they said
|
||||
- Challenge assumptions
|
||||
- Reframe the problem
|
||||
- Find analogies
|
||||
|
||||
**Investigate the codebase**
|
||||
- Map existing architecture relevant to the discussion
|
||||
- Find integration points
|
||||
- Identify patterns already in use
|
||||
- Surface hidden complexity
|
||||
|
||||
**Compare options**
|
||||
- Brainstorm multiple approaches
|
||||
- Build comparison tables
|
||||
- Sketch tradeoffs
|
||||
- Recommend a path (if asked)
|
||||
|
||||
**Visualize**
|
||||
```
|
||||
┌─────────────────────────────────────────┐
|
||||
│ Use ASCII diagrams liberally │
|
||||
├─────────────────────────────────────────┤
|
||||
│ │
|
||||
│ ┌────────┐ ┌────────┐ │
|
||||
│ │ State │────────▶│ State │ │
|
||||
│ │ A │ │ B │ │
|
||||
│ └────────┘ └────────┘ │
|
||||
│ │
|
||||
│ System diagrams, state machines, │
|
||||
│ data flows, architecture sketches, │
|
||||
│ dependency graphs, comparison tables │
|
||||
│ │
|
||||
└─────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
**Surface risks and unknowns**
|
||||
- Identify what could go wrong
|
||||
- Find gaps in understanding
|
||||
- Suggest spikes or investigations
|
||||
|
||||
---
|
||||
|
||||
## OpenSpec Awareness
|
||||
|
||||
You have full context of the OpenSpec system. Use it naturally, don't force it.
|
||||
|
||||
### Check for context
|
||||
|
||||
At the start, quickly check what exists:
|
||||
```bash
|
||||
openspec list --json
|
||||
```
|
||||
|
||||
This tells you:
|
||||
- If there are active changes
|
||||
- Their names, schemas, and status
|
||||
- What the user might be working on
|
||||
|
||||
If the user mentioned a specific change name, read its artifacts for context.
|
||||
|
||||
### When no change exists
|
||||
|
||||
Think freely. When insights crystallize, you might offer:
|
||||
|
||||
- "This feels solid enough to start a change. Want me to create a proposal?"
|
||||
- Or keep exploring - no pressure to formalize
|
||||
|
||||
### When a change exists
|
||||
|
||||
If the user mentions a change or you detect one is relevant:
|
||||
|
||||
1. **Read existing artifacts for context**
|
||||
- `openspec/changes/<name>/proposal.md`
|
||||
- `openspec/changes/<name>/design.md`
|
||||
- `openspec/changes/<name>/tasks.md`
|
||||
- etc.
|
||||
|
||||
2. **Reference them naturally in conversation**
|
||||
- "Your design mentions using Redis, but we just realized SQLite fits better..."
|
||||
- "The proposal scopes this to premium users, but we're now thinking everyone..."
|
||||
|
||||
3. **Offer to capture when decisions are made**
|
||||
|
||||
| Insight Type | Where to Capture |
|
||||
|----------------------------|--------------------------------|
|
||||
| New requirement discovered | `specs/<capability>/spec.md` |
|
||||
| Requirement changed | `specs/<capability>/spec.md` |
|
||||
| Design decision made | `design.md` |
|
||||
| Scope changed | `proposal.md` |
|
||||
| New work identified | `tasks.md` |
|
||||
| Assumption invalidated | Relevant artifact |
|
||||
|
||||
Example offers:
|
||||
- "That's a design decision. Capture it in design.md?"
|
||||
- "This is a new requirement. Add it to specs?"
|
||||
- "This changes scope. Update the proposal?"
|
||||
|
||||
4. **The user decides** - Offer and move on. Don't pressure. Don't auto-capture.
|
||||
|
||||
---
|
||||
|
||||
## What You Don't Have To Do
|
||||
|
||||
- Follow a script
|
||||
- Ask the same questions every time
|
||||
- Produce a specific artifact
|
||||
- Reach a conclusion
|
||||
- Stay on topic if a tangent is valuable
|
||||
- Be brief (this is thinking time)
|
||||
|
||||
---
|
||||
|
||||
## Ending Discovery
|
||||
|
||||
There's no required ending. Discovery might:
|
||||
|
||||
- **Flow into a proposal**: "Ready to start? I can create a change proposal."
|
||||
- **Result in artifact updates**: "Updated design.md with these decisions"
|
||||
- **Just provide clarity**: User has what they need, moves on
|
||||
- **Continue later**: "We can pick this up anytime"
|
||||
|
||||
When things crystallize, you might offer a summary - but it's optional. Sometimes the thinking IS the value.
|
||||
|
||||
---
|
||||
|
||||
## Guardrails
|
||||
|
||||
- **Don't implement** - Never write code or implement features. Creating OpenSpec artifacts is fine, writing application code is not.
|
||||
- **Don't fake understanding** - If something is unclear, dig deeper
|
||||
- **Don't rush** - Discovery is thinking time, not task time
|
||||
- **Don't force structure** - Let patterns emerge naturally
|
||||
- **Don't auto-capture** - Offer to save insights, don't just do it
|
||||
- **Do visualize** - A good diagram is worth many paragraphs
|
||||
- **Do explore the codebase** - Ground discussions in reality
|
||||
- **Do question assumptions** - Including the user's and your own
|
||||
97
.claude/commands/opsx/ff.md
Normal file
97
.claude/commands/opsx/ff.md
Normal file
|
|
@ -0,0 +1,97 @@
|
|||
---
|
||||
name: "OPSX: Fast Forward"
|
||||
description: Create a change and generate all artifacts needed for implementation in one go
|
||||
category: Workflow
|
||||
tags: [workflow, artifacts, experimental]
|
||||
---
|
||||
|
||||
Fast-forward through artifact creation - generate everything needed to start implementation.
|
||||
|
||||
**Input**: The argument after `/opsx:ff` is the change name (kebab-case), OR a description of what the user wants to build.
|
||||
|
||||
**Steps**
|
||||
|
||||
1. **If no input provided, ask what they want to build**
|
||||
|
||||
Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
|
||||
> "What change do you want to work on? Describe what you want to build or fix."
|
||||
|
||||
From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
|
||||
|
||||
**IMPORTANT**: Do NOT proceed without understanding what the user wants to build.
|
||||
|
||||
2. **Create the change directory**
|
||||
```bash
|
||||
openspec new change "<name>"
|
||||
```
|
||||
This creates a scaffolded change at `openspec/changes/<name>/`.
|
||||
|
||||
3. **Get the artifact build order**
|
||||
```bash
|
||||
openspec status --change "<name>" --json
|
||||
```
|
||||
Parse the JSON to get:
|
||||
- `applyRequires`: array of artifact IDs needed before implementation (e.g., `["tasks"]`)
|
||||
- `artifacts`: list of all artifacts with their status and dependencies
|
||||
|
||||
4. **Create artifacts in sequence until apply-ready**
|
||||
|
||||
Use the **TodoWrite tool** to track progress through the artifacts.
|
||||
|
||||
Loop through artifacts in dependency order (artifacts with no pending dependencies first):
|
||||
|
||||
a. **For each artifact that is `ready` (dependencies satisfied)**:
|
||||
- Get instructions:
|
||||
```bash
|
||||
openspec instructions <artifact-id> --change "<name>" --json
|
||||
```
|
||||
- The instructions JSON includes:
|
||||
- `context`: Project background (constraints for you - do NOT include in output)
|
||||
- `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
|
||||
- `template`: The structure to use for your output file
|
||||
- `instruction`: Schema-specific guidance for this artifact type
|
||||
- `outputPath`: Where to write the artifact
|
||||
- `dependencies`: Completed artifacts to read for context
|
||||
- Read any completed dependency files for context
|
||||
- Create the artifact file using `template` as the structure
|
||||
- Apply `context` and `rules` as constraints - but do NOT copy them into the file
|
||||
- Show brief progress: "✓ Created <artifact-id>"
|
||||
|
||||
b. **Continue until all `applyRequires` artifacts are complete**
|
||||
- After creating each artifact, re-run `openspec status --change "<name>" --json`
|
||||
- Check if every artifact ID in `applyRequires` has `status: "done"` in the artifacts array
|
||||
- Stop when all `applyRequires` artifacts are done
|
||||
|
||||
c. **If an artifact requires user input** (unclear context):
|
||||
- Use **AskUserQuestion tool** to clarify
|
||||
- Then continue with creation
|
||||
|
||||
5. **Show final status**
|
||||
```bash
|
||||
openspec status --change "<name>"
|
||||
```
|
||||
|
||||
**Output**
|
||||
|
||||
After completing all artifacts, summarize:
|
||||
- Change name and location
|
||||
- List of artifacts created with brief descriptions
|
||||
- What's ready: "All artifacts created! Ready for implementation."
|
||||
- Prompt: "Run `/opsx:apply` to start implementing."
|
||||
|
||||
**Artifact Creation Guidelines**
|
||||
|
||||
- Follow the `instruction` field from `openspec instructions` for each artifact type
|
||||
- The schema defines what each artifact should contain - follow it
|
||||
- Read dependency artifacts for context before creating new ones
|
||||
- Use `template` as the structure for your output file - fill in its sections
|
||||
- **IMPORTANT**: `context` and `rules` are constraints for YOU, not content for the file
|
||||
- Do NOT copy `<context>`, `<rules>`, `<project_context>` blocks into the artifact
|
||||
- These guide what you write, but should never appear in the output
|
||||
|
||||
**Guardrails**
|
||||
- Create ALL artifacts needed for implementation (as defined by schema's `apply.requires`)
|
||||
- Always read dependency artifacts before creating a new one
|
||||
- If context is critically unclear, ask the user - but prefer making reasonable decisions to keep momentum
|
||||
- If a change with that name already exists, ask if user wants to continue it or create a new one
|
||||
- Verify each artifact file exists after writing before proceeding to next
|
||||
69
.claude/commands/opsx/new.md
Normal file
69
.claude/commands/opsx/new.md
Normal file
|
|
@ -0,0 +1,69 @@
|
|||
---
|
||||
name: "OPSX: New"
|
||||
description: Start a new change using the experimental artifact workflow (OPSX)
|
||||
category: Workflow
|
||||
tags: [workflow, artifacts, experimental]
|
||||
---
|
||||
|
||||
Start a new change using the experimental artifact-driven approach.
|
||||
|
||||
**Input**: The argument after `/opsx:new` is the change name (kebab-case), OR a description of what the user wants to build.
|
||||
|
||||
**Steps**
|
||||
|
||||
1. **If no input provided, ask what they want to build**
|
||||
|
||||
Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
|
||||
> "What change do you want to work on? Describe what you want to build or fix."
|
||||
|
||||
From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
|
||||
|
||||
**IMPORTANT**: Do NOT proceed without understanding what the user wants to build.
|
||||
|
||||
2. **Determine the workflow schema**
|
||||
|
||||
Use the default schema (omit `--schema`) unless the user explicitly requests a different workflow.
|
||||
|
||||
**Use a different schema only if the user mentions:**
|
||||
- A specific schema name → use `--schema <name>`
|
||||
- "show workflows" or "what workflows" → run `openspec schemas --json` and let them choose
|
||||
|
||||
**Otherwise**: Omit `--schema` to use the default.
|
||||
|
||||
3. **Create the change directory**
|
||||
```bash
|
||||
openspec new change "<name>"
|
||||
```
|
||||
Add `--schema <name>` only if the user requested a specific workflow.
|
||||
This creates a scaffolded change at `openspec/changes/<name>/` with the selected schema.
|
||||
|
||||
4. **Show the artifact status**
|
||||
```bash
|
||||
openspec status --change "<name>"
|
||||
```
|
||||
This shows which artifacts need to be created and which are ready (dependencies satisfied).
|
||||
|
||||
5. **Get instructions for the first artifact**
|
||||
The first artifact depends on the schema. Check the status output to find the first artifact with status "ready".
|
||||
```bash
|
||||
openspec instructions <first-artifact-id> --change "<name>"
|
||||
```
|
||||
This outputs the template and context for creating the first artifact.
|
||||
|
||||
6. **STOP and wait for user direction**
|
||||
|
||||
**Output**
|
||||
|
||||
After completing the steps, summarize:
|
||||
- Change name and location
|
||||
- Schema/workflow being used and its artifact sequence
|
||||
- Current status (0/N artifacts complete)
|
||||
- The template for the first artifact
|
||||
- Prompt: "Ready to create the first artifact? Run `/opsx:continue` or just describe what this change is about and I'll draft it."
|
||||
|
||||
**Guardrails**
|
||||
- Do NOT create any artifacts yet - just show the instructions
|
||||
- Do NOT advance beyond showing the first artifact template
|
||||
- If the name is invalid (not kebab-case), ask for a valid name
|
||||
- If a change with that name already exists, suggest using `/opsx:continue` instead
|
||||
- Pass --schema if using a non-default workflow
|
||||
550
.claude/commands/opsx/onboard.md
Normal file
550
.claude/commands/opsx/onboard.md
Normal file
|
|
@ -0,0 +1,550 @@
|
|||
---
|
||||
name: "OPSX: Onboard"
|
||||
description: Guided onboarding - walk through a complete OpenSpec workflow cycle with narration
|
||||
category: Workflow
|
||||
tags: [workflow, onboarding, tutorial, learning]
|
||||
---
|
||||
|
||||
Guide the user through their first complete OpenSpec workflow cycle. This is a teaching experience—you'll do real work in their codebase while explaining each step.
|
||||
|
||||
---
|
||||
|
||||
## Preflight
|
||||
|
||||
Before starting, check if the OpenSpec CLI is installed:
|
||||
|
||||
```bash
|
||||
# Unix/macOS
|
||||
openspec --version 2>&1 || echo "CLI_NOT_INSTALLED"
|
||||
# Windows (PowerShell)
|
||||
# if (Get-Command openspec -ErrorAction SilentlyContinue) { openspec --version } else { echo "CLI_NOT_INSTALLED" }
|
||||
```
|
||||
|
||||
**If CLI not installed:**
|
||||
> OpenSpec CLI is not installed. Install it first, then come back to `/opsx:onboard`.
|
||||
|
||||
Stop here if not installed.
|
||||
|
||||
---
|
||||
|
||||
## Phase 1: Welcome
|
||||
|
||||
Display:
|
||||
|
||||
```
|
||||
## Welcome to OpenSpec!
|
||||
|
||||
I'll walk you through a complete change cycle—from idea to implementation—using a real task in your codebase. Along the way, you'll learn the workflow by doing it.
|
||||
|
||||
**What we'll do:**
|
||||
1. Pick a small, real task in your codebase
|
||||
2. Explore the problem briefly
|
||||
3. Create a change (the container for our work)
|
||||
4. Build the artifacts: proposal → specs → design → tasks
|
||||
5. Implement the tasks
|
||||
6. Archive the completed change
|
||||
|
||||
**Time:** ~15-20 minutes
|
||||
|
||||
Let's start by finding something to work on.
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Phase 2: Task Selection
|
||||
|
||||
### Codebase Analysis
|
||||
|
||||
Scan the codebase for small improvement opportunities. Look for:
|
||||
|
||||
1. **TODO/FIXME comments** - Search for `TODO`, `FIXME`, `HACK`, `XXX` in code files
|
||||
2. **Missing error handling** - `catch` blocks that swallow errors, risky operations without try-catch
|
||||
3. **Functions without tests** - Cross-reference `src/` with test directories
|
||||
4. **Type issues** - `any` types in TypeScript files (`: any`, `as any`)
|
||||
5. **Debug artifacts** - `console.log`, `console.debug`, `debugger` statements in non-debug code
|
||||
6. **Missing validation** - User input handlers without validation
|
||||
|
||||
Also check recent git activity:
|
||||
```bash
|
||||
# Unix/macOS
|
||||
git log --oneline -10 2>/dev/null || echo "No git history"
|
||||
# Windows (PowerShell)
|
||||
# git log --oneline -10 2>$null; if ($LASTEXITCODE -ne 0) { echo "No git history" }
|
||||
```
|
||||
|
||||
### Present Suggestions
|
||||
|
||||
From your analysis, present 3-4 specific suggestions:
|
||||
|
||||
```
|
||||
## Task Suggestions
|
||||
|
||||
Based on scanning your codebase, here are some good starter tasks:
|
||||
|
||||
**1. [Most promising task]**
|
||||
Location: `src/path/to/file.ts:42`
|
||||
Scope: ~1-2 files, ~20-30 lines
|
||||
Why it's good: [brief reason]
|
||||
|
||||
**2. [Second task]**
|
||||
Location: `src/another/file.ts`
|
||||
Scope: ~1 file, ~15 lines
|
||||
Why it's good: [brief reason]
|
||||
|
||||
**3. [Third task]**
|
||||
Location: [location]
|
||||
Scope: [estimate]
|
||||
Why it's good: [brief reason]
|
||||
|
||||
**4. Something else?**
|
||||
Tell me what you'd like to work on.
|
||||
|
||||
Which task interests you? (Pick a number or describe your own)
|
||||
```
|
||||
|
||||
**If nothing found:** Fall back to asking what the user wants to build:
|
||||
> I didn't find obvious quick wins in your codebase. What's something small you've been meaning to add or fix?
|
||||
|
||||
### Scope Guardrail
|
||||
|
||||
If the user picks or describes something too large (major feature, multi-day work):
|
||||
|
||||
```
|
||||
That's a valuable task, but it's probably larger than ideal for your first OpenSpec run-through.
|
||||
|
||||
For learning the workflow, smaller is better—it lets you see the full cycle without getting stuck in implementation details.
|
||||
|
||||
**Options:**
|
||||
1. **Slice it smaller** - What's the smallest useful piece of [their task]? Maybe just [specific slice]?
|
||||
2. **Pick something else** - One of the other suggestions, or a different small task?
|
||||
3. **Do it anyway** - If you really want to tackle this, we can. Just know it'll take longer.
|
||||
|
||||
What would you prefer?
|
||||
```
|
||||
|
||||
Let the user override if they insist—this is a soft guardrail.
|
||||
|
||||
---
|
||||
|
||||
## Phase 3: Explore Demo
|
||||
|
||||
Once a task is selected, briefly demonstrate explore mode:
|
||||
|
||||
```
|
||||
Before we create a change, let me quickly show you **explore mode**—it's how you think through problems before committing to a direction.
|
||||
```
|
||||
|
||||
Spend 1-2 minutes investigating the relevant code:
|
||||
- Read the file(s) involved
|
||||
- Draw a quick ASCII diagram if it helps
|
||||
- Note any considerations
|
||||
|
||||
```
|
||||
## Quick Exploration
|
||||
|
||||
[Your brief analysis—what you found, any considerations]
|
||||
|
||||
┌─────────────────────────────────────────┐
|
||||
│ [Optional: ASCII diagram if helpful] │
|
||||
└─────────────────────────────────────────┘
|
||||
|
||||
Explore mode (`/opsx:explore`) is for this kind of thinking—investigating before implementing. You can use it anytime you need to think through a problem.
|
||||
|
||||
Now let's create a change to hold our work.
|
||||
```
|
||||
|
||||
**PAUSE** - Wait for user acknowledgment before proceeding.
|
||||
|
||||
---
|
||||
|
||||
## Phase 4: Create the Change
|
||||
|
||||
**EXPLAIN:**
|
||||
```
|
||||
## Creating a Change
|
||||
|
||||
A "change" in OpenSpec is a container for all the thinking and planning around a piece of work. It lives in `openspec/changes/<name>/` and holds your artifacts—proposal, specs, design, tasks.
|
||||
|
||||
Let me create one for our task.
|
||||
```
|
||||
|
||||
**DO:** Create the change with a derived kebab-case name:
|
||||
```bash
|
||||
openspec new change "<derived-name>"
|
||||
```
|
||||
|
||||
**SHOW:**
|
||||
```
|
||||
Created: `openspec/changes/<name>/`
|
||||
|
||||
The folder structure:
|
||||
```
|
||||
openspec/changes/<name>/
|
||||
├── proposal.md ← Why we're doing this (empty, we'll fill it)
|
||||
├── design.md ← How we'll build it (empty)
|
||||
├── specs/ ← Detailed requirements (empty)
|
||||
└── tasks.md ← Implementation checklist (empty)
|
||||
```
|
||||
|
||||
Now let's fill in the first artifact—the proposal.
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Phase 5: Proposal
|
||||
|
||||
**EXPLAIN:**
|
||||
```
|
||||
## The Proposal
|
||||
|
||||
The proposal captures **why** we're making this change and **what** it involves at a high level. It's the "elevator pitch" for the work.
|
||||
|
||||
I'll draft one based on our task.
|
||||
```
|
||||
|
||||
**DO:** Draft the proposal content (don't save yet):
|
||||
|
||||
```
|
||||
Here's a draft proposal:
|
||||
|
||||
---
|
||||
|
||||
## Why
|
||||
|
||||
[1-2 sentences explaining the problem/opportunity]
|
||||
|
||||
## What Changes
|
||||
|
||||
[Bullet points of what will be different]
|
||||
|
||||
## Capabilities
|
||||
|
||||
### New Capabilities
|
||||
- `<capability-name>`: [brief description]
|
||||
|
||||
### Modified Capabilities
|
||||
<!-- If modifying existing behavior -->
|
||||
|
||||
## Impact
|
||||
|
||||
- `src/path/to/file.ts`: [what changes]
|
||||
- [other files if applicable]
|
||||
|
||||
---
|
||||
|
||||
Does this capture the intent? I can adjust before we save it.
|
||||
```
|
||||
|
||||
**PAUSE** - Wait for user approval/feedback.
|
||||
|
||||
After approval, save the proposal:
|
||||
```bash
|
||||
openspec instructions proposal --change "<name>" --json
|
||||
```
|
||||
Then write the content to `openspec/changes/<name>/proposal.md`.
|
||||
|
||||
```
|
||||
Proposal saved. This is your "why" document—you can always come back and refine it as understanding evolves.
|
||||
|
||||
Next up: specs.
