@leing2021/super-pi 0.18.2 → 0.19.1

package/README.md

@@ -29,12 +29,44 @@ Super Pi's answers:
 ## The Five-Step Loop
 
 ```
-01-brainstorm → 02-plan → 03-work → 04-review → 05-compound
-    think          plan      build      review      compound
+01-brainstorm → 02-plan → 03-work → 04-review → 05-learn
+    think          plan      build      review      learn
 ```
 
 Each step has a dedicated skill + tool pair. Not just prompts — structured toolchains.
 
+### New: Stage model routing + optional auto-continue
+
+Configure once in `.pi/settings.json`:
+
+```json
+{
+  "modelStrategy": {
+    "01-brainstorm": "claude-sonnet-4-20250514",
+    "02-plan": "claude-opus-4-20250115",
+    "03-work": "claude-sonnet-4-20250514",
+    "04-review": "claude-sonnet-4-20250514",
+    "05-learn": "claude-haiku-4-20250414",
+    "default": "claude-sonnet-4-20250514"
+  },
+  "pipeline": {
+    "autoContinue": false
+  }
+}
+```
+
+How it works:
+- Each stage picks `modelStrategy[stage]`, or `modelStrategy.default` as fallback.
+- Every stage prints a `📊 Pipeline Status` block with `Current / Output / Next`.
+- If `pipeline.autoContinue=true`, super-pi can trigger the next stage automatically.
+- Auto-continue is gate-aware: it will NOT skip required approvals (brainstorm approval, plan/review A/B/C choices).
+
+Quick example:
+1. Run `/skill:01-brainstorm`
+2. Approve the design
+3. If `autoContinue=true`, it moves to `/skill:02-plan` automatically
+4. If `autoContinue=false`, it stops after status output and waits for your command
+
 ---
 
 ## What Each Step Does
@@ -73,7 +105,7 @@ Breaks requirements into implementation units, each following strict **RED → G
 
 **Browser QA (optional)**: Uses `agent-browser` to open your app, click through pages, screenshot bugs, fix by severity, up to 3 auto-fix iterations. Can auto-generate regression tests. Like having a QA engineer run acceptance tests.
 
-### 05-compound: Compound Learnings
+### 05-learn: Compound Learnings
 
 `pattern_extractor` scans existing artifacts, extracts and categorizes patterns. Turns "the pitfall we hit this time" into a YAML-tagged solution card in `docs/solutions/`.
 
@@ -93,7 +125,7 @@ Next time `02-plan` or `04-review` runs, a grep-first search strategy automatica
 | `02-plan` | Break into units, TDD gates, incremental updates | `plan_diff` |
 | `03-work` | Parallel execution, checkpoint resume, error recovery | `session_checkpoint`, `task_splitter`, `parallel_subagent` |
 | `04-review` | Persona-routed review + live browser testing | `review_router` |
-| `05-compound` | Pattern extraction → knowledge card compounding | `pattern_extractor` |
+| `05-learn` | Pattern extraction → knowledge card compounding | `pattern_extractor` |
 | `06-next` | Not sure what to do next? Ask this | `workflow_state`, `session_history` |
 | `07-worktree` | Git worktree isolated development | `worktree_manager` |
 | `08-status` | Scan artifacts, report progress | `workflow_state`, `session_history` |
@@ -174,7 +206,7 @@ You: continue
 
 → 03-work parallel execution, checkpoint resume
 → 04-review code review + optional browser QA
-→ 05-compound knowledge compounding
+→ 05-learn knowledge compounding
 ```
 
 ### Adding a feature
@@ -183,7 +215,7 @@ You: continue
 You: I want to add user authentication to the project
 
 → 01-brainstorm CE mode, multi-round dialog: OAuth2? JWT? MFA?
-→ Requirements doc → 02-plan → 03-work → 04-review → 05-compound
+→ Requirements doc → 02-plan → 03-work → 04-review → 05-learn
 ```
 
 ### Resume after interruption
@@ -219,7 +251,7 @@ your-project/
 ├── docs/
 │   ├── brainstorms/                  # Requirements (01-brainstorm)
 │   ├── plans/                        # Execution plans (02-plan)
-│   └── solutions/                    # Knowledge cards (05-compound)
+│   └── solutions/                    # Knowledge cards (05-learn)
 └── .context/
     └── compound-engineering/
         ├── checkpoints/              # Breakpoint files (session_checkpoint)
@@ -351,6 +383,12 @@ Not a fork. Not a wrapper. Methodologies extracted and rebuilt with Pi's native
 
