pi-agent-browser-native 0.2.71 → 0.2.72

package/CHANGELOG.md

@@ -1,5 +1,24 @@
 # Changelog
 
+## 0.2.72 - 2026-07-23
+
+### Changed
+
+- Rebaselined the command/help inventory, source evidence, prompt guidance, and package docs to `agent-browser 0.33.0` / vercel-labs/agent-browser@1ed371f3af472cc0d6cd8fdaea75d1a085ff7534 (includes 0.32.3–0.32.4 HAR/`find`/`derive-client` surfaces).
+- Documented HAR response-body capture modes (`network har start --content text|all|none`), `skills get derive-client`, and the new `a11y [url]` axe-core accessibility audit (`--tags`, `--selector`).
+- Documented upstream 0.32.4 `find role` implicit ARIA / accessible-name matching, locator-detail miss text, and the aligned `find` action list (`click, fill, check, hover, text`).
+- Added compact model-facing presentation for `a11y` violation/incomplete summaries.
+
+### Fixed
+
+- Classified upstream 0.32.4+ locator-detail misses (`Names seen:`, `No element found: getByRole(...)`, `Element not found: … Verify the selector, role, or name`) as `failureCategory: "selector-not-found"` so snapshot-ref recovery still runs, without treating bare accessible-name text containing `timeout` or `Confirmation required` as unrelated categories.
+- Treated command-scoped `--content` and `--tags` as value-taking flags during argv planning so `network har start --content all` and `a11y --tags wcag2a,wcag2aa` keep mode/tag tokens with their flags.
+
+### Validation
+
+- Passed `npm run verify` (590 tests passed, 2 opt-in skips), live command-reference verification, and `npm run verify -- real-upstream` (2/2 tests) against installed `agent-browser 0.33.0`.
+- Passed `npm run verify -- release`, including configured-source lifecycle, packaged Pi smoke, and macOS/Ubuntu/native-Windows Crabbox `platform-build` plus `browser-dogfood-smoke` on `agent-browser 0.33.0` (Windows snapshot `crabbox-ready-ab-0.33.0`, Ubuntu image `node24-agent-browser0.33.0`).
+
 ## 0.2.71 - 2026-07-18
 
 ### Fixed

package/dist/extensions/agent-browser/lib/argv-grammar.js

@@ -45,6 +45,7 @@ export const COMMAND_VALUE_FLAGS = [
     "--baseline",
     "--body",
     "--categories",
+    "--content",
     "--curl",
     "--depth",
     "-d",
@@ -68,6 +69,7 @@ export const COMMAND_VALUE_FLAGS = [
     "--selector",
     "-s",
     "--status",
+    "--tags",
     "--text",
     "--threshold",
     "--timeout",

package/dist/extensions/agent-browser/lib/command-taxonomy.js

@@ -5,7 +5,7 @@
  * Scope: Static command capability taxonomy only; command-shape parsing, spawning, and formatting live elsewhere.
  */
 const ADDITIONAL_COMMAND_TOKENS = [
-    "auth", "chat", "clipboard", "confirm", "connect", "dashboard", "deny", "device", "dialog", "diff", "doctor", "errors", "eval", "find", "frame", "get", "highlight", "inspect", "install", "is", "mcp", "plugin", "plugins", "profiles", "profiler", "react", "record", "removeinitscript", "session", "set", "skills", "snapshot", "state", "stream", "trace", "upgrade", "vitals", "wait", "web-vitals", "window",
+    "a11y", "auth", "chat", "clipboard", "confirm", "connect", "dashboard", "deny", "device", "dialog", "diff", "doctor", "errors", "eval", "find", "frame", "get", "highlight", "inspect", "install", "is", "mcp", "plugin", "plugins", "profiles", "profiler", "react", "record", "removeinitscript", "session", "set", "skills", "snapshot", "state", "stream", "trace", "upgrade", "vitals", "wait", "web-vitals", "window",
 ];
 const COMMAND_CAPABILITIES = [
     {

