pi-agent-browser-native 0.2.69 → 0.2.70

package/CHANGELOG.md

@@ -1,5 +1,23 @@
 # Changelog
 
+## 0.2.70 - 2026-07-18
+
+### Changed
+
+- Removed unused TypeScript imports, locals, exports, declaration sidecars, compatibility barrels, inert `browser.defaultLaunchArgs` config handling, and duplicated platform/build orchestration while preserving the browser runtime contract.
+- Condensed completed plans and the historical support ledger into current ADR/decision indexes, removed obsolete archive material, and enabled `noUnusedLocals` for ongoing enforcement.
+- Kept one guaranteed build owner before every `dist/` consumer; package verification now lets `prepare` create a missing `dist/` before expanding the publish contract and forbids internal `docs/plans/` content by prefix.
+
+### Compatibility
+
+- Undocumented deep imports through `lib/results/shared.js` or `lib/orchestration/browser-run.js`, the inert `browser.defaultLaunchArgs` config field, unused named platform-config exports, and the redundant default-export `supportedTargets` platform-smoke property are no longer supported. Native `agent_browser` behavior and documented package entrypoints are unchanged.
+
+### Validation
+
+- Passed `npm run verify -- release` (587 tests passed, 2 opt-in skips), configured-source lifecycle, packaged Pi smoke, live command-reference verification, and macOS/Ubuntu/native-Windows Crabbox `platform-build` plus `browser-dogfood-smoke` suites.
+- Passed opt-in real-upstream, deterministic dogfood, benchmark, and startup-profile gates; the three-sample startup maximum was 51.9 ms against the 250 ms budget.
+- Passed a checkout-loaded Pi 0.80.10 tmux smoke on `example.com` and `react.dev`, including QA, fresh-session snapshot/link navigation, verified screenshot evidence, recovery from stale selector attempts, and zero active browser sessions after cleanup.
+
 ## 0.2.69 - 2026-07-17
 
 ### Changed

package/README.md

@@ -78,7 +78,7 @@ The result is optimized for agent work:
 | Auth/profile workflows can leak secrets | Supports `auth save --password-stdin` and redacts sensitive args, URLs, stdout/stderr, details, and parse-failure spills | `test/agent-browser.extension-security-redaction.test.ts` |
 | Stateful cookies/storage/auth output bloats or leaks context | Presentation layer redacts `details.data` for cookies and credential-like storage values while keeping low-risk local QA values such as `theme: dark` readable; recursively scrubs other structured upstream JSON (network, diff, trace/profiler, stream, dashboard, chat, auth, dialog, frame, state, and similar) using sensitive key names plus string heuristics; masks sensitive argv flags and positionals; scrubs secrets from failed batch step errors; and exposes a compact redacted `batch` matrix on top-level `details.data` | `extensions/agent-browser/lib/results/presentation.ts`, `extensions/agent-browser/lib/results/presentation/diagnostics.ts`, `extensions/agent-browser/lib/runtime.ts`, `test/agent-browser.presentation-diagnostics.test.ts` |
 | Stale `@eN` refs fail mysteriously | Records per-session `details.refSnapshot`, rejects mismatched URLs / unknown refs / unsafe `batch` stdin ordering before spawn, adds recovery guidance to rerun `snapshot -i` or use stable `find` locators | `extensions/agent-browser/index.ts`, `extensions/agent-browser/lib/session-page-state.ts`, `test/agent-browser.session-page-state.test.ts`, `test/agent-browser.results.test.ts`, `test/agent-browser.extension-ref-guards.test.ts`, `test/agent-browser.extension-semantic-recovery.test.ts` |
-| Agents need stable success/failure buckets | Exposes bounded `resultCategory`, `successCategory`, and `failureCategory` on tool `details` for branching without parsing prose; a `tool_result` hook also aligns real Pi `isError` semantics, naming `Pi tool isError: true` in prose output while preserving parseable caller-requested `--json` output | [`docs/TOOL_CONTRACT.md`](docs/TOOL_CONTRACT.md#details), `extensions/agent-browser/lib/results/categories.ts`, `extensions/agent-browser/lib/results/shared.ts` (re-export barrel), `extensions/agent-browser/index.ts`, `extensions/agent-browser/lib/pi-tool-rendering.ts`, `test/agent-browser.results.test.ts`, `test/agent-browser.extension-validation.test.ts`, `test/agent-browser.pi-pipeline.test.ts` |
+| Agents need stable success/failure buckets | Exposes bounded `resultCategory`, `successCategory`, and `failureCategory` on tool `details` for branching without parsing prose; a `tool_result` hook also aligns real Pi `isError` semantics, naming `Pi tool isError: true` in prose output while preserving parseable caller-requested `--json` output | [`docs/TOOL_CONTRACT.md`](docs/TOOL_CONTRACT.md#details), `extensions/agent-browser/lib/results/categories.ts`, `extensions/agent-browser/index.ts`, `extensions/agent-browser/lib/pi-tool-rendering.ts`, `test/agent-browser.results.test.ts`, `test/agent-browser.extension-validation.test.ts`, `test/agent-browser.pi-pipeline.test.ts` |
 | Clicks can report success without the page receiving the event | Top-level non-Electron direct `click` calls on `xpath=` targets or role-gated current `@e…` refs (`button`, `checkbox`, `menuitem`, `radio`, `switch`, `tab`) install a bounded target-specific DOM-event probe; eligible `@e…` refs use the latest snapshot role/name metadata, and duplicate-name refs use snapshot-order `duplicateIndex` rather than requiring a unique name. If upstream reports success but no trusted event reaches the resolved target, the wrapper fails the tool, exposes `details.clickDispatch`, and suggests explicit retry/inspect next actions (no in-page replay), including a nested-scroll `scrollintoview` action when the probe sees the target outside a scroll container or viewport. Unresolved locator clicks such as raw `find … click` are left upstream-owned to avoid false failures for frame-scoped targets. Other click results still expose `details.pageChangeSummary`, and unchanged-URL clicks can surface evidence-backed `details.overlayBlockers` candidates. | [`docs/TOOL_CONTRACT.md`](docs/TOOL_CONTRACT.md#details), `extensions/agent-browser/lib/orchestration/browser-run/click-dispatch.ts`, `extensions/agent-browser/lib/results/presentation/navigation.ts`, `test/agent-browser.presentation.test.ts`, `test/agent-browser.extension-click-dispatch.test.ts` |
 | Dashboard scroll commands can look successful while nothing moves | Samples viewport and prominent scroll-container positions around large top-level `scroll` calls on an existing or fresh managed session; unchanged positions produce `details.scrollNoop`, visible recovery guidance, and exact `nextActions` for snapshot/screenshot verification | [`docs/TOOL_CONTRACT.md`](docs/TOOL_CONTRACT.md#details), [`docs/COMMAND_REFERENCE.md`](docs/COMMAND_REFERENCE.md#core-page-and-element-commands), `test/agent-browser.extension-validation.test.ts` |
 | Dropdown/combobox clicks can focus or hit native option box-model errors | Adds first-class `select <selector> <value...>` paths through raw `args`, `semanticAction`, and `job`; for custom combobox clicks, detects focused controls with explicit `aria-expanded` state but no visible options and returns `details.comboboxFocus` plus exact recovery `nextActions` | [`docs/TOOL_CONTRACT.md`](docs/TOOL_CONTRACT.md#details), [`docs/COMMAND_REFERENCE.md`](docs/COMMAND_REFERENCE.md#core-page-and-element-commands), `extensions/agent-browser/lib/input-modes/semantic-action.ts`, `test/agent-browser.extension-input-modes.test.ts`, `test/agent-browser.extension-validation.test.ts` |
@@ -601,7 +601,7 @@ For larger local handoffs or PR-ready confidence before expensive release/lifecy
 npm run verify -- pre-pr
 ```
 
-That mode composes the full default gate with `npm run verify -- package`, so package contents and forbidden archived/repo-only files are checked without launching Pi lifecycle, Crabbox, or live dogfood flows. Package, package-pi, lifecycle, platform-target, and startup-profile modes all build `dist/` first so clean checkouts do not validate stale or missing compiled output. GitHub/source installs run the package `prepare` script; when Pi installs with `npm install --omit=dev`, that script installs the source-build dev dependencies with lifecycle scripts disabled before building the ignored `dist/` entrypoint that Pi loads.