 ## Changelog
 
+### 0.19.0 — 0.69.0 alignment + learn rename
+- TypeBox migration: `@sinclair/typebox` → `typebox` (zero old-path imports)
+- Peer/dev dependency upgrade: pi-coding-agent `0.67.6` → `0.69.0`
+- Tool termination: 6 pure-query tools now return `terminate: true` to reduce unnecessary LLM rounds
+- Skill rename: `05-compound` → `05-learn` for clarity
+
 ### 0.18.0 — Progressive rules
 - Built-in `rules/` directory with 13 language layers + common + web (78 Markdown files)
 - New `10-rules` skill: progressive on-demand loading, zero waste

package/extensions/ce-core/index.ts

@@ -1,5 +1,5 @@
 import type { ExtensionAPI } from "@mariozechner/pi-coding-agent"
-import { Type } from "@sinclair/typebox"
+import { Type } from "typebox"
 import { createArtifactHelperTool, type ArtifactType } from "./tools/artifact-helper"
 import { createAskUserQuestionTool } from "./tools/ask-user-question"
 import { createSubagentTool } from "./tools/subagent"
@@ -282,8 +282,8 @@ export default function ceCoreExtension(pi: ExtensionAPI) {
           allowCustom: params.allowCustom,
         },
         {
-          input: async (question) => ctx.ui.input(question),
-          select: async (question, options) => ctx.ui.select(question, options),
+          input: async (question) => (await ctx.ui.input(question)) ?? null,
+          select: async (question, options) => (await ctx.ui.select(question, options)) ?? null,
         },
       )
 
@@ -338,6 +338,7 @@ export default function ceCoreExtension(pi: ExtensionAPI) {
       return {
         content: [{ type: "text", text: JSON.stringify(result, null, 2) }],
         details: result,
+        terminate: true,
       }
     },
   })
@@ -392,6 +393,7 @@ export default function ceCoreExtension(pi: ExtensionAPI) {
       return {
         content: [{ type: "text", text: JSON.stringify(result, null, 2) }],
         details: result,
+        terminate: true,
       }
     },
   })
@@ -447,6 +449,7 @@ export default function ceCoreExtension(pi: ExtensionAPI) {
       return {
         content: [{ type: "text", text: JSON.stringify(result, null, 2) }],
         details: result,
+        terminate: true,
       }
     },
   })
@@ -486,6 +489,7 @@ export default function ceCoreExtension(pi: ExtensionAPI) {
       return {
         content: [{ type: "text", text: JSON.stringify(result, null, 2) }],
         details: result,
+        terminate: true,
       }
     },
   })
@@ -527,6 +531,7 @@ export default function ceCoreExtension(pi: ExtensionAPI) {
       return {
         content: [{ type: "text", text: JSON.stringify(result, null, 2) }],
         details: result,
+        terminate: true,
       }
     },
   })
@@ -548,6 +553,7 @@ export default function ceCoreExtension(pi: ExtensionAPI) {
       return {
         content: [{ type: "text", text: JSON.stringify(result, null, 2) }],
         details: result,
+        terminate: true,
       }
     },
   })
@@ -580,7 +586,7 @@ export default function ceCoreExtension(pi: ExtensionAPI) {
     return {
       content: [{ type: "text", text: result.output }],
       details: {
-        ...event.details,
+        ...(event.details && typeof event.details === "object" ? event.details : {}),
         bashFilter: {
           strategy: result.strategy,
           originalBytes: result.originalBytes,
@@ -617,7 +623,7 @@ export default function ceCoreExtension(pi: ExtensionAPI) {
     return {
       content: [{ type: "text", text: result.output }],
       details: {
-        ...event.details,
+        ...(event.details && typeof event.details === "object" ? event.details : {}),
         readFilter: {
           strategy: result.strategy,
           originalBytes: result.originalBytes,
@@ -627,10 +633,11 @@ export default function ceCoreExtension(pi: ExtensionAPI) {
     }
   })
 