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Phase 6: Specs
|
||||
|
||||
**EXPLAIN:**
|
||||
```
|
||||
## Specs
|
||||
|
||||
Specs define **what** we're building in precise, testable terms. They use a requirement/scenario format that makes expected behavior crystal clear.
|
||||
|
||||
For a small task like this, we might only need one spec file.
|
||||
```
|
||||
|
||||
**DO:** Create the spec file:
|
||||
```bash
|
||||
# Unix/macOS
|
||||
mkdir -p openspec/changes/<name>/specs/<capability-name>
|
||||
# Windows (PowerShell)
|
||||
# New-Item -ItemType Directory -Force -Path "openspec/changes/<name>/specs/<capability-name>"
|
||||
```
|
||||
|
||||
Draft the spec content:
|
||||
|
||||
```
|
||||
Here's the spec:
|
||||
|
||||
---
|
||||
|
||||
## ADDED Requirements
|
||||
|
||||
### Requirement: <Name>
|
||||
|
||||
<Description of what the system should do>
|
||||
|
||||
#### Scenario: <Scenario name>
|
||||
|
||||
- **WHEN** <trigger condition>
|
||||
- **THEN** <expected outcome>
|
||||
- **AND** <additional outcome if needed>
|
||||
|
||||
---
|
||||
|
||||
This format—WHEN/THEN/AND—makes requirements testable. You can literally read them as test cases.
|
||||
```
|
||||
|
||||
Save to `openspec/changes/<name>/specs/<capability>/spec.md`.
|
||||
|
||||
---
|
||||
|
||||
## Phase 7: Design
|
||||
|
||||
**EXPLAIN:**
|
||||
```
|
||||
## Design
|
||||
|
||||
The design captures **how** we'll build it—technical decisions, tradeoffs, approach.
|
||||
|
||||
For small changes, this might be brief. That's fine—not every change needs deep design discussion.
|
||||
```
|
||||
|
||||
**DO:** Draft design.md:
|
||||
|
||||
```
|
||||
Here's the design:
|
||||
|
||||
---
|
||||
|
||||
## Context
|
||||
|
||||
[Brief context about the current state]
|
||||
|
||||
## Goals / Non-Goals
|
||||
|
||||
**Goals:**
|
||||
- [What we're trying to achieve]
|
||||
|
||||
**Non-Goals:**
|
||||
- [What's explicitly out of scope]
|
||||
|
||||
## Decisions
|
||||
|
||||
### Decision 1: [Key decision]
|
||||
|
||||
[Explanation of approach and rationale]
|
||||
|
||||
---
|
||||
|
||||
For a small task, this captures the key decisions without over-engineering.
|
||||
```
|
||||
|
||||
Save to `openspec/changes/<name>/design.md`.
|
||||
|
||||
---
|
||||
|
||||
## Phase 8: Tasks
|
||||
|
||||
**EXPLAIN:**
|
||||
```
|
||||
## Tasks
|
||||
|
||||
Finally, we break the work into implementation tasks—checkboxes that drive the apply phase.
|
||||
|
||||
These should be small, clear, and in logical order.
|
||||
```
|
||||
|
||||
**DO:** Generate tasks based on specs and design:
|
||||
|
||||
```
|
||||
Here are the implementation tasks:
|
||||
|
||||
---
|
||||
|
||||
## 1. [Category or file]
|
||||
|
||||
- [ ] 1.1 [Specific task]
|
||||
- [ ] 1.2 [Specific task]
|
||||
|
||||
## 2. Verify
|
||||
|
||||
- [ ] 2.1 [Verification step]
|
||||
|
||||
---
|
||||
|
||||
Each checkbox becomes a unit of work in the apply phase. Ready to implement?
|
||||
```
|
||||
|
||||
**PAUSE** - Wait for user to confirm they're ready to implement.
|
||||
|
||||
Save to `openspec/changes/<name>/tasks.md`.
|
||||
|
||||
---
|
||||
|
||||
## Phase 9: Apply (Implementation)
|
||||
|
||||
**EXPLAIN:**
|
||||
```
|
||||
## Implementation
|
||||
|
||||
Now we implement each task, checking them off as we go. I'll announce each one and occasionally note how the specs/design informed the approach.
|
||||
```
|
||||
|
||||
**DO:** For each task:
|
||||
|
||||
1. Announce: "Working on task N: [description]"
|
||||
2. Implement the change in the codebase
|
||||
3. Reference specs/design naturally: "The spec says X, so I'm doing Y"
|
||||
4. Mark complete in tasks.md: `- [ ]` → `- [x]`
|
||||
5. Brief status: "✓ Task N complete"
|
||||
|
||||
Keep narration light—don't over-explain every line of code.
|
||||
|
||||
After all tasks:
|
||||
|
||||
```
|
||||
## Implementation Complete
|
||||
|
||||
All tasks done:
|
||||
- [x] Task 1
|
||||
- [x] Task 2
|
||||
- [x] ...
|
||||
|
||||
The change is implemented! One more step—let's archive it.
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Phase 10: Archive
|
||||
|
||||
**EXPLAIN:**
|
||||
```
|
||||
## Archiving
|
||||
|
||||
When a change is complete, we archive it. This moves it from `openspec/changes/` to `openspec/changes/archive/YYYY-MM-DD-<name>/`.
|
||||
|
||||
Archived changes become your project's decision history—you can always find them later to understand why something was built a certain way.
|
||||
```
|
||||
|
||||
**DO:**
|
||||
```bash
|
||||
openspec archive "<name>"
|
||||
```
|
||||
|
||||
**SHOW:**
|
||||
```
|
||||
Archived to: `openspec/changes/archive/YYYY-MM-DD-<name>/`
|
||||
|
||||
The change is now part of your project's history. The code is in your codebase, the decision record is preserved.
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Phase 11: Recap & Next Steps
|
||||
|
||||
```
|
||||
## Congratulations!
|
||||
|
||||
You just completed a full OpenSpec cycle:
|
||||
|
||||
1. **Explore** - Thought through the problem
|
||||
2. **New** - Created a change container
|
||||
3. **Proposal** - Captured WHY
|
||||
4. **Specs** - Defined WHAT in detail
|
||||
5. **Design** - Decided HOW
|
||||
6. **Tasks** - Broke it into steps
|
||||
7. **Apply** - Implemented the work
|
||||
8. **Archive** - Preserved the record
|
||||
|
||||
This same rhythm works for any size change—a small fix or a major feature.
|
||||
|
||||
---
|
||||
|
||||
## Command Reference
|
||||
|
||||
**Core workflow:**
|
||||
|
||||
| Command | What it does |
|
||||
|-------------------|--------------------------------------------|
|
||||
| `/opsx:propose` | Create a change and generate all artifacts |
|
||||
| `/opsx:explore` | Think through problems before/during work |
|
||||
| `/opsx:apply` | Implement tasks from a change |
|
||||
| `/opsx:archive` | Archive a completed change |
|
||||
|
||||
**Additional commands:**
|
||||
|
||||
| Command | What it does |
|
||||
|--------------------|----------------------------------------------------------|
|
||||
| `/opsx:new` | Start a new change, step through artifacts one at a time |
|
||||
| `/opsx:continue` | Continue working on an existing change |
|
||||
| `/opsx:ff` | Fast-forward: create all artifacts at once |
|
||||
| `/opsx:verify` | Verify implementation matches artifacts |
|
||||
|
||||
---
|
||||
|
||||
## What's Next?
|
||||
|
||||
Try `/opsx:propose` on something you actually want to build. You've got the rhythm now!
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Graceful Exit Handling
|
||||
|
||||
### User wants to stop mid-way
|
||||
|
||||
If the user says they need to stop, want to pause, or seem disengaged:
|
||||
|
||||
```
|
||||
No problem! Your change is saved at `openspec/changes/<name>/`.
|
||||
|
||||
To pick up where we left off later:
|
||||
- `/opsx:continue <name>` - Resume artifact creation
|
||||
- `/opsx:apply <name>` - Jump to implementation (if tasks exist)
|
||||
|
||||
The work won't be lost. Come back whenever you're ready.
|
||||
```
|
||||
|
||||
Exit gracefully without pressure.
|
||||
|
||||
### User just wants command reference
|
||||
|
||||
If the user says they just want to see the commands or skip the tutorial:
|
||||
|
||||
```
|
||||
## OpenSpec Quick Reference
|
||||
|
||||
**Core workflow:**
|
||||
|
||||
| Command | What it does |
|
||||
|--------------------------|--------------------------------------------|
|
||||
| `/opsx:propose <name>` | Create a change and generate all artifacts |
|
||||
| `/opsx:explore` | Think through problems (no code changes) |
|
||||
| `/opsx:apply <name>` | Implement tasks |
|
||||
| `/opsx:archive <name>` | Archive when done |
|
||||
|
||||
**Additional commands:**
|
||||
|
||||
| Command | What it does |
|
||||
|---------------------------|-------------------------------------|
|
||||
| `/opsx:new <name>` | Start a new change, step by step |
|
||||
| `/opsx:continue <name>` | Continue an existing change |
|
||||
| `/opsx:ff <name>` | Fast-forward: all artifacts at once |
|
||||
| `/opsx:verify <name>` | Verify implementation |
|
||||
|
||||
Try `/opsx:propose` to start your first change.
|
||||
```
|
||||
|
||||
Exit gracefully.
|
||||
|
||||
---
|
||||
|
||||
## Guardrails
|
||||
|
||||
- **Follow the EXPLAIN → DO → SHOW → PAUSE pattern** at key transitions (after explore, after proposal draft, after tasks, after archive)
|
||||
- **Keep narration light** during implementation—teach without lecturing
|
||||
- **Don't skip phases** even if the change is small—the goal is teaching the workflow
|
||||
- **Pause for acknowledgment** at marked points, but don't over-pause
|
||||
- **Handle exits gracefully**—never pressure the user to continue
|
||||
- **Use real codebase tasks**—don't simulate or use fake examples
|
||||
- **Adjust scope gently**—guide toward smaller tasks but respect user choice
|
||||
134
.claude/commands/opsx/sync.md
Normal file
134
.claude/commands/opsx/sync.md
Normal file
|
|
@ -0,0 +1,134 @@
|
|||
---
|
||||
name: "OPSX: Sync"
|
||||
description: Sync delta specs from a change to main specs
|
||||
category: Workflow
|
||||
tags: [workflow, specs, experimental]
|
||||
---
|
||||
|
||||
Sync delta specs from a change to main specs.
|
||||
|
||||
This is an **agent-driven** operation - you will read delta specs and directly edit main specs to apply the changes. This allows intelligent merging (e.g., adding a scenario without copying the entire requirement).
|
||||
|
||||
**Input**: Optionally specify a change name after `/opsx:sync` (e.g., `/opsx:sync add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
|
||||
|
||||
**Steps**
|
||||
|
||||
1. **If no change name provided, prompt for selection**
|
||||
|
||||
Run `openspec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
|
||||
|
||||
Show changes that have delta specs (under `specs/` directory).
|
||||
|
||||
**IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
|
||||
|
||||
2. **Find delta specs**
|
||||
|
||||
Look for delta spec files in `openspec/changes/<name>/specs/*/spec.md`.
|
||||
|
||||
Each delta spec file contains sections like:
|
||||
- `## ADDED Requirements` - New requirements to add
|
||||
- `## MODIFIED Requirements` - Changes to existing requirements
|
||||
- `## REMOVED Requirements` - Requirements to remove
|
||||
- `## RENAMED Requirements` - Requirements to rename (FROM:/TO: format)
|
||||
|
||||
If no delta specs found, inform user and stop.
|
||||
|
||||
3. **For each delta spec, apply changes to main specs**
|
||||
|
||||
For each capability with a delta spec at `openspec/changes/<name>/specs/<capability>/spec.md`:
|
||||
|
||||
a. **Read the delta spec** to understand the intended changes
|
||||
|
||||
b. **Read the main spec** at `openspec/specs/<capability>/spec.md` (may not exist yet)
|
||||
|
||||
c. **Apply changes intelligently**:
|
||||
|
||||
**ADDED Requirements:**
|
||||
- If requirement doesn't exist in main spec → add it
|
||||
- If requirement already exists → update it to match (treat as implicit MODIFIED)
|
||||
|
||||
**MODIFIED Requirements:**
|
||||
- Find the requirement in main spec
|
||||
- Apply the changes - this can be:
|
||||
- Adding new scenarios (don't need to copy existing ones)
|
||||
- Modifying existing scenarios
|
||||
- Changing the requirement description
|
||||
- Preserve scenarios/content not mentioned in the delta
|
||||
|
||||
**REMOVED Requirements:**
|
||||
- Remove the entire requirement block from main spec
|
||||
|
||||
**RENAMED Requirements:**
|
||||
- Find the FROM requirement, rename to TO
|
||||
|
||||
d. **Create new main spec** if capability doesn't exist yet:
|
||||
- Create `openspec/specs/<capability>/spec.md`
|
||||
- Add Purpose section (can be brief, mark as TBD)
|
||||
- Add Requirements section with the ADDED requirements
|
||||
|
||||
4. **Show summary**
|
||||
|
||||
After applying all changes, summarize:
|
||||
- Which capabilities were updated
|
||||
- What changes were made (requirements added/modified/removed/renamed)
|
||||
|
||||
**Delta Spec Format Reference**
|
||||
|
||||
```markdown
|
||||
## ADDED Requirements
|
||||
|
||||
### Requirement: New Feature
|
||||
The system SHALL do something new.
|
||||
|
||||
#### Scenario: Basic case
|
||||
- **WHEN** user does X
|
||||
- **THEN** system does Y
|
||||
|
||||
## MODIFIED Requirements
|
||||
|
||||
### Requirement: Existing Feature
|
||||
#### Scenario: New scenario to add
|
||||
- **WHEN** user does A
|
||||
- **THEN** system does B
|
||||
|
||||
## REMOVED Requirements
|
||||
|
||||
### Requirement: Deprecated Feature
|
||||
|
||||
## RENAMED Requirements
|
||||
|
||||
- FROM: `### Requirement: Old Name`
|
||||
- TO: `### Requirement: New Name`
|
||||
```
|
||||
|
||||
**Key Principle: Intelligent Merging**
|
||||
|
||||
Unlike programmatic merging, you can apply **partial updates**:
|
||||
- To add a scenario, just include that scenario under MODIFIED - don't copy existing scenarios
|
||||
- The delta represents *intent*, not a wholesale replacement
|
||||
- Use your judgment to merge changes sensibly
|
||||
|
||||
**Output On Success**
|
||||
|
||||
```
|
||||
## Specs Synced: <change-name>
|
||||
|
||||
Updated main specs:
|
||||
|
||||
**<capability-1>**:
|
||||
- Added requirement: "New Feature"
|
||||
- Modified requirement: "Existing Feature" (added 1 scenario)
|
||||
|
||||
**<capability-2>**:
|
||||
- Created new spec file
|
||||
- Added requirement: "Another Feature"
|
||||
|
||||
Main specs are now updated. The change remains active - archive when implementation is complete.
|
||||
```
|
||||
|
||||
**Guardrails**
|
||||
- Read both delta and main specs before making changes
|
||||
- Preserve existing content not mentioned in delta
|
||||
- If something is unclear, ask for clarification
|
||||
- Show what you're changing as you go
|
||||
- The operation should be idempotent - running twice should give same result
|
||||
164
.claude/commands/opsx/verify.md
Normal file
164
.claude/commands/opsx/verify.md
Normal file
|
|
@ -0,0 +1,164 @@
|
|||
---
|
||||
name: "OPSX: Verify"
|
||||
description: Verify implementation matches change artifacts before archiving
|
||||
category: Workflow
|
||||
tags: [workflow, verify, experimental]
|
||||
---
|
||||
|
||||
Verify that an implementation matches the change artifacts (specs, tasks, design).
|
||||
|
||||
**Input**: Optionally specify a change name after `/opsx:verify` (e.g., `/opsx:verify add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
|
||||
|
||||
**Steps**
|
||||
|
||||
1. **If no change name provided, prompt for selection**
|
||||
|
||||
Run `openspec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
|
||||
|
||||
Show changes that have implementation tasks (tasks artifact exists).
|
||||
Include the schema used for each change if available.
|
||||
Mark changes with incomplete tasks as "(In Progress)".
|
||||
|
||||
**IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
|
||||
|
||||
2. **Check status to understand the schema**
|
||||
```bash
|
||||
openspec status --change "<name>" --json
|
||||
```
|
||||
Parse the JSON to understand:
|
||||
- `schemaName`: The workflow being used (e.g., "spec-driven")
|
||||
- Which artifacts exist for this change
|
||||
|
||||
3. **Get the change directory and load artifacts**
|
||||
|
||||
```bash
|
||||
openspec instructions apply --change "<name>" --json
|
||||
```
|
||||
|
||||
This returns the change directory and `contextFiles` (artifact ID -> array of concrete file paths). Read all available artifacts from `contextFiles`.
|
||||
|
||||
4. **Initialize verification report structure**
|
||||
|
||||
Create a report structure with three dimensions:
|
||||
- **Completeness**: Track tasks and spec coverage
|
||||
- **Correctness**: Track requirement implementation and scenario coverage
|
||||
- **Coherence**: Track design adherence and pattern consistency
|
||||
|
||||
Each dimension can have CRITICAL, WARNING, or SUGGESTION issues.
|
||||
|
||||
5. **Verify Completeness**
|
||||
|
||||
**Task Completion**:
|
||||
- If `contextFiles.tasks` exists, read every file path in it
|
||||
- Parse checkboxes: `- [ ]` (incomplete) vs `- [x]` (complete)
|
||||
- Count complete vs total tasks
|
||||
- If incomplete tasks exist:
|
||||
- Add CRITICAL issue for each incomplete task
|
||||
- Recommendation: "Complete task: <description>" or "Mark as done if already implemented"
|
||||
|
||||
**Spec Coverage**:
|
||||
- If delta specs exist in `openspec/changes/<name>/specs/`:
|
||||
- Extract all requirements (marked with "### Requirement:")
|
||||
- For each requirement:
|
||||
- Search codebase for keywords related to the requirement
|
||||
- Assess if implementation likely exists
|
||||
- If requirements appear unimplemented:
|
||||
- Add CRITICAL issue: "Requirement not found: <requirement name>"
|
||||
- Recommendation: "Implement requirement X: <description>"
|
||||
|
||||
6. **Verify Correctness**
|
||||
|
||||
**Requirement Implementation Mapping**:
|
||||
- For each requirement from delta specs:
|
||||
- Search codebase for implementation evidence
|
||||
- If found, note file paths and line ranges
|
||||
- Assess if implementation matches requirement intent
|
||||
- If divergence detected:
|
||||
- Add WARNING: "Implementation may diverge from spec: <details>"
|
||||
- Recommendation: "Review <file>:<lines> against requirement X"
|
||||
|
||||
**Scenario Coverage**:
|
||||
- For each scenario in delta specs (marked with "#### Scenario:"):
|
||||
- Check if conditions are handled in code
|
||||
- Check if tests exist covering the scenario
|
||||
- If scenario appears uncovered:
|
||||
- Add WARNING: "Scenario not covered: <scenario name>"
|
||||
- Recommendation: "Add test or implementation for scenario: <description>"
|
||||
|
||||
7. **Verify Coherence**
|
||||
|
||||
**Design Adherence**:
|
||||
- If `contextFiles.design` exists:
|
||||
- Extract key decisions (look for sections like "Decision:", "Approach:", "Architecture:")
|
||||
- Verify implementation follows those decisions
|
||||
- If contradiction detected:
|
||||
- Add WARNING: "Design decision not followed: <decision>"
|
||||
- Recommendation: "Update implementation or revise design.md to match reality"
|
||||
- If no design.md: Skip design adherence check, note "No design.md to verify against"
|
||||
|
||||
**Code Pattern Consistency**:
|
||||
- Review new code for consistency with project patterns
|
||||
- Check file naming, directory structure, coding style
|
||||
- If significant deviations found:
|
||||
- Add SUGGESTION: "Code pattern deviation: <details>"
|
||||
- Recommendation: "Consider following project pattern: <example>"
|
||||
|
||||
8. **Generate Verification Report**
|
||||
|
||||
**Summary Scorecard**:
|
||||
```
|
||||
## Verification Report: <change-name>
|
||||
|
||||
### Summary
|
||||
| Dimension | Status |
|
||||
|--------------|------------------|
|
||||
| Completeness | X/Y tasks, N reqs|
|
||||
| Correctness | M/N reqs covered |
|
||||
| Coherence | Followed/Issues |
|
||||
```
|
||||
|
||||
**Issues by Priority**:
|
||||
|
||||
1. **CRITICAL** (Must fix before archive):
|
||||
- Incomplete tasks
|
||||
- Missing requirement implementations
|
||||
- Each with specific, actionable recommendation
|
||||
|
||||
2. **WARNING** (Should fix):
|
||||
- Spec/design divergences
|
||||
- Missing scenario coverage
|
||||
- Each with specific recommendation
|
||||
|
||||
3. **SUGGESTION** (Nice to fix):
|
||||
- Pattern inconsistencies
|
||||
- Minor improvements
|
||||
- Each with specific recommendation
|
||||
|
||||
**Final Assessment**:
|
||||
- If CRITICAL issues: "X critical issue(s) found. Fix before archiving."
|
||||
- If only warnings: "No critical issues. Y warning(s) to consider. Ready for archive (with noted improvements)."
|
||||
- If all clear: "All checks passed. Ready for archive."
|
||||
|
||||
**Verification Heuristics**
|
||||
|
||||
- **Completeness**: Focus on objective checklist items (checkboxes, requirements list)
|
||||
- **Correctness**: Use keyword search, file path analysis, reasonable inference - don't require perfect certainty
|
||||
- **Coherence**: Look for glaring inconsistencies, don't nitpick style
|
||||
- **False Positives**: When uncertain, prefer SUGGESTION over WARNING, WARNING over CRITICAL
|
||||
- **Actionability**: Every issue must have a specific recommendation with file/line references where applicable
|
||||
|
||||
**Graceful Degradation**
|
||||
|
||||
- If only tasks.md exists: verify task completion only, skip spec/design checks
|
||||
- If tasks + specs exist: verify completeness and correctness, skip design
|
||||
- If full artifacts: verify all three dimensions
|
||||
- Always note which checks were skipped and why
|
||||
|
||||
**Output Format**
|
||||
|
||||
Use clear markdown with:
|
||||
- Table for summary scorecard
|
||||
- Grouped lists for issues (CRITICAL/WARNING/SUGGESTION)
|
||||
- Code references in format: `file.ts:123`
|
||||
- Specific, actionable recommendations
|
||||
- No vague suggestions like "consider reviewing"
|
||||
156
.claude/skills/openspec-apply-change/SKILL.md
Normal file
156
.claude/skills/openspec-apply-change/SKILL.md
Normal file
|
|
@ -0,0 +1,156 @@
|
|||
---
|
||||
name: openspec-apply-change
|
||||
description: Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
|
||||
license: MIT
|
||||
compatibility: Requires openspec CLI.
|
||||
metadata:
|
||||
author: openspec
|
||||
version: "1.0"
|
||||
generatedBy: "1.3.1"
|
||||
---
|
||||
|
||||
Implement tasks from an OpenSpec change.
|
||||
|
||||
**Input**: Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
|
||||
|
||||
**Steps**
|
||||
|
||||
1. **Select the change**
|
||||
|
||||
If a name is provided, use it. Otherwise:
|
||||
- Infer from conversation context if the user mentioned a change
|
||||
- Auto-select if only one active change exists
|
||||
- If ambiguous, run `openspec list --json` to get available changes and use the **AskUserQuestion tool** to let the user select
|
||||
|
||||
Always announce: "Using change: <name>" and how to override (e.g., `/opsx:apply <other>`).
|
||||
|
||||
2. **Check status to understand the schema**
|
||||
```bash
|
||||
openspec status --change "<name>" --json
|
||||
```
|
||||
Parse the JSON to understand:
|
||||
- `schemaName`: The workflow being used (e.g., "spec-driven")
|
||||
- Which artifact contains the tasks (typically "tasks" for spec-driven, check status for others)
|
||||
|
||||
3. **Get apply instructions**
|
||||
|
||||
```bash
|
||||
openspec instructions apply --change "<name>" --json
|
||||
```
|
||||
|
||||
This returns:
|
||||
- `contextFiles`: artifact ID -> array of concrete file paths (varies by schema - could be proposal/specs/design/tasks or spec/tests/implementation/docs)
|
||||
- Progress (total, complete, remaining)
|
||||
- Task list with status
|
||||
- Dynamic instruction based on current state
|
||||
|
||||
**Handle states:**
|
||||
- If `state: "blocked"` (missing artifacts): show message, suggest using openspec-continue-change
|
||||
- If `state: "all_done"`: congratulate, suggest archive
|
||||
- Otherwise: proceed to implementation
|
||||
|
||||
4. **Read context files**
|
||||
|
||||
Read every file path listed under `contextFiles` from the apply instructions output.
|
||||
The files depend on the schema being used:
|
||||
- **spec-driven**: proposal, specs, design, tasks
|
||||
- Other schemas: follow the contextFiles from CLI output
|
||||
|
||||
5. **Show current progress**
|
||||
|
||||
Display:
|
||||
- Schema being used
|
||||
- Progress: "N/M tasks complete"
|
||||
- Remaining tasks overview
|
||||
- Dynamic instruction from CLI
|
||||
|
||||
6. **Implement tasks (loop until done or blocked)**
|
||||
|
||||
For each pending task:
|
||||
- Show which task is being worked on
|
||||
- Make the code changes required
|
||||
- Keep changes minimal and focused
|
||||
- Mark task complete in the tasks file: `- [ ]` → `- [x]`
|
||||
- Continue to next task
|
||||
|
||||
**Pause if:**
|
||||
- Task is unclear → ask for clarification
|
||||
- Implementation reveals a design issue → suggest updating artifacts
|
||||
- Error or blocker encountered → report and wait for guidance
|
||||
- User interrupts
|
||||
|
||||
7. **On completion or pause, show status**
|
||||
|
||||
Display:
|
||||
- Tasks completed this session
|
||||
- Overall progress: "N/M tasks complete"
|
||||
- If all done: suggest archive
|
||||
- If paused: explain why and wait for guidance
|
||||
|
||||
**Output During Implementation**
|
||||
|
||||
```
|
||||
## Implementing: <change-name> (schema: <schema-name>)
|
||||
|
||||
Working on task 3/7: <task description>
|
||||
[...implementation happening...]
