@ancleto/spec 0.6.5 → 0.6.7

package/README.md

@@ -106,7 +106,7 @@ ancleto init --agent opencode --tier normal
 
 * `normal`: Modelos balanceados sin restricciones agresivas de contexto (default).
 * `minimo`: Enfoque en el modelo pago más económico viable, con alta compresión de contexto y exclusión de tests/docs en el discovery.
-* `gratis`: Bloqueado a modelos gratuitos (ej. `opencode/big-pickle`), empaquetado ultra-agresivo y un límite estricto (budget) de tokens enviado al LLM.
+* `gratis`: Bloqueado a modelos gratuitos, empaquetado ultra-agresivo y un límite estricto (budget) de tokens enviado al LLM. Si tenés acceso a **Muse Spark 1.3 Free** (`opencode/muse-spark-1.3-contributor-free`, no abierto a todos), se usa ese; si no, se usa `opencode/big-pickle`. En modo interactivo el instalador te lo pregunta; la elección queda guardada en `.ancletorc` (`gratisModel`).
 
 La configuración se preserva en `.ancletorc` (raíz del proyecto) y `.ancleto-tier` (junto a la configuración instalada).
 
@@ -211,3 +211,28 @@ ancleto init --with-azure
 ```
 
 Esto escribe `azure.enabled: true` en tu `.ancletorc`. Solo deberás completar la sección de Azure en el archivo `PRODUCT.md` e instalar su extensión (`az extension add --name azure-devops`).
+
+---
+
+## 🤖 Referencia: Agentes y Modelos por Tier
+
+Los 10 agentes instalados y el modelo que usa cada uno según tu tier. Al instalar, el nivel elegido se escribe en la línea `model:` de cada agente (y se re-aplica en cada `update`).
+
+| Agente | `normal` (default) | `minimo` | `gratis` |
+|---|---|---|---|
+| orchestrator | `opencode-go/qwen3.7-plus` | `opencode-go/deepseek-v4.1-flash` | ver nota ↓ |
+| coder | `opencode-go/minimax-m3` | `opencode-go/deepseek-v4.1-flash` | ver nota ↓ |
+| tester | `opencode-go/deepseek-v4.1-flash` | `opencode-go/deepseek-v4.1-flash` | ver nota ↓ |
+| spec-writer | `opencode-go/qwen3.7-plus` | `opencode-go/deepseek-v4.1-flash` | ver nota ↓ |
+| reviewer | `opencode-go/qwen3.6-plus` | `opencode-go/deepseek-v4.1-flash` | ver nota ↓ |
+| technical-discovery | `opencode-go/deepseek-v4.1-flash` | `opencode-go/deepseek-v4.1-flash` | ver nota ↓ |
+| technical-seed-writer | `opencode-go/minimax-m3` | `opencode-go/deepseek-v4.1-flash` | ver nota ↓ |
+| memory-keeper | `opencode-go/deepseek-v4.1-flash` | `opencode-go/deepseek-v4.1-flash` | ver nota ↓ |
+| context-resolver | `opencode-go/deepseek-v4.1-flash` | `opencode-go/deepseek-v4.1-flash` | ver nota ↓ |
+| documenter | `opencode-go/deepseek-v4.1-flash` | `opencode-go/deepseek-v4.1-flash` | ver nota ↓ |
+
+El tier `minimo` usa un único modelo (`deepseek-v4.1-flash`) para los 10 agentes: es el más económico del catálogo para coding (0.15/0.60 por millón de tokens) con 1M de contexto.
+
+**Tier `gratis`:** los 10 agentes usan **Muse Spark 1.3 Free** (`opencode/muse-spark-1.3-contributor-free`) **si está disponible** en tu cuenta (no está abierto a todos). En una instalación interactiva el wizard te lo pregunta; la respuesta se guarda en `.ancletorc` (`gratisModel`) y se reutiliza en los siguientes `install`/`update`. Sin TTY (CI) se detecta con `opencode models` — con timeout — y si no se puede confirmar se usa `opencode/big-pickle`. El instalador siempre informa cuál aplicó (`ancleto: modelo gratis: ...`).
+
+> Variable avanzada: `ANCLETO_MUSE_SPARK=1` fuerza Muse Spark, `ANCLETO_MUSE_SPARK=0` fuerza `big-pickle` (útil para tests o para fijar el comportamiento; tiene prioridad sobre la elección guardada).

package/agents/context-resolver.md

@@ -1,7 +1,7 @@
 ---
 description: Resolves intake grounding context (Work Item / card) before triage, so the orchestrator classifies and delegates with the real card content
 mode: subagent
-model: opencode-go/deepseek-v4-flash
+model: opencode-go/deepseek-v4.1-flash
 temperature: 0.1
 color: '#8b5cf6'
 tools:

package/agents/documenter.md

@@ -1,7 +1,7 @@
 ---
 description: Finalizes and archives completed aspec changes in alignment with the aspec lifecycle
 mode: subagent
-model: opencode-go/deepseek-v4-flash
+model: opencode-go/deepseek-v4.1-flash
 temperature: 0.1
 color: '#10b981'
 tools:
@@ -116,6 +116,8 @@ Do not treat archive as a blind file move.
 
 When a completed change modifies behavior through aspec deltas, `aspec/specs/` must reflect that completed behavior before the change is archived.
 
+**Language**: spec artifacts are written in English. The requirement/scenario keywords (`Requirement`, `Scenario`, `SHALL`, `WHEN`/`THEN`, `ADDED/MODIFIED/REMOVED/RENAMED Requirements`) are literal and MUST NOT be translated. Paths, file names, and identifiers stay unchanged.
+
 Handle these delta sections carefully:
 
 - `ADDED Requirements`

package/agents/memory-keeper.md

@@ -1,7 +1,7 @@
 ---
 description: Owns the repository memory (.ancleto/memory.db) — recalls prior lessons at intake and records rules and decisions at close, so a finding survives the session that produced it
 mode: subagent
-model: opencode-go/deepseek-v4-flash
+model: opencode-go/deepseek-v4.1-flash
 temperature: 0.1
 color: '#f59e0b'
 tools:

package/agents/spec-writer.md

@@ -19,7 +19,8 @@ Read `AGENTS.md` at the repo root for project-specific conventions, tech stack,
 
 ## Language Requirement
 
-- All artifact content MUST be written in Spanish
+- All artifact content MUST be written in English
+- Keywords are literal and MUST NOT be translated: `Requirement`, `Scenario`, `SHALL`, `WHEN`/`THEN`, `ADDED Requirements`, `MODIFIED Requirements`, `REMOVED Requirements`, `RENAMED Requirements`
 - File names and directory names MUST remain in English, following aspec conventions
 
 ## Primary Responsibility

package/agents/technical-discovery.md

@@ -1,7 +1,7 @@
 ---
 description: Internal repository-context specialist, invoked only by the orchestrator to avoid repository sweeps
 mode: subagent
-model: opencode-go/deepseek-v4-flash
+model: opencode-go/deepseek-v4.1-flash
 temperature: 0.1
 color: '#0ea5e9'
 tools:

package/agents/tester.md

@@ -1,7 +1,7 @@
 ---
 description: Writes and updates tests, and verifies implementation against approved change inputs
 mode: subagent
-model: opencode-go/deepseek-v4-flash
+model: opencode-go/deepseek-v4.1-flash
 temperature: 0.1
 color: '#3b82f6'
 tools:

package/commands/cleto-apply.md

@@ -2,160 +2,8 @@
 description: Implement tasks from an aspec change (Experimental)
 ---
 
-Implement tasks from an aspec change.
+Invoke the `ancleto-apply` skill with the Skill tool and follow it exactly; do not improvise steps.
 
 **Input**: Optionally specify a change name (e.g., `/cleto-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 `aspec 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., `/cleto-apply <other>`).
-
-2. **Check status to understand the schema**
-
-   ```bash
-   aspec 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
-   aspec 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 `/cleto-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 `/cleto-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
+Work Item grounding (when the request references a Work Item) is owned by `@context-resolver`.

