@fyeeme/pi-review 2.0.0 → 2.1.0

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@fyeeme/pi-review",
-  "version": "2.0.0",
-  "description": "Review & cleanup extension for pi. Registers /code-review and /code-simplify commands plus a general-purpose `subagent` tool that spawns parallel pi subprocesses — providing the real fan-out capability the code-review and simplify skills (bundled under `skills/`) need for their multi-agent flows. The /code-simplify handler uses ctx.getContextUsage() to decide parallel vs single-pass mode deterministically.",
+  "version": "2.1.0",
+  "description": "Review & cleanup assets for pi: /code-review and /code-simplify commands dispatching declarative prompt templates (parallel strategy as frontmatter data) plus review methodology skills and finder/verifier agent definitions. Spawning lives in @fyeeme/pi-subagents; this package registers the review_report findings sink and the generic dispatcher.",
   "type": "module",
   "license": "MIT",
   "author": "fyeeme",
@@ -9,25 +9,29 @@
     "node": ">=18"
   },
   "keywords": [
-    "pi-package",
     "pi",
+    "pi-package",
     "code-review",
     "simplify",
     "cleanup",
-    "subagent",
-    "fan-out",
     "review"
   ],
   "files": [
     "*.ts",
     "src/**/*.ts",
     "skills/**/*.md",
+    "prompts/**/*.md",
+    "agents/**/*.md",
     "README.md",
     "LICENSE"
   ],
   "pi": {
     "extensions": [
       "./index.ts"
+    ],
+    "skills": [
+      "skills/code-review",
+      "skills/code-simplify"
     ]
   },
   "scripts": {
@@ -35,20 +39,18 @@
     "typecheck": "tsc"
   },
   "dependencies": {
-    "@fyeeme/pi-subagent-core": "^0.3.3"
+    "@fyeeme/pi-subagents": "2.1.1"
   },
   "peerDependencies": {
-    "@earendil-works/pi-ai": ">=0.84.1",
-    "@earendil-works/pi-coding-agent": ">=0.84.1",
-    "@earendil-works/pi-tui": ">=0.84.1",
-    "jiti": ">=2.0.0",
-    "typebox": ">=1.0.0",
-    "typescript": ">=5.0.0"
+    "@earendil-works/pi-ai": ">=0.84.4",
+    "@earendil-works/pi-coding-agent": ">=0.84.4",
+    "@earendil-works/pi-tui": ">=0.84.4",
+    "typebox": ">=1.0.0"
   },
   "devDependencies": {
-    "@earendil-works/pi-ai": "0.84.1",
-    "@earendil-works/pi-coding-agent": "0.84.1",
-    "@earendil-works/pi-tui": "0.84.1",
+    "@earendil-works/pi-ai": "0.85.1",
+    "@earendil-works/pi-coding-agent": "0.85.1",
+    "@earendil-works/pi-tui": "0.85.1",
     "@types/node": "22.19.19",
     "jiti": "2.7.0",
     "typebox": "1.1.38",

package/prompts/review.parallel.md

@@ -0,0 +1,23 @@
+---
+description: "/code-review trigger — xhigh/max deep sweep: finder/verifier/gap-hunt fan-out via the code-review skill"
+vars: [effort, effort-source, extra-args, skill, finder-max-turns, verifier-max-turns, gap-hunt-max-turns, verify]
+---
+Run a code review now. Effective effort: {{effort}} ({{effort-source}}){{extra-args}}.
+
+First load the code-review skill with the read tool: {{skill}}. Then follow its
+XHIGH/MAX FLOW exactly — dispatch the finder / verifier / gap-hunter agents it
+calls for through the `subagent` tool (bundled agents: finder-diff-scan,
+finder-removed-behavior, finder-cross-file, finder-language-pitfall,
+finder-wrapper-proxy, cleaner-reuse, cleaner-simplification,
+cleaner-efficiency, cleaner-altitude, finder-conventions, verifier,
+gap-hunter), with `maxTurns: {{finder-max-turns}}` per finder batch,
+`maxTurns: {{verifier-max-turns}}` per verifier and `maxTurns: {{gap-hunt-max-turns}}`
+for the gap-hunt as the skill instructs.
+
+The `subagent` tool is a pi extension tool in your session toolset — judge
+its availability from that list, never via `mcp` tool search (which only
+indexes MCP-server tools and cannot see extension tools).
+
+Verification guidance (the skill's `--fix` flow consumes it):
+
+{{verify}}