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

@@ -46,7 +46,7 @@ export const SHARED_BROWSER_PLAYBOOK_GUIDELINES = [
     "For batch chains that touch cookies, storage, auth, or other secret-bearing commands, use details.batchSteps for per-step artifacts, categories, spill paths, and full structured errors; top-level details.data on batch is only a compact redacted step matrix (success, argv-redacted command, redacted result or scrubbed error text) built from the same presentation rules as standalone calls.",
     "For non-core families, pass current upstream commands through the native tool directly: network requests, network route <url>, network har start/stop [path], diff snapshot, diff screenshot --baseline <file>, diff url <u1> <u2>, trace start, trace stop [path], profiler start, profiler stop [path], record start <path>, record stop, console/errors [--clear], highlight <selector>, inspect, clipboard read, clipboard write <text>, clipboard copy/paste, stream enable/disable/status, dashboard start/stop, device list for iOS simulator inventory, and chat <message>. For compact network requests output, prefer details.nextActions for request detail, route-mock diagnostics, actionable failed-request networkSourceLookup, filtering, clearing the aggregate buffer before repro, or HAR capture follow-ups instead of guessing request-id syntax. Artifact-producing commands report details.artifacts and verification state; long-running starts such as stream, dashboard, trace/profiler, and record should be paired with the matching stop/disable command when the task is done; stream enable already-enabled outcomes are treated as idempotent success with status/disable follow-ups.",
     "For Electron desktop apps, prefer top-level electron for wrapper-owned discovery, isolated launch, status, compact probe, and cleanup: list first, treat likely-sensitive annotations as hints rather than enforcement, launch with the default snapshot handoff unless handoff: \"tabs\" is the safer diagnostic starting point, use electron.probe or snapshot -i/qa.attached for current-session state, and always cleanup the returned launchId when done. electron.launch uses an isolated temporary profile; it does not reuse the app's normal signed-in profile or attach to an already-running authenticated app. For signed-in local app state, host-launch the normal app with --remote-debugging-port when appropriate, then use raw args connect <port|url>; after connect, inspect tab list, select the stable tab id such as tab t2, then run a condition wait or snapshot -i before using refs. close commands (`close`, `quit`, or `exit`) only close the browser/CDP session; leave manually launched app shutdown, profile cleanup, and explicit artifacts to the host owner.",
-    "For provider or specialized app workflows, load version-matched upstream guidance with skills get agentcore|electron|slack|dogfood|vercel-sandbox through the native tool; add --full when you need references/templates, and use skills get --all only for broad skill audits. Hosted sandbox workflows should use upstream @agent-browser/sandbox helpers outside this wrapper. Provider launches such as -p ios, --provider browserbase/kernel/browseruse/browserless/agentcore, and iOS --device are upstream-owned setup paths; use sessionMode fresh when switching providers and expect external credentials or local Appium/Xcode setup to be required.",
+    "For provider or specialized app workflows, load version-matched upstream guidance with skills get agentcore|electron|slack|dogfood|vercel-sandbox|derive-client through the native tool; add --full when you need references/templates, and use skills get --all only for broad skill audits. Use derive-client when recording HAR traffic to generate a standalone API client; prefer network har start (text bodies by default) or network har start --content all|none before multi-step capture. For accessibility audits use a11y or a11y --tags wcag2a,wcag2aa (CDP browsers only). Hosted sandbox workflows should use upstream @agent-browser/sandbox helpers outside this wrapper. Provider launches such as -p ios, --provider browserbase/kernel/browseruse/browserless/agentcore, and iOS --device are upstream-owned setup paths; use sessionMode fresh when switching providers and expect external credentials or local Appium/Xcode setup to be required.",
     "For dialogs and frames, use dialog status/accept/dismiss and frame <selector|main> through native args; dialog commands and eval snippets that look like alert/confirm/prompt/dialog triggers are shorter-bounded than normal browser calls, and timed-out dialog-like interactions may add inspect-dialog-after-timeout, dismiss-dialog-after-timeout, or recover-fresh-session-after-dialog-timeout nextActions. When --confirm-actions produces a pending confirmation, use details.nextActions or exact confirm <id> / deny <id> calls instead of inventing ids.",
     "If a session lands on the wrong page or tab, an interaction changes origin unexpectedly, or an open call returns blocked, blank, or otherwise unexpected results, use tab list / tab <tab-id-or-label> / snapshot -i to recover state before retrying different URLs or fallback strategies. For headed demos, put --headed on the first launch with sessionMode=fresh and verify with screenshot/tab/get-url evidence because tool success cannot prove the OS window is visible to the user. For desktop readiness, prefer real conditions first: wait --text, wait --url, wait --fn, wait --load <state>, wait --download, or qa.attached; for disappearance checks, use wait --fn predicates instead of stale upstream-help examples like wait <selector> --state hidden. Use electron.probe/status for wrapper-owned launch health or target mismatch. Fixed waits are a last resort: use explicit --timeout or top-level timeoutMs for legitimately slow waits, and treat a successful payload like \"waited\":\"timeout\" as elapsed time only—verify completion with an observed condition, fresh snapshot, or screenshot.",
     "For feed, timeline, or inbox reading tasks, focus on the main timeline/list region and read the first item there rather than unrelated composer or sidebar content.",

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

@@ -22,10 +22,29 @@ export function classifyAgentBrowserFailureCategory(options) {
     const text = [options.errorText, options.validationError, options.parseError, options.spawnError, options.stderr].filter(Boolean).join("\n");
     const command = options.command ?? "";
     const usedRef = options.args?.some((arg) => /^@e\d+\b/.test(arg)) ?? false;
-    if (options.confirmationRequired || /confirmation required|pending confirmation|requires confirmation/i.test(text))
+    // Explicit confirmation flag wins. Text-derived confirmation phrases come after locator-miss detection so a
+    // missed control named "Confirmation required" still gets selector recovery.
+    if (options.confirmationRequired)
         return "confirmation-required";
-    if (options.timedOut || /timeout|timed out|watchdog|IPC read timeout|must stay under its 30s IPC read timeout/i.test(text))
+    // Upstream 0.32.4+ locator misses keep detail and may echo getByRole/getByText or Names seen lists.
+    // Evaluate before text-derived timeout/confirmation so accessible-name substrings cannot suppress recovery.
+    const isUpstreamLocatorMiss = /\bNo element found:\s*(?:getBy[A-Za-z]+|role=|text=|label=|placeholder=|alt=|title=|testid=)/i.test(text) ||
+        // No trailing \b after ":" — colon is non-word, so "Element not found: text=…" would not match.
+        (/\bElement not found:/i.test(text) && /\bVerify the selector, role, or name\b/i.test(text)) ||
+        /\bnone match name\b/i.test(text) ||
+        // Scope Names seen to role/name miss context (or find) so unrelated prose cannot trip selector-not-found.
+        (/\bNames seen:/i.test(text) && (command === "find" || /\belement has role\b|\bnone match name\b|\bgetByRole\b/i.test(text))) ||
+        /\belement has role\b[\s\S]*\bnone match\b/i.test(text);
+    if (isUpstreamLocatorMiss)
+        return "selector-not-found";
+    if (/confirmation required|pending confirmation|requires confirmation/i.test(text))
+        return "confirmation-required";
+    // Match real timeout phrasing only. Do not treat bare "timeout" as a hit — accessible names can include that word,
+    // and `timed?\s*out` would also match the substring "timeout" as time+out.
+    if (options.timedOut ||
+        /\b(?:timed\s+out|timeout exceeded|watchdog|IPC read timeout)\b|must stay under its 30s IPC read timeout|Operation timed out/i.test(text)) {
         return "timeout";
+    }
     if (/ENOENT|not found on PATH|could not find.*agent-browser|agent-browser is required but was not found/i.test(text))
         return "missing-binary";
     if (options.parseError || /invalid JSON|missing boolean success|success field must be boolean|returned no JSON output/i.test(text))