+That mode composes the full default gate with `npm run verify -- package`, so package contents and forbidden repo-only files are checked without launching Pi lifecycle, Crabbox, or live dogfood flows. Package modes build through npm `prepare`; lifecycle and startup-profile build in their focused scripts; default and platform-target build before consuming `dist/`, so clean checkouts do not validate stale or missing compiled output. The same `prepare` script owns GitHub/source installs; when Pi installs with `npm install --omit=dev`, it installs the source-build dev dependencies with lifecycle scripts disabled before building the ignored `dist/` entrypoint that Pi loads.
 
 The deterministic agent-efficiency benchmark’s **standalone JSON/Markdown accounting run** is not part of default or pre-PR `npm run verify` (only `npm run verify -- benchmark` or `npm run benchmark:agent-browser` invokes the script). The full unit suite still exercises `test/agent-browser.efficiency-benchmark.test.ts`. Use the script before and after agent-facing abstractions to prove call-count, output-size, stale-ref, artifact, failure-category coverage, success-rate, and elapsed-time effects before changing the wrapper UX:
 

package/dist/extensions/agent-browser/index.js

@@ -15,21 +15,20 @@ import { createEphemeralSessionSeed, createFreshSessionName, createImplicitSessi
 import { isRecord } from "./lib/parsing.js";
 import { buildPromptPolicy, getLatestUserPrompt, shouldAppendBrowserSystemPrompt } from "./lib/prompt-policy.js";
 import { isCloseCommand } from "./lib/command-taxonomy.js";
-import { cleanupSecureTempArtifacts, } from "./lib/temp.js";
+import { cleanupSecureTempArtifacts } from "./lib/temp.js";
 import { AGENT_BROWSER_PARAMS, } from "./lib/input-modes.js";
 import { parseAllowedDomainsPolicyFromArgs } from "./lib/navigation-policy.js";
-import { closeManagedSession, getSessionContextKey, runAgentBrowserTool } from "./lib/orchestration/browser-run.js";
+import { closeManagedSession, getSessionContextKey, runAgentBrowserTool } from "./lib/orchestration/browser-run/index.js";
 import { findElectronLaunchRecordForSession, getActiveElectronRecords } from "./lib/orchestration/browser-run/session-state.js";
 import { parseBatchStdinJsonArray } from "./lib/orchestration/batch-stdin.js";
 import { ELECTRON_POST_COMMAND_STATUS_SETTLE_MS, ELECTRON_PROFILE_ISOLATION_DETAILS, cleanupActiveElectronHostLaunches, handleElectronHostInput, restoreElectronLaunchRecordsFromBranch, } from "./lib/orchestration/electron-host/index.js";
 import { buildValidationFailureResult, resolveAgentBrowserInput } from "./lib/orchestration/input-plan.js";
 import { applyAgentBrowserOutputPath } from "./lib/orchestration/output-file.js";
-import { isSessionArtifactManifest, } from "./lib/results/artifact-manifest.js";
+import { isSessionArtifactManifest } from "./lib/results/artifact-manifest.js";
 import { canRegisterWebSearchTool, loadAgentBrowserConfigSync } from "./lib/config.js";
 import { createAgentBrowserWebSearchTool } from "./lib/web-search.js";
 import { isDirectAgentBrowserBashAllowed, isHarmlessAgentBrowserInspectionCommand, looksLikeDirectAgentBrowserBash, } from "./lib/bash-guard.js";
 import { AgentBrowserResultComponent, buildAgentBrowserToolResultPatch, formatAgentBrowserRenderCall, formatAgentBrowserRenderResult, } from "./lib/pi-tool-rendering.js";
-const DEFAULT_SESSION_MODE = "auto";
 function isBashToolCallEvent(event) {
     if (!isRecord(event) || event.toolName !== "bash" || !isRecord(event.input))
         return false;

package/dist/extensions/agent-browser/lib/config-policy.js

@@ -16,7 +16,7 @@ import { join, resolve } from "node:path";
 /** @typedef {{ provider: WebSearchProvider; apiKeyEnv: string; configKey: WebSearchProviderConfigKey; label: string }} WebSearchProviderDescriptor */
 /** @typedef {{ name: string; policy?: BrowserDefaultProfilePolicy }} BrowserDefaultProfileConfig */
 /** @typedef {{ enabled?: boolean; preferredProvider?: WebSearchProvider; braveApiKey?: string; exaApiKey?: string }} WebSearchConfig */
-/** @typedef {{ defaultProfile?: BrowserDefaultProfileConfig; executablePath?: string; defaultLaunchArgs?: string[] }} BrowserConfig */
+/** @typedef {{ defaultProfile?: BrowserDefaultProfileConfig; executablePath?: string }} BrowserConfig */
 /** @typedef {{ version?: 1; webSearch?: WebSearchConfig; browser?: BrowserConfig }} AgentBrowserConfig */
 /** @typedef {{ config: AgentBrowserConfig; path: string; scope: ConfigLayerScope }} ConfigLayer */
 /** @typedef {{ kind: CredentialSourceKind; provider?: WebSearchProvider; rawValue: string; scope: AgentBrowserConfigScope }} CredentialSource */
@@ -155,21 +155,6 @@ function validateString(value, path, errors) {
     }
     return value;
 }
-/**
- * @param {unknown} value
- * @param {string} path
- * @param {string[]} errors
- * @returns {string[] | undefined}
- */
-function validateStringArray(value, path, errors) {
-    if (value === undefined)
-        return undefined;
-    if (!Array.isArray(value) || value.some((entry) => typeof entry !== "string")) {
-        errors.push(`${path} must be an array of strings.`);
-        return undefined;
-    }
-    return value;
-}
 /**
  * @param {unknown} value
  * @param {string} path
@@ -244,12 +229,11 @@ export function isProjectSafeCredentialValueForProvider(rawValue, provider) {
 /**
  * @param {unknown} value
  * @param {string} path
- * @param {ConfigLayerScope} scope
  * @param {string[]} errors
  * @param {string[]} warnings
  * @returns {AgentBrowserConfig | undefined}
  */
-export function validateAgentBrowserConfig(value, path, scope, errors, warnings) {
+export function validateAgentBrowserConfig(value, path, errors, warnings) {
     if (!isRecord(value)) {
         errors.push(`${path} must contain a JSON object.`);
         return undefined;
@@ -297,11 +281,6 @@ export function validateAgentBrowserConfig(value, path, scope, errors, warnings)
             if (executablePath) {
                 config.browser.executablePath = executablePath;
             }
-            const defaultLaunchArgs = validateStringArray(value.browser.defaultLaunchArgs, `${path}.browser.defaultLaunchArgs`, errors);
-            if (defaultLaunchArgs) {
-                config.browser.defaultLaunchArgs = defaultLaunchArgs;
-                warnings.push(`${path}.browser.defaultLaunchArgs is recorded for future use; current releases do not auto-inject default launch args.`);
-            }
         }
     }
     for (const key of Object.keys(value)) {
@@ -328,7 +307,7 @@ export function parseAgentBrowserConfigLayer(raw, path, scope, errors, warnings)
         errors.push(`Could not parse ${scope} config ${path}: ${error instanceof Error ? error.message : String(error)}`);
         return undefined;
     }
-    const config = validateAgentBrowserConfig(parsed, path, scope, errors, warnings);
+    const config = validateAgentBrowserConfig(parsed, path, errors, warnings);
     return config ? { config, path, scope } : undefined;
 }
 /**

package/dist/extensions/agent-browser/lib/config.js

@@ -106,17 +106,3 @@ export async function resolvePreferredWebSearchCredential(state, options = {}) {
     }
     return undefined;
 }
-export async function hasResolvableCredentialSource(state, options = {}) {
-    if (!state.webSearchEnabled || state.errors.length > 0)
-        return false;
-    for (const provider of getWebSearchProviderOrder(state)) {
-        const source = getWebSearchCredentialSource(state, provider);
-        if (!source)
-            continue;
-        if (source.kind === "command")
-            return true;
-        if ((await resolveCredentialSource(source, options))?.value)
-            return true;
-    }
-    return false;
-}

package/dist/extensions/agent-browser/lib/orchestration/browser-run/prepare.js

@@ -296,7 +296,7 @@ export async function resolveSemanticActionVisibleRefArgs(options) {
     return resolveSemanticActionVisibleRefArgsFromSnapshot(options.compiled, snapshotData);
 }
 export async function prepareBrowserRun(options) {
-    const { cwd, implicitSessionIdleTimeoutMs, onUpdate, params, signal, state } = options;
+    const { cwd, onUpdate, params, signal, state } = options;
     const { sessionPageState, traceOwners, managedSessionBaseName, ephemeralSessionSeed } = state;
     let freshSessionOrdinal = state.freshSessionOrdinal;
     const { compiledElectron, compiledJob, compiledNetworkSourceLookup, compiledQaPreset, compiledSemanticAction, compiledSourceLookup, redactedArgs, redactedCompiledElectron, redactedCompiledJob, redactedCompiledNetworkSourceLookup, redactedCompiledQaPreset, redactedCompiledSemanticAction, redactedCompiledSourceLookup, toolArgs, toolStdin, } = normalizeRunInput(options.input);

package/dist/extensions/agent-browser/lib/playbook.js

@@ -79,13 +79,6 @@ export const WRAPPER_TAB_RECOVERY_BEHAVIOR = [
     "For sessions with observed tab-drift risk, after a successful command on a known target tab, agent_browser also best-effort restores that intended tab if a restored/background tab steals focus after the command completes. Routine same-session commands skip this post-command tab-list probe.",