|
||||
✓ Task complete
|
||||
|
||||
Working on task 4/7: <task description>
|
||||
[...implementation happening...]
|
||||
✓ Task complete
|
||||
```
|
||||
|
||||
**Output On Completion**
|
||||
|
||||
```
|
||||
## Implementation Complete
|
||||
|
||||
**Change:** <change-name>
|
||||
**Schema:** <schema-name>
|
||||
**Progress:** 7/7 tasks complete ✓
|
||||
|
||||
### Completed This Session
|
||||
- [x] Task 1
|
||||
- [x] Task 2
|
||||
...
|
||||
|
||||
All tasks complete! Ready to archive this change.
|
||||
```
|
||||
|
||||
**Output On Pause (Issue Encountered)**
|
||||
|
||||
```
|
||||
## Implementation Paused
|
||||
|
||||
**Change:** <change-name>
|
||||
**Schema:** <schema-name>
|
||||
**Progress:** 4/7 tasks complete
|
||||
|
||||
### Issue Encountered
|
||||
<description of the issue>
|
||||
|
||||
**Options:**
|
||||
1. <option 1>
|
||||
2. <option 2>
|
||||
3. Other approach
|
||||
|
||||
What would you like to do?
|
||||
```
|
||||
|
||||
**Guardrails**
|
||||
- Keep going through tasks until done or blocked
|
||||
- Always read context files before starting (from the apply instructions output)
|
||||
- If task is ambiguous, pause and ask before implementing
|
||||
- If implementation reveals issues, pause and suggest artifact updates
|
||||
- Keep code changes minimal and scoped to each task
|
||||
- Update task checkbox immediately after completing each task
|
||||
- Pause on errors, blockers, or unclear requirements - don't guess
|
||||
- Use contextFiles from CLI output, don't assume specific file names
|
||||
|
||||
**Fluid Workflow Integration**
|
||||
|
||||
This skill supports the "actions on a change" model:
|
||||
|
||||
- **Can be invoked anytime**: Before all artifacts are done (if tasks exist), after partial implementation, interleaved with other actions
|
||||
- **Allows artifact updates**: If implementation reveals design issues, suggest updating artifacts - not phase-locked, work fluidly
|
||||
114
.claude/skills/openspec-archive-change/SKILL.md
Normal file
114
.claude/skills/openspec-archive-change/SKILL.md
Normal file
|
|
@ -0,0 +1,114 @@
|
|||
---
|
||||
name: openspec-archive-change
|
||||
description: Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
|
||||
license: MIT
|
||||
compatibility: Requires openspec CLI.
|
||||
metadata:
|
||||
author: openspec
|
||||
version: "1.0"
|
||||
generatedBy: "1.3.1"
|
||||
---
|
||||
|
||||
Archive a completed change in the experimental workflow.
|
||||
|
||||
**Input**: Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
|
||||
|
||||
**Steps**
|
||||
|
||||
1. **If no change name provided, prompt for selection**
|
||||
|
||||
Run `openspec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
|
||||
|
||||
Show only active changes (not already archived).
|
||||
Include the schema used for each change if available.
|
||||
|
||||
**IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
|
||||
|
||||
2. **Check artifact completion status**
|
||||
|
||||
Run `openspec status --change "<name>" --json` to check artifact completion.
|
||||
|
||||
Parse the JSON to understand:
|
||||
- `schemaName`: The workflow being used
|
||||
- `artifacts`: List of artifacts with their status (`done` or other)
|
||||
|
||||
**If any artifacts are not `done`:**
|
||||
- Display warning listing incomplete artifacts
|
||||
- Use **AskUserQuestion tool** to confirm user wants to proceed
|
||||
- Proceed if user confirms
|
||||
|
||||
3. **Check task completion status**
|
||||
|
||||
Read the tasks file (typically `tasks.md`) to check for incomplete tasks.
|
||||
|
||||
Count tasks marked with `- [ ]` (incomplete) vs `- [x]` (complete).
|
||||
|
||||
**If incomplete tasks found:**
|
||||
- Display warning showing count of incomplete tasks
|
||||
- Use **AskUserQuestion tool** to confirm user wants to proceed
|
||||
- Proceed if user confirms
|
||||
|
||||
**If no tasks file exists:** Proceed without task-related warning.
|
||||
|
||||
4. **Assess delta spec sync state**
|
||||
|
||||
Check for delta specs at `openspec/changes/<name>/specs/`. If none exist, proceed without sync prompt.
|
||||
|
||||
**If delta specs exist:**
|
||||
- Compare each delta spec with its corresponding main spec at `openspec/specs/<capability>/spec.md`
|
||||
- Determine what changes would be applied (adds, modifications, removals, renames)
|
||||
- Show a combined summary before prompting
|
||||
|
||||
**Prompt options:**
|
||||
- If changes needed: "Sync now (recommended)", "Archive without syncing"
|
||||
- If already synced: "Archive now", "Sync anyway", "Cancel"
|
||||
|
||||
If user chooses sync, use Task tool (subagent_type: "general-purpose", prompt: "Use Skill tool to invoke openspec-sync-specs for change '<name>'. Delta spec analysis: <include the analyzed delta spec summary>"). Proceed to archive regardless of choice.
|
||||
|
||||
5. **Perform the archive**
|
||||
|
||||
Create the archive directory if it doesn't exist:
|
||||
```bash
|
||||
mkdir -p openspec/changes/archive
|
||||
```
|
||||
|
||||
Generate target name using current date: `YYYY-MM-DD-<change-name>`
|
||||
|
||||
**Check if target already exists:**
|
||||
- If yes: Fail with error, suggest renaming existing archive or using different date
|
||||
- If no: Move the change directory to archive
|
||||
|
||||
```bash
|
||||
mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
|
||||
```
|
||||
|
||||
6. **Display summary**
|
||||
|
||||
Show archive completion summary including:
|
||||
- Change name
|
||||
- Schema that was used
|
||||
- Archive location
|
||||
- Whether specs were synced (if applicable)
|
||||
- Note about any warnings (incomplete artifacts/tasks)
|
||||
|
||||
**Output On Success**
|
||||
|
||||
```
|
||||
## Archive Complete
|
||||
|
||||
**Change:** <change-name>
|
||||
**Schema:** <schema-name>
|
||||
**Archived to:** openspec/changes/archive/YYYY-MM-DD-<name>/
|
||||
**Specs:** ✓ Synced to main specs (or "No delta specs" or "Sync skipped")
|
||||
|
||||
All artifacts complete. All tasks complete.
|
||||
```
|
||||
|
||||
**Guardrails**
|
||||
- Always prompt for change selection if not provided
|
||||
- Use artifact graph (openspec status --json) for completion checking
|
||||
- Don't block archive on warnings - just inform and confirm
|
||||
- Preserve .openspec.yaml when moving to archive (it moves with the directory)
|
||||
- Show clear summary of what happened
|
||||
- If sync is requested, use openspec-sync-specs approach (agent-driven)
|
||||
- If delta specs exist, always run the sync assessment and show the combined summary before prompting
|
||||
246
.claude/skills/openspec-bulk-archive-change/SKILL.md
Normal file
246
.claude/skills/openspec-bulk-archive-change/SKILL.md
Normal file
|
|
@ -0,0 +1,246 @@
|
|||
---
|
||||
name: openspec-bulk-archive-change
|
||||
description: Archive multiple completed changes at once. Use when archiving several parallel changes.
|
||||
license: MIT
|
||||
compatibility: Requires openspec CLI.
|
||||
metadata:
|
||||
author: openspec
|
||||
version: "1.0"
|
||||
generatedBy: "1.3.1"
|
||||
---
|
||||
|
||||
Archive multiple completed changes in a single operation.
|
||||
|
||||
This skill allows you to batch-archive changes, handling spec conflicts intelligently by checking the codebase to determine what's actually implemented.
|
||||
|
||||
**Input**: None required (prompts for selection)
|
||||
|
||||
**Steps**
|
||||
|
||||
1. **Get active changes**
|
||||
|
||||
Run `openspec list --json` to get all active changes.
|
||||
|
||||
If no active changes exist, inform user and stop.
|
||||
|
||||
2. **Prompt for change selection**
|
||||
|
||||
Use **AskUserQuestion tool** with multi-select to let user choose changes:
|
||||
- Show each change with its schema
|
||||
- Include an option for "All changes"
|
||||
- Allow any number of selections (1+ works, 2+ is the typical use case)
|
||||
|
||||
**IMPORTANT**: Do NOT auto-select. Always let the user choose.
|
||||
|
||||
3. **Batch validation - gather status for all selected changes**
|
||||
|
||||
For each selected change, collect:
|
||||
|
||||
a. **Artifact status** - Run `openspec status --change "<name>" --json`
|
||||
- Parse `schemaName` and `artifacts` list
|
||||
- Note which artifacts are `done` vs other states
|
||||
|
||||
b. **Task completion** - Read `openspec/changes/<name>/tasks.md`
|
||||
- Count `- [ ]` (incomplete) vs `- [x]` (complete)
|
||||
- If no tasks file exists, note as "No tasks"
|
||||
|
||||
c. **Delta specs** - Check `openspec/changes/<name>/specs/` directory
|
||||
- List which capability specs exist
|
||||
- For each, extract requirement names (lines matching `### Requirement: <name>`)
|
||||
|
||||
4. **Detect spec conflicts**
|
||||
|
||||
Build a map of `capability -> [changes that touch it]`:
|
||||
|
||||
```
|
||||
auth -> [change-a, change-b] <- CONFLICT (2+ changes)
|
||||
api -> [change-c] <- OK (only 1 change)
|
||||
```
|
||||
|
||||
A conflict exists when 2+ selected changes have delta specs for the same capability.
|
||||
|
||||
5. **Resolve conflicts agentically**
|
||||
|
||||
**For each conflict**, investigate the codebase:
|
||||
|
||||
a. **Read the delta specs** from each conflicting change to understand what each claims to add/modify
|
||||
|
||||
b. **Search the codebase** for implementation evidence:
|
||||
- Look for code implementing requirements from each delta spec
|
||||
- Check for related files, functions, or tests
|
||||
|
||||
c. **Determine resolution**:
|
||||
- If only one change is actually implemented -> sync that one's specs
|
||||
- If both implemented -> apply in chronological order (older first, newer overwrites)
|
||||
- If neither implemented -> skip spec sync, warn user
|
||||
|
||||
d. **Record resolution** for each conflict:
|
||||
- Which change's specs to apply
|
||||
- In what order (if both)
|
||||
- Rationale (what was found in codebase)
|
||||
|
||||
6. **Show consolidated status table**
|
||||
|
||||
Display a table summarizing all changes:
|
||||
|
||||
```
|
||||
| Change | Artifacts | Tasks | Specs | Conflicts | Status |
|
||||
|---------------------|-----------|-------|---------|-----------|--------|
|
||||
| schema-management | Done | 5/5 | 2 delta | None | Ready |
|
||||
| project-config | Done | 3/3 | 1 delta | None | Ready |
|
||||
| add-oauth | Done | 4/4 | 1 delta | auth (!) | Ready* |
|
||||
| add-verify-skill | 1 left | 2/5 | None | None | Warn |
|
||||
```
|
||||
|
||||
For conflicts, show the resolution:
|
||||
```
|
||||
* Conflict resolution:
|
||||
- auth spec: Will apply add-oauth then add-jwt (both implemented, chronological order)
|
||||
```
|
||||
|
||||
For incomplete changes, show warnings:
|
||||
```
|
||||
Warnings:
|
||||
- add-verify-skill: 1 incomplete artifact, 3 incomplete tasks
|
||||
```
|
||||
|
||||
7. **Confirm batch operation**
|
||||
|
||||
Use **AskUserQuestion tool** with a single confirmation:
|
||||
|
||||
- "Archive N changes?" with options based on status
|
||||
- Options might include:
|
||||
- "Archive all N changes"
|
||||
- "Archive only N ready changes (skip incomplete)"
|
||||
- "Cancel"
|
||||
|
||||
If there are incomplete changes, make clear they'll be archived with warnings.
|
||||
|
||||
8. **Execute archive for each confirmed change**
|
||||
|
||||
Process changes in the determined order (respecting conflict resolution):
|
||||
|
||||
a. **Sync specs** if delta specs exist:
|
||||
- Use the openspec-sync-specs approach (agent-driven intelligent merge)
|
||||
- For conflicts, apply in resolved order
|
||||
- Track if sync was done
|
||||
|
||||
b. **Perform the archive**:
|
||||
```bash
|
||||
mkdir -p openspec/changes/archive
|
||||
mv openspec/changes/<name> openspec/changes/archive/YYYY-MM-DD-<name>
|
||||
```
|
||||
|
||||
c. **Track outcome** for each change:
|
||||
- Success: archived successfully
|
||||
- Failed: error during archive (record error)
|
||||
- Skipped: user chose not to archive (if applicable)
|
||||
|
||||
9. **Display summary**
|
||||
|
||||
Show final results:
|
||||
|
||||
```
|
||||
## Bulk Archive Complete
|
||||
|
||||
Archived 3 changes:
|
||||
- schema-management-cli -> archive/2026-01-19-schema-management-cli/
|
||||
- project-config -> archive/2026-01-19-project-config/
|
||||
- add-oauth -> archive/2026-01-19-add-oauth/
|
||||
|
||||
Skipped 1 change:
|
||||
- add-verify-skill (user chose not to archive incomplete)
|
||||
|
||||
Spec sync summary:
|
||||
- 4 delta specs synced to main specs
|
||||
- 1 conflict resolved (auth: applied both in chronological order)
|
||||
```
|
||||
|
||||
If any failures:
|
||||
```
|
||||
Failed 1 change:
|
||||
- some-change: Archive directory already exists
|
||||
```
|
||||
|
||||
**Conflict Resolution Examples**
|
||||
|
||||
Example 1: Only one implemented
|
||||
```
|
||||
Conflict: specs/auth/spec.md touched by [add-oauth, add-jwt]
|
||||
|
||||
Checking add-oauth:
|
||||
- Delta adds "OAuth Provider Integration" requirement
|
||||
- Searching codebase... found src/auth/oauth.ts implementing OAuth flow
|
||||
|
||||
Checking add-jwt:
|
||||
- Delta adds "JWT Token Handling" requirement
|
||||
- Searching codebase... no JWT implementation found
|
||||
|
||||
Resolution: Only add-oauth is implemented. Will sync add-oauth specs only.
|
||||
```
|
||||
|
||||
Example 2: Both implemented
|
||||
```
|
||||
Conflict: specs/api/spec.md touched by [add-rest-api, add-graphql]
|
||||
|
||||
Checking add-rest-api (created 2026-01-10):
|
||||
- Delta adds "REST Endpoints" requirement
|
||||
- Searching codebase... found src/api/rest.ts
|
||||
|
||||
Checking add-graphql (created 2026-01-15):
|
||||
- Delta adds "GraphQL Schema" requirement
|
||||
- Searching codebase... found src/api/graphql.ts
|
||||
|
||||
Resolution: Both implemented. Will apply add-rest-api specs first,
|
||||
then add-graphql specs (chronological order, newer takes precedence).
|
||||
```
|
||||
|
||||
**Output On Success**
|
||||
|
||||
```
|
||||
## Bulk Archive Complete
|
||||
|
||||
Archived N changes:
|
||||
- <change-1> -> archive/YYYY-MM-DD-<change-1>/
|
||||
- <change-2> -> archive/YYYY-MM-DD-<change-2>/
|
||||
|
||||
Spec sync summary:
|
||||
- N delta specs synced to main specs
|
||||
- No conflicts (or: M conflicts resolved)
|
||||
```
|
||||
|
||||
**Output On Partial Success**
|
||||
|
||||
```
|
||||
## Bulk Archive Complete (partial)
|
||||
|
||||
Archived N changes:
|
||||
- <change-1> -> archive/YYYY-MM-DD-<change-1>/
|
||||
|
||||
Skipped M changes:
|
||||
- <change-2> (user chose not to archive incomplete)
|
||||
|
||||
Failed K changes:
|
||||
- <change-3>: Archive directory already exists
|
||||
```
|
||||
|
||||
**Output When No Changes**
|
||||
|
||||
```
|
||||
## No Changes to Archive
|
||||
|
||||
No active changes found. Create a new change to get started.
|
||||
```
|
||||
|
||||
**Guardrails**
|
||||
- Allow any number of changes (1+ is fine, 2+ is the typical use case)
|
||||
- Always prompt for selection, never auto-select
|
||||
- Detect spec conflicts early and resolve by checking codebase
|
||||
- When both changes are implemented, apply specs in chronological order
|
||||
- Skip spec sync only when implementation is missing (warn user)
|
||||
- Show clear per-change status before confirming
|
||||
- Use single confirmation for entire batch
|
||||
- Track and report all outcomes (success/skip/fail)
|
||||
- Preserve .openspec.yaml when moving to archive
|
||||
- Archive directory target uses current date: YYYY-MM-DD-<name>
|
||||
- If archive target exists, fail that change but continue with others
|
||||
118
.claude/skills/openspec-continue-change/SKILL.md
Normal file
118
.claude/skills/openspec-continue-change/SKILL.md
Normal file
|
|
@ -0,0 +1,118 @@
|
|||
---
|
||||
name: openspec-continue-change
|
||||
description: Continue working on an OpenSpec change by creating the next artifact. Use when the user wants to progress their change, create the next artifact, or continue their workflow.
|
||||
license: MIT
|
||||
compatibility: Requires openspec CLI.
|
||||
metadata:
|
||||
author: openspec
|
||||
version: "1.0"
|
||||
generatedBy: "1.3.1"
|
||||
---
|
||||
|
||||
Continue working on a change by creating the next artifact.
|
||||
|
||||
**Input**: Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
|
||||
|
||||
**Steps**
|
||||
|
||||
1. **If no change name provided, prompt for selection**
|
||||
|
||||
Run `openspec list --json` to get available changes sorted by most recently modified. Then use the **AskUserQuestion tool** to let the user select which change to work on.
|
||||
|
||||
Present the top 3-4 most recently modified changes as options, showing:
|
||||
- Change name
|
||||
- Schema (from `schema` field if present, otherwise "spec-driven")
|
||||
- Status (e.g., "0/5 tasks", "complete", "no tasks")
|
||||
- How recently it was modified (from `lastModified` field)
|
||||
|
||||
Mark the most recently modified change as "(Recommended)" since it's likely what the user wants to continue.
|
||||
|
||||
**IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
|
||||
|
||||
2. **Check current status**
|
||||
```bash
|
||||
openspec status --change "<name>" --json
|
||||
```
|
||||
Parse the JSON to understand current state. The response includes:
|
||||
- `schemaName`: The workflow schema being used (e.g., "spec-driven")
|
||||
- `artifacts`: Array of artifacts with their status ("done", "ready", "blocked")
|
||||
- `isComplete`: Boolean indicating if all artifacts are complete
|
||||
|
||||
3. **Act based on status**:
|
||||
|
||||
---
|
||||
|
||||
**If all artifacts are complete (`isComplete: true`)**:
|
||||
- Congratulate the user
|
||||
- Show final status including the schema used
|
||||
- Suggest: "All artifacts created! You can now implement this change or archive it."
|
||||
- STOP
|
||||
|
||||
---
|
||||
|
||||
**If artifacts are ready to create** (status shows artifacts with `status: "ready"`):
|
||||
- Pick the FIRST artifact with `status: "ready"` from the status output
|
||||
- Get its instructions:
|
||||
```bash
|
||||
openspec instructions <artifact-id> --change "<name>" --json
|
||||
```
|
||||
- Parse the JSON. The key fields are:
|
||||
- `context`: Project background (constraints for you - do NOT include in output)
|
||||
- `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
|
||||
- `template`: The structure to use for your output file
|
||||
- `instruction`: Schema-specific guidance
|
||||
- `outputPath`: Where to write the artifact
|
||||
- `dependencies`: Completed artifacts to read for context
|
||||
- **Create the artifact file**:
|
||||
- Read any completed dependency files for context
|
||||
- Use `template` as the structure - fill in its sections
|
||||
- Apply `context` and `rules` as constraints when writing - but do NOT copy them into the file
|
||||
- Write to the output path specified in instructions
|
||||
- Show what was created and what's now unlocked
|
||||
- STOP after creating ONE artifact
|
||||
|
||||
---
|
||||
|
||||
**If no artifacts are ready (all blocked)**:
|
||||
- This shouldn't happen with a valid schema
|
||||
- Show status and suggest checking for issues
|
||||
|
||||
4. **After creating an artifact, show progress**
|
||||
```bash
|
||||
openspec status --change "<name>"
|
||||
```
|
||||
|
||||
**Output**
|
||||
|
||||
After each invocation, show:
|
||||
- Which artifact was created
|
||||
- Schema workflow being used
|
||||
- Current progress (N/M complete)
|
||||
- What artifacts are now unlocked
|
||||
- Prompt: "Want to continue? Just ask me to continue or tell me what to do next."
|
||||
|
||||
**Artifact Creation Guidelines**
|
||||
|
||||
The artifact types and their purpose depend on the schema. Use the `instruction` field from the instructions output to understand what to create.
|
||||
|
||||
Common artifact patterns:
|
||||
|
||||
**spec-driven schema** (proposal → specs → design → tasks):
|
||||
- **proposal.md**: Ask user about the change if not clear. Fill in Why, What Changes, Capabilities, Impact.
|
||||
- The Capabilities section is critical - each capability listed will need a spec file.
|
||||
- **specs/<capability>/spec.md**: Create one spec per capability listed in the proposal's Capabilities section (use the capability name, not the change name).
|
||||
- **design.md**: Document technical decisions, architecture, and implementation approach.
|
||||
- **tasks.md**: Break down implementation into checkboxed tasks.
|
||||
|
||||
For other schemas, follow the `instruction` field from the CLI output.
|
||||
|
||||
**Guardrails**
|
||||
- Create ONE artifact per invocation
|
||||
- Always read dependency artifacts before creating a new one
|
||||
- Never skip artifacts or create out of order
|
||||
- If context is unclear, ask the user before creating
|
||||
- Verify the artifact file exists after writing before marking progress
|
||||
- Use the schema's artifact sequence, don't assume specific artifact names
|
||||
- **IMPORTANT**: `context` and `rules` are constraints for YOU, not content for the file
|
||||
- Do NOT copy `<context>`, `<rules>`, `<project_context>` blocks into the artifact
|
||||
- These guide what you write, but should never appear in the output
|
||||
288
.claude/skills/openspec-explore/SKILL.md
Normal file
288
.claude/skills/openspec-explore/SKILL.md
Normal file
|
|
@ -0,0 +1,288 @@
|
|||
---
|
||||
name: openspec-explore
|
||||
description: Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
|
||||
license: MIT
|
||||
compatibility: Requires openspec CLI.
|
||||
metadata:
|
||||
author: openspec
|
||||
version: "1.0"
|
||||
generatedBy: "1.3.1"
|
||||
---
|
||||
|
||||
Enter explore mode. Think deeply. Visualize freely. Follow the conversation wherever it goes.
|
||||
|
||||
**IMPORTANT: Explore mode is for thinking, not implementing.** You may read files, search code, and investigate the codebase, but you must NEVER write code or implement features. If the user asks you to implement something, remind them to exit explore mode first and create a change proposal. You MAY create OpenSpec artifacts (proposals, designs, specs) if the user asks—that's capturing thinking, not implementing.
|
||||
|
||||
**This is a stance, not a workflow.** There are no fixed steps, no required sequence, no mandatory outputs. You're a thinking partner helping the user explore.