package/dist/extensions/agent-browser/lib/results/presentation/diagnostics.js

@@ -617,6 +617,49 @@ function formatConsoleText(data, commandInfo) {
     }
     return shown.join("\n");
 }
+function formatA11yText(data) {
+    const counts = isRecord(data.counts) ? data.counts : undefined;
+    const violations = getArrayField(data, "violations") ?? [];
+    const incomplete = getArrayField(data, "incomplete") ?? [];
+    if (!counts && violations.length === 0 && incomplete.length === 0)
+        return undefined;
+    const lines = [];
+    const axeVersion = getStringField(data, "axeVersion");
+    if (axeVersion)
+        lines.push(`axe-core ${redactModelFacingText(axeVersion)}`);
+    const url = getStringField(data, "url");
+    if (url)
+        lines.push(`URL: ${redactModelFacingText(url)}`);
+    const violationCount = typeof counts?.violations === "number" ? counts.violations : violations.length;
+    const incompleteCount = typeof counts?.incomplete === "number" ? counts.incomplete : incomplete.length;
+    const passCount = typeof counts?.passes === "number" ? counts.passes : undefined;
+    const inapplicableCount = typeof counts?.inapplicable === "number" ? counts.inapplicable : undefined;
+    const countParts = [`${violationCount} violation${violationCount === 1 ? "" : "s"}`, `${incompleteCount} incomplete`];
+    if (passCount !== undefined)
+        countParts.push(`${passCount} passes`);
+    if (inapplicableCount !== undefined)
+        countParts.push(`${inapplicableCount} inapplicable`);
+    lines.push(`A11y audit: ${countParts.join(", ")}.`);
+    const previewLimit = Math.min(10, DIAGNOSTIC_LOG_PREVIEW_LIMIT);
+    const preview = violations.slice(0, previewLimit).map((item, index) => {
+        if (!isRecord(item))
+            return `${index + 1}. ${stringifyModelFacing(item)}`;
+        const id = redactModelFacingText(getStringField(item, "id") ?? "rule");
+        const impact = redactModelFacingText(getStringField(item, "impact") ?? "unknown");
+        const help = firstLine(redactModelFacingText(getStringField(item, "help") ?? "").replace(/\s+/g, " ").trim(), 160);
+        const nodeCount = typeof item.nodeCount === "number" ? item.nodeCount : getArrayField(item, "nodes")?.length;
+        const nodePart = typeof nodeCount === "number" ? `, ${nodeCount} node${nodeCount === 1 ? "" : "s"}` : "";
+        return `${index + 1}. [${impact}] ${id}${nodePart}${help ? ` — ${help}` : ""}`;
+    });
+    lines.push(...preview);
+    if (violations.length > preview.length) {
+        lines.push(`... (${violations.length - preview.length} additional violations omitted from preview)`);
+    }
+    if (incompleteCount > 0) {
+        lines.push(`${incompleteCount} incomplete check${incompleteCount === 1 ? "" : "s"} need manual review (see details.data.incomplete).`);
+    }
+    return lines.join("\n");
+}
 function formatErrorsText(data, commandInfo) {
     const errors = getArrayField(data, "errors");
     if (!errors)
@@ -966,6 +1009,8 @@ export function formatDiagnosticText(commandInfo, data) {
         return formatConsoleText(data, commandInfo);
     if (commandInfo.command === "errors")
         return formatErrorsText(data, commandInfo);
+    if (commandInfo.command === "a11y")
+        return formatA11yText(data);
     if (commandInfo.command === "dashboard")
         return formatDashboardText(data);
     if (commandInfo.command === "doctor")

package/docs/COMMAND_REFERENCE.md

@@ -18,13 +18,23 @@ This project intentionally blocks normal `agent-browser` bash usage in most agen
 
 <!-- agent-browser-capability-baseline:start upstream-baseline -->
 <!-- Generated from scripts/agent-browser-capability-baseline.mjs. Run `npm run docs -- command-reference write` to update. Do not edit manually. -->
-This reference is baselined to the locally installed `agent-browser 0.32.2` command/help surface, audited against vercel-labs/agent-browser@6ede7a9470ac4b681cabf838af8668b9aa99e957. Upstream `agent-browser` remains the source of truth for command semantics; this file is the local fallback for Pi agent sessions where direct binary help is blocked or discouraged.
+This reference is baselined to the locally installed `agent-browser 0.33.0` command/help surface, audited against vercel-labs/agent-browser@1ed371f3af472cc0d6cd8fdaea75d1a085ff7534. Upstream `agent-browser` remains the source of truth for command semantics; this file is the local fallback for Pi agent sessions where direct binary help is blocked or discouraged.
 