     "If a known session target unexpectedly reports about:blank, agent_browser best-effort re-selects the prior intended target when it still exists; if recovery fails, it records the observed about:blank target and reports exact recovery guidance instead of treating the prior page as active.",
 ];
-export function buildSharedBrowserPlaybookGuidelines(options) {
-    return [
-        SHARED_BROWSER_PLAYBOOK_GUIDELINES[0],
-        ...(options.includeWebSearch ? [WEB_SEARCH_PROMPT_GUIDELINE] : []),
-        ...SHARED_BROWSER_PLAYBOOK_GUIDELINES.slice(1),
-    ];
-}
 /** Tier A: always-on tool promptGuidelines (keep small; Tier B lives in SHARED_BROWSER_PLAYBOOK_GUIDELINES and docs). */
 export const RUNTIME_PROMPT_GUIDELINES = [
     "Use agent_browser with one input mode: args, semanticAction, job, qa, sourceLookup/networkSourceLookup, or electron. stdin only for batch/eval/auth/wrapper batch; electron rejects stdin; never pass --json.",

package/dist/extensions/agent-browser/lib/results/editable-ref-evidence.js

@@ -69,6 +69,3 @@ export function getEditableRefEvidence(options) {
         hasPositiveEvidence = true;
     return hasPositiveEvidence ? true : undefined;
 }
-export function hasPositiveEditableRefEvidence(options) {
-    return getEditableRefEvidence(options) === true;
-}

package/dist/extensions/agent-browser/lib/runtime.js

@@ -779,7 +779,6 @@ export function buildExecutionPlan(args, options) {
     const startupScopedFlags = getStartupScopedFlags(args).filter((flag) => !(flag === "--namespace" && explicitNamespace === options.managedSessionNamespace));
     const plainTextInspection = isPlainTextInspectionArgs(args);
     const argvDescriptor = parseArgvDescriptor(args);
-    const commandTokens = argvDescriptor.commandTokens;
     const commandInfo = argvDescriptor.commandInfo;
     const commandNeedsManagedSession = !plainTextInspection && needsManagedSession(argvDescriptor);
     const effectiveArgs = plainTextInspection ? [...args] : args.includes("--json") ? [] : ["--json"];

package/docs/ARCHITECTURE.md

@@ -109,7 +109,7 @@ Why:
 - keeps reload and exact-session relaunch validation tied to Pi's configured-source lifecycle instead of an isolated quick-test path, while `session_tree` state changes stay covered by focused extension harness tests
 - keeps the published tarball focused on the package manifest, extension code, canonical docs, and license
 
-The published package should exclude agent-only and superseded repo materials such as `AGENTS.md`, archived drafts under `docs/archive/`, and other internal planning notes.
+The published package should exclude agent-only and internal planning materials such as `AGENTS.md` and `docs/plans/`.
 
 ## Session model
 
@@ -206,7 +206,7 @@ Upstream restore-state persistence remains upstream-owned. The wrapper passes `A
 - subprocess execution and JSON parsing through `buildAgentBrowserProcessEnv` in `extensions/agent-browser/lib/process.ts`: copies the parent process environment so user-approved provider credentials and other runtime variables reach upstream, then applies wrapper overrides such as the managed socket directory and clamped default operation timeout
 - clear missing-binary errors
 - compact result summaries, including presentation-time redaction: stateful browser-context commands (`auth`, `cookies`, `storage`, `dialog`, `frame`, `state`) use field-aware value redaction and compact formatters, while other structured upstream JSON (for example `network`, `diff`, `trace` / `profiler` / `record`, `console` / `errors` / `highlight` / `inspect` / `clipboard`, `stream`, `dashboard`, and `chat`) is passed through `redactPresentationData` in `extensions/agent-browser/lib/results/presentation.ts` so model-facing `details.data` and batch roll-ups stay compact and do not echo bearer tokens, proxy passwords, or similar fields verbatim; `redactInvocationArgs` in `extensions/agent-browser/lib/runtime.ts` masks trailing values for sensitive global flags such as `--body`, `--headers`, `--password`, and `--proxy`, preserves positional rules for `cookies set` and `storage local|session set`, and nested `batch` steps use the same argv and error-body scrubbing before echoing commands or errors
-- bounded machine-readable outcome metadata on tool `details` (`resultCategory`, `successCategory`, `failureCategory`, optional `nextActions`, optional `pageChangeSummary` with per-step summaries on `batch`, optional `artifactVerification` with the same shape on each successful `batchSteps[]` row) so agents can branch without parsing prose; enums, classifier precedence, and generic follow-up payloads are implemented under `extensions/agent-browser/lib/results/` in focused modules (`contracts.ts` for shared types, `categories.ts` for `classifyAgentBrowserSuccessCategory` / `classifyAgentBrowserFailureCategory` / `buildAgentBrowserResultCategoryDetails`, `action-recommendations.ts` for `buildAgentBrowserNextActions`, `next-actions.ts` for the `AgentBrowserNextAction` shape and merge helpers, `recovery-actions.ts` for recovery id registries and `buildRecoveryNextActions`, `network.ts` for `classifyNetworkRequestFailure` / `summarizeNetworkFailures`, and related helpers; `shared.ts` in that directory is a **re-export-only** barrel so historical `./results/shared.js` imports keep working without growing a monolith). Per-session tab target, `refSnapshot` alignment, invalidation, and tab pinning observations flow through `extensions/agent-browser/lib/session-page-state.ts` from `extensions/agent-browser/index.ts`. Compact page-change summaries and artifact verification rollups are built in `extensions/agent-browser/lib/results/presentation.ts` (`buildPageChangeSummary`, `buildArtifactVerificationSummary`), and the human contract lives in [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details). Real Pi custom tools otherwise only mark a row failed when `execute` throws, so the extension also registers `pi.on("tool_result", …)` and patches `agent_browser` results whose `details.resultCategory` is `failure` to set `isError: true`. Prose results also receive a short category notice, while caller-requested `--json` results with parseable JSON content keep that text unchanged so JSONL transcripts, UI affordances, and the machine-readable contract stay aligned for wrapper-side reclassifications such as `qa-failure` (`buildAgentBrowserToolResultPatch` in `extensions/agent-browser/lib/pi-tool-rendering.ts`; transcript semantics in the same contract doc)
+- bounded machine-readable outcome metadata on tool `details` (`resultCategory`, `successCategory`, `failureCategory`, optional `nextActions`, optional `pageChangeSummary` with per-step summaries on `batch`, optional `artifactVerification` with the same shape on each successful `batchSteps[]` row) so agents can branch without parsing prose; enums, classifier precedence, and generic follow-up payloads are implemented under `extensions/agent-browser/lib/results/` in focused modules (`contracts.ts` for shared types, `categories.ts` for `classifyAgentBrowserSuccessCategory` / `classifyAgentBrowserFailureCategory` / `buildAgentBrowserResultCategoryDetails`, `action-recommendations.ts` for `buildAgentBrowserNextActions`, `next-actions.ts` for the `AgentBrowserNextAction` shape and merge helpers, `recovery-actions.ts` for recovery id registries and `buildRecoveryNextActions`, `network.ts` for `classifyNetworkRequestFailure` / `summarizeNetworkFailures`, and related helpers). Per-session tab target, `refSnapshot` alignment, invalidation, and tab pinning observations flow through `extensions/agent-browser/lib/session-page-state.ts` from `extensions/agent-browser/index.ts`. Compact page-change summaries and artifact verification rollups are built in `extensions/agent-browser/lib/results/presentation.ts` (`buildPageChangeSummary`, `buildArtifactVerificationSummary`), and the human contract lives in [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details). Real Pi custom tools otherwise only mark a row failed when `execute` throws, so the extension also registers `pi.on("tool_result", …)` and patches `agent_browser` results whose `details.resultCategory` is `failure` to set `isError: true`. Prose results also receive a short category notice, while caller-requested `--json` results with parseable JSON content keep that text unchanged so JSONL transcripts, UI affordances, and the machine-readable contract stay aligned for wrapper-side reclassifications such as `qa-failure` (`buildAgentBrowserToolResultPatch` in `extensions/agent-browser/lib/pi-tool-rendering.ts`; transcript semantics in the same contract doc)
 - inline screenshots/images for the plain `screenshot` command; other image-like saves (for example `diff screenshot`) still appear in `details.artifacts` and summaries but are not auto-inlined as Pi image attachments (see [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details))
 - lightweight session convenience
 - docs, including a repo-readable command reference that mirrors the blocked direct-binary help path closely enough for normal agent work

package/docs/ELECTRON.md

@@ -364,8 +364,8 @@ Electron support is gated by the same release evidence as the rest of the wrappe
 
 - `RQ-0096` in [`SUPPORT_MATRIX.md`](SUPPORT_MATRIX.md) records the contract, runtime, test, and verification coverage.
