@sebastianandreasson/pi-autonomous-agents 0.2.0 → 0.4.0

package/src/pi-telemetry.mjs

@@ -1,6 +1,6 @@
 import fs from 'node:fs/promises'
 
-const CSV_HEADER = 'timestamp,iteration,phase,kind,status,transport,session_id,timed_out,exit_code,duration_seconds,commit_before,commit_after,repo_changed,changed_files_count,verification_status,retry_count,notes\n'
+const CSV_HEADER = 'timestamp,iteration,phase,kind,status,transport,session_id,timed_out,exit_code,duration_seconds,commit_before,commit_after,repo_changed,changed_files_count,verification_status,retry_count,role,model,tool_calls,tool_errors,message_updates,stop_reason,loop_detected,loop_signature,tester_verdict,commit_plan_found,terminal_reason,risk_warnings,notes\n'
 
 function csvEscape(value) {
   const text = String(value ?? '')
@@ -11,6 +11,8 @@ export async function ensureTelemetryFiles(config) {
   await fs.writeFile(config.lastAgentOutputFile, '', 'utf8')
   await fs.writeFile(config.lastVerificationOutputFile, '', 'utf8')
   await fs.writeFile(config.changedFilesFile, '', 'utf8')
+  await fs.writeFile(config.lastPromptFile, '', 'utf8')
+  await fs.writeFile(config.lastIterationSummaryFile, '', 'utf8')
 
   await fs.appendFile(config.logFile, '', 'utf8')
   await fs.appendFile(config.telemetryJsonl, '', 'utf8')
@@ -43,6 +45,18 @@ export async function appendTelemetry(config, event) {
     event.changedFilesCount,
     event.verificationStatus,
     event.retryCount,
+    event.role,
+    event.model,
+    event.toolCalls,
+    event.toolErrors,
+    event.messageUpdates,
+    event.stopReason,
+    event.loopDetected,
+    event.loopSignature,
+    event.testerVerdict,
+    event.commitPlanFound,
+    event.terminalReason,
+    event.riskWarnings,
     event.notes,
   ].map(csvEscape).join(',')
 

package/templates/DEVELOPER.md

@@ -20,6 +20,9 @@ Rules:
 - Use the configured smoke verification path as the fast inner-loop gate. Do not replace it with a long full-flow Playwright spec unless the task explicitly requires it.
 - If a long Playwright happy-path spec changes, validate with smoke plus one narrow targeted spec or deterministic state hook, not the entire full-flow run.
 - Reserve long full-flow Playwright specs for an explicit nightly or post-run lane, not the developer turn.
+- Use `read` for source inspection. Use shell only for `git`, tests, and narrow diagnostics.
+- If a snippet seems incomplete, reread a smaller exact window instead of another huge overlapping shell range.
+- Do not build edits from large `sed`/`grep` output or from memory after partial shell reads.
 - Trust tool output over your own guesses.
 - Do not repeatedly reread or rewrite the same file when one focused fix will do.
 - After one failed edit attempt, reread the file before retrying.

package/templates/TESTER.md

@@ -7,7 +7,7 @@ Your job:
 - review the developer's change from an independent user-facing perspective
 - add or improve focused verification where needed
 - verify actual functionality, not just plausibility
-- produce a commit plan when the work is truly ready
+- create the final commit only when the work is truly ready
 
 Rules:
 
@@ -16,6 +16,9 @@ Rules:
 - Run the configured smoke verification command as the default inner-loop gate.
 - Do not run long full-flow Playwright happy-path specs in the tester turn unless the task explicitly requires them.
 - If a long spec changed, validate with smoke plus one narrow targeted spec or deterministic state setup instead of replaying the entire run.
+- Use `read` for source inspection. Use shell only for `git`, tests, and narrow diagnostics.
+- If a snippet seems incomplete, reread a smaller exact window instead of another huge overlapping shell range.
+- Do not build edits from large `sed`/`grep` output or from memory after partial shell reads.
 - Treat player-facing dead ends, missing affordances, broken progression, console/runtime failures, and unusable UI as real failures.
 - If the task affects menus, unlocks, progression, classes, routes, shops, onboarding, or gating, verify a fresh-save path.
 - Do not hide product bugs by weakening tests.
@@ -23,7 +26,7 @@ Rules:
 - After one failed edit attempt, reread the file before retrying.
 - Do not repeat the same exact oldText-based edit on the same file.
 - If visual review is enabled, maintain the screenshot capture flow and manifest expected by the harness.
-- If the change passes, do not run `git add` or `git commit` yourself. Provide a commit plan for the harness instead.
+- If the change passes, stage only the related files and create the commit yourself.
 - If the working tree cannot be isolated safely, return `VERDICT: BLOCKED`.
 
 Before stopping:
@@ -31,7 +34,7 @@ Before stopping:
 - include `Observed flow:`
 - include `Player-facing result:`
 - include `Regression check:`
+- if passing, include `COMMIT_CREATED: true`
 - if passing, include `COMMIT_MESSAGE: ...`
-- if passing, include `COMMIT_FILES:`
-- if passing, include one `- path/to/file` line per file
+- if passing, include `COMMIT_SHA: ...`
 - end with exactly one verdict line: `VERDICT: PASS`, `VERDICT: FAIL`, or `VERDICT: BLOCKED`

package/templates/pi.config.example.json

@@ -4,6 +4,10 @@
   "taskFile": "TODOS.md",
   "developerInstructionsFile": "pi/DEVELOPER.md",
   "testerInstructionsFile": "pi/TESTER.md",
+  "commitMode": "agent",
+  "promptMode": "compact",
+  "largeFileWarningLines": 500,
+  "largeSpecWarningLines": 300,
   "piModel": "local/text-model",
   "models": {
     "local/text-model": {
@@ -32,7 +36,6 @@
     "developerFix": "local/text-model",
     "developerRetry": "local/text-model",
     "tester": "local/tester-model",
-    "testerCommit": "local/tester-model",
     "visualReview": "local/vision-model"
   },
   "testCommand": "pnpm test:e2e:smoke",