 The lightweight drift check is `npm run verify -- command-reference`. Run it whenever the installed upstream `agent-browser` version changes or this reference is edited.
 
 Use `npm run benchmark:agent-browser` or `npm run verify -- benchmark` before and after agent-facing workflow abstractions to measure task success, tool calls, model-visible output size, stale-ref behavior, artifact success, failure-category coverage, and elapsed-time estimates.
 <!-- agent-browser-capability-baseline:end upstream-baseline -->
 
+### Upstream 0.33.0 rebaseline
+
+The 0.32.3–0.33.0 releases add HAR body capture, fix semantic locators, and ship accessibility audits:
+
+- 0.32.3 embeds text response bodies in HAR captures by default and adds `network har start --content <mode>` with `text` (default), `all`, and `none`. It also ships the `derive-client` skill for recording traffic and generating a standalone API client from HAR data.
+- 0.32.4 makes `find role` match implicit ARIA roles and browser-computed accessible names (for example `find role heading text --name` against `<h2>`, lists, and banners), keeps case-insensitive substring name matching by default, preserves locator detail in element-not-found errors (`Names seen: …`), and aligns advertised `find` actions to `click, fill, check, hover, text`.
+- 0.33.0 adds `a11y [url]` axe-core accessibility audits (`--tags`, `--selector`, structured JSON) with an embedded offline engine, plus a native fix that revives discarded tabs on tab switch instead of hanging the daemon.
+
+This wrapper classifies 0.32.4+ locator-detail misses as `selector-not-found`, treats HAR `--content` and a11y `--tags` as command-scoped value flags, renders compact `a11y` summaries, and documents the skill/HAR/a11y surfaces. No Eve-specific Pi runtime is added.
+
 ### Upstream 0.32.2 rebaseline
 
 The 0.32.1 and 0.32.2 releases only update the separate `@agent-browser/eve` integration; the CLI/help/schema surface is unchanged:
@@ -62,7 +72,7 @@ The 0.31.1 rebaseline is a React bugfix release: `react tree`, `react inspect <i
 
 The 0.31.0 rebaseline adds restore workflow and namespace/session lifecycle surfaces: `--restore [name]`, `--restore-save <policy>`, restore check flags, `--namespace <name>`, `session id`, and `session info`. The wrapper parses those globals, keeps `--namespace` before `--session`, carries namespace context through managed-session probes and state, and keeps `session id` / `session info` sessionless. Use `agent_browser` with `args: ["session", "id", "--scope", "worktree", "--prefix", "my-skill"]` to derive reusable session ids from inside Pi; use `--restore=<key>` when passing an explicit key that could be confused with a command word.
 
-Runtime probes retain the 0.30.1 `wait --url` fix: `wait --url "**/dashboard"` succeeds after a `pushstate /dashboard`, so `job.assertUrl` delegates exact and glob patterns to upstream `wait --url`. Two old caveats still stand: `find ... uncheck` and `wait <selector> --state hidden|detached` remain advertised by help but fail at runtime. Keep the wrapper's direct `uncheck` passthrough and `wait --fn` disappearance guidance.
+Runtime probes retain the 0.30.1 `wait --url` fix: `wait --url "**/dashboard"` succeeds after a `pushstate /dashboard`, so `job.assertUrl` delegates exact and glob patterns to upstream `wait --url`. Upstream 0.32.4 aligns advertised `find` actions with the dispatcher: `click, fill, check, hover, text` only—use top-level `uncheck <selector-or-ref>` (and `type` / `focus`) instead of `find ... uncheck|type|focus`. One older caveat still stands: `wait <selector> --state hidden|detached` remains advertised by some help paths but fails at runtime, so keep `wait --fn` disappearance guidance.
 
 ### Upstream 0.29.1 rebaseline
 
@@ -148,7 +158,7 @@ Tool parameters (use exactly one of `args`, `semanticAction`, `job`, `qa`, `sour
 
 ### Debug, diff, stream, dashboard, and chat families
 
-Upstream also exposes non-core families (`network`, `diff`, `trace` / `profiler` / `record`, `console` / `errors` / `highlight` / `inspect` / `clipboard`, `stream`, `dashboard`, `chat`, and related subcommands). The wrapper still owns argv planning, `--json`, managed sessions where applicable, artifact metadata, and model-facing presentation: structured results are compacted and scrubbed in `extensions/agent-browser/lib/results/presentation.ts`, and echoed argv uses the same `redactInvocationArgs` rules as core commands (see [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details) for the field contract). Deterministic fake-upstream coverage for representative JSON shapes and redaction lives in `test/agent-browser.extension-validation.test.ts` under `agentBrowserExtension passes through non-core network debug diff stream dashboard and chat families`.
+Upstream also exposes non-core families (`network`, `diff`, `trace` / `profiler` / `record`, `console` / `errors` / `a11y` / `highlight` / `inspect` / `clipboard`, `stream`, `dashboard`, `chat`, and related subcommands). The wrapper still owns argv planning, `--json`, managed sessions where applicable, artifact metadata, and model-facing presentation: structured results are compacted and scrubbed in `extensions/agent-browser/lib/results/presentation.ts`, and echoed argv uses the same `redactInvocationArgs` rules as core commands (see [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details) for the field contract). Deterministic fake-upstream coverage for representative JSON shapes and redaction lives in `test/agent-browser.extension-validation.test.ts` under `agentBrowserExtension passes through non-core network debug diff stream dashboard and chat families`.
 