 - `electron-lifecycle` and `electron-probe` scenarios in `scripts/agent-browser-efficiency-benchmark.mjs` track the token-efficiency claim deterministically (no real browser, no real launches).
-- Fake-upstream coverage for Electron schema/probe/mismatch/post-command-health/fill-verification/broad-text/discovery-sensitivity lives in `test/agent-browser.extension-validation.test.ts`.
-- Real-app validation is a manual `tmux` smoke pass per the maintainer notes in `AGENTS.md`; the 2026-05-21 dogfood result is recorded in the repo-local `docs/plans/electron-extension-2026-05-20.md` plan.
+- Fake-upstream Electron discovery and lifecycle coverage lives in `test/agent-browser.extension-electron-discovery.test.ts` and `test/agent-browser.extension-electron-lifecycle.test.ts`; ref/session recovery coverage lives in `test/agent-browser.extension-ref-guards.test.ts`, with shared validation paths in `test/agent-browser.extension-validation.test.ts`.
+- Real-app validation is a manual `tmux` smoke pass per the maintainer notes in `AGENTS.md`; the 2026-05-21 dogfood result and resulting decision are summarized in the repo-local [`Electron ADR`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/plans/electron-extension-2026-05-20.md).
 
 Run the local gate the same way as the rest of the project:
 

package/docs/RELEASE.md

@@ -173,8 +173,8 @@ Maintainer constraints for evolving scenarios and version bumps are summarized u
 - no repo-local `.pi/extensions/agent-browser.ts` autoload shim is present
 - `LICENSE` exists in the repo and the packed tarball
 - canonical published docs are present
-- `npm pack --json --dry-run` runs the `prepack` build and packs the compiled `dist/extensions/agent-browser/index.js` entrypoint
-- GitHub/source installs run the package `prepare` build; when Pi installs with `npm install --omit=dev`, `scripts/prepare.mjs` installs source-build dev dependencies with lifecycle scripts disabled before building so Pi can load the ignored compiled `dist/extensions/agent-browser/index.js` entrypoint from a fresh clone
+- `npm pack --json --dry-run` runs the package `prepare` build once and packs the compiled `dist/extensions/agent-browser/index.js` entrypoint
+- GitHub/source installs use the same `prepare` build; when Pi installs with `npm install --omit=dev`, `scripts/prepare.mjs` installs source-build dev dependencies with lifecycle scripts disabled before building so Pi can load the ignored compiled entrypoint from a fresh clone
 - the package-level doctor command and capability baseline are present
 - compiled extension runtime files are present, including the split result-rendering modules required by the published facade
 - source-only, agent-only, and superseded docs are absent from the tarball
@@ -192,7 +192,7 @@ The packaged execution smoke intentionally uses a temporary fake `agent-browser`
 Current forbidden packed files include:
 
 - `AGENTS.md`
-- archived planning drafts under `docs/archive/`
+- internal planning docs under `docs/plans/`
 - `.pi/extensions/agent-browser.ts`
 - TypeScript extension source and other test/repo-only maintenance files
 

package/docs/REQUIREMENTS.md

@@ -81,7 +81,7 @@ Define the product requirements and constraints for `pi-agent-browser-native`.
 - Because direct-binary usage is commonly blocked in normal agent sessions, the repo must carry a local command reference for the effective `agent_browser` surface and keep it in sync with upstream changes.
 - Repository verification must include a lightweight command-reference drift check against the targeted installed upstream `agent-browser` version.
 - Published package contents should include the canonical user-facing docs plus `LICENSE`.
-- Published package contents should exclude agent-only and superseded docs such as `AGENTS.md` and archived drafts under `docs/archive/`.
+- Published package contents should exclude agent-only and internal planning docs such as `AGENTS.md` and `docs/plans/`.
 
 ### Testing guidance
 
@@ -114,7 +114,7 @@ The design should comfortably support workflows such as:
 - Package-manifest behavior matters more than repo-local development wiring.
 - The extension should use official `pi` hooks and package resources where possible.
 - The wrapper should stay thin, with upstream `agent-browser` remaining the source of truth for command semantics.
-- Successful and failed tool outcomes should surface bounded machine-readable fields on Pi-facing `details` (`resultCategory`, `successCategory`, `failureCategory`, optional structured `nextActions`, optional `pageChangeSummary` with per-step summaries on `batch`, optional `artifactVerification` with the same shape on successful `batchSteps[]` rows, optional `outputFile`, optional `timeoutPartialProgress`) so agents can branch without parsing prose; stateful commands (`auth`, `cookies`, `storage`, `dialog`, `frame`, `state`) plus other structured diagnostics (for example `network`, `diff`, `trace`, `stream`, `dashboard`, `chat`) and `batch` should redact secret-bearing payloads in model-facing `details.data`, including the compact per-step `batch` roll-up on the parent result (full per-step payloads live on `batchSteps[]`). Dialog/prompt-related timeouts should be bounded with recovery `nextActions`; non-dialog timeouts should prefer best-effort per-step progress and retry payloads when a plan is available; no-op scrolls should expose no-movement state instead of only an upstream success boolean; explicit page/container scroll helpers should expose before/after movement evidence. The contract lives in [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details), enums and classifier precedence live in `extensions/agent-browser/lib/results/categories.ts` and `contracts.ts` (also re-exported from `shared.ts`), and presentation-time summaries, redaction, network request follow-ups, and artifact verification rollups are assembled in `extensions/agent-browser/lib/results/presentation.ts` (`buildPageChangeSummary`, command taxonomy predicates from `command-taxonomy.ts`, `redactPresentationData`, `buildArtifactVerificationSummary`, `buildBatchPresentation`).
+- Successful and failed tool outcomes should surface bounded machine-readable fields on Pi-facing `details` (`resultCategory`, `successCategory`, `failureCategory`, optional structured `nextActions`, optional `pageChangeSummary` with per-step summaries on `batch`, optional `artifactVerification` with the same shape on successful `batchSteps[]` rows, optional `outputFile`, optional `timeoutPartialProgress`) so agents can branch without parsing prose; stateful commands (`auth`, `cookies`, `storage`, `dialog`, `frame`, `state`) plus other structured diagnostics (for example `network`, `diff`, `trace`, `stream`, `dashboard`, `chat`) and `batch` should redact secret-bearing payloads in model-facing `details.data`, including the compact per-step `batch` roll-up on the parent result (full per-step payloads live on `batchSteps[]`). Dialog/prompt-related timeouts should be bounded with recovery `nextActions`; non-dialog timeouts should prefer best-effort per-step progress and retry payloads when a plan is available; no-op scrolls should expose no-movement state instead of only an upstream success boolean; explicit page/container scroll helpers should expose before/after movement evidence. The contract lives in [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details), enums and classifier precedence live in `extensions/agent-browser/lib/results/categories.ts` and `contracts.ts`, and presentation-time summaries, redaction, network request follow-ups, and artifact verification rollups are assembled in `extensions/agent-browser/lib/results/presentation.ts` (`buildPageChangeSummary`, command taxonomy predicates from `command-taxonomy.ts`, `redactPresentationData`, `buildArtifactVerificationSummary`, `buildBatchPresentation`).
 - User-facing docs belong in `README.md` and the canonical published files under `docs/`.
 - Agent workflow and deeper testing procedures can stay in `AGENTS.md`, but published docs must not depend on that file being present.