|
||||
|
||||
---
|
||||
|
||||
## The Stance
|
||||
|
||||
- **Curious, not prescriptive** - Ask questions that emerge naturally, don't follow a script
|
||||
- **Open threads, not interrogations** - Surface multiple interesting directions and let the user follow what resonates. Don't funnel them through a single path of questions.
|
||||
- **Visual** - Use ASCII diagrams liberally when they'd help clarify thinking
|
||||
- **Adaptive** - Follow interesting threads, pivot when new information emerges
|
||||
- **Patient** - Don't rush to conclusions, let the shape of the problem emerge
|
||||
- **Grounded** - Explore the actual codebase when relevant, don't just theorize
|
||||
|
||||
---
|
||||
|
||||
## What You Might Do
|
||||
|
||||
Depending on what the user brings, you might:
|
||||
|
||||
**Explore the problem space**
|
||||
- Ask clarifying questions that emerge from what they said
|
||||
- Challenge assumptions
|
||||
- Reframe the problem
|
||||
- Find analogies
|
||||
|
||||
**Investigate the codebase**
|
||||
- Map existing architecture relevant to the discussion
|
||||
- Find integration points
|
||||
- Identify patterns already in use
|
||||
- Surface hidden complexity
|
||||
|
||||
**Compare options**
|
||||
- Brainstorm multiple approaches
|
||||
- Build comparison tables
|
||||
- Sketch tradeoffs
|
||||
- Recommend a path (if asked)
|
||||
|
||||
**Visualize**
|
||||
```
|
||||
┌─────────────────────────────────────────┐
|
||||
│ Use ASCII diagrams liberally │
|
||||
├─────────────────────────────────────────┤
|
||||
│ │
|
||||
│ ┌────────┐ ┌────────┐ │
|
||||
│ │ State │────────▶│ State │ │
|
||||
│ │ A │ │ B │ │
|
||||
│ └────────┘ └────────┘ │
|
||||
│ │
|
||||
│ System diagrams, state machines, │
|
||||
│ data flows, architecture sketches, │
|
||||
│ dependency graphs, comparison tables │
|
||||
│ │
|
||||
└─────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
**Surface risks and unknowns**
|
||||
- Identify what could go wrong
|
||||
- Find gaps in understanding
|
||||
- Suggest spikes or investigations
|
||||
|
||||
---
|
||||
|
||||
## OpenSpec Awareness
|
||||
|
||||
You have full context of the OpenSpec system. Use it naturally, don't force it.
|
||||
|
||||
### Check for context
|
||||
|
||||
At the start, quickly check what exists:
|
||||
```bash
|
||||
openspec list --json
|
||||
```
|
||||
|
||||
This tells you:
|
||||
- If there are active changes
|
||||
- Their names, schemas, and status
|
||||
- What the user might be working on
|
||||
|
||||
### When no change exists
|
||||
|
||||
Think freely. When insights crystallize, you might offer:
|
||||
|
||||
- "This feels solid enough to start a change. Want me to create a proposal?"
|
||||
- Or keep exploring - no pressure to formalize
|
||||
|
||||
### When a change exists
|
||||
|
||||
If the user mentions a change or you detect one is relevant:
|
||||
|
||||
1. **Read existing artifacts for context**
|
||||
- `openspec/changes/<name>/proposal.md`
|
||||
- `openspec/changes/<name>/design.md`
|
||||
- `openspec/changes/<name>/tasks.md`
|
||||
- etc.
|
||||
|
||||
2. **Reference them naturally in conversation**
|
||||
- "Your design mentions using Redis, but we just realized SQLite fits better..."
|
||||
- "The proposal scopes this to premium users, but we're now thinking everyone..."
|
||||
|
||||
3. **Offer to capture when decisions are made**
|
||||
|
||||
| Insight Type | Where to Capture |
|
||||
|----------------------------|--------------------------------|
|
||||
| New requirement discovered | `specs/<capability>/spec.md` |
|
||||
| Requirement changed | `specs/<capability>/spec.md` |
|
||||
| Design decision made | `design.md` |
|
||||
| Scope changed | `proposal.md` |
|
||||
| New work identified | `tasks.md` |
|
||||
| Assumption invalidated | Relevant artifact |
|
||||
|
||||
Example offers:
|
||||
- "That's a design decision. Capture it in design.md?"
|
||||
- "This is a new requirement. Add it to specs?"
|
||||
- "This changes scope. Update the proposal?"
|
||||
|
||||
4. **The user decides** - Offer and move on. Don't pressure. Don't auto-capture.
|
||||
|
||||
---
|
||||
|
||||
## What You Don't Have To Do
|
||||
|
||||
- Follow a script
|
||||
- Ask the same questions every time
|
||||
- Produce a specific artifact
|
||||
- Reach a conclusion
|
||||
- Stay on topic if a tangent is valuable
|
||||
- Be brief (this is thinking time)
|
||||
|
||||
---
|
||||
|
||||
## Handling Different Entry Points
|
||||
|
||||
**User brings a vague idea:**
|
||||
```
|
||||
User: I'm thinking about adding real-time collaboration
|
||||
|
||||
You: Real-time collab is a big space. Let me think about this...
|
||||
|
||||
COLLABORATION SPECTRUM
|
||||
════════════════════════════════════════════
|
||||
|
||||
Awareness Coordination Sync
|
||||
│ │ │
|
||||
▼ ▼ ▼
|
||||
┌────────┐ ┌────────┐ ┌────────┐
|
||||
│Presence│ │Cursors │ │ CRDT │
|
||||
│ "3 │ │ Multi │ │Conflict│
|
||||
│online" │ │ select │ │ free │
|
||||
└────────┘ └────────┘ └────────┘
|
||||
│ │ │
|
||||
trivial moderate complex
|
||||
|
||||
Where's your head at?
|
||||
```
|
||||
|
||||
**User brings a specific problem:**
|
||||
```
|
||||
User: The auth system is a mess
|
||||
|
||||
You: [reads codebase]
|
||||
|
||||
┌─────────────────────────────────────────────┐
|
||||
│ CURRENT AUTH FLOW │
|
||||
└─────────────────────────────────────────────┘
|
||||
│
|
||||
┌─────────────┼─────────────┐
|
||||
▼ ▼ ▼
|
||||
┌─────────┐ ┌─────────┐ ┌─────────┐
|
||||
│ Google │ │ GitHub │ │ Email │
|
||||
│ OAuth │ │ OAuth │ │ Magic │
|
||||
└────┬────┘ └────┬────┘ └────┬────┘
|
||||
│ │ │
|
||||
└─────────────┼─────────────┘
|
||||
▼
|
||||
┌───────────┐
|
||||
│ Session │
|
||||
└─────┬─────┘
|
||||
│
|
||||
▼
|
||||
┌───────────┐
|
||||
│ Perms │
|
||||
└───────────┘
|
||||
|
||||
I see three tangles. Which one's burning?
|
||||
```
|
||||
|
||||
**User is stuck mid-implementation:**
|
||||
```
|
||||
User: /opsx:explore add-auth-system
|
||||
The OAuth integration is more complex than expected
|
||||
|
||||
You: [reads change artifacts]
|
||||
|
||||
You're on task 4: "Implement OAuth flow"
|
||||
|
||||
Let me trace what's involved...
|
||||
|
||||
[draws diagram, explores options, suggests paths]
|
||||
|
||||
Want to update the design to reflect this?
|
||||
Or add a spike task to investigate?
|
||||
```
|
||||
|
||||
**User wants to compare options:**
|
||||
```
|
||||
User: Should we use Postgres or SQLite?
|
||||
|
||||
You: Generic answer is boring. What's the context?
|
||||
|
||||
User: A CLI tool that tracks local dev environments
|
||||
|
||||
You: That changes everything.
|
||||
|
||||
┌─────────────────────────────────────────────────┐
|
||||
│ CLI TOOL DATA STORAGE │
|
||||
└─────────────────────────────────────────────────┘
|
||||
|
||||
Key constraints:
|
||||
• No daemon running
|
||||
• Must work offline
|
||||
• Single user
|
||||
|
||||
SQLite Postgres
|
||||
Deployment embedded ✓ needs server ✗
|
||||
Offline yes ✓ no ✗
|
||||
Single file yes ✓ no ✗
|
||||
|
||||
SQLite. Not even close.
|
||||
|
||||
Unless... is there a sync component?
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Ending Discovery
|
||||
|
||||
There's no required ending. Discovery might:
|
||||
|
||||
- **Flow into a proposal**: "Ready to start? I can create a change proposal."
|
||||
- **Result in artifact updates**: "Updated design.md with these decisions"
|
||||
- **Just provide clarity**: User has what they need, moves on
|
||||
- **Continue later**: "We can pick this up anytime"
|
||||
|
||||
When it feels like things are crystallizing, you might summarize:
|
||||
|
||||
```
|
||||
## What We Figured Out
|
||||
|
||||
**The problem**: [crystallized understanding]
|
||||
|
||||
**The approach**: [if one emerged]
|
||||
|
||||
**Open questions**: [if any remain]
|
||||
|
||||
**Next steps** (if ready):
|
||||
- Create a change proposal
|
||||
- Keep exploring: just keep talking
|
||||
```
|
||||
|
||||
But this summary is optional. Sometimes the thinking IS the value.
|
||||
|
||||
---
|
||||
|
||||
## Guardrails
|
||||
|
||||
- **Don't implement** - Never write code or implement features. Creating OpenSpec artifacts is fine, writing application code is not.
|
||||
- **Don't fake understanding** - If something is unclear, dig deeper
|
||||
- **Don't rush** - Discovery is thinking time, not task time
|
||||
- **Don't force structure** - Let patterns emerge naturally
|
||||
- **Don't auto-capture** - Offer to save insights, don't just do it
|
||||
- **Do visualize** - A good diagram is worth many paragraphs
|
||||
- **Do explore the codebase** - Ground discussions in reality
|
||||
- **Do question assumptions** - Including the user's and your own
|
||||
101
.claude/skills/openspec-ff-change/SKILL.md
Normal file
101
.claude/skills/openspec-ff-change/SKILL.md
Normal file
|
|
@ -0,0 +1,101 @@
|
|||
---
|
||||
name: openspec-ff-change
|
||||
description: Fast-forward through OpenSpec artifact creation. Use when the user wants to quickly create all artifacts needed for implementation without stepping through each one individually.
|
||||
license: MIT
|
||||
compatibility: Requires openspec CLI.
|
||||
metadata:
|
||||
author: openspec
|
||||
version: "1.0"
|
||||
generatedBy: "1.3.1"
|
||||
---
|
||||
|
||||
Fast-forward through artifact creation - generate everything needed to start implementation in one go.
|
||||
|
||||
**Input**: The user's request should include a change name (kebab-case) OR a description of what they want to build.
|
||||
|
||||
**Steps**
|
||||
|
||||
1. **If no clear input provided, ask what they want to build**
|
||||
|
||||
Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
|
||||
> "What change do you want to work on? Describe what you want to build or fix."
|
||||
|
||||
From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
|
||||
|
||||
**IMPORTANT**: Do NOT proceed without understanding what the user wants to build.
|
||||
|
||||
2. **Create the change directory**
|
||||
```bash
|
||||
openspec new change "<name>"
|
||||
```
|
||||
This creates a scaffolded change at `openspec/changes/<name>/`.
|
||||
|
||||
3. **Get the artifact build order**
|
||||
```bash
|
||||
openspec status --change "<name>" --json
|
||||
```
|
||||
Parse the JSON to get:
|
||||
- `applyRequires`: array of artifact IDs needed before implementation (e.g., `["tasks"]`)
|
||||
- `artifacts`: list of all artifacts with their status and dependencies
|
||||
|
||||
4. **Create artifacts in sequence until apply-ready**
|
||||
|
||||
Use the **TodoWrite tool** to track progress through the artifacts.
|
||||
|
||||
Loop through artifacts in dependency order (artifacts with no pending dependencies first):
|
||||
|
||||
a. **For each artifact that is `ready` (dependencies satisfied)**:
|
||||
- Get instructions:
|
||||
```bash
|
||||
openspec instructions <artifact-id> --change "<name>" --json
|
||||
```
|
||||
- The instructions JSON includes:
|
||||
- `context`: Project background (constraints for you - do NOT include in output)
|
||||
- `rules`: Artifact-specific rules (constraints for you - do NOT include in output)
|
||||
- `template`: The structure to use for your output file
|
||||
- `instruction`: Schema-specific guidance for this artifact type
|
||||
- `outputPath`: Where to write the artifact
|
||||
- `dependencies`: Completed artifacts to read for context
|
||||
- Read any completed dependency files for context
|
||||
- Create the artifact file using `template` as the structure
|
||||
- Apply `context` and `rules` as constraints - but do NOT copy them into the file
|
||||
- Show brief progress: "✓ Created <artifact-id>"
|
||||
|
||||
b. **Continue until all `applyRequires` artifacts are complete**
|
||||
- After creating each artifact, re-run `openspec status --change "<name>" --json`
|
||||
- Check if every artifact ID in `applyRequires` has `status: "done"` in the artifacts array
|
||||
- Stop when all `applyRequires` artifacts are done
|
||||
|
||||
c. **If an artifact requires user input** (unclear context):
|
||||
- Use **AskUserQuestion tool** to clarify
|
||||
- Then continue with creation
|
||||
|
||||
5. **Show final status**
|
||||
```bash
|
||||
openspec status --change "<name>"
|
||||
```
|
||||
|
||||
**Output**
|
||||
|
||||
After completing all artifacts, summarize:
|
||||
- Change name and location
|
||||
- List of artifacts created with brief descriptions
|
||||
- What's ready: "All artifacts created! Ready for implementation."
|
||||
- Prompt: "Run `/opsx:apply` or ask me to implement to start working on the tasks."
|
||||
|
||||
**Artifact Creation Guidelines**
|
||||
|
||||
- Follow the `instruction` field from `openspec instructions` for each artifact type
|
||||
- The schema defines what each artifact should contain - follow it
|
||||
- Read dependency artifacts for context before creating new ones
|
||||
- Use `template` as the structure for your output file - fill in its sections
|
||||
- **IMPORTANT**: `context` and `rules` are constraints for YOU, not content for the file
|
||||
- Do NOT copy `<context>`, `<rules>`, `<project_context>` blocks into the artifact
|
||||
- These guide what you write, but should never appear in the output
|
||||
|
||||
**Guardrails**
|
||||
- Create ALL artifacts needed for implementation (as defined by schema's `apply.requires`)
|
||||
- Always read dependency artifacts before creating a new one
|
||||
- If context is critically unclear, ask the user - but prefer making reasonable decisions to keep momentum
|
||||
- If a change with that name already exists, suggest continuing that change instead
|
||||
- Verify each artifact file exists after writing before proceeding to next
|
||||
74
.claude/skills/openspec-new-change/SKILL.md
Normal file
74
.claude/skills/openspec-new-change/SKILL.md
Normal file
|
|
@ -0,0 +1,74 @@
|
|||
---
|
||||
name: openspec-new-change
|
||||
description: Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.
|
||||
license: MIT
|
||||
compatibility: Requires openspec CLI.
|
||||
metadata:
|
||||
author: openspec
|
||||
version: "1.0"
|
||||
generatedBy: "1.3.1"
|
||||
---
|
||||
|
||||
Start a new change using the experimental artifact-driven approach.
|
||||
|
||||
**Input**: The user's request should include a change name (kebab-case) OR a description of what they want to build.
|
||||
|
||||
**Steps**
|
||||
|
||||
1. **If no clear input provided, ask what they want to build**
|
||||
|
||||
Use the **AskUserQuestion tool** (open-ended, no preset options) to ask:
|
||||
> "What change do you want to work on? Describe what you want to build or fix."
|
||||
|
||||
From their description, derive a kebab-case name (e.g., "add user authentication" → `add-user-auth`).
|
||||
|
||||
**IMPORTANT**: Do NOT proceed without understanding what the user wants to build.
|
||||
|
||||
2. **Determine the workflow schema**
|
||||
|
||||
Use the default schema (omit `--schema`) unless the user explicitly requests a different workflow.
|
||||
|
||||
**Use a different schema only if the user mentions:**
|
||||
- A specific schema name → use `--schema <name>`
|
||||
- "show workflows" or "what workflows" → run `openspec schemas --json` and let them choose
|
||||
|
||||
**Otherwise**: Omit `--schema` to use the default.
|
||||
|
||||
3. **Create the change directory**
|
||||
```bash
|
||||
openspec new change "<name>"
|
||||
```
|
||||
Add `--schema <name>` only if the user requested a specific workflow.
|
||||
This creates a scaffolded change at `openspec/changes/<name>/` with the selected schema.
|
||||
|
||||
4. **Show the artifact status**
|
||||
```bash
|
||||
openspec status --change "<name>"
|
||||
```
|
||||
This shows which artifacts need to be created and which are ready (dependencies satisfied).
|
||||
|
||||
5. **Get instructions for the first artifact**
|
||||
The first artifact depends on the schema (e.g., `proposal` for spec-driven).
|
||||
Check the status output to find the first artifact with status "ready".
|
||||
```bash
|
||||
openspec instructions <first-artifact-id> --change "<name>"
|
||||
```
|
||||
This outputs the template and context for creating the first artifact.
|
||||
|
||||
6. **STOP and wait for user direction**
|
||||
|
||||
**Output**
|
||||
|
||||
After completing the steps, summarize:
|
||||
- Change name and location
|
||||
- Schema/workflow being used and its artifact sequence
|
||||
- Current status (0/N artifacts complete)
|
||||
- The template for the first artifact
|
||||
- Prompt: "Ready to create the first artifact? Just describe what this change is about and I'll draft it, or ask me to continue."
|
||||
|
||||
**Guardrails**
|
||||
- Do NOT create any artifacts yet - just show the instructions
|
||||
- Do NOT advance beyond showing the first artifact template
|
||||
- If the name is invalid (not kebab-case), ask for a valid name
|
||||
- If a change with that name already exists, suggest continuing that change instead
|
||||
- Pass --schema if using a non-default workflow
|
||||
554
.claude/skills/openspec-onboard/SKILL.md
Normal file
554
.claude/skills/openspec-onboard/SKILL.md
Normal file
|
|
@ -0,0 +1,554 @@
|
|||
---
|
||||
name: openspec-onboard
|
||||
description: Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
|
||||
license: MIT
|
||||
compatibility: Requires openspec CLI.
|
||||
metadata:
|
||||
author: openspec
|
||||
version: "1.0"
|
||||
generatedBy: "1.3.1"
|
||||
---
|
||||
|
||||
Guide the user through their first complete OpenSpec workflow cycle. This is a teaching experience—you'll do real work in their codebase while explaining each step.
|
||||
|
||||
---
|
||||
|
||||
## Preflight
|
||||
|
||||
Before starting, check if the OpenSpec CLI is installed:
|
||||
|
||||
```bash
|
||||
# Unix/macOS
|
||||
openspec --version 2>&1 || echo "CLI_NOT_INSTALLED"
|
||||
# Windows (PowerShell)
|
||||
# if (Get-Command openspec -ErrorAction SilentlyContinue) { openspec --version } else { echo "CLI_NOT_INSTALLED" }
|
||||
```
|
||||
|
||||
**If CLI not installed:**
|
||||
> OpenSpec CLI is not installed. Install it first, then come back to `/opsx:onboard`.
|
||||
|
||||
Stop here if not installed.
|
||||
|
||||
---
|
||||
|
||||
## Phase 1: Welcome
|
||||
|
||||
Display:
|
||||
|
||||
```
|
||||
## Welcome to OpenSpec!
|
||||
|
||||
I'll walk you through a complete change cycle—from idea to implementation—using a real task in your codebase. Along the way, you'll learn the workflow by doing it.
|
||||
|
||||
**What we'll do:**
|
||||
1. Pick a small, real task in your codebase
|
||||
2. Explore the problem briefly
|
||||
3. Create a change (the container for our work)
|
||||
4. Build the artifacts: proposal → specs → design → tasks
|
||||
5. Implement the tasks
|
||||
6. Archive the completed change
|
||||
|
||||
**Time:** ~15-20 minutes
|
||||
|
||||
Let's start by finding something to work on.
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Phase 2: Task Selection
|
||||
|
||||
### Codebase Analysis
|
||||
|
||||
Scan the codebase for small improvement opportunities. Look for:
|
||||
|
||||
1. **TODO/FIXME comments** - Search for `TODO`, `FIXME`, `HACK`, `XXX` in code files
|
||||
2. **Missing error handling** - `catch` blocks that swallow errors, risky operations without try-catch
|
||||
3. **Functions without tests** - Cross-reference `src/` with test directories
|
||||
4. **Type issues** - `any` types in TypeScript files (`: any`, `as any`)
|
||||
5. **Debug artifacts** - `console.log`, `console.debug`, `debugger` statements in non-debug code
|
||||
6. **Missing validation** - User input handlers without validation
|
||||
|
||||
Also check recent git activity:
|
||||
```bash
|
||||
# Unix/macOS
|
||||
git log --oneline -10 2>/dev/null || echo "No git history"
|
||||
# Windows (PowerShell)
|
||||
# git log --oneline -10 2>$null; if ($LASTEXITCODE -ne 0) { echo "No git history" }
|
||||
```
|
||||
|
||||
### Present Suggestions
|
||||
|
||||
From your analysis, present 3-4 specific suggestions:
|
||||
|
||||
```
|
||||
## Task Suggestions
|
||||
|
||||
Based on scanning your codebase, here are some good starter tasks:
|
||||
|
||||
**1. [Most promising task]**
|
||||
Location: `src/path/to/file.ts:42`
|
||||
Scope: ~1-2 files, ~20-30 lines
|
||||
Why it's good: [brief reason]
|
||||
|
||||
**2. [Second task]**
|
||||
Location: `src/another/file.ts`
|
||||
Scope: ~1 file, ~15 lines
|
||||
Why it's good: [brief reason]
|
||||
|
||||
**3. [Third task]**
|
||||
Location: [location]
|
||||
Scope: [estimate]
|
||||
Why it's good: [brief reason]
|
||||
|
||||
**4. Something else?**
|
||||
Tell me what you'd like to work on.
|
||||
|
||||
Which task interests you? (Pick a number or describe your own)
|
||||
```
|
||||
|
||||
**If nothing found:** Fall back to asking what the user wants to build:
|
||||
> I didn't find obvious quick wins in your codebase. What's something small you've been meaning to add or fix?
|
||||
|
||||
### Scope Guardrail
|
||||
|
||||
If the user picks or describes something too large (major feature, multi-day work):
|
||||
|
||||
```
|
||||
That's a valuable task, but it's probably larger than ideal for your first OpenSpec run-through.
|
||||
|
||||
For learning the workflow, smaller is better—it lets you see the full cycle without getting stuck in implementation details.
|
||||
|
||||
**Options:**
|
||||
1. **Slice it smaller** - What's the smallest useful piece of [their task]? Maybe just [specific slice]?
|
||||
2. **Pick something else** - One of the other suggestions, or a different small task?
|
||||
3. **Do it anyway** - If you really want to tackle this, we can. Just know it'll take longer.
|
||||
|
||||
What would you prefer?
|
||||
```
|
||||
|
||||
Let the user override if they insist—this is a soft guardrail.
|
||||
|
||||
---
|
||||
|
||||
## Phase 3: Explore Demo
|
||||
|
||||
Once a task is selected, briefly demonstrate explore mode:
|
||||
|
||||
```
|
||||
Before we create a change, let me quickly show you **explore mode**—it's how you think through problems before committing to a direction.
|
||||
```
|
||||
|
||||
Spend 1-2 minutes investigating the relevant code:
|
||||
- Read the file(s) involved
|
||||
- Draw a quick ASCII diagram if it helps
|
||||
- Note any considerations
|
||||
|
||||
```
|
||||
## Quick Exploration
|
||||
|
||||
[Your brief analysis—what you found, any considerations]
|
||||
|
||||
┌─────────────────────────────────────────┐
|
||||
│ [Optional: ASCII diagram if helpful] │
|
||||
└─────────────────────────────────────────┘
|
||||
|
||||
Explore mode (`/opsx:explore`) is for this kind of thinking—investigating before implementing. You can use it anytime you need to think through a problem.
|
||||
|
||||
Now let's create a change to hold our work.
|
||||
```
|
||||
|
||||
**PAUSE** - Wait for user acknowledgment before proceeding.
|
||||
|
||||
---
|
||||
|
||||
## Phase 4: Create the Change
|
||||
|
||||
**EXPLAIN:**
|
||||
```
|
||||
## Creating a Change
|
||||
|
||||
A "change" in OpenSpec is a container for all the thinking and planning around a piece of work. It lives in `openspec/changes/<name>/` and holds your artifacts—proposal, specs, design, tasks.
|
||||
|
||||
Let me create one for our task.
|
||||
```
|
||||
|
||||
**DO:** Create the change with a derived kebab-case name:
|
||||
```bash
|
||||
openspec new change "<derived-name>"
|
||||
```
|
||||
|
||||
**SHOW:**
|
||||
```
|
||||
Created: `openspec/changes/<name>/`
|
||||
|
||||
The folder structure:
|
||||
```
|
||||
openspec/changes/<name>/
|
||||
├── proposal.md ← Why we're doing this (empty, we'll fill it)
|
||||
├── design.md ← How we'll build it (empty)
|
||||
├── specs/ ← Detailed requirements (empty)
|
||||
└── tasks.md ← Implementation checklist (empty)
|
||||
```
|
||||
|
||||
Now let's fill in the first artifact—the proposal.