 ## Recommended workflow
 
@@ -242,7 +252,7 @@ Examples:
 { "args": ["snapshot", "-i"] }
 ```
 
-The optional native `semanticAction` object is only a thin schema for common locator-based actions, direct selector/ref click/check/fill, and native dropdown selection; it compiles locator actions to existing upstream `find` commands, direct selector/ref actions to `click` / `check` / `fill`, compiles `action: "select"` to upstream `select <selector> <value...>`, and reports the compiled argv in `details.compiledSemanticAction` (see [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#semanticaction) for the full field rules). For `locator: "role"`, pass either `value: "button"` or `role: "button"`; if both are present they must match. It is a top-level alternative to `args`, `job`, `qa`, `sourceLookup`, `networkSourceLookup`, and `electron`, not a nested shape inside `batch` stdin arrays. Add `session` inside `semanticAction` when the shorthand should target a named upstream browser session; the compiled argv prepends `--session <name>` before `find`, direct selector/ref commands, or `select`, and fallback candidate actions preserve that prefix. For active sessions, role/name click/check/fill shorthands may resolve through the current `snapshot -i` refs before execution so hidden duplicate matches do not steal the action; fill only resolves when there is one exact editable current ref match. Inspect `details.effectiveArgs` when you need the exact executed argv. `semanticAction` does not expose `uncheck` while upstream `find ... uncheck` is not runtime-supported; use raw `uncheck <selector-or-ref>` after choosing a stable selector or current snapshot ref. `select` shorthand intentionally requires a stable selector or current `@ref` plus `value`/`values`; upstream `find` does not expose a verified `select` action, so role/name/label dropdown resolution stays a snapshot/selector decision instead of hidden wrapper magic. If a raw `find` or semantic action misses with `selector-not-found`, the wrapper may take one fresh snapshot and append `Current snapshot ref fallback` when that snapshot has exact visible role/name matches for the failed target. Non-fill matches can include direct `try-current-visible-ref*` next actions. Semantic click misses may also include `Agent-browser candidate fallbacks`; `details.nextActions` first recommends a fresh `snapshot -i` and may include bounded role/name retries such as `button`/`link` for a missed `text` click, each as a `try-*-candidate` entry carrying redacted `find role …` argv.
+The optional native `semanticAction` object is only a thin schema for common locator-based actions, direct selector/ref click/check/fill, and native dropdown selection; it compiles locator actions to existing upstream `find` commands, direct selector/ref actions to `click` / `check` / `fill`, compiles `action: "select"` to upstream `select <selector> <value...>`, and reports the compiled argv in `details.compiledSemanticAction` (see [`TOOL_CONTRACT.md`](TOOL_CONTRACT.md#semanticaction) for the full field rules). For `locator: "role"`, pass either `value: "button"` or `role: "button"`; if both are present they must match. It is a top-level alternative to `args`, `job`, `qa`, `sourceLookup`, `networkSourceLookup`, and `electron`, not a nested shape inside `batch` stdin arrays. Add `session` inside `semanticAction` when the shorthand should target a named upstream browser session; the compiled argv prepends `--session <name>` before `find`, direct selector/ref commands, or `select`, and fallback candidate actions preserve that prefix. For active sessions, role/name click/check/fill shorthands may resolve through the current `snapshot -i` refs before execution so hidden duplicate matches do not steal the action; fill only resolves when there is one exact editable current ref match. Inspect `details.effectiveArgs` when you need the exact executed argv. `semanticAction` does not expose `uncheck` because upstream `find` actions are only `click, fill, check, hover, text`; use raw `uncheck <selector-or-ref>` after choosing a stable selector or current snapshot ref. `select` shorthand intentionally requires a stable selector or current `@ref` plus `value`/`values`; upstream `find` does not expose a verified `select` action, so role/name/label dropdown resolution stays a snapshot/selector decision instead of hidden wrapper magic. If a raw `find` or semantic action misses with `selector-not-found`, the wrapper may take one fresh snapshot and append `Current snapshot ref fallback` when that snapshot has exact visible role/name matches for the failed target. Non-fill matches can include direct `try-current-visible-ref*` next actions. Semantic click misses may also include `Agent-browser candidate fallbacks`; `details.nextActions` first recommends a fresh `snapshot -i` and may include bounded role/name retries such as `button`/`link` for a missed `text` click, each as a `try-*-candidate` entry carrying redacted `find role …` argv.
 