-  // Compaction prompt optimizer — makes summaries more focused and useful
-  pi.on("session_before_compact", async (_event, _ctx) => {
+  // Tree summary prompt optimizer — keeps branch summaries focused
+  pi.on("session_before_tree", async (_event, _ctx) => {
     return {
       customInstructions: COMPACTION_FOCUS_INSTRUCTIONS,
+      replaceInstructions: false,
     }
   })
 }

package/extensions/ce-core/tools/bash-output-filter.ts

@@ -1,4 +1,4 @@
-import { Type } from "@sinclair/typebox"
+import { Type } from "typebox"
 
 // ============================================================================
 // Types

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@leing2021/super-pi",
-  "version": "0.18.2",
+  "version": "0.19.1",
   "private": false,
   "type": "module",
   "description": "Pi-native Compound Engineering package for iterative development workflows",
@@ -36,11 +36,10 @@
   },
   "peerDependencies": {
     "@mariozechner/pi-coding-agent": "*",
-    "@sinclair/typebox": "*"
+    "typebox": "*"
   },
   "devDependencies": {
-    "@mariozechner/pi-coding-agent": "0.67.6",
-    "@sinclair/typebox": "0.34.41",
+    "@mariozechner/pi-coding-agent": "0.69.0",
     "bun-types": "^1.3.12"
   },
   "pi": {

package/skills/01-brainstorm/SKILL.md

@@ -7,6 +7,8 @@ description: "Brainstorm requirements with three modes: CE discovery, Startup Di
 
 Use this skill when the request is ambiguous, needs requirements discovery before planning, or the user describes a new idea/product.
 
+See [shared pipeline instructions](../references/pipeline-config.md) for model routing and pipeline behavior.
+
 ## Core rules
 
 - Use **`brainstorm_dialog`** to manage multi-round conversations.
@@ -118,3 +120,5 @@ Before handing off to `02-plan`:
 ## Artifact contract
 
 Use `references/requirements-template.md` to structure the requirements document. Keep implementation details out unless the brainstorm is specifically about architecture or technical direction.
+
+Before finishing this skill, apply the completion checklist in [shared pipeline instructions](../references/pipeline-config.md).

package/skills/02-plan/SKILL.md

@@ -7,6 +7,8 @@ description: "Turn requirements into a plan. Optional CEO-style strategic review
 
 Use this skill when requirements are ready to become an execution-ready plan.
 
+See [shared pipeline instructions](../references/pipeline-config.md) for model routing and pipeline behavior.
+
 ## Core rules
 
 - Before planning, read the `10-rules` skill and load `rules/common/development-workflow.md` and `rules/common/testing.md` for coding standards context.
@@ -76,3 +78,5 @@ Every unit must include:
   6. Run unit-level verification
 - **Verification commands**: exact commands to run
 - **Expected results**: what success looks like
+
+Before finishing this skill, apply the completion checklist in [shared pipeline instructions](../references/pipeline-config.md).

package/skills/03-work/SKILL.md

@@ -7,6 +7,8 @@ description: Execute plan-driven work in a controlled Phase 1 workflow.
 
 Use this skill when there is a plan path or a tightly scoped bare prompt ready for execution.
 
+See [shared pipeline instructions](../references/pipeline-config.md) for model routing and pipeline behavior.
+
 ## Core rules
 
 - Before execution, read the `10-rules` skill and load language-specific rules matching the active codebase (e.g. `rules/typescript/` for TS work).
@@ -64,3 +66,5 @@ When all units are done, provide:
 - **Commands run**: all verification commands executed
 - **Verification results**: pass/fail status for each
 - **Follow-up work**: any remaining risks or open questions
+
+Before finishing this skill, apply the completion checklist in [shared pipeline instructions](../references/pipeline-config.md).

package/skills/04-review/SKILL.md

@@ -7,6 +7,8 @@ description: "Review code with structured findings. Optional browser QA and regr
 
 Use this skill after implementation to review changes against the diff, the relevant plan, and prior learnings.
 
+See [shared pipeline instructions](../references/pipeline-config.md) for model routing and pipeline behavior.
+
 ## Core rules
 
 - Before reviewing, read the `10-rules` skill and load `rules/common/code-review.md` plus language-specific rules matching the changed files.
@@ -16,7 +18,7 @@ Use this skill after implementation to review changes against the diff, the rele
 - Search solutions with grep-first strategy: extract keywords from the task → `bash grep -rl "tags:.*keyword" docs/solutions/ ~/.pi/agent/docs/solutions/` → read only frontmatter (first 15 lines) of matching files → score by severity + tag relevance → fully read top 3. Search both project-level (`docs/solutions/`) and global-level (`~/.pi/agent/docs/solutions/`). If no matches, report "No relevant solutions found" and proceed.
 - Produce **structured findings** using `references/findings-schema.md`.
 - When findings are **autofixable**, apply fixes and re-review (max 3 iterations).
-- End with a handoff that can point toward fixes, re-review, or `05-compound`.
+- End with a handoff that can point toward fixes, re-review, or `05-learn`.
 