 - When upstream `agent-browser` changes, refresh the local command reference, prompt guidance, and other extension-side docs so agents still have a repo-readable equivalent of the blocked direct-binary help path.
@@ -130,8 +130,3 @@ The design should comfortably support workflows such as:
 - Upstream restore-state periodic autosave remains upstream-owned. Forward `AGENT_BROWSER_AUTOSAVE_INTERVAL_MS` unchanged, document its 30-second default and `0` disable behavior, and do not duplicate its timer or claim its restore files as wrapper artifacts.
 - Read-only upstream `skills list`, `skills get …`, and `skills path …` must stay free of implicit managed `--session` under default `sessionMode: "auto"` (still with `--json`), matching plain-text `--help` / `--version` inspection semantics so bundled skill text does not pin or rotate the active browser session; new `skills` subcommands pick up that behavior only after allowlisting in `extensions/agent-browser/lib/runtime.ts` with regression coverage.
 - Optional `semanticAction.session` on native `agent_browser` must compile to a leading `--session <name>` pair before upstream `find` or `select` argv so the shorthand can target a named upstream browser without hand-built `args`, while `buildExecutionPlan` still skips double-injecting the extension-managed implicit session whenever planned argv already starts with `--session`; stale-ref retries for compiled `find` actions and bounded `try-*` candidate `nextActions` must preserve that same prefix. Contract in [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#semanticaction) / [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#sessionmode); implementation in `extensions/agent-browser/index.ts` and `extensions/agent-browser/lib/runtime.ts`.
-
-## Open design questions
-
-- How much session convenience should the extension add by default versus leaving explicit session naming entirely to upstream `agent-browser` semantics?
-- Exactly which high-value result renderers belong in v1 beyond screenshots/images and a few compact summaries?

package/docs/SUPPORT_MATRIX.md

@@ -32,9 +32,9 @@ When upstream ships a new `agent-browser` or the inventory changes:
 - High-priority support gaps: 2026-05-26 audit found sessionless local commands and command-scoped value flags needed sharper wrapper handling; runtime/tests/docs now cover those paths. The 0.28.0 rebaseline added local `mcp` and `plugin` surfaces plus plugin-backed credential login; wrapper docs/tests mark `mcp` and known `plugin` commands sessionless, with no compatibility shim for older upstream releases. The 0.29.1 rebaseline added upstream `@agent-browser/sandbox` helper-package guidance and stricter `install --with-deps` failure semantics; no new wrapper runtime mode or bundled dependency was required. The 0.30.1 rebaseline fixed upstream `wait --url` glob matching, so constrained `job.assertUrl` delegates glob and exact patterns directly to `wait --url`. The 0.31.0 rebaseline adds restore workflow and namespace/session lifecycle surfaces (`--restore`, restore checks, `--namespace`, `session id`, and `session info`) without adding a wrapper compatibility layer. The 0.31.1 rebaseline fixes upstream React renderer selection for `react tree`, `react inspect`, and `react suspense`; no wrapper runtime change was required. The 0.31.2 rebaseline adds the local-launch-only `--webgpu` preset and `doctor --webgpu`, plus periodic restore-state autosaves controlled by `AGENT_BROWSER_AUTOSAVE_INTERVAL_MS`; the wrapper treats WebGPU as launch-scoped and leaves autosave ownership upstream. The 0.32.0 rebaseline hardens request/worker/popup/WebRTC containment behind `--allowed-domains`, fixes waits against already-complete documents, and adds a separate `@agent-browser/eve` package; the wrapper makes containment launch-scoped, retains its final-URL check as defense in depth, and adds no Eve-specific mode. The 0.32.1–0.32.2 rebaseline updates only eve compatibility/packaging, but the full current-surface audit also found the local reference had omitted upstream `read [url]` since 0.30.0; baseline/help sampling, content-first presentation, tab-target preservation, timeout budgeting, docs, and tests now cover it. Remaining upstream-owned caveat: current help still mentions `wait <selector> --state hidden` / `detached` and `find ... uncheck`, but runtime probes show those advertised shapes still fail, so wrapper docs keep `wait --fn` predicates and direct `uncheck` passthrough guidance.
 - Post-`v0.2.29` review state: commits `eb55320` through `86abbfb` add browser guidance/smoke coverage plus `RQ-0086` click-probe reduction, `RQ-0087` same-snapshot form fill batching, `RQ-0088` current-ref fallback on locator misses, `RQ-0089` direct-upstream click mutation investigation, and `RQ-0090` stop-boundary/artifact-path guidance. Verification gates below were rerun on 2026-05-18 after those tasks landed. Constrained `job` (`RQ-0064`), the lightweight `qa` preset (`RQ-0065`), the experimental `sourceLookup` helper (`RQ-0066`), the experimental `networkSourceLookup` helper (`RQ-0067`), optional Exa/Brave-backed `agent_browser_web_search` with Pi-scoped package config (`RQ-0121`), and agent recovery for search/profile configuration failures (`RQ-0122`) are implemented; see [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#job), [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#qa), [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#sourcelookup), [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#networksourcelookup), and [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#optional-companion-web-search). Reusable browser recipes (`RQ-0068`) are intentionally not adopted as a runtime surface; see [`ARCHITECTURE.md`](ARCHITECTURE.md#no-reusable-recipe-layer-yet).
 
-## Open UX/reliability follow-ups from 2026-05-29 agent feedback
+## UX/reliability decisions from 2026-05-29 agent feedback
 
-Detailed feedback triage and implementation notes live in the repository source at [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) under the 2026-05-29 agent feedback section. Keep this active matrix limited to release-critical status and gates.
+Closed feedback decisions map to their canonical contracts in [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md). Keep this active matrix limited to release-critical status and gates.
 
 Current summary:
 
@@ -42,7 +42,7 @@ Current summary:
 | --- | --- | --- |
 | RQ-0110–RQ-0120 | Agent feedback triage resolved or documented; remaining unsupported areas are environment/upstream-owned. | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
 | RQ-0123–RQ-0127 | Stress-report wrapper fixes shipped; prompt-derived business-action blocking remains intentionally out of scope. | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
-| RQ-0101 | Upstream `agent-browser 0.27.2` rebaseline shipped. | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
+| `agent-browser 0.27.2` baseline | Historical upstream rebaseline shipped; `RQ-0101` remains the compact-snapshot high-value-controls decision. | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
 | RQ-0128 | Upstream `agent-browser 0.27.3` install-only rebaseline shipped; no new wrapper capability adopted. | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
 | RQ-0129 | Upstream `agent-browser 0.29.1` rebaseline shipped; sandbox helpers are documented upstream package guidance, not a wrapper runtime. | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
 | RQ-0130 | Upstream `agent-browser 0.30.1` rebaseline shipped; `wait --url` glob support replaces the wrapper `job.assertUrl` predicate workaround. | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
@@ -86,9 +86,9 @@ Runtime floor note: package metadata keeps Pi core package peer ranges wildcard
 
 ## Follow-up decision after closure
 
-Detailed closure notes live in the repository source at [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) under the follow-up decision section. Keep this section as the active index of shipped follow-up areas and their canonical contracts.
+The compact decision index lives at [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md). Keep this section as the active index of shipped follow-up areas and their canonical contracts.
 
-| Area | Active contract | Detail archive |
+| Area | Active contract | Decision index |
 | --- | --- | --- |
 | Native structured input modes (`job`, `qa`, `sourceLookup`, `networkSourceLookup`, `semanticAction`) | [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md), [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md) | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |
 | Electron lifecycle, manual CDP attach, desktop readiness, and tab/surface recovery | [`ELECTRON.md`](ELECTRON.md), [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#electron), [`COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#electron-desktop-apps) | [`docs/support-notes.md`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/docs/support-notes.md) |

package/docs/TOOL_CONTRACT.md

@@ -252,7 +252,7 @@ If a raw `find` or compiled `semanticAction` fails with `failureCategory: "selec
 
 If a compiled `semanticAction` fails with `failureCategory: "selector-not-found"`, visible content can also include an `Agent-browser candidate fallbacks` block when the wrapper has bounded role/name retries for that locator and action, and `details.nextActions` includes the normal `refresh-interactive-refs` snapshot step plus those entries. When `session` was provided, candidate retry args preserve the same `--session <session>` prefix. Today `buildSemanticActionCandidateActions` in `extensions/agent-browser/index.ts` only appends click candidates for `click` + `text` → `try-button-name-candidate` and `try-link-name-candidate`. Fill misses no longer emit `find … fill <text>` retry actions because those would repeat potentially sensitive text. Instead, when the same selector-miss snapshot finds exact current editable refs (`searchbox` or `textbox`), the wrapper emits `details.richInputRecovery`, visible `Rich input recovery`, and `focus-current-editable-ref` / `click-current-editable-ref` (numbered when ambiguous) next actions. Those actions carry only focus/click argv for the candidate ref; they do not copy fill text, press `Enter`, or submit. Use `keyboard inserttext` or `keyboard type` with the intended text only after focusing the right current ref, and submit only when the user flow explicitly calls for it. Candidate fallbacks are heuristics, not proof that an element exists; inspect the page when several controls could share the same name.