 For desktop, contenteditable, or host-controlled rich inputs, treat a semantic `fill` miss or mismatch differently. Active-session role/name fills can execute through one exact current editable `combobox`, `searchbox`, or `textbox` ref before upstream `find` runs. If a later selector miss still finds an exact current editable ref (`searchbox` or `textbox`), `details.richInputRecovery` and visible `Rich input recovery` describe the candidate and append `focus-current-editable-ref*` / `click-current-editable-ref*` next actions. Those actions deliberately do **not** copy the fill text and never press `Enter` or submit. Direct `fill @ref <text>` on contenteditable refs may also append/prepend instead of replacing; when the latest snapshot proves the target is contenteditable, the wrapper verifies `get text` after a successful fill and appends `details.fillVerification` plus `inspect-after-fill-verification` / `verify-filled-value` if the visible text does not match. Use the safe ladder instead: refresh refs, choose the current editable `@ref`, focus or click it, then send the intended text with `keyboard inserttext` or `keyboard type` in a separate call. Do not auto-submit unless the user flow explicitly calls for it.
 
@@ -562,7 +572,7 @@ Session note: `skills list`, `skills get …`, and `skills path …` are **state
 | `skills list` | List available CLI-bundled skills. |
 | `skills get core` | Print the core usage guide. |
 | `skills get core --full` | Print the full version-matched core command reference and templates. |
-| `skills get <name>` | Load a specialized skill such as `electron` or `slack`. Common specialized calls include `skills get electron`, `skills get slack`, `skills get dogfood`, `skills get vercel-sandbox`, and `skills get agentcore`. |
+| `skills get <name>` | Load a specialized skill such as `electron` or `slack`. Common specialized calls include `skills get electron`, `skills get slack`, `skills get dogfood`, `skills get vercel-sandbox`, `skills get agentcore`, and `skills get derive-client` (HAR-to-API-client workflow). |
 | `skills get <name> --full` | Include a skill's supplementary references/templates when present. |
 | `skills get --all` | Print all visible bundled skills for broad audit/debug work. |
 | `skills path [name]` | Print a skill directory path. |
@@ -663,10 +673,10 @@ These calls return plain text and stay stateless: the extension does not inject
 | `get text/html/value/count <selector>` | Read matched elements; use `get text body` for whole-page text. |
 | `get attr <selector> <name>`, `get box <selector>`, `get styles <selector>` | Read an attribute, bounding box, or computed styles from matched elements. |
 | `is <what> <selector>` | Check `visible`, `enabled`, or `checked`. |
-| `find <locator> <value> <action> [text]` | Locator types include `role`, `text`, `label`, `placeholder`, `alt`, `title`, and `testid`; selector helpers include `find first <sel>`, `find last <sel>`, and `find nth <n> <sel>`. Role/text filters include `find role <role> --name <name>` and `find ... --exact`. |
+| `find <locator> <value> <action> [text]` | Locator types include `role`, `text`, `label`, `placeholder`, `alt`, `title`, and `testid`; selector helpers include `find first <sel>`, `find last <sel>`, and `find nth <n> <sel>`. Role/text filters include `find role <role> --name <name>` and `find ... --exact`. Actions are `click, fill, check, hover, text` only. Prefer `find role` for semantic elements: implicit roles work (`find role heading text --name` for `<h2>`, list/banner landmarks, and similar). Default name matching is a case-insensitive substring; `--exact` makes the accessible name case-sensitive. On misses, upstream 0.32.4+ keeps locator detail such as `Names seen: …` or `No element found: getByRole(...)` instead of a generic flatten. |
 | `mouse <action> [args]` | `move <x> <y>`, `down [btn]`, `up [btn]`, `wheel <dy> [dx]`. |
 | `set <setting> [value]` | `viewport <w> <h>`, `device <name>`, `geo <lat> <lng>`, `offline [on|off]`, `headers <json>`, `credentials <user> <pass>`, and `set media <features>` (`dark`, `light`, and/or `reduced-motion`). |
-| `network <action>` | `network route <url> [--abort|--body <json>] [--resource-type <csv>]`, `network unroute [url]`, `network requests [--clear] [--filter <pattern>] [--type <csv>] [--method <method>] [--status <code|range>]`, `network request <requestId>`, `network har start`, and `network har stop [path]`. `--resource-type` filters intercepted requests by CDP resource type, such as `script`, `image`, `font`, `xhr`, or `fetch`; request listing filters accept resource types (`xhr,fetch`), methods (`POST`), and statuses (`2xx`, `400-499`). |
+| `network <action>` | `network route <url> [--abort|--body <json>] [--resource-type <csv>]`, `network unroute [url]`, `network requests [--clear] [--filter <pattern>] [--type <csv>] [--method <method>] [--status <code|range>]`, `network request <requestId>`, `network har start`, `network har start --content text` (default; embeds text bodies), `network har start --content all`, `network har start --content none`, and `network har stop [path]`. `--resource-type` filters intercepted requests by CDP resource type, such as `script`, `image`, `font`, `xhr`, or `fetch`; request listing filters accept resource types (`xhr,fetch`), methods (`POST`), and statuses (`2xx`, `400-499`). HAR files can include auth headers and bodies—do not share them unredacted. For turning a recording into a reusable API client, load `skills get derive-client`. |
 | `cookies [get|set|clear]` | Manage cookies. Full set form: `cookies set <name> <value> --url <url> --domain <domain> --path <path> --httpOnly --secure --sameSite <Strict|Lax|None> --expires <timestamp>`; also supports `cookies set --curl <file>` for JSON, cURL, or bare Cookie-header bulk imports. |
 | `storage <local|session>` | Manage web storage. |
 
@@ -742,6 +752,7 @@ Current upstream still does not parse `wait <selector> --state hidden` / `wait <
 | `react renders start` | Start recording React render activity. |
