@sebastianandreasson/pi-autonomous-agents 0.11.0 → 0.12.1

package/README.md

@@ -190,10 +190,13 @@ Common fields in `pi.config.json`:
 - `testCommand`
 - `visualReviewEnabled`
 - `visualCaptureCommand`
+- `failureArtifactDir`
 - `continueAfterSeconds`
 - `toolContinueAfterSeconds`
 - `noEventTimeoutSeconds`
 - `toolNoEventTimeoutSeconds`
+- `sameFileLoopBudget`
+- `loopHistoryLimit`
 - `largeFileWarningLines`
 - `largeSpecWarningLines`
 
@@ -207,6 +210,8 @@ Key defaults:
 - `toolContinueAfterSeconds`: `900`
 - `noEventTimeoutSeconds`: `900`
 - `toolNoEventTimeoutSeconds`: `1800`
+- `sameFileLoopBudget`: `2`
+- `loopHistoryLimit`: `25`
 
 ## Prompt and Tooling Behavior
 
@@ -217,6 +222,7 @@ The package is optimized for local models by default:
 - prompts prefer `read` for source inspection
 - shell is intended for `git`, tests, and narrow diagnostics
 - SDK transport carries forward oversized shell-read warnings and loop/timeout guards
+- repeated same-file loop failures are remembered across iterations and escalate the next edit strategy
 - the supervisor emits large-file/spec warnings when touched files are getting risky
 
 This is deliberate. Large monolith files, huge e2e specs, and broad TODO items are one of the main causes of local-model drift and retry loops.
@@ -255,6 +261,8 @@ Useful files during a run:
   Latest verification output snapshot.
 - `.pi-last-iteration.json`
   Structured summary of the last completed iteration.
+- `pi-output/failure-artifacts/`
+  Compact failure artifacts with command, exit code, changed files, tester summary, and output excerpt.
 - `.pi-state.json`
   Persistent harness state, including in-progress iteration data.
 - `pi.log`
@@ -264,7 +272,7 @@ Useful files during a run:
 - `.pi-runtime/active-run.json`
 - `.pi-runtime/runs/<runId>/...`
 
-`pi-harness report` summarizes recent telemetry and surfaces things like terminal reasons and large-file warnings.
+`pi-harness report` summarizes recent telemetry and surfaces things like terminal reasons, large-file warnings, and recent failure artifacts.
 
 `pi-harness run` now also starts lightweight local web UI for orchestration flow by default. By default it listens on `127.0.0.1:4317`. Override with `PI_VISUALIZER_HOST` and `PI_VISUALIZER_PORT`. Set `PI_VISUALIZER=0` to disable embedded web UI for a run.
 

package/docs/PI_SUPERVISOR.md

@@ -80,10 +80,13 @@ Projects typically provide their own `pi.config.json` with fields such as:
 - `visualCaptureCommand`
 - `visualFeedbackFile`
 - `testerFeedbackFile`
+- `failureArtifactDir`
 - `models`
 - `piModel`
 - `visualReviewModel`
 - `commitMode`
+- `sameFileLoopBudget`
+- `loopHistoryLimit`
 
 Model entries may carry their own OpenAI-compatible endpoint settings, so the PI text loop and the multimodal visual reviewer can point at different backends without changing code.
 
@@ -124,6 +127,10 @@ The default flow keeps commit ownership with the active agent:
 2. `tester` should review functionality and, on `PASS`, stage only the task-related files and create the commit directly.
 3. If the working tree is too messy to isolate safely, tester should return `VERDICT: BLOCKED` instead of guessing.
 
+If tester returns `PASS` but leaves a dirty tree without creating the commit, the harness now treats that as a protocol error and automatically falls back to a commit-plan follow-up instead of stalling the iteration.
+
+If tester edits files before finalization, the harness re-runs the configured smoke verification command immediately and records which files tester touched.
+
 If a repo explicitly needs the older harness-managed commit-plan flow, set `commitMode` to `plan`. In that mode, `testerCommit` and parsed commit plans are used as a compatibility path rather than the default.
 
 For source inspection, prompts prefer `read` and reserve shell usage for `git`, tests, and narrow diagnostics. Large shell file reads are more likely to truncate under context pressure than focused `read` calls.
@@ -175,6 +182,7 @@ SDK transport mitigates obvious local loops by watching agent and tool events:
 
 - repeated identical tool calls are aborted
 - repeated same-path churn is aborted
+- repeated same-file loop targets are persisted in harness state and escalate the next retry strategy
 - a soft `continue` can be sent after inactivity
 - a separate tool-aware watchdog can tolerate long-running `bash` or browser work without treating the turn as dead
 - a hard no-event timeout aborts a wedged turn instead of hanging indefinitely
@@ -200,4 +208,6 @@ Each step records:
 - changed file count
 - verification status
 - retry count
+- artifact path for compact failure diagnostics when available
+- output excerpt for failed verification-style events
 - notes