package/prompts/review.single.md

@@ -0,0 +1,16 @@
+---
+description: "/code-review trigger — single-pass main-session review via the code-review skill (low/medium/high)"
+vars: [effort, effort-source, extra-args, skill, verify, loop-note]
+---
+Run a code review now. Effective effort: {{effort}} ({{effort-source}}){{extra-args}}.
+
+First load the code-review skill with the read tool: {{skill}}. Then follow its
+SINGLE-PASS FLOW for effort {{effort}}: review the diff yourself in this
+session — read it, surface candidates against the skill's rubric, self-verify
+them (medium/high), and report via the `review_report` tool. No subagent
+fan-out at this level: do NOT dispatch finder or verifier agents, even though
+the `subagent` tool may be in your session toolset.
+{{loop-note}}
+Verification guidance (the skill's `--fix` flow consumes it):
+
+{{verify}}

package/prompts/simplify.parallel.md

@@ -0,0 +1,45 @@
+---
+description: "/code-simplify trigger — PARALLEL mode (4-agent fan-out via the subagent tool)"
+parallel-when:
+  context-below: 0.8
+  diff-chars-below: 400000
+vars: [target, scope-label, pct, git-command, context-package, skill, verify, simplify-max-turns]
+---
+Clean up the changed code now. Target: {{target}}.
+
+Dispatcher decided PARALLEL mode (context {{pct}} full; scope {{scope-label}}).
+Follow the phases IN ORDER — do not launch anything before Phase 0 is done.
+
+## Phase 0 — read the diff (visible, before any agent launches)
+
+{{context-package}}
+
+Run exactly this command (the dispatcher already resolved the scope — do not
+re-derive a different range):
+
+    {{git-command}}
+
+Read the full diff, then write a 2–4 line change-intent summary BEFORE
+launching anything — that summary and your first-hand reading are what you
+will use to merge, dedup, and judge the agents' findings in Phase 2.
+
+## Phase 1 — launch the 4 cleanup agents
+
+Call the `subagent` tool in parallel mode with 4 tasks, one per agent —
+cleaner-reuse, cleaner-simplification, cleaner-efficiency, cleaner-altitude —
+each task being: "Review the changed code of {{target}} for <angle> findings.
+Run this first to see the diff: {{git-command}}. Report file:line — one-line
+summary — the concrete cost." Set `maxTurns: {{simplify-max-turns}}` on the call (the slowest
+agent pins the wave's wall time; a capped agent still owes partial output).
+The agents' angle guidance rides their own definitions — do not write the
+agent prompts yourself or inline the diff anywhere. The tool's result carries
+the four findings reports.
+
+## Phase 2 — apply, verify, report
+
+When the tool result arrives, merge/dedup the findings against your Phase 0
+reading, then load {{skill}} via the read tool and follow its Phase 2
+(snapshot → apply → verify → auto-revert on failure → report via
+review_report with `fanned_out: true` — the 4-agent fan-out actually ran).
+Never apply changes the findings don't justify.
+{{verify}}

package/prompts/simplify.single.md

@@ -0,0 +1,23 @@
+---
+description: "/code-simplify trigger — SINGLE-PASS mode (angles worked inline, no fan-out)"
+vars: [target, reasons, scope-label, too-large, git-command, context-package, skill, verify]
+---
+Clean up the changed code now. Target: {{target}}.
+
+Dispatcher decided SINGLE-PASS mode ({{reasons}}). Scope: {{scope-label}}.
+
+## Phase 0 — read the diff first
+
+{{context-package}}
+
+Run exactly this command (the dispatcher already resolved the scope — do not
+re-derive a different range):
+
+    {{git-command}}
+
+Read the full diff, then write a 2–4 line change-intent summary before
+reviewing.{{too-large}}
+
+Then load {{skill}} via the read tool and follow its single-pass body. Work
+the four angles inline — do not fake fan-out.
+{{verify}}