 | `react renders stop [--json]` | Stop render recording and print mount/re-render counts and changed details. |
 | `react suspense [--only-dynamic] [--json]` | Classify Suspense boundaries with grouped root-cause recommendations. |
+| `a11y [url]` | Run an embedded axe-core accessibility audit on the current page, or navigate to `url` first. Options: `a11y --tags wcag2a,wcag2aa`, `a11y --selector "#main"`. CDP browsers only (not Safari/iOS WebDriver). Model-facing text summarizes violation/incomplete counts and top rules; full node targets stay in `details.data`. |
 | `vitals [url] [--json]` | Report Core Web Vitals: LCP, CLS, TTFB, FCP, INP, plus React hydration timing when available. `web-vitals [url] [--json]` is the upstream alias. |
 | `pushstate <url>` | Perform SPA client-side navigation; detects Next.js router pushes and falls back to history navigation events. |
 | `removeinitscript <id>` | Remove an init script registered through upstream init-script mechanisms. |
@@ -949,19 +960,23 @@ Other useful environment variables include `AGENT_BROWSER_DEFAULT_TIMEOUT`, `AGE
 <!-- agent-browser-capability-baseline:start capability-token-baseline -->
 <!-- Generated from scripts/agent-browser-capability-baseline.mjs. Run `npm run docs -- command-reference write` to update. Do not edit manually. -->
 <details>
-<summary>Generated verifier capability baseline for agent-browser 0.32.2</summary>
+<summary>Generated verifier capability baseline for agent-browser 0.33.0</summary>
 
 This generated block is review data for maintainers. The human-authored reference sections above remain the readable command guide.
 
 #### Source evidence
 - repository: `vercel-labs/agent-browser`
-- upstream HEAD: `6ede7a9470ac4b681cabf838af8668b9aa99e957`
-- upstream package version: `0.32.2`
+- upstream HEAD: `1ed371f3af472cc0d6cd8fdaea75d1a085ff7534`
+- upstream package version: `0.33.0`
 - inspected: `agent-browser --version`
 - inspected: `agent-browser --help`
 - inspected: `selected agent-browser <command> --help output`
+- inspected: `agent-browser a11y --help`
 - inspected: `agent-browser mcp --help`
 - inspected: `agent-browser plugin --help`
+- inspected: `agent-browser skills list`
+- inspected: `agent-browser skills get core --full`
+- inspected: `agent-browser skills get derive-client --full`
 - inspected: `README.md`
 - inspected: `CHANGELOG.md`
 - inspected: `agent-browser.schema.json`
@@ -970,8 +985,17 @@ This generated block is review data for maintainers. The human-authored referenc
 - inspected: `cli/src/read.rs`
 - inspected: `cli/src/doctor/webgpu.rs`
 - inspected: `cli/src/native/actions.rs`
+- inspected: `cli/src/native/a11y/mod.rs`
+- inspected: `cli/src/native/browser.rs`
 - inspected: `cli/src/native/daemon.rs`
+- inspected: `cli/src/output.rs`
 - inspected: `docs/src/app/webgpu/page.mdx`
+- inspected: `docs/src/app/network/page.mdx`
+- inspected: `docs/src/app/selectors/page.mdx`
+- inspected: `docs/src/app/skills/page.mdx`
+- inspected: `docs/src/app/commands/page.mdx`
+- inspected: `skill-data/derive-client/SKILL.md`
+- inspected: `skill-data/core/SKILL.md`
 - inspected: `packages/@agent-browser/eve/README.md`
 - inspected: `packages/@agent-browser/eve/package.json`
 - inspected: `packages/@agent-browser/eve/test/extension.test.mjs`
@@ -1027,6 +1051,7 @@ This generated block is review data for maintainers. The human-authored referenc
 - record help: `agent-browser record --help`
 - console help: `agent-browser console --help`
 - errors help: `agent-browser errors --help`
+- a11y help: `agent-browser a11y --help`
 - clipboard help: `agent-browser clipboard --help`
 - tap help: `agent-browser tap --help`
 - swipe help: `agent-browser swipe --help`
@@ -1038,10 +1063,10 @@ This generated block is review data for maintainers. The human-authored referenc
 - plugin help: `agent-browser plugin --help`
 
 #### Inventory sections
-- Built-in skills: 15 human-doc token(s), 15 upstream token(s)
-- Core page, element, navigation, and extraction commands: 81 human-doc token(s), 82 upstream token(s)
+- Built-in skills: 16 human-doc token(s), 18 upstream token(s)
+- Core page, element, navigation, and extraction commands: 82 human-doc token(s), 84 upstream token(s)
 - Sessions, state, tabs, frames, dialogs, and windows: 24 human-doc token(s), 20 upstream token(s)
-- Network, storage, artifacts, diagnostics, and performance: 43 human-doc token(s), 53 upstream token(s)
+- Network, storage, artifacts, diagnostics, and performance: 49 human-doc token(s), 60 upstream token(s)
 - Batch, auth, confirmations, setup, dashboard, devices, and AI commands: 33 human-doc token(s), 37 upstream token(s)
 - Global flags, config, providers, policy, and environment: 138 human-doc token(s), 106 upstream token(s)
 
@@ -1058,6 +1083,7 @@ This generated block is review data for maintainers. The human-authored referenc
 - `skills get dogfood`
 - `skills get vercel-sandbox`
 - `skills get agentcore`
+- `skills get derive-client`
 - `@agent-browser/sandbox`
 - `installSystemDependencies: false`
 - `skills path [name]`
@@ -1139,6 +1165,7 @@ This generated block is review data for maintainers. The human-authored referenc
 - `find last <sel>`
 - `find nth <n> <sel>`
 - `find role <role> --name <name>`
+- `find role heading text --name`
 - `find ... --exact`
 - `mouse <action> [args]`
 - `set <setting> [value]`
@@ -1179,6 +1206,9 @@ This generated block is review data for maintainers. The human-authored referenc