 ## Review discipline — technical evaluation
 
@@ -69,5 +71,7 @@ After QA:
 After review (and optional QA) is complete, hand off using `references/handoff.md`:
 1. Summarize all findings (code review + QA if run).
 2. Note fix commits if any were applied.
-3. Recommend `05-compound` if learnings are worth capturing.
+3. Recommend `05-learn` if learnings are worth capturing.
 4. Recommend `03-work` if fixes need further implementation.
+
+Before finishing this skill, apply the completion checklist in [shared pipeline instructions](../references/pipeline-config.md).

package/skills/04-review/references/handoff.md

@@ -6,7 +6,7 @@ When the review is complete:
 2. State whether fixes or re-review are needed.
 3. If findings are **autofixable**, apply the fixes and re-review the changes.
 4. After autofix, report what was changed and whether re-review confirms the fix.
-5. Recommend `05-compound` when the review surfaced a reusable learning or newly solved problem.
+5. Recommend `05-learn` when the review surfaced a reusable learning or newly solved problem.
 6. Mention any relevant plan or solution artifacts referenced during review.
 
 ## Autofix loop

package/skills/{05-compound → 05-learn}/SKILL.md

@@ -1,12 +1,14 @@
 ---
-name: 05-compound
+name: 05-learn
 description: Capture solved problems as reusable solution artifacts.
 ---
 
-# Compound
+# Learn
 
 Use this skill after solving a problem so the repository gains a reusable learning in `docs/solutions/`.
 
+See [shared pipeline instructions](../references/pipeline-config.md) for model routing and pipeline behavior.
+
 ## Core rules
 
 - Every solution MUST include YAML frontmatter per `references/solution-schema.yaml` (title, category, severity, tags, applies_when).
@@ -30,3 +32,5 @@ Use this skill after solving a problem so the repository gains a reusable learni
 5. Choose the correct category using `references/category-map.md`.
 6. Write or update the solution artifact under `docs/solutions/<category>/`.
 7. Mention how future `02-plan` and `04-review` runs should benefit from the new learning.
+
+Before finishing this skill, apply the completion checklist in [shared pipeline instructions](../references/pipeline-config.md).

package/skills/06-next/SKILL.md

@@ -34,4 +34,4 @@ Use this skill when the user wants to know what to run next in the Compound Engi
 - `02-plan` — turn requirements into implementation units
 - `03-work` — execute the plan
 - `04-review` — review changes with structured findings
-- `05-compound` — capture learnings as solution artifacts
+- `05-learn` — capture learnings as solution artifacts

package/skills/06-next/references/recommendation-logic.md

@@ -26,18 +26,18 @@ If code changes have been made (detected by git diff) and no recent review exist
 - Recommend `04-review`
 - Reason: Implementation is done. Review the changes with structured findings.
 
-## Rule 5: After review, compound
+## Rule 5: After review, learn
 
 If a review has been completed and `solutions.count` has not increased since the last workflow cycle:
-- Recommend `05-compound`
+- Recommend `05-learn`
 - Reason: A review was completed. Capture key learnings as a durable solution artifact.
 
 ## Rule 6: All artifacts exist
 
 If brainstorm, plan, and solution all exist:
-- Recommend `05-compound` if no recent solution was added
+- Recommend `05-learn` if no recent solution was added
 - Otherwise recommend `01-brainstorm` for a new cycle
-- Reason: A full loop may be complete. Either compound learnings or start a new cycle.
+- Reason: A full loop may be complete. Either learn learnings or start a new cycle.
 