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Phase 5: Proposal
|
||||
|
||||
**EXPLAIN:**
|
||||
```
|
||||
## The Proposal
|
||||
|
||||
The proposal captures **why** we're making this change and **what** it involves at a high level. It's the "elevator pitch" for the work.
|
||||
|
||||
I'll draft one based on our task.
|
||||
```
|
||||
|
||||
**DO:** Draft the proposal content (don't save yet):
|
||||
|
||||
```
|
||||
Here's a draft proposal:
|
||||
|
||||
---
|
||||
|
||||
## Why
|
||||
|
||||
[1-2 sentences explaining the problem/opportunity]
|
||||
|
||||
## What Changes
|
||||
|
||||
[Bullet points of what will be different]
|
||||
|
||||
## Capabilities
|
||||
|
||||
### New Capabilities
|
||||
- `<capability-name>`: [brief description]
|
||||
|
||||
### Modified Capabilities
|
||||
<!-- If modifying existing behavior -->
|
||||
|
||||
## Impact
|
||||
|
||||
- `src/path/to/file.ts`: [what changes]
|
||||
- [other files if applicable]
|
||||
|
||||
---
|
||||
|
||||
Does this capture the intent? I can adjust before we save it.
|
||||
```
|
||||
|
||||
**PAUSE** - Wait for user approval/feedback.
|
||||
|
||||
After approval, save the proposal:
|
||||
```bash
|
||||
openspec instructions proposal --change "<name>" --json
|
||||
```
|
||||
Then write the content to `openspec/changes/<name>/proposal.md`.
|
||||
|
||||
```
|
||||
Proposal saved. This is your "why" document—you can always come back and refine it as understanding evolves.
|
||||
|
||||
Next up: specs.
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Phase 6: Specs
|
||||
|
||||
**EXPLAIN:**
|
||||
```
|
||||
## Specs
|
||||
|
||||
Specs define **what** we're building in precise, testable terms. They use a requirement/scenario format that makes expected behavior crystal clear.
|
||||
|
||||
For a small task like this, we might only need one spec file.
|
||||
```
|
||||
|
||||
**DO:** Create the spec file:
|
||||
```bash
|
||||
# Unix/macOS
|
||||
mkdir -p openspec/changes/<name>/specs/<capability-name>
|
||||
# Windows (PowerShell)
|
||||
# New-Item -ItemType Directory -Force -Path "openspec/changes/<name>/specs/<capability-name>"
|
||||
```
|
||||
|
||||
Draft the spec content:
|
||||
|
||||
```
|
||||
Here's the spec:
|
||||
|
||||
---
|
||||
|
||||
## ADDED Requirements
|
||||
|
||||
### Requirement: <Name>
|
||||
|
||||
<Description of what the system should do>
|
||||
|
||||
#### Scenario: <Scenario name>
|
||||
|
||||
- **WHEN** <trigger condition>
|
||||
- **THEN** <expected outcome>
|
||||
- **AND** <additional outcome if needed>
|
||||
|
||||
---
|
||||
|
||||
This format—WHEN/THEN/AND—makes requirements testable. You can literally read them as test cases.
|
||||
```
|
||||
|
||||
Save to `openspec/changes/<name>/specs/<capability>/spec.md`.
|
||||
|
||||
---
|
||||
|
||||
## Phase 7: Design
|
||||
|
||||
**EXPLAIN:**
|
||||
```
|
||||
## Design
|
||||
|
||||
The design captures **how** we'll build it—technical decisions, tradeoffs, approach.
|
||||
|
||||
For small changes, this might be brief. That's fine—not every change needs deep design discussion.
|
||||
```
|
||||
|
||||
**DO:** Draft design.md:
|
||||
|
||||
```
|
||||
Here's the design:
|
||||
|
||||
---
|
||||
|
||||
## Context
|
||||
|
||||
[Brief context about the current state]
|
||||
|
||||
## Goals / Non-Goals
|
||||
|
||||
**Goals:**
|
||||
- [What we're trying to achieve]
|
||||
|
||||
**Non-Goals:**
|
||||
- [What's explicitly out of scope]
|
||||
|
||||
## Decisions
|
||||
|
||||
### Decision 1: [Key decision]
|
||||
|
||||
[Explanation of approach and rationale]
|
||||
|
||||
---
|
||||
|
||||
For a small task, this captures the key decisions without over-engineering.
|
||||
```
|
||||
|
||||
Save to `openspec/changes/<name>/design.md`.
|
||||
|
||||
---
|
||||
|
||||
## Phase 8: Tasks
|
||||
|
||||
**EXPLAIN:**
|
||||
```
|
||||
## Tasks
|
||||
|
||||
Finally, we break the work into implementation tasks—checkboxes that drive the apply phase.
|
||||
|
||||
These should be small, clear, and in logical order.
|
||||
```
|
||||
|
||||
**DO:** Generate tasks based on specs and design:
|
||||
|
||||
```
|
||||
Here are the implementation tasks:
|
||||
|
||||
---
|
||||
|
||||
## 1. [Category or file]
|
||||
|
||||
- [ ] 1.1 [Specific task]
|
||||
- [ ] 1.2 [Specific task]
|
||||
|
||||
## 2. Verify
|
||||
|
||||
- [ ] 2.1 [Verification step]
|
||||
|
||||
---
|
||||
|
||||
Each checkbox becomes a unit of work in the apply phase. Ready to implement?
|
||||
```
|
||||
|
||||
**PAUSE** - Wait for user to confirm they're ready to implement.
|
||||
|
||||
Save to `openspec/changes/<name>/tasks.md`.
|
||||
|
||||
---
|
||||
|
||||
## Phase 9: Apply (Implementation)
|
||||
|
||||
**EXPLAIN:**
|
||||
```
|
||||
## Implementation
|
||||
|
||||
Now we implement each task, checking them off as we go. I'll announce each one and occasionally note how the specs/design informed the approach.
|
||||
```
|
||||
|
||||
**DO:** For each task:
|
||||
|
||||
1. Announce: "Working on task N: [description]"
|
||||
2. Implement the change in the codebase
|
||||
3. Reference specs/design naturally: "The spec says X, so I'm doing Y"
|
||||
4. Mark complete in tasks.md: `- [ ]` → `- [x]`
|
||||
5. Brief status: "✓ Task N complete"
|
||||
|
||||
Keep narration light—don't over-explain every line of code.
|
||||
|
||||
After all tasks:
|
||||
|
||||
```
|
||||
## Implementation Complete
|
||||
|
||||
All tasks done:
|
||||
- [x] Task 1
|
||||
- [x] Task 2
|
||||
- [x] ...
|
||||
|
||||
The change is implemented! One more step—let's archive it.
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Phase 10: Archive
|
||||
|
||||
**EXPLAIN:**
|
||||
```
|
||||
## Archiving
|
||||
|
||||
When a change is complete, we archive it. This moves it from `openspec/changes/` to `openspec/changes/archive/YYYY-MM-DD-<name>/`.
|
||||
|
||||
Archived changes become your project's decision history—you can always find them later to understand why something was built a certain way.
|
||||
```
|
||||
|
||||
**DO:**
|
||||
```bash
|
||||
openspec archive "<name>"
|
||||
```
|
||||
|
||||
**SHOW:**
|
||||
```
|
||||
Archived to: `openspec/changes/archive/YYYY-MM-DD-<name>/`
|
||||
|
||||
The change is now part of your project's history. The code is in your codebase, the decision record is preserved.
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Phase 11: Recap & Next Steps
|
||||
|
||||
```
|
||||
## Congratulations!
|
||||
|
||||
You just completed a full OpenSpec cycle:
|
||||
|
||||
1. **Explore** - Thought through the problem
|
||||
2. **New** - Created a change container
|
||||
3. **Proposal** - Captured WHY
|
||||
4. **Specs** - Defined WHAT in detail
|
||||
5. **Design** - Decided HOW
|
||||
6. **Tasks** - Broke it into steps
|
||||
7. **Apply** - Implemented the work
|
||||
8. **Archive** - Preserved the record
|
||||
|
||||
This same rhythm works for any size change—a small fix or a major feature.
|
||||
|
||||
---
|
||||
|
||||
## Command Reference
|
||||
|
||||
**Core workflow:**
|
||||
|
||||
| Command | What it does |
|
||||
|-------------------|--------------------------------------------|
|
||||
| `/opsx:propose` | Create a change and generate all artifacts |
|
||||
| `/opsx:explore` | Think through problems before/during work |
|
||||
| `/opsx:apply` | Implement tasks from a change |
|
||||
| `/opsx:archive` | Archive a completed change |
|
||||
|
||||
**Additional commands:**
|
||||
|
||||
| Command | What it does |
|
||||
|--------------------|----------------------------------------------------------|
|
||||
| `/opsx:new` | Start a new change, step through artifacts one at a time |
|
||||
| `/opsx:continue` | Continue working on an existing change |
|
||||
| `/opsx:ff` | Fast-forward: create all artifacts at once |
|
||||
| `/opsx:verify` | Verify implementation matches artifacts |
|
||||
|
||||
---
|
||||
|
||||
## What's Next?
|
||||
|
||||
Try `/opsx:propose` on something you actually want to build. You've got the rhythm now!
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Graceful Exit Handling
|
||||
|
||||
### User wants to stop mid-way
|
||||
|
||||
If the user says they need to stop, want to pause, or seem disengaged:
|
||||
|
||||
```
|
||||
No problem! Your change is saved at `openspec/changes/<name>/`.
|
||||
|
||||
To pick up where we left off later:
|
||||
- `/opsx:continue <name>` - Resume artifact creation
|
||||
- `/opsx:apply <name>` - Jump to implementation (if tasks exist)
|
||||
|
||||
The work won't be lost. Come back whenever you're ready.
|
||||
```
|
||||
|
||||
Exit gracefully without pressure.
|
||||
|
||||
### User just wants command reference
|
||||
|
||||
If the user says they just want to see the commands or skip the tutorial:
|
||||
|
||||
```
|
||||
## OpenSpec Quick Reference
|
||||
|
||||
**Core workflow:**
|
||||
|
||||
| Command | What it does |
|
||||
|--------------------------|--------------------------------------------|
|
||||
| `/opsx:propose <name>` | Create a change and generate all artifacts |
|
||||
| `/opsx:explore` | Think through problems (no code changes) |
|
||||
| `/opsx:apply <name>` | Implement tasks |
|
||||
| `/opsx:archive <name>` | Archive when done |
|
||||
|
||||
**Additional commands:**
|
||||
|
||||
| Command | What it does |
|
||||
|---------------------------|-------------------------------------|
|
||||
| `/opsx:new <name>` | Start a new change, step by step |
|
||||
| `/opsx:continue <name>` | Continue an existing change |
|
||||
| `/opsx:ff <name>` | Fast-forward: all artifacts at once |
|
||||
| `/opsx:verify <name>` | Verify implementation |
|
||||
|
||||
Try `/opsx:propose` to start your first change.
|
||||
```
|
||||
|
||||
Exit gracefully.
|
||||
|
||||
---
|
||||
|
||||
## Guardrails
|
||||
|
||||
- **Follow the EXPLAIN → DO → SHOW → PAUSE pattern** at key transitions (after explore, after proposal draft, after tasks, after archive)
|
||||
- **Keep narration light** during implementation—teach without lecturing
|
||||
- **Don't skip phases** even if the change is small—the goal is teaching the workflow
|
||||
- **Pause for acknowledgment** at marked points, but don't over-pause
|
||||
- **Handle exits gracefully**—never pressure the user to continue
|
||||
- **Use real codebase tasks**—don't simulate or use fake examples
|
||||
- **Adjust scope gently**—guide toward smaller tasks but respect user choice
|
||||
138
.claude/skills/openspec-sync-specs/SKILL.md
Normal file
138
.claude/skills/openspec-sync-specs/SKILL.md
Normal file
|
|
@ -0,0 +1,138 @@
|
|||
---
|
||||
name: openspec-sync-specs
|
||||
description: Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.
|
||||
license: MIT
|
||||
compatibility: Requires openspec CLI.
|
||||
metadata:
|
||||
author: openspec
|
||||
version: "1.0"
|
||||
generatedBy: "1.3.1"
|
||||
---
|
||||
|
||||
Sync delta specs from a change to main specs.
|
||||
|
||||
This is an **agent-driven** operation - you will read delta specs and directly edit main specs to apply the changes. This allows intelligent merging (e.g., adding a scenario without copying the entire requirement).
|
||||
|
||||
**Input**: Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
|
||||
|
||||
**Steps**
|
||||
|
||||
1. **If no change name provided, prompt for selection**
|
||||
|
||||
Run `openspec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
|
||||
|
||||
Show changes that have delta specs (under `specs/` directory).
|
||||
|
||||
**IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
|
||||
|
||||
2. **Find delta specs**
|
||||
|
||||
Look for delta spec files in `openspec/changes/<name>/specs/*/spec.md`.
|
||||
|
||||
Each delta spec file contains sections like:
|
||||
- `## ADDED Requirements` - New requirements to add
|
||||
- `## MODIFIED Requirements` - Changes to existing requirements
|
||||
- `## REMOVED Requirements` - Requirements to remove
|
||||
- `## RENAMED Requirements` - Requirements to rename (FROM:/TO: format)
|
||||
|
||||
If no delta specs found, inform user and stop.
|
||||
|
||||
3. **For each delta spec, apply changes to main specs**
|
||||
|
||||
For each capability with a delta spec at `openspec/changes/<name>/specs/<capability>/spec.md`:
|
||||
|
||||
a. **Read the delta spec** to understand the intended changes
|
||||
|
||||
b. **Read the main spec** at `openspec/specs/<capability>/spec.md` (may not exist yet)
|
||||
|
||||
c. **Apply changes intelligently**:
|
||||
|
||||
**ADDED Requirements:**
|
||||
- If requirement doesn't exist in main spec → add it
|
||||
- If requirement already exists → update it to match (treat as implicit MODIFIED)
|
||||
|
||||
**MODIFIED Requirements:**
|
||||
- Find the requirement in main spec
|
||||
- Apply the changes - this can be:
|
||||
- Adding new scenarios (don't need to copy existing ones)
|
||||
- Modifying existing scenarios
|
||||
- Changing the requirement description
|
||||
- Preserve scenarios/content not mentioned in the delta
|
||||
|
||||
**REMOVED Requirements:**
|
||||
- Remove the entire requirement block from main spec
|
||||
|
||||
**RENAMED Requirements:**
|
||||
- Find the FROM requirement, rename to TO
|
||||
|
||||
d. **Create new main spec** if capability doesn't exist yet:
|
||||
- Create `openspec/specs/<capability>/spec.md`
|
||||
- Add Purpose section (can be brief, mark as TBD)
|
||||
- Add Requirements section with the ADDED requirements
|
||||
|
||||
4. **Show summary**
|
||||
|
||||
After applying all changes, summarize:
|
||||
- Which capabilities were updated
|
||||
- What changes were made (requirements added/modified/removed/renamed)
|
||||
|
||||
**Delta Spec Format Reference**
|
||||
|
||||
```markdown
|
||||
## ADDED Requirements
|
||||
|
||||
### Requirement: New Feature
|
||||
The system SHALL do something new.
|
||||
|
||||
#### Scenario: Basic case
|
||||
- **WHEN** user does X
|
||||
- **THEN** system does Y
|
||||
|
||||
## MODIFIED Requirements
|
||||
|
||||
### Requirement: Existing Feature
|
||||
#### Scenario: New scenario to add
|
||||
- **WHEN** user does A
|
||||
- **THEN** system does B
|
||||
|
||||
## REMOVED Requirements
|
||||
|
||||
### Requirement: Deprecated Feature
|
||||
|
||||
## RENAMED Requirements
|
||||
|
||||
- FROM: `### Requirement: Old Name`
|
||||
- TO: `### Requirement: New Name`
|
||||
```
|
||||
|
||||
**Key Principle: Intelligent Merging**
|
||||
|
||||
Unlike programmatic merging, you can apply **partial updates**:
|
||||
- To add a scenario, just include that scenario under MODIFIED - don't copy existing scenarios
|
||||
- The delta represents *intent*, not a wholesale replacement
|
||||
- Use your judgment to merge changes sensibly
|
||||
|
||||
**Output On Success**
|
||||
|
||||
```
|
||||
## Specs Synced: <change-name>
|
||||
|
||||
Updated main specs:
|
||||
|
||||
**<capability-1>**:
|
||||
- Added requirement: "New Feature"
|
||||
- Modified requirement: "Existing Feature" (added 1 scenario)
|
||||
|
||||
**<capability-2>**:
|
||||
- Created new spec file
|
||||
- Added requirement: "Another Feature"
|
||||
|
||||
Main specs are now updated. The change remains active - archive when implementation is complete.
|
||||
```
|
||||
|
||||
**Guardrails**
|
||||
- Read both delta and main specs before making changes
|
||||
- Preserve existing content not mentioned in delta
|
||||
- If something is unclear, ask for clarification
|
||||
- Show what you're changing as you go
|
||||
- The operation should be idempotent - running twice should give same result
|
||||
168
.claude/skills/openspec-verify-change/SKILL.md
Normal file
168
.claude/skills/openspec-verify-change/SKILL.md
Normal file
|
|
@ -0,0 +1,168 @@
|
|||
---
|
||||
name: openspec-verify-change
|
||||
description: Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
|
||||
license: MIT
|
||||
compatibility: Requires openspec CLI.
|
||||
metadata:
|
||||
author: openspec
|
||||
version: "1.0"
|
||||
generatedBy: "1.3.1"
|
||||
---
|
||||
|
||||
Verify that an implementation matches the change artifacts (specs, tasks, design).
|
||||
|
||||
**Input**: Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
|
||||
|
||||
**Steps**
|
||||
|
||||
1. **If no change name provided, prompt for selection**
|
||||
|
||||
Run `openspec list --json` to get available changes. Use the **AskUserQuestion tool** to let the user select.
|
||||
|
||||
Show changes that have implementation tasks (tasks artifact exists).
|
||||
Include the schema used for each change if available.
|
||||
Mark changes with incomplete tasks as "(In Progress)".
|
||||
|
||||
**IMPORTANT**: Do NOT guess or auto-select a change. Always let the user choose.
|
||||
|
||||
2. **Check status to understand the schema**
|
||||
```bash
|
||||
openspec status --change "<name>" --json
|
||||
```
|
||||
Parse the JSON to understand:
|
||||
- `schemaName`: The workflow being used (e.g., "spec-driven")
|
||||
- Which artifacts exist for this change
|
||||
|
||||
3. **Get the change directory and load artifacts**
|
||||
|
||||
```bash
|
||||
openspec instructions apply --change "<name>" --json
|
||||
```
|
||||
|
||||
This returns the change directory and `contextFiles` (artifact ID -> array of concrete file paths). Read all available artifacts from `contextFiles`.
|
||||
|
||||
4. **Initialize verification report structure**
|
||||
|
||||
Create a report structure with three dimensions:
|
||||
- **Completeness**: Track tasks and spec coverage
|
||||
- **Correctness**: Track requirement implementation and scenario coverage
|
||||
- **Coherence**: Track design adherence and pattern consistency
|
||||
|
||||
Each dimension can have CRITICAL, WARNING, or SUGGESTION issues.
|
||||
|
||||
5. **Verify Completeness**
|
||||
|
||||
**Task Completion**:
|
||||
- If `contextFiles.tasks` exists, read every file path in it
|
||||
- Parse checkboxes: `- [ ]` (incomplete) vs `- [x]` (complete)
|
||||
- Count complete vs total tasks
|
||||
- If incomplete tasks exist:
|
||||
- Add CRITICAL issue for each incomplete task
|
||||
- Recommendation: "Complete task: <description>" or "Mark as done if already implemented"
|
||||
|
||||
**Spec Coverage**:
|
||||
- If delta specs exist in `openspec/changes/<name>/specs/`:
|
||||
- Extract all requirements (marked with "### Requirement:")
|
||||
- For each requirement:
|
||||
- Search codebase for keywords related to the requirement
|
||||
- Assess if implementation likely exists
|
||||
- If requirements appear unimplemented:
|
||||
- Add CRITICAL issue: "Requirement not found: <requirement name>"
|
||||
- Recommendation: "Implement requirement X: <description>"
|
||||
|
||||
6. **Verify Correctness**
|
||||
|
||||
**Requirement Implementation Mapping**:
|
||||
- For each requirement from delta specs:
|
||||
- Search codebase for implementation evidence
|
||||
- If found, note file paths and line ranges
|
||||
- Assess if implementation matches requirement intent
|
||||
- If divergence detected:
|
||||
- Add WARNING: "Implementation may diverge from spec: <details>"
|
||||
- Recommendation: "Review <file>:<lines> against requirement X"
|
||||
|
||||
**Scenario Coverage**:
|
||||
- For each scenario in delta specs (marked with "#### Scenario:"):
|
||||
- Check if conditions are handled in code
|
||||
- Check if tests exist covering the scenario
|
||||
- If scenario appears uncovered:
|
||||
- Add WARNING: "Scenario not covered: <scenario name>"
|
||||
- Recommendation: "Add test or implementation for scenario: <description>"
|
||||
|
||||
7. **Verify Coherence**
|
||||
|
||||
**Design Adherence**:
|
||||
- If `contextFiles.design` exists:
|
||||
- Extract key decisions (look for sections like "Decision:", "Approach:", "Architecture:")
|
||||
- Verify implementation follows those decisions
|
||||
- If contradiction detected:
|
||||
- Add WARNING: "Design decision not followed: <decision>"
|
||||
- Recommendation: "Update implementation or revise design.md to match reality"
|
||||
- If no design.md: Skip design adherence check, note "No design.md to verify against"
|
||||
|
||||
**Code Pattern Consistency**:
|
||||
- Review new code for consistency with project patterns
|
||||
- Check file naming, directory structure, coding style
|
||||
- If significant deviations found:
|
||||
- Add SUGGESTION: "Code pattern deviation: <details>"
|
||||
- Recommendation: "Consider following project pattern: <example>"
|
||||
|
||||
8. **Generate Verification Report**
|
||||
|
||||
**Summary Scorecard**:
|
||||
```
|
||||
## Verification Report: <change-name>
|
||||
|
||||
### Summary
|
||||
| Dimension | Status |
|
||||
|--------------|------------------|
|
||||
| Completeness | X/Y tasks, N reqs|
|
||||
| Correctness | M/N reqs covered |
|
||||
| Coherence | Followed/Issues |
|
||||
```
|
||||
|
||||
**Issues by Priority**:
|
||||
|
||||
1. **CRITICAL** (Must fix before archive):
|
||||
- Incomplete tasks
|
||||
- Missing requirement implementations
|
||||
- Each with specific, actionable recommendation
|
||||
|
||||
2. **WARNING** (Should fix):
|
||||
- Spec/design divergences
|
||||
- Missing scenario coverage
|
||||
- Each with specific recommendation
|
||||
|
||||
3. **SUGGESTION** (Nice to fix):
|
||||
- Pattern inconsistencies
|
||||
- Minor improvements
|
||||
- Each with specific recommendation
|
||||
|
||||
**Final Assessment**:
|
||||
- If CRITICAL issues: "X critical issue(s) found. Fix before archiving."