 
-If a compiled `semanticAction` `find` action fails with `failureCategory: "stale-ref"`, `details.nextActions` includes `retry-semantic-action-after-stale-ref` with the same redacted compiled argv as `details.compiledSemanticAction` in `params.args` (any leading `--session` pair from `semanticAction.session`, then the `find` tokens). The wrapper appends that entry **after** any `refresh-interactive-refs` snapshot step from `buildAgentBrowserNextActions` in `extensions/agent-browser/lib/results/action-recommendations.ts` (re-exported from `shared.ts`; see `extensions/agent-browser/index.ts` where `nextActions` is merged). That retry is only offered because the semantic target is stable and the stale-ref error proves the previous action did not execute; `select` shorthands with stale `@e…` selectors and direct stale `@e…` commands still return refresh guidance instead of an unsafe blind retry.
+If a compiled `semanticAction` `find` action fails with `failureCategory: "stale-ref"`, `details.nextActions` includes `retry-semantic-action-after-stale-ref` with the same redacted compiled argv as `details.compiledSemanticAction` in `params.args` (any leading `--session` pair from `semanticAction.session`, then the `find` tokens). The wrapper appends that entry **after** any `refresh-interactive-refs` snapshot step from `buildAgentBrowserNextActions` in `extensions/agent-browser/lib/results/action-recommendations.ts` (see `extensions/agent-browser/index.ts` where `nextActions` is merged). That retry is only offered because the semantic target is stable and the stale-ref error proves the previous action did not execute; `select` shorthands with stale `@e…` selectors and direct stale `@e…` commands still return refresh guidance instead of an unsafe blind retry.
 
 For direct page-scoped `@e…` refs, successful `snapshot` results record `details.refSnapshot` with the latest ref ids and page target for the session. A failed session `snapshot` whose upstream error says `No active page` clears that session’s prior ref snapshot and records `details.refSnapshotInvalidation.reason: "no-active-page"`; mutation-prone `@e…` preflight then fails with `failureCategory: "stale-ref"` until a later successful `snapshot -i` records fresh refs. Before mutation-prone ref commands such as `click`, `fill`, `check`, `select`, `download`, drag/upload/keyboard-style actions, or equivalent batch steps run, the wrapper rejects refs from an older page target, refs absent from the latest same-page snapshot, or refs from an invalidated snapshot state. This is a best-effort wrapper guard against upstream ref-number recycling after navigation; it does not prove the DOM stayed unchanged after the snapshot. Refresh with the session-aware `refresh-interactive-refs` next action before retrying.
 
@@ -713,7 +713,7 @@ Ref preflight details (command taxonomy in `extensions/agent-browser/lib/command
 
 **Presentation redaction (implementation map):** Successful non-`batch` tool calls and each successful `batchSteps[]` row run upstream `data` through `redactPresentationData` in `extensions/agent-browser/lib/results/presentation/diagnostics.ts`: `cookies` still walk objects/arrays and replace case-insensitive `value` keys with `"[REDACTED]"`; `storage` redacts values when the key or value looks credential-like (token, cookie, auth, secret, JWT, bearer/basic credential, high-entropy token-like string, or nested sensitive JSON) but keeps low-risk primitive QA values such as booleans, numbers, and short strings visible. Redacted storage entries add `valueRedacted` plus `valueRedactionReason` in `details.data`; diagnostic formatters mirror the same decision. Every other command’s payload is recursively scrubbed with `redactStructuredPresentationValue`, which redacts known sensitive key names and applies string-level sensitivity heuristics so network, diff, trace/profiler, stream, dashboard, chat, and other structured results do not echo bearer tokens, proxy credentials, or similar fields verbatim into `details.data`. Echoed `command` arrays in `details` and in batch roll-ups use `redactInvocationArgs` from `extensions/agent-browser/lib/runtime.ts` to mask trailing values for sensitive global flags (including `--body`, `--headers`, `--password`, and `--proxy`), preserve the special positional rules for `cookies set`, `storage local|session set`, and `set credentials`, and scrub other argv tokens for URLs and inline secrets. Failed batch steps additionally run `redactExactValues` on structured step errors so literals taken from that step’s argv (cookie value, storage set value, `--password` / `--password=` tokens) cannot reappear inside formatted error blobs.
 
-`nextActions` is an optional machine-readable list of exact native `agent_browser` follow-ups. Each entry includes `tool: "agent_browser"`, an `id`, a short `reason`, optional `safety`, and either `params` (`args`, optional `stdin`, optional `sessionMode`, optional `networkSourceLookup`, optional `electron`) or an `artifactPath` for saved-file workflows. Agents should prefer these payloads over prose when present. When a result ran under upstream `--namespace <name>`, follow-up `params.args` preserve that namespace so retries and diagnostics target the same daemon/restore-state space. Tab/session recovery id strings are centralized in `AGENT_BROWSER_RECOVERY_NEXT_ACTION_IDS`, while rich-input focus/click recovery ids are centralized in `AGENT_BROWSER_RICH_INPUT_RECOVERY_NEXT_ACTION_IDS` plus `getAgentBrowserRichInputRecoveryNextActionId(s)` in `extensions/agent-browser/lib/results/recovery-actions.ts` (both registries are also re-exported from `shared.ts`); docs and tests mirror those registries/helpers rather than inventing recovery ids in prose. Current recommendations include: timed-out jobs/batches with a retryable read-only/idempotent first incomplete step → `retry-timeout-step`, while timed-out flows whose first incomplete step may be mutating → `inspect-current-page-after-timeout` (`snapshot -i`) before splitting the remaining work into shorter batches; raw `connect` success → session-scoped `list-connected-session-tabs` only, then the agent should inspect/select a stable `tab t<N>` target and run `snapshot -i` explicitly; `snapshot` failures whose upstream error says `No active page` and whose wrapper result has a known session → `list-tabs-after-no-active-page` only, because this path has no wrapper-observed safe tab id to select atomically; browser profile/user-data-dir resolution failures → `inspect-browser-profiles` (`profiles`) and `run-agent-browser-doctor` (`doctor`) before retrying opens; Electron launches → wrapper-tracked `electron.status` / `electron.probe` / `electron.cleanup` actions plus session-scoped tab/snapshot inspection when attached; Electron status/probe mismatch diagnostics → `reattach-electron-launch` plus fresh tab/snapshot inspection; Electron post-command health failures → status/probe/cleanup for the same `launchId`; Electron or contenteditable fill verification mismatches → `inspect-after-fill-verification` and `verify-filled-value`; Electron same-URL ref freshness warnings → `refresh-electron-refs-after-rerender`; packaged-Electron `sourceLookup` no-candidate diagnostics → session snapshot, launch probe, and tab list; Electron cleanup partial failures → status plus retry-cleanup for the same wrapper-owned `launchId`; `open` success → `snapshot -i`; mutating/navigation commands (see `buildAgentBrowserNextActions` in source for the exact command set) → `snapshot -i`; stale refs and selector failures → `snapshot -i` via `refresh-interactive-refs` (prefixed with `--session <name>` when the failed call ran in a named or managed session); selector misses with exact current snapshot role/name matches → direct ref retries via `try-current-visible-ref` or bounded `try-current-visible-ref-N` for non-fill targets; semantic `fill` selector misses with exact current editable refs → `focus-current-editable-ref` / `click-current-editable-ref` or numbered variants that do not include fill text or submit; unknown getter shortcuts such as `title` / `url` → exact read-only retries like `get title` / `get url` with ids `use-get-title` / `use-get-url`; compact `network requests` results with safe request IDs → bounded read-only request detail, `networkSourceLookup`, path filter, or HAR-capture follow-ups; semantic `selector-not-found` failures that compiled from `semanticAction` may append `try-button-name-candidate` or `try-link-name-candidate` after presentation `nextActions` only for the bounded click pair enumerated under `semanticAction`; semantic `stale-ref` failures that compiled from `semanticAction` `find` argv may also include `retry-semantic-action-after-stale-ref` after that snapshot step; successful snapshots or qualifying same-URL non-Electron top-level clicks (see `overlayBlockers` below) with snapshot evidence of likely overlay/banner/dialog close controls may append `inspect-overlay-state` and bounded `try-overlay-blocker-candidate-*` entries; successful top-level `scroll` calls whose pre/post viewport and sampled scroll-container positions do not change may append `inspect-after-noop-scroll` and `verify-noop-scroll-visually`; explicit combobox-targeted actions that focus a combobox without visible options may append `inspect-focused-combobox`, `try-open-combobox-with-arrow`, and `try-open-combobox-with-enter`; `get text <selector>` calls with hidden/multiple CSS matches may append `inspect-visible-text-candidates` with a read-only `eval --stdin` probe (each prefixed with `--session <name>` when `details.sessionName` is set, same `sessionPrefixArgs` rule as other session-scoped follow-ups); confirmations → exact `confirm <id>` and `deny <id>` choices; generic tab drift → `list-tabs-for-recovery` with `tab list` first, then select or confirm the stable target before running `snapshot -i`; about:blank or tab-drift recovery with a wrapper-known target → `list-tabs-for-about-blank-recovery` or `list-tabs-for-tab-drift-recovery`, plus `select-intended-tab-after-drift` and `snapshot-after-tab-recovery` when the wrapper already observed the stable `t<N>` tab id; `wait --text` assertion failures → `inspect-after-text-assertion-failure` with a read-only snapshot; download verification failures or missing successful download artifacts → `wait --download [path]`; saved artifacts → the artifact path to inspect/consume after checking `artifactVerification`/metadata; missing non-download artifacts → `verify-artifact-path` so agents do not trust an absent file. When nothing applies, the field is omitted.