package/commands/cleto-archive.md

@@ -2,170 +2,8 @@
 description: Archive a completed change in the experimental workflow
 ---
 
-Archive a completed change in the experimental workflow.
+Invoke the `ancleto-archive` skill with the Skill tool and follow it exactly; do not improvise steps.
 
 **Input**: Optionally specify a change name after `/cleto-archive` (e.g., `/cleto-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 `aspec 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 `aspec 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 `aspec/changes/<name>/specs/`. If none exist, proceed without sync prompt.
-
-   **If delta specs exist:**
-
-   - Compare each delta spec with its corresponding main spec at `aspec/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 ancleto-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 aspec/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: Clean up scaffold files and move the change directory to archive
-
-   **Before moving**, delete scaffold-only files if present — they must not be preserved in the archive:
-
-   ```bash
-   rm -f aspec/changes/<name>/context.md
-   ```
-
-   Then move:
-
-   ```bash
-   mv aspec/changes/<name> aspec/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:** aspec/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:** aspec/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:** aspec/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:** aspec/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 (aspec status --json) for completion checking
-- Don't block archive on warnings - just inform and confirm
-- Preserve .aspec.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 `ancleto-sync-specs` (agent-driven)
-- If delta specs exist, always run the sync assessment and show the combined summary before prompting
+Work Item grounding (when the request references a Work Item) is owned by `@context-resolver`.