|
||||
- If only warnings: "No critical issues. Y warning(s) to consider. Ready for archive (with noted improvements)."
|
||||
- If all clear: "All checks passed. Ready for archive."
|
||||
|
||||
**Verification Heuristics**
|
||||
|
||||
- **Completeness**: Focus on objective checklist items (checkboxes, requirements list)
|
||||
- **Correctness**: Use keyword search, file path analysis, reasonable inference - don't require perfect certainty
|
||||
- **Coherence**: Look for glaring inconsistencies, don't nitpick style
|
||||
- **False Positives**: When uncertain, prefer SUGGESTION over WARNING, WARNING over CRITICAL
|
||||
- **Actionability**: Every issue must have a specific recommendation with file/line references where applicable
|
||||
|
||||
**Graceful Degradation**
|
||||
|
||||
- If only tasks.md exists: verify task completion only, skip spec/design checks
|
||||
- If tasks + specs exist: verify completeness and correctness, skip design
|
||||
- If full artifacts: verify all three dimensions
|
||||
- Always note which checks were skipped and why
|
||||
|
||||
**Output Format**
|
||||
|
||||
Use clear markdown with:
|
||||
- Table for summary scorecard
|
||||
- Grouped lists for issues (CRITICAL/WARNING/SUGGESTION)
|
||||
- Code references in format: `file.ts:123`
|
||||
- Specific, actionable recommendations
|
||||
- No vague suggestions like "consider reviewing"
|
||||
107
CLAUDE.md
Normal file
107
CLAUDE.md
Normal file
|
|
@ -0,0 +1,107 @@
|
|||
# CLAUDE.md
|
||||
|
||||
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
|
||||
|
||||
## What this is
|
||||
|
||||
A CDiT fork of [basnijholt/adaptive-lighting](https://github.com/basnijholt/adaptive-lighting) — a Home Assistant custom component that adjusts light brightness and color temperature in sync with the sun curve. The fork is opinionated about CDiT's single-household setup and explicitly diverges from upstream on the integration's configuration surface.
|
||||
|
||||
**Fork is not a drop-in replacement.** Existing upstream config entries will fail to load (deliberate, see `openspec/changes/cdit-config-redesign/design.md` decision 4).
|
||||
|
||||
## Remote topology
|
||||
|
||||
```
|
||||
origin git@github.com:CaseyRo/adaptive-lighting.git (the fork, read-write)
|
||||
upstream https://github.com/basnijholt/adaptive-lighting.git (read-only)
|
||||
```
|
||||
|
||||
Sync upstream changes:
|
||||
|
||||
```bash
|
||||
git fetch upstream
|
||||
git merge upstream/main # or rebase, depending on local policy
|
||||
# resolve conflicts under custom_components/adaptive_lighting/
|
||||
```
|
||||
|
||||
## Commands
|
||||
|
||||
Python tooling is `uv` (not `pip` or `poetry`). All commands assume an activated venv from `./scripts/setup-devcontainer`.
|
||||
|
||||
| Task | Command |
|
||||
|---|---|
|
||||
| Run the test suite | `uv run pytest` |
|
||||
| Run a single test | `uv run pytest tests/test_config_flow.py::test_options_flow_init` |
|
||||
| Lint everything (pre-commit) | `./scripts/lint` |
|
||||
| Run HA locally with the custom component loaded | `./scripts/develop` (boots HA on `localhost:8123` from `./config/`) |
|
||||
| Update generated docs/content in README | `./scripts/update-generated-content` |
|
||||
| Refresh test matrix | `./scripts/update-test-matrix.py` |
|
||||
|
||||
Ruff config lives in `.ruff.toml`. Pre-commit hooks in `.pre-commit-config.yaml`. Both enforce on push via `./scripts/lint`.
|
||||
|
||||
## Architecture
|
||||
|
||||
This is a standard Home Assistant **custom component** packaged under `custom_components/adaptive_lighting/`. HA loads it by directory name when present in a HA config's `custom_components/`. The HACS integration provides distribution.
|
||||
|
||||
Big-picture layout:
|
||||
|
||||
```
|
||||
custom_components/adaptive_lighting/
|
||||
├── __init__.py entry point: async_setup_entry, async_unload_entry,
|
||||
│ and the curve math (sun-position + brightness/CT calc)
|
||||
├── config_flow.py UI flow for setup and reconfiguration. Iterates
|
||||
│ VALIDATION_TUPLES from const.py to build the schema.
|
||||
├── switch.py the 4 switch entities per AL config (master, sleep,
|
||||
│ adapt_color, adapt_brightness). After
|
||||
│ cdit-config-redesign lands: 3 switches (no sleep).
|
||||
├── const.py CONF_/DEFAULT_ constants + VALIDATION_TUPLES — the
|
||||
│ single source for what fields exist in the schema.
|
||||
├── color_and_brightness.py pure math: tanh, sun-elevation curve, color-temp
|
||||
│ interpolation.
|
||||
├── adaptation_utils.py per-light service-call shaping (intercept,
|
||||
│ skip_redundant_commands, split commands, etc.)
|
||||
├── hass_utils.py HA-specific helpers (entity registry lookups,
|
||||
│ timestamps, service-call dispatch).
|
||||
├── manifest.json integration metadata; `version` here gates
|
||||
│ the strict break in cdit-config-redesign.
|
||||
└── strings.json UI labels for the config flow, errors, abort reasons.
|
||||
```
|
||||
|
||||
The CDiT fork is also planning two follow-on changes that layer cleanly on top:
|
||||
- `add-runtime-range-controls` — adds a `number` platform with live entities for the 4 brightness/CT ranges.
|
||||
- `house-mode-modes` — adds an `input_select`-driven behavior matrix that drives the 3 runtime switches on house-mode change.
|
||||
|
||||
Neither is implemented yet; both have proposal stubs in `openspec/changes/`.
|
||||
|
||||
## Planning workflow — OpenSpec under `opsx`
|
||||
|
||||
All non-trivial changes go through OpenSpec before code lands. The experimental `opsx` schema (artifact-driven: proposal → design → specs → tasks) is configured. Drive it via `.claude/commands/opsx/*` slash commands or the `openspec-*` skills.
|
||||
|
||||
```
|
||||
openspec/
|
||||
├── config.yaml (project context lives here once filled in)
|
||||
├── specs/ long-lived capability specs (empty until a change archives)
|
||||
└── changes/
|
||||
├── cdit-config-redesign/ active, 4/4 artifacts, strict-validate green
|
||||
│ ├── proposal.md why + what changes + capabilities + impact
|
||||
│ ├── design.md 15 decisions with rejected alternatives, risks, migration
|
||||
│ ├── specs/options-flow/spec.md 9 requirements, 22 Given/When/Then scenarios
|
||||
│ └── tasks.md 9 task groups, 36 checkboxes with [R, D] annotations
|
||||
├── add-runtime-range-controls/ stub, proposal only
|
||||
└── house-mode-modes/ stub, proposal only
|
||||
```
|
||||
|
||||
Validate any active change with:
|
||||
|
||||
```bash
|
||||
openspec validate <change-name> --strict
|
||||
```
|
||||
|
||||
When implementing tasks for an active change, prefer `/opsx:apply <change-name>` over manual edits — it walks `tasks.md` checkbox by checkbox. `/opsx:verify` checks the resulting code against the spec's scenarios before archive.
|
||||
|
||||
## Conventions worth preserving
|
||||
|
||||
- **Change names**: kebab-case (e.g., `cdit-config-redesign`, `add-runtime-range-controls`).
|
||||
- **Capability slugs**: kebab-case, scoped tight (`options-flow`, `runtime-range-controls`, `house-mode-binding`) — not broad umbrellas.
|
||||
- **Annotations in `tasks.md`**: each task ends with `[R…, D…]` referencing requirements in the change's spec delta and decisions in `design.md`. Keep traceability.
|
||||
- **No silent migrations**: CDiT-fork breaking changes bump `manifest.json` major and reject incompatible config entries with a clear error (see `cdit-config-redesign` design decision 4).
|
||||
- **`openspec/config.yaml` `context:` field**: still unset. Fill in once CDiT tech-stack conventions stabilize — it propagates into every artifact prompt.
|
||||
|
|
@ -0,0 +1,2 @@
|
|||
schema: spec-driven
|
||||
created: 2026-05-16
|
||||
43
openspec/changes/add-runtime-range-controls/proposal.md
Normal file
43
openspec/changes/add-runtime-range-controls/proposal.md
Normal file
|
|
@ -0,0 +1,43 @@
|
|||
## Why
|
||||
|
||||
The four brightness/color-temperature ranges (`min_brightness`, `max_brightness`, `min_color_temp`, `max_color_temp`) are exactly the values a CDiT household wants to live-tune from a Lovelace card — the difference between "kitchen feels too warm" and "kitchen feels right" is one slider away. Today they are setup-time options buried in the integration's options dialog; every tweak forces a click trail through Settings → Devices → Adaptive Lighting → Configure → Save, and triggers a full integration reload via `OptionsFlowWithReload`.
|
||||
|
||||
This change promotes the four ranges to first-class runtime entities (HA's `number` platform), with the config flow remaining the place to seed the initial defaults and any subsequent UI edit writing through transparently.
|
||||
|
||||
> **Status**: stub proposal. Specs, design, and tasks to be written when work on this change starts. Depends on `cdit-config-redesign` landing first.
|
||||
|
||||
## What Changes
|
||||
|
||||
- **Add a `number` platform** to the integration. Each AL config entry creates four `number` entities:
|
||||
- `number.adaptive_lighting_<name>_min_brightness` (range 1–100, step 1, %, slider mode)
|
||||
- `number.adaptive_lighting_<name>_max_brightness` (same)
|
||||
- `number.adaptive_lighting_<name>_min_color_temp` (range 1000–10000, step 100, K, slider mode)
|
||||
- `number.adaptive_lighting_<name>_max_color_temp` (same)
|
||||
- **Source-of-truth model: write-through** (Decision C from the prior session). The number entity is canonical at runtime; config flow values seed the entity on first creation and act as a mirror afterwards.
|
||||
- On config-entry creation, the four number entities are initialized from `entry.options`.
|
||||
- When the user moves a slider on the number entity, the new value is persisted back to `entry.options` via `async_update_entry`.
|
||||
- When the user saves the options flow, the four corresponding number entities have their state updated to match.
|
||||
- **Curve math reads from number entities**, not from `entry.options` directly. Single read path at evaluation time.
|
||||
- **Options flow keeps the four fields visible** in the Daytime curve section so users can still tune them from the config screen (especially first-time setup). Both surfaces stay in sync.
|
||||
|
||||
## Capabilities
|
||||
|
||||
### New Capabilities
|
||||
|
||||
- `runtime-range-controls`: live-tunable brightness and color-temperature range entities, with bidirectional sync to the config entry options. Covers entity creation, write-through semantics, curve-math read path, and conflict resolution between the two surfaces.
|
||||
|
||||
### Modified Capabilities
|
||||
|
||||
- `options-flow`: the Daytime curve section's four range fields gain write-through behavior to the new number entities. Spec delta will capture this as a MODIFIED requirement.
|
||||
|
||||
## Impact
|
||||
|
||||
- **`custom_components/adaptive_lighting/number.py`** — new file, `number` platform implementation.
|
||||
- **`custom_components/adaptive_lighting/const.py`** — `Platform.NUMBER` appended to platform list; entity unique-id pattern constants.
|
||||
- **`custom_components/adaptive_lighting/__init__.py`** — curve math switches its reads for the four ranges from `entry.options[...]` to `hass.states.get(<number_entity_id>)`. `async_setup_entry` registers number platform.
|
||||
- **`custom_components/adaptive_lighting/config_flow.py`** — save path also writes through to the four number entities (if they exist). Initial setup creates them.
|
||||
- **`tests/test_number_platform.py`** — new file. Tests: entity creation on first setup, slider change persists to options, options save writes to entity, curve reads pick up latest value, removal cleans up entities.
|
||||
- **`tests/test_config_flow.py`** — extends existing tests to cover the write-through path.
|
||||
- **No new runtime dependencies.**
|
||||
|
||||
**Sequencing**: this change MUST land after `cdit-config-redesign` — relies on its pruned schema, native selectors, and `OptionsFlowWithReload` pattern.
|
||||
2
openspec/changes/cdit-config-redesign/.openspec.yaml
Normal file
2
openspec/changes/cdit-config-redesign/.openspec.yaml
Normal file
|
|
@ -0,0 +1,2 @@
|
|||
schema: spec-driven
|
||||
created: 2026-05-16
|
||||
212
openspec/changes/cdit-config-redesign/design.md
Normal file
212
openspec/changes/cdit-config-redesign/design.md
Normal file
|
|
@ -0,0 +1,212 @@
|
|||
## Context
|
||||
|
||||
Upstream `basnijholt/adaptive-lighting` is a mature HA custom component (~10k LOC, 800+ stars). Its options flow is built by iterating over `VALIDATION_TUPLES` in `const.py` — 39 entries, each a `(key, default, voluptuous_validator)` tuple. The result is one flat `vol.Schema` rendered as a single tall form with no grouping, no conditional visibility, custom `int_between` validators (no slider UI), and silent no-op behavior when the entry was YAML-configured.
|
||||
|
||||
CDiT's install is one household, opinionated about scenes and house modes, and uses Sun2 for precise twilight events. Half of upstream's options are dead weight in that context (sleep mode, take-over-control, manual sun-time math). The other half is hard to find because nothing is grouped.
|
||||
|
||||
This change resets the dialog. It also removes the sleep-mode switch entity from the switch platform — sleep mode is dropped wholesale, not just hidden.
|
||||
|
||||
## Goals / Non-Goals
|
||||
|
||||
**Goals:**
|
||||
- 18-field dialog that fits on one screen via collapsible sections.
|
||||
- Sun curve driven by HA entities, so Sun2 (or any other twilight source) plugs in via the existing entity selector.
|
||||
- Native HA selectors for everything (sliders, dropdowns, entity pickers) instead of voluptuous `int_between` wrappers.
|
||||
- Reload-on-save without manual `async_unload_entry` / `async_setup_entry` plumbing.
|
||||
- Honest message when the entry is YAML-managed (currently silently no-ops).
|
||||
- One-shot break: no migration code, manifest version bump, clear "recreate your entry" message.
|
||||
|
||||
**Non-Goals:**
|
||||
- Multi-step wizard. Editing dominates over setup in this integration's lifetime; sections beat steps.
|
||||
- Backwards compatibility with upstream config entries.
|
||||
- Translations beyond `en.json`. Other locales are out of scope; upstream's translations can be culled in a follow-up.
|
||||
- Replacing the simulator webapp at `webapp/`. It targets the upstream curve model and is decoupled from the HA integration. Out of scope.
|
||||
- Removing `astral` as a transitive dep. It's still imported elsewhere; pruning it is a follow-up.
|
||||
- Touching `tests/` for unaffected features (color helpers, light state diffing, etc.). Only config-flow, sleep-mode, and take-over-control tests get rewritten.
|
||||
|
||||
## Decisions
|
||||
|
||||
### Decision 1: Collapsible sections via HA's `section()` helper, not a multi-step flow
|
||||
|
||||
**What we chose:** One `async_step_init` that returns a single schema with grouped sections built via the HA Frontend `section()` helper. All fields visible (or conditionally visible) on one screen.
|
||||
|
||||
**Why:** Setup happens once per AL config; editing happens dozens of times over the install's lifetime. Wizards optimize for first-run cost (guidance) at the expense of every subsequent edit (clicks). Sections give us guidance through grouping while keeping editing fast.
|
||||
|
||||
**Alternatives considered:**
|
||||
- **Multi-step flow** (`async_step_basics` → `async_step_curve` → ...). Rejected — every edit becomes a click-through. Also, conditional visibility across steps is messier than within a single section-grouped form.
|
||||
- **One flat dialog with field-order reshuffling.** Rejected — without visual grouping, ordering alone doesn't communicate which fields belong together.
|
||||
|
||||
### Decision 2: Entity-driven sun timing, no `astral` in the curve path
|
||||
|
||||
**What we chose:** Two entity selectors (`sunrise_entity`, `sunset_entity`) of `domain: sensor, device_class: timestamp`. Defaults to built-in `sensor.sun_next_rising` / `sensor.sun_next_setting`. The curve math reads `hass.states.get(<entity_id>)` for the timestamps, not `astral`.
|
||||
|
||||
**Why:** Lets Sun2 (or any custom sun source) plug in without a code change. Matches HA convention ("everything is an entity"). Decouples us from `astral`'s quirks at high latitudes (irrelevant to Germany, but it's free elegance). Single source of truth — your `sensor.sun_next_rising` is also what every other automation in the house reads.
|
||||
|
||||
**Alternatives considered:**
|
||||
- **Keep `astral` and offer a "sun source" toggle.** Rejected — code path bifurcation, two implementations to test, defeats the simplification goal.
|
||||
- **Hardcode `sun.sun` and drop the selector.** Rejected — explicitly precludes Sun2, which is the whole reason to refactor sun timing.
|
||||
|
||||
### Decision 3: Hardcoded tanh curve with 30-minute half-width
|
||||
|
||||
**What we chose:** `brightness_mode` field is deleted. Curve is always tanh. The half-width (`brightness_mode_time_dark` / `_time_light` upstream) is hardcoded as a single constant `RAMP_HALF_WIDTH_SECONDS = 1800` in `const.py`.
|
||||
|
||||
**Why:** Three modes (default / linear / tanh) were a research-era artifact; tanh is the eye-friendly choice for any household use case. The half-width sweet spot (30 min) is well-studied for circadian-friendly transitions and looks reasonable from solstice (sunrise 04:30) to equinox (sunrise 06:00). Removing the knob removes a UX maze.
|
||||
|
||||
**Alternatives considered:**
|
||||
- **Keep `brightness_mode` as a hidden constant, expose half-width.** Rejected — same maintenance cost as keeping both, with no real win.
|
||||
- **Expose half-width as one Advanced slider.** Rejected (initially considered). One less knob is genuinely better than one customizable knob — advanced fields rot when unused.
|
||||
|
||||
### Decision 4: Strict break, no migration code
|
||||
|
||||
**What we chose:** Bump `manifest.json` major version (1.x → 2.0.0-cdit.1). On upgrade, HA fails to load old config entries with a "this version is incompatible" toast. User recreates the entry manually.
|
||||
|
||||
**Why:** Single-household fork. The cost of one manual re-setup is ~5 minutes. Migration code that strips removed keys and silently translates old values would be ~50 LOC, would carry across the next two breaks, and is the kind of code that hides edge-case bugs.
|
||||
|
||||
**Alternatives considered:**
|
||||
- **Silent strip on `async_setup_entry`.** Rejected — looks magical, hides which fields the user thought were configured.
|
||||
- **`async_migrate_entry` with explicit version bump.** Rejected — correct for a public fork, overkill for one user. Re-evaluate if anyone outside CDiT installs this.
|
||||
|
||||
### Decision 5: Native HA selectors instead of voluptuous `int_between`
|
||||
|
||||
**What we chose:** `NumberSelector` with `min`, `max`, `step`, `unit_of_measurement`, `mode=NumberSelectorMode.SLIDER` (or `BOX` for fine-grained); `EntitySelector` with domain/device_class filters; `BooleanSelector`; `DurationSelector` for time intervals. All in `homeassistant.helpers.selector`.
|
||||
|
||||
**Why:** Selectors render as proper UI (sliders, dropdowns, color pickers, entity pickers). `int_between(1, 100)` validates correctly but renders as a plain text field — same UX whether the range is brightness, color temp, or seconds. Selectors are the direction HA core is moving; staying on voluptuous custom validators means re-implementing this every minor HA release.
|
||||
|
||||
**Alternatives considered:**
|
||||
- **Keep voluptuous wrappers, restyle via custom frontend card.** Rejected — explicitly pulls us into frontend territory, which is out of scope for this change.
|
||||
|
||||
### Decision 6: `OptionsFlowWithReload` instead of manual reload
|
||||
|
||||
**What we chose:** Subclass `homeassistant.config_entries.OptionsFlowWithReload` (added to HA core in 2024.10). Override `async_step_init` only. No `async_unload_entry` / `async_setup_entry` reload plumbing.
|
||||
|
||||
**Why:** The documented, supported path. Manual reload has subtle bugs around entity registry stale state and listener leakage. `OptionsFlowWithReload` handles them by tearing down and rebuilding the entry atomically.
|
||||
|
||||
**Alternatives considered:**
|
||||
- **Stay on `OptionsFlow` and call `hass.config_entries.async_reload(...)` manually after save.** Rejected — duplicates HA framework code, easy to forget on edge paths.
|
||||
|
||||
### Decision 7: Delete the sleep mode switch entity, don't hide it
|
||||
|
||||
**What we chose:** Remove the sleep-mode switch class from `switch.py` entirely. Each AL config now creates 3 switches (master, adapt_brightness, adapt_color), not 4. Sleep-mode state machine is also stripped from the master switch class.
|
||||
|
||||
**Why:** Keeping unused entities pollutes the device page, accumulates state, and creates ambiguity ("will this wake up if I flip it?"). Hiding from UI but keeping the code path means the state machine still runs, just invisibly — worst of both worlds.
|
||||
|
||||
**Alternatives considered:**
|
||||
- **Keep the entity, hide from UI.** Rejected — see above.
|
||||
- **Keep the class, gate behind a feature flag.** Rejected — dead code with a flag is still dead code.
|
||||
|
||||
### Decision 8: Delete take-over-control, don't gate it
|
||||
|
||||
**What we chose:** Remove `take_over_control`, `take_over_control_mode`, `detect_non_ha_changes`, `autoreset_control`, `only_once`, `adapt_only_on_bare_turn_on`. Strip the take-over-control state machine from `switch.py`.
|
||||
|
||||
**Why:** Manual-override semantics live at the scene/automation layer in CDiT's house. The take-over-control code threads through every adapter call in `switch.py` — making it conditional via a feature flag doesn't reduce complexity, just relocates it. Delete is the only honest option.
|
||||
|
||||
**Alternatives considered:**
|
||||
- **Gate behind `enable_legacy_overrides` flag.** Rejected — preserves the code, defeats the simplification goal, accumulates "advanced settings" that nobody ever turns on.
|
||||
- **Keep `intercept` and `multi_light_intercept`** — these *are* kept. They're transport behavior (hooking `light.turn_on` to merge adaptive values), not manual-override semantics. Different concern.
|
||||
|
||||
### Decision 9: Conditional visibility costs one submit cycle
|
||||
|
||||
**What we chose:** Fields with drivers (`send_split_delay` driven by `separate_turn_on_commands`; sun-time min/max pairs driven by whether the sun-entity is set) are conditionally included in the schema. When the driver changes, the user submits the form and HA re-renders with the new fields.
|
||||
|
||||
**Why:** HA's config flow can't re-render a single step dynamically when a field changes within that step. The supported path is to submit and let the next render reflect the new state. This costs one extra submit when a driver changes — accepted because driver changes are rare (you set `separate_turn_on_commands` once and forget).
|
||||
|
||||
**Alternatives considered:**
|
||||
- **Always show all fields.** Rejected — the whole point is to hide noise.
|
||||
- **Split into multiple steps when a driver changes.** Rejected — back to the wizard problem.
|
||||
|
||||
### Decision 10: Capability slug is `options-flow`, scoped tight
|
||||
|
||||
**What we chose:** This change defines one capability, `options-flow`, covering the integration's setup/reconfigure UI. Future changes get their own capabilities (`runtime-controls` for the number entities, `house-mode-binding` for the per-mode matrix).