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@sebastianandreasson/pi-autonomous-agents",
   "private": false,
-  "version": "0.11.0",
+  "version": "0.12.1",
   "type": "module",
   "description": "Portable unattended PI harness for developer/tester/visual-review loops.",
   "license": "MIT",

package/src/cli.mjs

@@ -36,11 +36,14 @@ function main() {
   if (subcommand === 'once' || subcommand === 'run') {
     childArgs.push(subcommand)
   }
+  const childStdio = subcommand === 'once' || subcommand === 'run'
+    ? ['pipe', 'inherit', 'inherit']
+    : 'inherit'
 
   const child = spawn(process.execPath, childArgs, {
     cwd: process.cwd(),
     env: process.env,
-    stdio: 'inherit',
+    stdio: childStdio,
   })
   registerOwnedChildProcess(child)
 

package/src/pi-config.mjs

@@ -259,6 +259,7 @@ export function loadConfig(mode = 'once') {
     maxTesterFeedbackLines: readInt('PI_MAX_TESTER_FEEDBACK_LINES', file.maxTesterFeedbackLines, 32),
     maxPromptNotesLines: readInt('PI_MAX_PROMPT_NOTES_LINES', file.maxPromptNotesLines, 16),
     maxVerificationExcerptLines: readInt('PI_MAX_VERIFICATION_EXCERPT_LINES', file.maxVerificationExcerptLines, 40),
+    maxFailureArtifactLines: readInt('PI_MAX_FAILURE_ARTIFACT_LINES', file.maxFailureArtifactLines, 80),
     largeFileWarningLines: readInt('PI_LARGE_FILE_WARNING_LINES', file.largeFileWarningLines, 500),
     largeSpecWarningLines: readInt('PI_LARGE_SPEC_WARNING_LINES', file.largeSpecWarningLines, 300),
     piTools: readString('PI_TOOLS', file.piTools, 'read,edit,write,find,ls,bash'),
@@ -280,6 +281,8 @@ export function loadConfig(mode = 'once') {
     verificationTimeoutSeconds: readInt('PI_VERIFICATION_TIMEOUT', file.verificationTimeoutSeconds, 300),
     idleRetryLimit: readInt('PI_IDLE_RETRY_LIMIT', file.idleRetryLimit, 1),
     noChangeRetryLimit: readInt('PI_NO_CHANGE_RETRY_LIMIT', file.noChangeRetryLimit, 1),
+    sameFileLoopBudget: readInt('PI_SAME_FILE_LOOP_BUDGET', file.sameFileLoopBudget, 2),
+    loopHistoryLimit: readInt('PI_LOOP_HISTORY_LIMIT', file.loopHistoryLimit, 25),
     visualFeedbackFile: resolveFromCwd(
       cwd,
       'PI_VISUAL_FEEDBACK_FILE',
@@ -298,6 +301,12 @@ export function loadConfig(mode = 'once') {
       file.testerFeedbackHistoryDir,
       'pi-output/tester-feedback/history'
     ),
+    failureArtifactDir: resolveFromCwd(
+      cwd,
+      'PI_FAILURE_ARTIFACT_DIR',
+      file.failureArtifactDir,
+      'pi-output/failure-artifacts'
+    ),
     visualReviewHistoryDir: resolveFromCwd(
       cwd,
       'PI_VISUAL_REVIEW_HISTORY_DIR',

package/src/pi-prompts.mjs

@@ -54,6 +54,16 @@ function formatLargeFileRiskHint(warnings) {
   return `\nLarge file risk in touched files:\n${lines}\nPrefer helper extraction, smaller scoped edits, or test splitting over broad in-place edits.\n`
 }
 
+function formatLoopRecoveryHint(hints) {
+  const list = Array.isArray(hints) ? hints.filter(Boolean) : []
+  if (list.length === 0) {
+    return ''
+  }
+
+  const lines = list.slice(0, 3).map((hint) => `- ${hint}`).join('\n')
+  return `\nRecent loop-recovery constraints:\n${lines}\n`
+}
+
 function displayPath(config, filePath) {
   const relativePath = path.relative(config.cwd, filePath)
   if (
@@ -190,11 +200,13 @@ export function buildMainPrompt(config, options = {}) {
     config.developerInstructionsFile,
     config.usingBundledDeveloperInstructions,
   )
+  const loopRecoveryHint = formatLoopRecoveryHint(options.loopRecoveryHints)
 
   if (!config.usingBundledDeveloperInstructions) {
     return `Read ${taskFile} and ${instructionsFile}.
 ${authorityLine}${visualFeedbackSection}
 ${testerFeedbackSection}
+${loopRecoveryHint}
 
 Work only on the current phase.
 Select the first unchecked actionable checkbox in phase order.
@@ -220,6 +232,7 @@ Before stopping:
   return `Read ${taskFile} and ${instructionsFile}.
 ${authorityLine}${visualFeedbackSection}
 ${testerFeedbackSection}
+${loopRecoveryHint}
 
 Do one current-phase unchecked task.
 