+`nextActions` is an optional machine-readable list of exact native `agent_browser` follow-ups. Each entry includes `tool: "agent_browser"`, an `id`, a short `reason`, optional `safety`, and either `params` (`args`, optional `stdin`, optional `sessionMode`, optional `networkSourceLookup`, optional `electron`) or an `artifactPath` for saved-file workflows. Agents should prefer these payloads over prose when present. When a result ran under upstream `--namespace <name>`, follow-up `params.args` preserve that namespace so retries and diagnostics target the same daemon/restore-state space. Tab/session recovery id strings are centralized in `AGENT_BROWSER_RECOVERY_NEXT_ACTION_IDS`, while rich-input focus/click recovery ids are centralized in `AGENT_BROWSER_RICH_INPUT_RECOVERY_NEXT_ACTION_IDS` plus `getAgentBrowserRichInputRecoveryNextActionId(s)` in `extensions/agent-browser/lib/results/recovery-actions.ts`; docs and tests mirror those registries/helpers rather than inventing recovery ids in prose. Current recommendations include: timed-out jobs/batches with a retryable read-only/idempotent first incomplete step → `retry-timeout-step`, while timed-out flows whose first incomplete step may be mutating → `inspect-current-page-after-timeout` (`snapshot -i`) before splitting the remaining work into shorter batches; raw `connect` success → session-scoped `list-connected-session-tabs` only, then the agent should inspect/select a stable `tab t<N>` target and run `snapshot -i` explicitly; `snapshot` failures whose upstream error says `No active page` and whose wrapper result has a known session → `list-tabs-after-no-active-page` only, because this path has no wrapper-observed safe tab id to select atomically; browser profile/user-data-dir resolution failures → `inspect-browser-profiles` (`profiles`) and `run-agent-browser-doctor` (`doctor`) before retrying opens; Electron launches → wrapper-tracked `electron.status` / `electron.probe` / `electron.cleanup` actions plus session-scoped tab/snapshot inspection when attached; Electron status/probe mismatch diagnostics → `reattach-electron-launch` plus fresh tab/snapshot inspection; Electron post-command health failures → status/probe/cleanup for the same `launchId`; Electron or contenteditable fill verification mismatches → `inspect-after-fill-verification` and `verify-filled-value`; Electron same-URL ref freshness warnings → `refresh-electron-refs-after-rerender`; packaged-Electron `sourceLookup` no-candidate diagnostics → session snapshot, launch probe, and tab list; Electron cleanup partial failures → status plus retry-cleanup for the same wrapper-owned `launchId`; `open` success → `snapshot -i`; mutating/navigation commands (see `buildAgentBrowserNextActions` in source for the exact command set) → `snapshot -i`; stale refs and selector failures → `snapshot -i` via `refresh-interactive-refs` (prefixed with `--session <name>` when the failed call ran in a named or managed session); selector misses with exact current snapshot role/name matches → direct ref retries via `try-current-visible-ref` or bounded `try-current-visible-ref-N` for non-fill targets; semantic `fill` selector misses with exact current editable refs → `focus-current-editable-ref` / `click-current-editable-ref` or numbered variants that do not include fill text or submit; unknown getter shortcuts such as `title` / `url` → exact read-only retries like `get title` / `get url` with ids `use-get-title` / `use-get-url`; compact `network requests` results with safe request IDs → bounded read-only request detail, `networkSourceLookup`, path filter, or HAR-capture follow-ups; semantic `selector-not-found` failures that compiled from `semanticAction` may append `try-button-name-candidate` or `try-link-name-candidate` after presentation `nextActions` only for the bounded click pair enumerated under `semanticAction`; semantic `stale-ref` failures that compiled from `semanticAction` `find` argv may also include `retry-semantic-action-after-stale-ref` after that snapshot step; successful snapshots or qualifying same-URL non-Electron top-level clicks (see `overlayBlockers` below) with snapshot evidence of likely overlay/banner/dialog close controls may append `inspect-overlay-state` and bounded `try-overlay-blocker-candidate-*` entries; successful top-level `scroll` calls whose pre/post viewport and sampled scroll-container positions do not change may append `inspect-after-noop-scroll` and `verify-noop-scroll-visually`; explicit combobox-targeted actions that focus a combobox without visible options may append `inspect-focused-combobox`, `try-open-combobox-with-arrow`, and `try-open-combobox-with-enter`; `get text <selector>` calls with hidden/multiple CSS matches may append `inspect-visible-text-candidates` with a read-only `eval --stdin` probe (each prefixed with `--session <name>` when `details.sessionName` is set, same `sessionPrefixArgs` rule as other session-scoped follow-ups); confirmations → exact `confirm <id>` and `deny <id>` choices; generic tab drift → `list-tabs-for-recovery` with `tab list` first, then select or confirm the stable target before running `snapshot -i`; about:blank or tab-drift recovery with a wrapper-known target → `list-tabs-for-about-blank-recovery` or `list-tabs-for-tab-drift-recovery`, plus `select-intended-tab-after-drift` and `snapshot-after-tab-recovery` when the wrapper already observed the stable `t<N>` tab id; `wait --text` assertion failures → `inspect-after-text-assertion-failure` with a read-only snapshot; download verification failures or missing successful download artifacts → `wait --download [path]`; saved artifacts → the artifact path to inspect/consume after checking `artifactVerification`/metadata; missing non-download artifacts → `verify-artifact-path` so agents do not trust an absent file. When nothing applies, the field is omitted.
 
 **Unknown-command getter hints (failure presentation):** `buildErrorPresentation` in `extensions/agent-browser/lib/results/presentation/errors.ts` only runs this path when upstream error text (after model-facing redaction) matches `unknown command`, `unknown subcommand`, or `unrecognized command` (case-insensitive) **and** the failed invocation’s primary command token is one of `attr`, `count`, `html`, `text`, `title`, `url`, or `value`. Visible text then includes a grouped-`get` hint line plus per-token guidance (`get text <selector>`, `get html …`, `get attr …`, `get count …`, `get value …`, `get title`, `get url`). Machine `nextActions` with ids `use-get-title` / `use-get-url` are emitted only for `title` / `url`, with `params.args` optionally prefixed by `--session <name>` when the failed call targeted a named session. If the error string already contains `Agent-browser hint:` from selector recovery (stale-ref or unsupported selector dialect appendages), the getter block is skipped so two stacked `Agent-browser hint:` headers are not emitted.