|
||||
|
||||
**Why:** Keeps each spec testable and each requirement focused. A single `integration-configuration` umbrella would collect every config-related requirement across multiple changes — hard to read, hard to maintain.
|
||||
|
||||
### Decision 11: Sun curve math — max brightness lives strictly between the two entities
|
||||
|
||||
**What we chose:** Given `t_sunrise` and `t_sunset` from the entities, the brightness curve is:
|
||||
|
||||
```
|
||||
t < t_sunrise - 1800s : brightness = min
|
||||
t in [t_sunrise - 1800s, t_sunrise + 1800s] : tanh ramp from min → max
|
||||
t in [t_sunrise + 1800s, t_sunset - 1800s] : brightness = max
|
||||
t in [t_sunset - 1800s, t_sunset + 1800s] : tanh ramp from max → min
|
||||
t > t_sunset + 1800s : brightness = min
|
||||
```
|
||||
|
||||
Same shape applied to color temperature, scaled between `min_color_temp` and `max_color_temp`.
|
||||
|
||||
**Why:** Symmetric, deterministic, easy to test. The user's pick of entity is the semantic anchor — pick `sun2_dawn` and full brightness arrives 30 min after civil dawn.
|
||||
|
||||
**Alternatives considered:**
|
||||
- **Treat the entities as ramp midpoints.** Rejected — less intuitive; "when does the day start" should map to "when does max brightness start," not "when am I halfway to max."
|
||||
- **Sun-elevation-style curve interpolated between events.** Rejected — adds astral-style math complexity without proportional benefit. The user picked entity-driven explicitly to avoid that.
|
||||
|
||||
### Decision 12: Auto-remove leftover sleep-mode switch entities on first load
|
||||
|
||||
**What we chose:** In `async_setup_entry`, scan the entity registry for any `switch.adaptive_lighting_sleep_mode_*` entries tied to this integration's config entry, remove them via `entity_registry.async_remove(entity_id)`, and log each removal at INFO level.
|
||||
|
||||
**Why:** Without this, upgrading users see orphan switches in Settings → Entities forever. The cleanup is bounded (only entities this integration created, identifiable by `unique_id` prefix), idempotent (runs every setup, no-op after the first), and small (~10 LOC). The log line gives auditability.
|
||||
|
||||
**Alternatives considered:**
|
||||
- **Log + leave for manual cleanup.** Rejected — pollutes the device page; CDiT install has half a dozen AL configs, that's half a dozen orphans.
|
||||
- **One-time cleanup script.** Rejected — extra step the user has to run.
|
||||
|
||||
### Decision 13: Pin `homeassistant` minimum version to 2025.1.0
|
||||
|
||||
**What we chose:** `manifest.json` declares `"homeassistant": "2025.1.0"` as the minimum supported HA version.
|
||||
|
||||
**Why:** Lets us use the latest stable selector API (`NumberSelector` with `BOX_OR_SLIDER` mode, `EntitySelector` with multi-domain filtering), `section()` helper with no rendering quirks, and `OptionsFlowWithReload` with all 2024.x bug fixes applied. Excludes pre-2025.1 installs intentionally — running HA more than ~6 months behind is its own problem.
|
||||
|
||||
**Alternatives considered:**
|
||||
- **Pin 2024.10.** Rejected (initially recommended) — gives back the headroom for no clear benefit; user explicitly chose to go bolder.
|
||||
- **No pin (`"homeassistant"` absent).** Rejected — silently runs on incompatible versions, fails confusingly when `section()` doesn't render right.
|
||||
|
||||
### Decision 14: Sun-entity selectors are strictly typed
|
||||
|
||||
**What we chose:** Both `sunrise_entity` and `sunset_entity` use `EntitySelector(EntitySelectorConfig(domain="sensor", device_class="timestamp"))`. Only sensors with `device_class: timestamp` show up in the picker.
|
||||
|
||||
**Why:** Covers all real use cases (built-in `sensor.sun_next_rising`, Sun2's `sensor.sun2_*`, any custom timestamp sensor) while preventing foot-guns — `input_datetime` entities don't auto-update for next sunrise, and picking one would silently produce wrong curves. Strict typing makes the wrong choice impossible.
|
||||
|
||||
**Alternatives considered:**
|
||||
- **Loose typing (any datetime entity).** Rejected — invites the `input_datetime` foot-gun.
|
||||
- **Strict + escape hatch constant.** Rejected — no real use case for loose mode; adding the knob now is YAGNI.
|
||||
|
||||
### Decision 15: `RAMP_HALF_WIDTH_SECONDS` lives in `const.py`
|
||||
|
||||
**What we chose:** Define `RAMP_HALF_WIDTH_SECONDS = 1800` in `const.py` near the other tuning defaults, with an inline comment explaining the 30-minute choice (eye-friendly circadian transition, robust across solstice-to-equinox sunrise drift).
|
||||
|
||||
**Why:** `const.py` is the canonical "knobs you might tweak" location in HA custom components. Discoverable to anyone reading the integration. The comment captures the rationale so future-CDiT doesn't relitigate.
|
||||
|
||||
**Alternatives considered:**
|
||||
- **`__init__.py` near curve math.** Rejected — cohesive but harder to find when you want to tune.
|
||||
- **Buried in `config_flow.py`.** Rejected — treats the constant as flow-private, but the curve math is the actual consumer.
|
||||
|
||||
## Risks / Trade-offs
|
||||
|
||||
- **[Sun2 isn't installed in HA]** → Defaults work fine — built-in `sensor.sun_next_*` is always present. Mitigation: README mentions Sun2 as a recommended-but-not-required HACS install.
|
||||
- **[`sensor.sun_next_rising` flips to tomorrow's date the moment sunrise passes]** → The curve math must handle this: after `t_sunrise` has passed, read `sun.sun.last_changed`/historical state, or anchor today's curve from `t_sunset` and the implicit "today is between yesterday's sunset and tomorrow's sunrise." Mitigation: write a small helper `today_sun_events()` that returns `(today_sunrise_dt, today_sunset_dt)` based on current time vs entity values; specs/tasks will cover this explicitly.
|
||||
- **[Removed sleep-mode switch entity lingers in HA's entity registry after upgrade]** → Old `switch.adaptive_lighting_sleep_mode_<name>` entries remain in `core.entity_registry` until manually deleted. Mitigation: document in CHANGELOG; provide a one-line `hass.config_entries.async_remove(...)` snippet for cleanup, or accept manual deletion via UI.
|
||||
- **[Strict break inconveniences any non-CDiT installer]** → Anyone forking the CDiT fork to use upstream config entries will hit the break. Mitigation: explicit "this fork is opinionated; existing AL entries will not load" notice in README and on the fork's GitHub description.
|
||||
- **[HA `section()` API is relatively young (added 2024.5)]** → Risk of styling/render quirks on older HA versions. Mitigation: bump `manifest.json` `homeassistant` minimum version to ≥ 2024.10 (when `OptionsFlowWithReload` also landed, so we're pinning both together).
|
||||
- **[The synthetic tanh curve drifts from astronomical reality near solstices]** → Won't perfectly match astral-computed elevation. Mitigation: this is by design — the user picked Sun2 entities for accuracy at the *endpoints*; smooth dimming between them is what matters, not physical accuracy.
|
||||
- **[`include_config_in_attributes` buried in Diagnostics could trip debug-time users]** → Mitigation: section is collapsed by default but not hidden; surfaces on expand. Mention in README's "Debugging" subsection.
|
||||
|
||||
## Migration Plan
|
||||
|
||||
This change is delivered as a single PR on the fork's `main` branch. No phased rollout; CDiT-dev is the only consumer.
|
||||
|
||||
1. Land the PR.
|
||||
2. Tag the release (`v2.0.0-cdit.1`).
|
||||
3. On the running HA install:
|
||||
- Snapshot current AL config (Settings → Integrations → Adaptive Lighting → ⋮ → Download Diagnostics, or just screenshot the options dialog).
|
||||
- Update via HACS or manual copy of `custom_components/adaptive_lighting/`.
|
||||
- Restart HA.
|
||||
- Old config entry shows as "failed to load."
|
||||
- Delete the failed entry.
|
||||
- Recreate via Settings → Add Integration → Adaptive Lighting, copying the snapshot's values into the new section layout.
|
||||
4. Manually delete leftover `switch.adaptive_lighting_sleep_mode_<name>` entries via Settings → Devices → Entities (filter by integration, sort by "missing").
|
||||
|
||||
**Rollback:** `git revert` the PR merge commit. Old upstream config entries do *not* auto-recover — you'd reinstall upstream AL from HACS and re-create the entry there.
|
||||
|
||||
## Open Questions
|
||||
|
||||
None — all resolved and folded into Decisions 12–15.
|
||||
50
openspec/changes/cdit-config-redesign/proposal.md
Normal file
50
openspec/changes/cdit-config-redesign/proposal.md
Normal file
|
|
@ -0,0 +1,50 @@
|
|||
## Why
|
||||
|
||||
The upstream Adaptive Lighting options dialog is a 40-field flat schema that mixes setup-time decisions, runtime-tunable values, and features CDiT does not use — sleep mode, automatic manual-override detection, three interchangeable brightness curve modes, and eight fields of manual sun-time bookkeeping. With no grouping, no conditional visibility, and expert-only field names, the dialog is hard to read and risky to edit; meaningful changes are buried in noise.
|
||||
|
||||
This change resets the integration config to what CDiT actually needs: an 18-field, sectioned dialog with conditional visibility, native HA selectors, and entity-driven sun timing that plugs into Sun2 cleanly.
|
||||
|
||||
## What Changes
|
||||
|
||||
**BREAKING** — existing upstream config entries will not load. `manifest.json` major version is bumped; users (CDiT only — one household) recreate the entry once.
|
||||
|
||||
- **Sectioned layout via `section()` helper** — 5 collapsible groups (Targets, Daytime curve, Sun schedule, Light control, Advanced) plus a collapsed Diagnostics subsection. One screen, grouped logically, no multi-step wizard.
|
||||
- **`OptionsFlowWithReload`** — saving reloads the integration without a full HA restart and without the stale-state bugs of manual reload.
|
||||
- **Conditional visibility** — fields appear only when their driver is set:
|
||||
- `send_split_delay` only when `separate_turn_on_commands` is true.
|
||||
- `include_config_in_attributes` lives under a collapsed Diagnostics subsection.
|
||||
- **Entity-driven sun timing** — two new fields replace eight:
|
||||
- `sunrise_entity`: any `sensor` with `device_class: timestamp`. Default `sensor.sun_next_rising`.
|
||||
- `sunset_entity`: same. Default `sensor.sun_next_setting`.
|
||||
- Users with Sun2 installed can point to civil / nautical / astronomical twilight sensors without code changes.
|
||||
- **Synthetic tanh brightness curve** — derived from `sunrise_entity` and `sunset_entity` with a hardcoded 30-minute half-width ramp at each end. Curve shape is no longer user-configurable.
|
||||
- **Native HA selectors throughout** — `EntitySelector` (lights and sun events), `NumberSelector` with explicit ranges (brightness, color temp, durations), `BooleanSelector` (flags). Replaces the upstream `int_between(...)` voluptuous custom validators with introspectable UI primitives.
|
||||
- **Explicit YAML-managed entry message** — currently the dialog appears editable but silently no-ops for YAML-configured entries. Replace with an `async_abort` and a clear "this entry is managed by YAML; edit `configuration.yaml`" message.
|
||||
- **Remove 21 fields and 1 entity:**
|
||||
- **Sleep cluster (6 fields + 1 entity)**: `sleep_brightness`, `sleep_rgb_or_color_temp`, `sleep_color_temp`, `sleep_rgb_color`, `sleep_transition`, `adapt_until_sleep`. Plus `switch.adaptive_lighting_sleep_mode_<name>` from the switch platform — runtime drops from 4 toggles to 3.
|
||||
- **Manual sun timing (8 fields)**: `sunrise_time`, `min_sunrise_time`, `max_sunrise_time`, `sunrise_offset`, and the four sunset counterparts. Replaced by `sunrise_entity` / `sunset_entity`.
|
||||
- **Curve shape (3 fields)**: `brightness_mode`, `brightness_mode_time_dark`, `brightness_mode_time_light`. Hardcoded to tanh with 30-min half-width.
|
||||
- **Take-over-control cluster (4 fields)**: `take_over_control`, `take_over_control_mode`, `detect_non_ha_changes`, `autoreset_control`. Manual overrides handled at the scene/automation layer; `only_once` and `adapt_only_on_bare_turn_on` removed as anti-AL flags.
|
||||
- **Kept from upstream override cluster (2 fields)**: `intercept` and `multi_light_intercept` — these are transport behavior (hooking `light.turn_on`), not manual-override semantics.
|
||||
|
||||
## Capabilities
|
||||
|
||||
### New Capabilities
|
||||
|
||||
- `options-flow`: integration setup and reconfiguration UI. Covers section layout, conditional field visibility, entity-driven sun timing, native HA selector usage, reload-on-save semantics, YAML-managed entry messaging, and the surface of fields that exist in the config dialog.
|
||||
|
||||
### Modified Capabilities
|
||||
|
||||
None. `openspec/specs/` is empty — this is the first capability defined in the fork.
|
||||
|
||||
## Impact
|
||||
|
||||
- **`custom_components/adaptive_lighting/const.py`** — `VALIDATION_TUPLES` shrinks from 39 to 18 entries; `CONF_*` / `DEFAULT_*` constants for removed fields are deleted; `EXTRA_VALIDATION` shrinks accordingly. New constants for the hardcoded tanh half-width and the two entity-config keys.
|
||||
- **`custom_components/adaptive_lighting/config_flow.py`** — schema build switches from a flat `vol.Schema({...})` loop over `VALIDATION_TUPLES` to a hand-shaped layout using `section()` and HA selector classes. `OptionsFlowWithReload` replaces `OptionsFlow`. YAML-managed branch replaces the silent no-op with `async_abort(reason="yaml_managed")`.
|
||||
- **`custom_components/adaptive_lighting/switch.py`** — sleep mode switch entity class and its state machine are removed from the master switch class. Take-over-control state machine and its `autoreset` timer are removed. Two fewer entities per AL config.
|
||||
- **`custom_components/adaptive_lighting/__init__.py`** — `astral` calls for sun timing are replaced with `hass.states.get(<sunrise_entity>)` reads; tanh curve math moves here as a stable, hardcoded function. Astral remains a transitive dep but is no longer called in the curve path.
|
||||
- **`custom_components/adaptive_lighting/manifest.json`** — `version` bumped to `2.0.0-cdit.1` (or equivalent CDiT-tagged major) to force config-entry rejection on upgrade.
|
||||
- **`custom_components/adaptive_lighting/strings.json` + `translations/en.json`** — re-shaped to match new section labels; keys for deleted fields removed; new keys for sun-entity labels, the YAML-managed abort reason, and section titles. Other locales left as upstream — out of scope for this change.
|
||||
- **`tests/test_config_flow.py`** — substantially rewritten against the new schema. Sleep-mode tests and take-over-control tests are deleted, not migrated. New tests cover: entity selector validation, conditional visibility, tanh curve output at fixed timestamps, YAML-managed abort path, and `OptionsFlowWithReload` behavior.
|
||||
- **No new runtime dependencies.** `astral` stays in `pyproject.toml` for now (used elsewhere); can be pruned in a follow-up.
|
||||
- **Future changes unlocked**: `add-runtime-range-controls` (number entities for the 4 brightness/color-temp ranges) and `house-mode-modes` (per-AL behavior matrix driven by an external mode entity) both layer on top of this redesign cleanly.
|
||||
195
openspec/changes/cdit-config-redesign/specs/options-flow/spec.md
Normal file
195
openspec/changes/cdit-config-redesign/specs/options-flow/spec.md
Normal file
|
|
@ -0,0 +1,195 @@
|
|||
## ADDED Requirements
|
||||
|
||||
### Requirement: Options dialog presents fields in named collapsible sections
|
||||
|
||||
The integration options dialog SHALL group its 18 configurable fields into five named sections plus a Diagnostics subsection, rendered using Home Assistant's `section()` schema helper. Section names and field membership SHALL match the layout below.
|
||||
|
||||
| Section | Default state | Fields |
|
||||
|---|---|---|
|
||||
| Targets | expanded | `lights` |
|
||||
| Daytime curve | expanded | `min_brightness`, `max_brightness`, `min_color_temp`, `max_color_temp`, `prefer_rgb_color` |
|
||||
| Sun schedule | expanded | `sunrise_entity`, `sunset_entity` |
|
||||
| Light control | expanded | `intercept`, `multi_light_intercept` |
|
||||
| Advanced | collapsed | `interval`, `transition`, `initial_transition`, `adapt_delay`, `separate_turn_on_commands`, `send_split_delay`, `skip_redundant_commands` |
|
||||
| Diagnostics | collapsed | `include_config_in_attributes` |
|
||||
|
||||
#### Scenario: User opens options dialog on a UI-managed entry
|
||||
|
||||
- **WHEN** the user navigates to Settings → Devices & Services → Adaptive Lighting → Configure
|
||||
- **THEN** the form SHALL render six sections in the order: Targets, Daytime curve, Sun schedule, Light control, Advanced, Diagnostics
|
||||
- **AND** the Advanced and Diagnostics sections SHALL be rendered in their collapsed state
|
||||
- **AND** the Targets, Daytime curve, Sun schedule, and Light control sections SHALL be rendered expanded
|
||||
|
||||
#### Scenario: Each section contains only the fields specified for it
|
||||
|
||||
- **WHEN** the user expands any section in the options dialog
|
||||
- **THEN** the fields shown in that section SHALL exactly match the field list in the table above for that section
|
||||
- **AND** no field SHALL appear in more than one section
|
||||
|
||||
### Requirement: Conditional fields hide when their driver makes them irrelevant
|
||||
|
||||
Fields whose configuration is meaningful only under a specific value of another field ("driver") SHALL be omitted from the rendered schema when the driver value makes them inapplicable. When the driver value changes, the form SHALL be re-submitted to re-render with the updated field set.
|
||||
|
||||
The conditional pairs are:
|
||||
- `send_split_delay` is conditional on `separate_turn_on_commands` being `true`.
|
||||
|
||||
#### Scenario: send_split_delay hidden when transport mode disables it
|
||||
|
||||
- **WHEN** the user opens the options dialog with `separate_turn_on_commands` set to `false`
|
||||
- **THEN** the Advanced section SHALL NOT include the `send_split_delay` field
|
||||
|
||||
#### Scenario: send_split_delay revealed when transport mode enables it
|
||||
|
||||
- **WHEN** the user toggles `separate_turn_on_commands` to `true` and submits the form
|
||||
- **THEN** the options dialog SHALL re-render with `send_split_delay` present in the Advanced section
|
||||
- **AND** the field SHALL accept values in the range 0–10000 milliseconds
|
||||
|
||||
### Requirement: Sun event timing is read from configurable HA entities
|
||||
|
||||
The integration SHALL read sunrise and sunset event timestamps from two user-configured HA sensor entities exposed in the options dialog as `sunrise_entity` and `sunset_entity`. Both fields SHALL use an entity selector strictly typed to `domain: sensor` and `device_class: timestamp`. The integration SHALL NOT compute sun events from `astral` or any other internal sun-position library when both entities are configured.
|
||||
|
||||
#### Scenario: Default sun entities point to the built-in sun integration
|
||||
|
||||
- **WHEN** the user creates a new Adaptive Lighting config entry
|
||||
- **THEN** `sunrise_entity` SHALL default to `sensor.sun_next_rising`
|
||||
- **AND** `sunset_entity` SHALL default to `sensor.sun_next_setting`
|
||||
|
||||
#### Scenario: Selector filters to timestamp sensors only
|
||||
|
||||
- **WHEN** the user opens the entity picker for `sunrise_entity` or `sunset_entity`
|
||||
- **THEN** only entities with `domain == "sensor"` and `device_class == "timestamp"` SHALL appear in the picker
|
||||
- **AND** entities of domain `input_datetime` SHALL NOT appear
|
||||
|
||||
#### Scenario: Curve math reads from the configured entity
|
||||
|
||||
- **WHEN** the user sets `sunrise_entity` to `sensor.sun2_dawn` and saves
|
||||
- **THEN** subsequent brightness curve calculations SHALL use the timestamp value of `sensor.sun2_dawn` as the morning sun event
|
||||
- **AND** no call to `astral` SHALL occur in the curve evaluation path for this config entry
|
||||
|
||||
### Requirement: Brightness and color temperature follow a synthetic tanh curve
|
||||
|
||||
For each config entry, the integration SHALL synthesize the daytime brightness and color-temperature values using a hyperbolic-tangent curve anchored at the timestamps from `sunrise_entity` and `sunset_entity`, with a hardcoded half-width of 30 minutes (`RAMP_HALF_WIDTH_SECONDS = 1800`) at each event. The brightness value at time `t` SHALL follow:
|
||||
|
||||
- `t ≤ t_sunrise − 1800s`: value = configured minimum
|
||||
- `t_sunrise − 1800s < t < t_sunrise + 1800s`: value = tanh-interpolated minimum → maximum
|
||||
- `t_sunrise + 1800s ≤ t ≤ t_sunset − 1800s`: value = configured maximum
|
||||
- `t_sunset − 1800s < t < t_sunset + 1800s`: value = tanh-interpolated maximum → minimum
|
||||
- `t ≥ t_sunset + 1800s`: value = configured minimum
|
||||
|
||||
The same curve shape SHALL be applied to color temperature using `min_color_temp` and `max_color_temp` as the curve bounds.
|
||||
|
||||
#### Scenario: Brightness is at minimum well before sunrise
|
||||
|
||||
- **WHEN** the current time is more than 30 minutes before the `sunrise_entity` timestamp
|
||||
- **THEN** the computed brightness SHALL equal the configured `min_brightness`
|
||||
|
||||
#### Scenario: Brightness is exactly at the midpoint at the sunrise event
|
||||
|
||||
- **WHEN** the current time equals the `sunrise_entity` timestamp
|
||||
- **THEN** the computed brightness SHALL equal `(min_brightness + max_brightness) / 2`
|
||||
|
||||
#### Scenario: Brightness is at maximum during the day
|
||||
|
||||
- **WHEN** the current time is between `sunrise_entity + 30min` and `sunset_entity − 30min`
|
||||
- **THEN** the computed brightness SHALL equal the configured `max_brightness`
|
||||
|
||||
#### Scenario: Color temperature follows the same curve shape
|
||||
|
||||
- **WHEN** the current time is at any point on the curve
|
||||
- **THEN** the computed color temperature SHALL follow the same tanh interpolation between `min_color_temp` and `max_color_temp` as the brightness curve does between `min_brightness` and `max_brightness`
|
||||
|
||||
### Requirement: All configurable fields use native HA selectors
|
||||
|
||||
Every field in the options dialog SHALL be rendered using a class from `homeassistant.helpers.selector`. The integration SHALL NOT use bare voluptuous primitive types (such as `vol.Coerce(int)` or custom `int_between`) as schema values for user-facing fields. Each field type SHALL be backed by the selector specified below.