@@ -254,12 +267,14 @@ export function buildFixPrompt(config, recentVerificationOutput, options = {}) {
   )
   const findings = clampLines(recentVerificationOutput, configMaxLines(config, 'maxVerificationExcerptLines', 40))
   const largeFileRiskHint = formatLargeFileRiskHint(options.largeFileWarnings)
+  const loopRecoveryHint = formatLoopRecoveryHint(options.loopRecoveryHints)
 
   if (!config.usingBundledDeveloperInstructions) {
     return `Read ${taskFile} and ${instructionsFile}.
 ${authorityLine}${visualFeedbackSection}
 ${testerFeedbackSection}
 ${largeFileRiskHint}
+${loopRecoveryHint}
 
 The tester step found a real problem in the current implementation. Fix only the product behavior related to the current phase and current task.
 
@@ -286,6 +301,7 @@ Before stopping:
 ${authorityLine}${visualFeedbackSection}
 ${testerFeedbackSection}
 ${largeFileRiskHint}
+${loopRecoveryHint}
 
 The tester step found a real problem in the current implementation. Fix only the product behavior related to the current phase and current task.
 
@@ -319,6 +335,7 @@ export function buildSteeringPrompt(config, reason, options = {}) {
     config.usingBundledDeveloperInstructions,
   )
   const largeFileRiskHint = formatLargeFileRiskHint(options.largeFileWarnings)
+  const loopRecoveryHint = formatLoopRecoveryHint(options.loopRecoveryHints)
 
   if (!config.usingBundledDeveloperInstructions) {
     return `Continue from the current repo state.
@@ -326,6 +343,7 @@ Read ${taskFile} and ${instructionsFile}.
 ${authorityLine}${visualFeedbackSection}
 ${testerFeedbackSection}
 ${largeFileRiskHint}
+${loopRecoveryHint}
 
 Reason for this follow-up: ${reason}
 
@@ -346,6 +364,7 @@ Read ${taskFile} and ${instructionsFile}.
 ${authorityLine}${visualFeedbackSection}
 ${testerFeedbackSection}
 ${largeFileRiskHint}
+${loopRecoveryHint}
 
 Reason for this follow-up: ${reason}
 

package/src/pi-repo.mjs

@@ -57,6 +57,7 @@ export async function readState(stateFile) {
       lastStatus: '',
       lastVerificationStatus: '',
       lastVisualStatus: '',
+      loopHistory: {},
       lastRunAt: '',
       runId: '',
       inProgress: null,
@@ -75,6 +76,7 @@ export async function readState(stateFile) {
       lastStatus: '',
       lastVerificationStatus: '',
       lastVisualStatus: '',
+      loopHistory: {},
       lastRunAt: '',
       runId: '',
       inProgress: null,
@@ -282,7 +284,8 @@ export function watchParentProcess(onParentExit, options = {}) {
     }
 
     const currentParentPid = normalizePid(process.ppid)
-    if (currentParentPid === expectedParentPid && currentParentPid > 1) {
+    const parentStillRunning = isProcessRunning(expectedParentPid)
+    if (currentParentPid === expectedParentPid && currentParentPid > 1 && parentStillRunning) {
       return
     }
 
@@ -483,7 +486,7 @@ function countLines(text) {
   return normalized.split('\n').length
 }
 
-function isSpecLikeFile(filePath) {
+export function isSpecLikeFile(filePath) {
   const normalized = String(filePath ?? '').replaceAll('\\', '/')
   return /(^|\/)(e2e|test|tests|spec|specs)\//.test(normalized)
     || /\.(spec|test)\.[cm]?[jt]sx?$/.test(normalized)

package/src/pi-report.mjs

@@ -46,6 +46,21 @@ async function main() {
     }
   }
 
+  const failureArtifacts = recent
+    .filter((event) => String(event.artifactPath ?? '').trim() !== '')
+    .slice(-5)
+
+  if (failureArtifacts.length > 0) {
+    console.log('\nFailure artifacts:')
+    for (const event of failureArtifacts) {
+      const excerpt = String(event.outputExcerpt ?? '').trim()
+      console.log(`- iteration ${event.iteration} ${event.kind}: ${event.artifactPath}`)
+      if (excerpt !== '') {
+        console.log(`  excerpt: ${excerpt.split('\n')[0]}`)
+      }
+    }
+  }
+
   const last = recent.at(-1)
   if (!last) {
     return