 
@@ -777,7 +777,7 @@ When `semanticAction` produced compiled `find` argv and the unified result is `f
 
 Implementation and precedence:
 
-- Shared machine-readable types are centralized in `extensions/agent-browser/lib/results/contracts.ts` (including re-exports such as `AgentBrowserNextAction` from `next-actions.ts`). Classifiers live in `categories.ts` (`classifyAgentBrowserSuccessCategory`, `classifyAgentBrowserFailureCategory`, `buildAgentBrowserResultCategoryDetails`—the last prefers an explicit `failureCategory` when the caller already knows the bucket, otherwise it runs the classifier). Generic follow-up assembly lives in `action-recommendations.ts` (`buildAgentBrowserNextActions`). Tab/session recovery ids live in `recovery-actions.ts` (`AGENT_BROWSER_RECOVERY_NEXT_ACTION_IDS`, `AGENT_BROWSER_RICH_INPUT_RECOVERY_NEXT_ACTION_IDS`, `getAgentBrowserRichInputRecoveryNextActionId`, `getAgentBrowserRichInputRecoveryNextActionIds`, `buildRecoveryNextActions`) and session-aware wrappers live in `recovery-next-actions.ts`. Selector miss and rich-input diagnostic shapes/actions live in `selector-recovery.ts`. `extensions/agent-browser/lib/results/shared.ts` re-exports focused modules for compatibility only. Failed upstream `network requests` rows flow through `classifyNetworkRequestFailure` / `summarizeNetworkFailures` in `network.ts` for QA analysis (`analyzeQaPresetResults` in `extensions/agent-browser/index.ts`) and for actionable-vs-benign lines plus request-specific nextActions in `network requests` presentation (`extensions/agent-browser/lib/results/presentation/diagnostics.ts`).
+- Shared machine-readable types are centralized in `extensions/agent-browser/lib/results/contracts.ts` (including re-exports such as `AgentBrowserNextAction` from `next-actions.ts`). Classifiers live in `categories.ts` (`classifyAgentBrowserSuccessCategory`, `classifyAgentBrowserFailureCategory`, `buildAgentBrowserResultCategoryDetails`—the last prefers an explicit `failureCategory` when the caller already knows the bucket, otherwise it runs the classifier). Generic follow-up assembly lives in `action-recommendations.ts` (`buildAgentBrowserNextActions`). Tab/session recovery ids live in `recovery-actions.ts` (`AGENT_BROWSER_RECOVERY_NEXT_ACTION_IDS`, `AGENT_BROWSER_RICH_INPUT_RECOVERY_NEXT_ACTION_IDS`, `getAgentBrowserRichInputRecoveryNextActionId`, `getAgentBrowserRichInputRecoveryNextActionIds`, `buildRecoveryNextActions`) and session-aware wrappers live in `recovery-next-actions.ts`. Selector miss and rich-input diagnostic shapes/actions live in `selector-recovery.ts`. Failed upstream `network requests` rows flow through `classifyNetworkRequestFailure` / `summarizeNetworkFailures` in `network.ts` for QA analysis (`analyzeQaPresetResults` in `extensions/agent-browser/index.ts`) and for actionable-vs-benign lines plus request-specific nextActions in `network requests` presentation (`extensions/agent-browser/lib/results/presentation/diagnostics.ts`).
 - Artifact verification: `ArtifactVerificationSummary` / `ArtifactVerificationEntry` types live in `contracts.ts`. `buildArtifactVerificationSummary`, `getArtifactVerificationEntry`, and `getManifestVerificationEntry` in `presentation/artifacts.ts` merge each resolved file artifact with manifest rows whose `storageScope` is not `explicit-path` (those rows duplicate file artifacts) and whose `path` is in the current result’s spill path set. Presentation then fails closed with `failureCategory: "artifact-missing"` when any resolved non-pending file artifact has `exists: false`; pending recording-start artifacts and non-explicit spill rows do not trigger this failure. If no hard-missing file artifact exists, successful presentation merges run `classifyPresentationSuccessCategory`, which can still force `successCategory: "artifact-unverified"` for unverified counts before delegating to `classifyAgentBrowserSuccessCategory`.
 - Inner success categories (`classifyAgentBrowserSuccessCategory` in `categories.ts`, after verification counts are clear): if `inspection` is true → `"inspection"`; else if any non-pending artifact lacks confirmed on-disk presence (`exists !== true`) and was not upgraded to an `artifact-missing` failure → `"artifact-unverified"`; else if there is a `savedFile` or any `artifacts` → `"artifact-saved"`; else → `"completed"`.
 - Failure: the classifier walks a single ordered chain (first match wins): `confirmation-required` → `timeout` → `missing-binary` → `parse-failure` → `aborted` → `policy-blocked` → `cleanup-failed` → `tab-drift` → `stale-ref` (including “unknown ref” text and a narrow `@eN` plus “element not found” heuristic) → `selector-unsupported` → `selector-not-found` → `download-not-verified` (download / wait-download style failures) → `validation-error` when a wrapper `validationError` is present → default `upstream-error`. Wrapper-known missing artifact checks pass an explicit `artifact-missing` category rather than relying on this text classifier.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-agent-browser-native",
-  "version": "0.2.69",
+  "version": "0.2.70",
   "description": "pi extension that exposes agent-browser as a native tool for browser automation",
   "type": "module",
   "author": "Mitch Fultz (https://github.com/fitchmultz)",
@@ -94,7 +94,6 @@
     "prepublishOnly": "npm run verify -- release && npm pack --dry-run",
     "build": "node ./scripts/build.mjs",
     "startup-profile": "node ./scripts/profile-startup.mjs",
-    "prepack": "npm run build",
     "prepare": "node ./scripts/prepare.mjs"
   },
   "packageManager": "npm@11.14.0",

package/platform-smoke.config.mjs

@@ -3,15 +3,14 @@
 
 import { CAPABILITY_BASELINE } from "./scripts/agent-browser-capability-baseline.mjs";
 
-export const PLATFORM_SMOKE_AGENT_BROWSER_VERSION = CAPABILITY_BASELINE.targetVersion;
-export const PLATFORM_SMOKE_UBUNTU_IMAGE = `pi-agent-browser-native-platform:node24-agent-browser${PLATFORM_SMOKE_AGENT_BROWSER_VERSION}`;
+const PLATFORM_SMOKE_AGENT_BROWSER_VERSION = CAPABILITY_BASELINE.targetVersion;
+const PLATFORM_SMOKE_UBUNTU_IMAGE = `pi-agent-browser-native-platform:node24-agent-browser${PLATFORM_SMOKE_AGENT_BROWSER_VERSION}`;
 
 export default {
 	packageName: "pi-agent-browser-native",
 	artifactRoot: ".artifacts/platform-smoke",
 	requiredTargets: ["macos", "ubuntu", "windows-native"],
 	requiredSuites: ["platform-build", "browser-dogfood-smoke"],
-	supportedTargets: ["macos", "ubuntu", "windows-native"],
 	requiredCrabbox: {
 		install: "Homebrew package or PLATFORM_SMOKE_CRABBOX override",
 		minVersion: "0.26.0",

package/scripts/platform-smoke.mjs

@@ -126,8 +126,7 @@ export async function main(argv = process.argv.slice(2)) {
 		const { runTargetSuites } = await import("./platform-smoke/targets.mjs");
 		const targets = args.target ? args.target.split(",").map((name) => name.trim()).filter(Boolean) : config.requiredTargets;
 		const suites = args.suite ? [args.suite] : config.requiredSuites;
-		const supportedTargets = config.supportedTargets ?? config.requiredTargets;
-		validateNames("target", targets, supportedTargets);
+		validateNames("target", targets, config.requiredTargets);
 		validateNames("suite", suites, config.requiredSuites);
 		const runs = targets.map(async (targetName) => {
 			console.log(`\n=== Target: ${targetName} ===`);

package/dist/extensions/agent-browser/lib/orchestration/browser-run.js

@@ -1 +0,0 @@
-export * from "./browser-run/index.js";

package/dist/extensions/agent-browser/lib/results/shared.js

@@ -1,20 +0,0 @@
-/**
- * Purpose: Compatibility barrel for focused result modules.
- * Responsibilities: Preserve the historical `./results/shared.js` import surface while delegating all logic to focused files.
- * Scope: Re-exports only; do not add runtime policy here.
- * Usage: Existing internal imports may keep using this path during migration, while new code should prefer focused modules.
- * Invariants/Assumptions: This file intentionally contains no business logic so `shared` cannot grow back into a catch-all module.
- */
-export * from "./contracts.js";
-export * from "./categories.js";
-export * from "./action-recommendations.js";
-export * from "./artifact-manifest.js";
-export * from "./artifact-state.js";
-export * from "./editable-ref-evidence.js";
-export * from "./network.js";
-export * from "./network-routes.js";
-export * from "./next-actions.js";
-export * from "./recovery-actions.js";
-export * from "./recovery-next-actions.js";
-export * from "./selector-recovery.js";
-export * from "./text.js";