|
||||
|
||||
| Field type | Selector |
|
||||
|---|---|
|
||||
| Numeric range (brightness, color temp) | `NumberSelector` with explicit `min`, `max`, `step`, `unit_of_measurement`, `mode=SLIDER` |
|
||||
| Duration (seconds) | `NumberSelector` with `unit_of_measurement="s"`, `mode=BOX` |
|
||||
| Duration (milliseconds) | `NumberSelector` with `unit_of_measurement="ms"`, `mode=BOX` |
|
||||
| Boolean | `BooleanSelector` |
|
||||
| Entity (lights) | `EntitySelector` with `domain="light"`, `multiple=True` |
|
||||
| Entity (sun events) | `EntitySelector` with `domain="sensor"`, `device_class="timestamp"` |
|
||||
|
||||
#### Scenario: Brightness ranges render as sliders
|
||||
|
||||
- **WHEN** the user opens the options dialog
|
||||
- **THEN** `min_brightness` and `max_brightness` SHALL render as slider controls with range 1–100 and step 1
|
||||
- **AND** both fields SHALL display the unit "%"
|
||||
|
||||
#### Scenario: Color temperature ranges render with explicit unit
|
||||
|
||||
- **WHEN** the user opens the options dialog
|
||||
- **THEN** `min_color_temp` and `max_color_temp` SHALL render as numeric inputs with range 1000–10000 and step 100
|
||||
- **AND** both fields SHALL display the unit "K"
|
||||
|
||||
#### Scenario: Booleans render as toggles
|
||||
|
||||
- **WHEN** the user opens the options dialog
|
||||
- **THEN** every boolean field (`prefer_rgb_color`, `intercept`, `multi_light_intercept`, `separate_turn_on_commands`, `skip_redundant_commands`, `include_config_in_attributes`) SHALL render as a toggle switch control
|
||||
|
||||
### Requirement: Saving options reloads the integration via OptionsFlowWithReload
|
||||
|
||||
The options flow class SHALL extend `homeassistant.config_entries.OptionsFlowWithReload`. Saving changes through the options dialog SHALL trigger an integration reload without the integration manually calling `hass.config_entries.async_reload()`. Custom `async_unload_entry` plumbing for reload purposes SHALL NOT exist in the integration.
|
||||
|
||||
#### Scenario: Saving valid options reloads the integration
|
||||
|
||||
- **WHEN** the user changes any field in the options dialog and submits the form
|
||||
- **THEN** the integration's `async_unload_entry` and `async_setup_entry` SHALL be invoked exactly once each as part of the reload
|
||||
- **AND** the user SHALL NOT see a "restart Home Assistant" prompt
|
||||
|
||||
#### Scenario: Reload preserves entity registry identity
|
||||
|
||||
- **WHEN** the integration reloads after a save
|
||||
- **THEN** the entity IDs of the AL device's switches SHALL remain unchanged
|
||||
- **AND** no duplicate entities SHALL appear in the entity registry
|
||||
|
||||
### Requirement: YAML-managed config entries cannot be edited via the options dialog
|
||||
|
||||
When a config entry was created from `configuration.yaml` rather than the UI, the options flow SHALL abort with `async_abort(reason="yaml_managed")` instead of presenting an editable form. The abort SHALL produce a translation-keyed message in the HA UI that directs the user to edit `configuration.yaml`.
|
||||
|
||||
#### Scenario: Opening options on a YAML-managed entry shows an abort message
|
||||
|
||||
- **WHEN** the user navigates to Configure on a config entry whose `source == SOURCE_IMPORT`
|
||||
- **THEN** the options flow SHALL abort with reason `yaml_managed`
|
||||
- **AND** the HA UI SHALL display a message indicating the entry is YAML-managed and must be edited in `configuration.yaml`
|
||||
- **AND** no editable form SHALL be shown
|
||||
|
||||
### Requirement: Incompatible config entry versions fail to load with a clear error
|
||||
|
||||
The integration's `manifest.json` SHALL declare a major `version` that increments on every breaking config-schema change. On `async_setup_entry`, the integration SHALL reject any config entry whose stored `version` is older than the current major and SHALL raise `ConfigEntryError` with a user-facing message instructing the user to recreate the entry. No silent migration of dropped fields SHALL occur.
|
||||
|
||||
#### Scenario: Loading an upstream config entry on first upgrade
|
||||
|
||||
- **WHEN** Home Assistant attempts to set up a config entry whose `version` is 1 and the current integration version is 2
|
||||
- **THEN** `async_setup_entry` SHALL raise `ConfigEntryError` with a message that names the incompatibility and instructs the user to delete and recreate the entry
|
||||
- **AND** the integration SHALL NOT silently drop or migrate any fields from the old entry
|
||||
|
||||
#### Scenario: Loading a current-version entry succeeds
|
||||
|
||||
- **WHEN** Home Assistant attempts to set up a config entry whose `version` matches the current integration version
|
||||
- **THEN** `async_setup_entry` SHALL complete without error
|
||||
|
||||
### Requirement: Sleep-mode switch entities left behind by upstream are auto-removed
|
||||
|
||||
On `async_setup_entry`, the integration SHALL scan the entity registry for entities whose `unique_id` matches the historical sleep-mode switch pattern owned by this integration's config entry and SHALL remove each match via `entity_registry.async_remove`. Each removal SHALL be logged at `INFO` level with the entity ID. The cleanup SHALL be idempotent: subsequent setups of the same entry SHALL find no matches and SHALL no-op.
|
||||
|
||||
#### Scenario: First load after upgrade removes the orphan sleep switch
|
||||
|
||||
- **WHEN** Home Assistant sets up a config entry on first launch after the version bump
|
||||
- **AND** the entity registry contains a `switch.adaptive_lighting_sleep_mode_<name>` entity owned by this config entry
|
||||
- **THEN** that entity SHALL be removed from the entity registry
|
||||
- **AND** an `INFO` log entry SHALL be emitted naming the removed entity ID
|
||||
|
||||
#### Scenario: Subsequent loads find nothing to remove
|
||||
|
||||
- **WHEN** the integration has already removed the orphan sleep switch on a prior setup
|
||||
- **AND** Home Assistant sets up the same config entry again
|
||||
- **THEN** the entity registry scan SHALL find no matching entities
|
||||
- **AND** no `INFO` log entry about sleep-switch removal SHALL be emitted
|
||||
|
||||
#### Scenario: Cleanup does not touch entities owned by other integrations
|
||||
|
||||
- **WHEN** the integration runs the sleep-switch cleanup
|
||||
- **AND** another integration owns a similarly named entity (e.g., a user-created `switch.adaptive_lighting_sleep_mode_demo` template switch)
|
||||
- **THEN** that foreign entity SHALL NOT be removed from the entity registry
|
||||
86
openspec/changes/cdit-config-redesign/tasks.md
Normal file
86
openspec/changes/cdit-config-redesign/tasks.md
Normal file
|
|
@ -0,0 +1,86 @@
|
|||
<!--
|
||||
Annotations:
|
||||
R1–R9 = Requirements in specs/options-flow/spec.md
|
||||
D1–D15 = Decisions in design.md
|
||||
|
||||
Build order: groups 1 and 2 are foundation (run sequentially or in parallel,
|
||||
no shared file). Groups 3-5 layer on top. Group 6 is the setup-entry guard.
|
||||
Group 7-9 are tests, translations, and docs (final polish).
|
||||
-->
|
||||
|
||||
## 1. Foundation — `const.py` and `manifest.json`
|
||||
|
||||
- [ ] 1.1 Remove the 21 retired `CONF_*` / `DEFAULT_*` constants from `const.py`: `sleep_brightness`, `sleep_rgb_or_color_temp`, `sleep_color_temp`, `sleep_rgb_color`, `sleep_transition`, `adapt_until_sleep`, `sunrise_time`, `min_sunrise_time`, `max_sunrise_time`, `sunrise_offset`, `sunset_time`, `min_sunset_time`, `max_sunset_time`, `sunset_offset`, `brightness_mode`, `brightness_mode_time_dark`, `brightness_mode_time_light`, `take_over_control`, `take_over_control_mode`, `detect_non_ha_changes`, `autoreset_control`, `only_once`, `adapt_only_on_bare_turn_on`. [R8]
|
||||
- [ ] 1.2 Trim `VALIDATION_TUPLES` to the 16 retained upstream entries plus 2 new sun-entity entries (target: 18 total). Also prune `EXTRA_VALIDATION` of orphaned keys. [R8]
|
||||
- [ ] 1.3 Add `CONF_SUNRISE_ENTITY = "sunrise_entity"` / `DEFAULT_SUNRISE_ENTITY = "sensor.sun_next_rising"` and the `_SUNSET_` pair. [R3]
|
||||
- [ ] 1.4 Add `RAMP_HALF_WIDTH_SECONDS = 1800` with an inline comment naming the design choice (30-min eye-friendly transition). [R4, D15]
|
||||
- [ ] 1.5 Bump `manifest.json` to `version: "2.0.0-cdit.1"`, add `"homeassistant": "2025.1.0"`, update `codeowners` to CDiT-dev maintainers, point `documentation` / `issue_tracker` at the fork URL. [R8, D4, D13]
|
||||
|
||||
## 2. Foundation — strip dead code from `switch.py`
|
||||
|
||||
- [ ] 2.1 Delete the sleep-mode switch entity class and its `unique_id` pattern from `switch.py`. The integration now creates 3 switches per AL config (master, adapt_brightness, adapt_color), not 4. [D7]
|
||||
- [ ] 2.2 Remove sleep-mode state machine from the master `AdaptiveSwitch` class (sleep transition logic, sleep brightness override, `adapt_until_sleep` handling). [D7]
|
||||
- [ ] 2.3 Remove the take-over-control state machine: `_manual_control` tracking, `_autoreset_handle`, `detect_non_ha_changes` polling, `only_once` short-circuits, `adapt_only_on_bare_turn_on` checks. [D8]
|
||||
- [ ] 2.4 Audit remaining `switch.py` for references to removed `CONF_*` keys and delete dead branches. Lint must pass. [D7, D8]
|
||||
|
||||
## 3. Config flow — sectioned schema
|
||||
|
||||
- [ ] 3.1 Replace the flat `VALIDATION_TUPLES` loop in `config_flow.py` with a hand-shaped builder that returns a `vol.Schema` containing six `section()`-wrapped subschemas: Targets, Daytime curve, Sun schedule, Light control, Advanced (collapsed), Diagnostics (collapsed). [R1, D1]
|
||||
- [ ] 3.2 Wire each field's selector per the table in R5: `NumberSelector` (slider mode for brightness 1–100 / step 1 / %; box-or-slider for color temp 1000–10000 / step 100 / K), `BooleanSelector`, `EntitySelector(domain="light", multiple=True)` for `lights`, `EntitySelector(domain="sensor", device_class="timestamp")` for the two sun entities. [R5, D5, D14]
|
||||
- [ ] 3.3 Implement conditional visibility for `send_split_delay` (driver: `separate_turn_on_commands`). The schema builder reads the current options/draft state and omits `send_split_delay` when the driver is false. [R2, D9]
|
||||
- [ ] 3.4 Move `include_config_in_attributes` into the Diagnostics collapsed subsection. [R1]
|
||||
- [ ] 3.5 Verify that no field appears in more than one section (spec R1 scenario 2). [R1]
|
||||
|
||||
## 4. Config flow — reload-on-save and YAML-managed abort
|
||||
|
||||
- [ ] 4.1 Change `OptionsFlow` → `OptionsFlowWithReload` in `config_flow.py`. Drop any custom `async_reload` / `async_unload_entry` plumbing that exists today for reload purposes. [R6, D6]
|
||||
- [ ] 4.2 In the options flow's `async_step_init`, detect `config_entry.source == SOURCE_IMPORT` and return `self.async_abort(reason="yaml_managed")`. [R7]
|
||||
- [ ] 4.3 Confirm via manual test that toggling a field and saving reloads the integration with no "restart HA" prompt, and that entity IDs of the AL switches are preserved across the reload. [R6]
|
||||
|
||||
## 5. Curve math — entity reads + synthetic tanh
|
||||
|
||||
- [ ] 5.1 Add a `today_sun_events(hass, entry)` helper in `__init__.py` (or a new `sun.py` module) that reads `entry.options[CONF_SUNRISE_ENTITY]` and `_SUNSET_ENTITY`, fetches their state via `hass.states.get(...)`, parses the timestamp, and handles the "next_rising flipped to tomorrow after sunrise" case by anchoring today's curve from whichever event is in the past. Returns `(today_sunrise_dt, today_sunset_dt)`. [R3, D2]
|
||||
- [ ] 5.2 Add a pure `tanh_curve(now, t_start, t_end, value_min, value_max, half_width=RAMP_HALF_WIDTH_SECONDS)` function. Returns `value_min` outside the active window, ramps via `tanh` between (`t_start - half_width`, `t_start + half_width`), holds at `value_max` between (`t_start + half_width`, `t_end - half_width`), ramps back via `tanh` between (`t_end - half_width`, `t_end + half_width`). [R4, D11]
|
||||
- [ ] 5.3 Replace upstream's `astral`-driven brightness and color-temp computation with two calls to `tanh_curve` — one for brightness using `min_brightness` / `max_brightness`, one for color temp using `min_color_temp` / `max_color_temp`. Same `(t_sunrise, t_sunset)` inputs for both. [R4]
|
||||
- [ ] 5.4 Verify the curve evaluation path no longer imports `astral.sun`. (`astral` may remain a transitive dep for now; pruning it is a follow-up.) [D2]
|
||||
|
||||
## 6. `async_setup_entry` guards
|
||||
|
||||
- [ ] 6.1 At the top of `async_setup_entry` in `__init__.py`, check `config_entry.version` against the current major (2). If older, raise `ConfigEntryError` with a user-facing message: "Adaptive Lighting v2 (CDiT fork) is incompatible with the existing config entry. Delete and recreate the entry from Settings → Devices & Services." [R8, D4]
|
||||
- [ ] 6.2 Add a sleep-switch tombstone helper: scan `entity_registry` for entities whose `unique_id` matches the historical `<entry.entry_id>_sleep_mode_*` pattern, call `entity_registry.async_remove(entity_id)` on each match, log `INFO` per removal with the entity ID. [R9, D12]
|
||||
- [ ] 6.3 Ensure the tombstone helper is idempotent — a second `async_setup_entry` call finds nothing and emits no log lines. [R9]
|
||||
- [ ] 6.4 Confirm the helper only removes entities whose `config_entry_id` matches the current entry (does not touch foreign entities matching the name pattern). [R9, D12]
|
||||
|
||||
## 7. Tests
|
||||
|
||||
- [ ] 7.1 Delete obsolete test files: `tests/test_*sleep*`, `tests/test_*take_over*`, `tests/test_*manual_control*`. Update `tests/conftest.py` to drop fixtures that referenced those features. [D7, D8]
|
||||
- [ ] 7.2 Add test: section layout — opening options on a UI-managed entry returns a flow result with six labeled sections in the specified order; Advanced and Diagnostics collapsed. [R1]
|
||||
- [ ] 7.3 Add test: each field appears in exactly one section, matching the R1 table. [R1]
|
||||
- [ ] 7.4 Add test: `send_split_delay` is absent from the schema when `separate_turn_on_commands` is false; present when true. [R2]
|
||||
- [ ] 7.5 Add test: `sunrise_entity` / `sunset_entity` default to `sensor.sun_next_rising` / `sensor.sun_next_setting` on a freshly created entry. [R3]
|
||||
- [ ] 7.6 Add test: entity selectors for the two sun fields are configured with `domain="sensor"` and `device_class="timestamp"`. [R3, D14]
|
||||
- [ ] 7.7 Add test: `tanh_curve` returns `value_min` more than `half_width` before `t_start`, midpoint at exactly `t_start`, `value_max` more than `half_width` after `t_start` (and the symmetric trio around `t_end`). [R4]
|
||||
- [ ] 7.8 Add test: color temperature uses the same curve shape as brightness, with `min_color_temp` / `max_color_temp` as bounds. [R4]
|
||||
- [ ] 7.9 Add test: `NumberSelector` types, ranges, units, and modes match the R5 table for brightness, color temp, durations, and milliseconds. [R5]
|
||||
- [ ] 7.10 Add test: saving valid options invokes `async_unload_entry` and `async_setup_entry` exactly once each (use mock spies) and produces no "restart HA" prompt. [R6]
|
||||
- [ ] 7.11 Add test: opening the options flow on a `SOURCE_IMPORT` config entry returns `async_abort(reason="yaml_managed")`. [R7]
|
||||
- [ ] 7.12 Add test: `async_setup_entry` raises `ConfigEntryError` when `config_entry.version == 1` and current is 2. [R8]
|
||||
- [ ] 7.13 Add test: `async_setup_entry` succeeds and runs no tombstone log line when entry version is current. [R8]
|
||||
- [ ] 7.14 Add test: the tombstone helper removes a seeded `switch.adaptive_lighting_sleep_mode_<name>` entity owned by this config entry, emits one INFO log line. [R9, D12]
|
||||
- [ ] 7.15 Add test: tombstone helper is idempotent — second run finds nothing, no log line. [R9]
|
||||
- [ ] 7.16 Add test: tombstone helper does not remove a foreign-owned entity matching the name pattern (different `config_entry_id`). [R9, D12]
|
||||
|
||||
## 8. Strings and translations
|
||||
|
||||
- [ ] 8.1 In `strings.json`, add section labels (`section.targets.name`, `section.daytime_curve.name`, etc.) and short descriptions per section. Add field labels for `sunrise_entity` / `sunset_entity`. [R1, R3]
|
||||
- [ ] 8.2 In `strings.json`, add the `yaml_managed` abort reason text: "This Adaptive Lighting config entry is managed from `configuration.yaml`. Edit it there to change options." [R7]
|
||||
- [ ] 8.3 In `strings.json`, add the version-incompatible error: "This entry was created with an older, incompatible version. Delete it and create a new one." [R8]
|
||||
- [ ] 8.4 Remove `strings.json` keys for the 21 deleted fields and the sleep switch entity. [R1, D7]
|
||||
- [ ] 8.5 Mirror the additions/removals in `translations/en.json`. Other locales (de, fr, etc.) are out of scope and may diverge until a follow-up change. [R1]
|
||||
|
||||
## 9. Docs — README and CHANGELOG
|
||||
|
||||
- [ ] 9.1 Replace the upstream README's "Installation" / "Configuration" sections (or add a CDiT-specific preamble at the top) explicitly stating: "This is a CDiT fork. Existing upstream config entries WILL NOT load; recreate them after upgrade." Reference the migration steps from design.md §Migration Plan. [D4]
|
||||
- [ ] 9.2 Add a "Recommended companions" section to README mentioning Sun2 as a HACS-installable source for precise civil / nautical / astronomical twilight sensors. Show the example of pointing `sunrise_entity` at `sensor.sun2_astro_dawn`. [D2, D14]
|
||||
- [ ] 9.3 Write `CHANGELOG.md` (or append to existing) entry for `2.0.0-cdit.1`: the 21 removed fields by name, the 2 added fields, the 1 removed entity, the breaking config-entry behavior, and the explicit recreate workflow. [D4]
|
||||
- [ ] 9.4 Update the fork's GitHub repo description and topics to mark it as opinionated/fork (not a drop-in replacement). [D4]
|
||||
2
openspec/changes/house-mode-modes/.openspec.yaml
Normal file
2
openspec/changes/house-mode-modes/.openspec.yaml
Normal file
|
|
@ -0,0 +1,2 @@
|
|||
schema: spec-driven
|
||||
created: 2026-05-16
|
||||
41
openspec/changes/house-mode-modes/proposal.md
Normal file
41
openspec/changes/house-mode-modes/proposal.md
Normal file
|
|
@ -0,0 +1,41 @@
|
|||
## Why
|
||||
|
||||
A CDiT house already organizes itself around a "house mode" (`input_select.house_mode` or similar) with values like `morning`, `day`, `evening`, `night`, `away`, `guest`. Adaptive Lighting today is mode-blind: enabling AL only during `morning` / `day` / `evening` while disabling adaptation during `away` and forcing fixed brightness in `guest` requires N HA automations per AL × M modes, with no single place to read the truth.
|
||||
|
||||
This change makes the house mode binding native to each AL config: pick the house mode source entity once, fill in a per-mode behavior matrix, and the integration drives its three runtime switches (`master`, `adapt_color`, `adapt_brightness`) on every `state_changed` event from the source entity.
|
||||
|
||||
> **Status**: stub proposal. Specs, design, and tasks to be written when work on this change starts. Depends on `cdit-config-redesign` landing first; can land in parallel with `add-runtime-range-controls`.
|
||||
|
||||
## What Changes
|
||||
|
||||
- **New "House mode" section in the options flow** (added to the layout established by `cdit-config-redesign`). Lives between "Sun schedule" and "Light control". Collapsed by default if no source entity is configured, expanded once one is selected.
|
||||
- **New field `house_mode_entity`** — entity selector. Accepts any entity (`input_select`, `sensor`, `input_text`) — strict typing isn't appropriate because users build mode entities from many sources.
|
||||
- **Per-mode behavior matrix** — dynamically rendered once a source entity is selected. For each mode value (auto-discovered from `input_select.options` when available; manually enumerable for other entity types), three booleans: `active`, `adapt_color`, `adapt_brightness`.
|
||||
- **State listener** — integration subscribes to `state_changed` events for the configured `house_mode_entity`. On change, looks up the new state value in the matrix and asserts the three runtime switches accordingly.
|
||||
- **Strict semantics** (TBD in design): every mode change re-asserts the table; manual user overrides between mode transitions are not preserved across the next transition. Alternative "sticky" semantics deferred until design.
|
||||
- **Graceful degradation**:
|
||||
- Source entity unavailable → no switch changes, log a warning once.
|
||||
- State value not in the matrix → log an info entry, leave switches untouched.
|
||||
- Matrix is empty (no `house_mode_entity` configured) → integration behaves as if this feature does not exist.
|
||||
- **No new runtime control entities** — this change operates only on the existing three switches created per AL config.
|
||||
|
||||
## Capabilities
|
||||
|
||||
### New Capabilities
|
||||
|
||||
- `house-mode-binding`: per-AL coupling between an external HA mode entity and the three runtime switches. Covers entity-source configuration, mode discovery, behavior-matrix data model, state-change handling, override semantics (strict by default), and degradation under missing/unavailable source entities.
|
||||
|
||||
### Modified Capabilities
|
||||
|
||||
- `options-flow`: gains a new "House mode" section with a driver field (`house_mode_entity`) and a conditional matrix renderer. Spec delta will capture this as ADDED Requirements + a MODIFIED Requirement on the section layout list.
|
||||
|
||||
## Impact
|
||||
|
||||
- **`custom_components/adaptive_lighting/config_flow.py`** — new section, new field, dynamic matrix rendering based on the discovered mode list of the selected entity.
|
||||
- **`custom_components/adaptive_lighting/__init__.py`** — `async_setup_entry` subscribes to `state_changed` for the configured `house_mode_entity` via `hass.helpers.event.async_track_state_change_event`.
|
||||
- **`custom_components/adaptive_lighting/switch.py`** — `AdaptiveSwitch` (the master class) gains an `_apply_house_mode(mode_value)` method that flips the three runtime switches per the configured matrix.
|
||||
- **`custom_components/adaptive_lighting/const.py`** — `CONF_HOUSE_MODE_ENTITY`, `CONF_HOUSE_MODE_MATRIX` constants; default matrix shape (empty dict).
|
||||
- **`tests/test_house_mode_binding.py`** — new file. Tests: mode change flips switches per matrix; unknown mode value is logged but doesn't crash; entity unavailable triggers warn-once behavior; empty matrix is a no-op; mode-discovery from `input_select.options`; manual mode list for non-select entities.
|
||||
- **No new runtime dependencies.**
|
||||
|
||||
**Sequencing**: depends on `cdit-config-redesign`. May land in parallel with `add-runtime-range-controls` (no overlap). Open architectural question for design: strict vs sticky override semantics.
|
||||
20
openspec/config.yaml
Normal file
20
openspec/config.yaml
Normal file
|
|
@ -0,0 +1,20 @@
|
|||
schema: spec-driven
|
||||
|
||||
# Project context (optional)
|
||||
# This is shown to AI when creating artifacts.
|
||||
# Add your tech stack, conventions, style guides, domain knowledge, etc.
|
||||
# Example:
|
||||
# context: |
|
||||
# Tech stack: TypeScript, React, Node.js
|
||||
# We use conventional commits
|
||||
# Domain: e-commerce platform
|
||||
|
||||
# Per-artifact rules (optional)
|
||||
# Add custom rules for specific artifacts.
|
||||
# Example:
|
||||
# rules:
|
||||
# proposal:
|
||||
# - Keep proposals under 500 words
|
||||
# - Always include a "Non-goals" section
|
||||
# tasks:
|
||||
# - Break tasks into chunks of max 2 hours
|
||||
Loading…
Add table
Add a link
Reference in a new issue