 ## Fallback
 

package/skills/08-status/SKILL.md

@@ -26,7 +26,7 @@ If `workflow_state` is not available, fall back to `bash` with `ls` and `find` t
 - If a recent brainstorm exists but there is no matching plan in `docs/plans/`, recommend `02-plan` next.
 - If a recent plan exists and implementation appears incomplete, recommend `03-work` next.
 - If code has changed after planning, recommend `04-review` next.
-- If a problem was just solved and there is no matching learning in `docs/solutions/`, recommend `05-compound` next.
+- If a problem was just solved and there is no matching learning in `docs/solutions/`, recommend `05-learn` next.
 - If multiple artifacts exist, summarize them briefly and name the single best next step.
 
 ## Output format

package/skills/09-help/SKILL.md

@@ -13,7 +13,7 @@ Use this skill when the user asks how to use the package, which workflow step co
 - `02-plan` — use when requirements are clear enough to turn into implementation units. After planning, user can optionally run a CEO-style strategic review or strict review (error maps, failure modes, test diagrams).
 - `03-work` — use when there is a plan or a tightly scoped task ready for controlled execution.
 - `04-review` — use after code changes to produce structured findings. After code review, user can optionally extend to browser-based QA testing (find visual/functional bugs with agent-browser) and regression test generation.
-- `05-compound` — use after solving a problem so the repo gains a durable learning in `docs/solutions/`.
+- `05-learn` — use after solving a problem so the repo gains a durable learning in `docs/solutions/`.
 - `08-status` — use when the user wants to know which artifact already exists and what the next workflow step should be.
 
 ## Recommended flow
@@ -29,7 +29,7 @@ Use this skill when the user asks how to use the package, which workflow step co
 4. Run `04-review` after implementation.
    - Optionally extend to **Browser QA** for visual and functional bug finding.
    - Or **Browser QA + Regression Tests** to also generate automated test coverage.
-5. Capture key learnings with `05-compound`.
+5. Capture key learnings with `05-learn`.
 6. Use `08-status` at any point to inspect repo-local workflow state.
 
 ## Output

package/skills/09-help/references/workflow-sequence.md

@@ -4,6 +4,6 @@
 2. `02-plan` → break it into concrete units (optionally + CEO Review / Strict Review)
 3. `03-work` → execute the plan
 4. `04-review` → inspect the changes (optionally + Browser QA / QA + Regression Tests)
-5. `05-compound` → save key learnings
+5. `05-learn` → save key learnings
 
 Use `08-status` at any point to see where you are.

package/skills/references/pipeline-config.md

@@ -0,0 +1,49 @@
+# Shared pipeline instructions
+
+Use these rules in all Phase 1 skills: `01-brainstorm` → `02-plan` → `03-work` → `04-review` → `05-learn`.
+
+## Start of skill: model routing
+
+Run this checklist before normal skill workflow:
+
+1. Read `.pi/settings.json` from the project root.
+2. Parse `modelStrategy` (if missing, skip switching).
+3. Resolve current stage key:
+   - `01-brainstorm`
+   - `02-plan`
+   - `03-work`
+   - `04-review`
+   - `05-learn`
+4. Pick `targetModel = modelStrategy[stageKey] ?? modelStrategy.default`.
+5. If `targetModel` exists and differs from the current model, run `/model <targetModel>`.
+6. If switching fails, continue with current model and mention the failure once.
+
+## End of skill: status + optional auto-continue
+
+Before final completion, always output this block (replace placeholders with real values, never output angle-bracket placeholders literally):
+
+```
+---
+📊 Pipeline Status
+- Current: <stageKey>
+- Output: <main artifact path or N/A>
+- Next: <next skill command or Completed>
+---
+```
+
+Next step mapping:
+- `01-brainstorm` → `/skill:02-plan`
+- `02-plan` → `/skill:03-work`
+- `03-work` → `/skill:04-review`
+- `04-review` → `/skill:05-learn`
+- `05-learn` → `Completed`
+
+Then read `.pi/settings.json` → `pipeline.autoContinue`:
+- If `false` or missing, stop after the status block and wait for user input.
+- If current stage is `05-learn`, stop after status block.
+- If `true` and current stage is not `05-learn`, auto-continue is allowed only after stage-specific gates are satisfied:
+  - `01-brainstorm`: user has explicitly approved the design handoff.
+  - `02-plan`: review choice is resolved (A/B/C flow completed) and user confirmed to proceed.
+  - `04-review`: optional QA choice is resolved (A/B/C flow completed) and user confirmed to proceed.
+  - Any unclear/ambiguous state: do not auto-continue; stop and ask.
+- When gates are satisfied, automatically trigger the mapped next skill command.