 - `network requests [--clear] [--filter <pattern>] [--type <csv>] [--method <method>] [--status <code|range>]`
 - `network request <requestId>`
 - `network har start`
+- `network har start --content all`
+- `network har start --content none`
+- `network har start --content text`
 - `network har stop [path]`
 - `cookies [get|set|clear]`
 - `cookies set <name> <value> --url <url> --domain <domain> --path <path> --httpOnly --secure --sameSite <Strict|Lax|None> --expires <timestamp>`
@@ -1215,6 +1245,9 @@ This generated block is review data for maintainers. The human-authored referenc
 - `react suspense [--only-dynamic] [--json]`
 - `vitals [url] [--json]`
 - `web-vitals [url] [--json]`
+- `a11y [url]`
+- `a11y --tags wcag2a,wcag2aa`
+- `a11y --selector "#main"`
 - `removeinitscript <id>`
 
 ##### Batch, auth, confirmations, setup, dashboard, devices, and AI commands
@@ -1404,11 +1437,14 @@ This generated block is review data for maintainers. The human-authored referenc
 - skills list: `dogfood`
 - skills list: `vercel-sandbox`
 - skills list: `agentcore`
+- skills list: `derive-client`
 - vercel sandbox skill full: `@agent-browser/sandbox`
 - vercel sandbox skill full: `installSystemDependencies: false`
 - core skill full: `agent-browser frame @e3`
 - core skill full: `agent-browser dialog accept`
 - core skill full: `agent-browser --session "$SESSION" --restore open https://app.example.com`
+- core skill full: `network har start --content all`
+- core skill full: `implicit roles work`
 
 ##### Core page, element, navigation, and extraction commands
 - open help: `open [url]`
@@ -1482,6 +1518,8 @@ This generated block is review data for maintainers. The human-authored referenc
 - find help: `nth <index> <selector>`
 - find help: `--name <name>`
 - find help: `--exact`
+- find help: `case-insensitive`
+- find help: `click, fill, check, hover, text`
 - root help: `Mouse:  agent-browser mouse <action> [args]`
 - root help: `Browser Settings:  agent-browser set <setting> [value]`
 - set help: `media [dark|light]`
@@ -1521,6 +1559,8 @@ This generated block is review data for maintainers. The human-authored referenc
 - root help: `--resource-type <csv>`
 - network help: `unroute [url]`
 - network help: `network har start`
+- network help: `network har start --content all`
+- network help: `--content <mode>`
 - network help: `network har stop ./capture.har`
 - root help: `cookies [get|set|clear]`
 - root help: `cookies set --curl <file>`
@@ -1550,6 +1590,11 @@ This generated block is review data for maintainers. The human-authored referenc
 - root help: `react renders stop [--json]`
 - root help: `react suspense [--only-dynamic] [--json]`
 - root help: `vitals [url] [--json]`
+- root help: `a11y [url] [--tags <t1,t2>] [--selector <css>] [--json]`
+- a11y help: `a11y [url]`
+- a11y help: `--tags <tag1,tag2>`
+- a11y help: `-s, --selector <css>`
+- core skill full: `agent-browser a11y`
 - root help: `removeinitscript <id>`
 - network help: `requests [options]`
 - network help: `--type <types>`

package/docs/SUPPORT_MATRIX.md

@@ -26,10 +26,10 @@ When upstream ships a new `agent-browser` or the inventory changes:
 
 ## Audit result
 
-- Target upstream: `agent-browser 0.32.2` (must match `CAPABILITY_BASELINE.targetVersion` in [`scripts/agent-browser-capability-baseline.mjs`](../scripts/agent-browser-capability-baseline.mjs)).
+- Target upstream: `agent-browser 0.33.0` (must match `CAPABILITY_BASELINE.targetVersion` in [`scripts/agent-browser-capability-baseline.mjs`](../scripts/agent-browser-capability-baseline.mjs)).
 - Source of truth: `CAPABILITY_BASELINE.inventorySections` in the same file (stable `id` keys: `skills`, `core-commands`, `state-tabs-frames-dialogs`, `network-storage-artifacts-diagnostics`, `batch-auth-setup-ai`, `options-and-env`).
-- Status: source and wrapper adaptation are complete for the 2026-07-18 0.32.2 audit; the 0.32.1–0.32.2 changes stay isolated to the separate `@agent-browser/eve` package, while the wrapper now also keeps hidden helper subprocesses on the same idle-timeout launch configuration, refreshes the remaining active target after `tab close`, and performs deterministic document-direction scrolls before wheel fallback.
-- 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.
+- Status: source and wrapper adaptation target the 2026-07-23 0.33.0 audit. The wrapper classifies 0.32.4+ locator-detail find misses as `selector-not-found`, treats HAR `--content` and a11y `--tags` as command-scoped value flags, documents `derive-client` / HAR body modes / `a11y`, and renders compact a11y summaries; prior helper idle-timeout, post-`tab close` target refresh, and document-direction scroll behavior remain. Upstream 0.33.0 also revives discarded tabs on tab switch.
+- 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. The 0.32.3–0.32.4 rebaseline adds HAR response-body capture modes, the `derive-client` skill, fixed `find role` implicit-ARIA / accessible-name matching with locator-detail misses, and an advertised `find` action list of `click, fill, check, hover, text` only; the wrapper documents and classifies those surfaces without adding a new input mode. Remaining upstream-owned caveat: some help paths still mention `wait <selector> --state hidden` / `detached`, but runtime probes show those shapes still fail, so wrapper docs keep `wait --fn` disappearance predicates and top-level `uncheck` / `type` / `focus` passthrough instead of `find` for those actions. `wait --download <path>` still reports the requested path without guaranteed on-disk persistence ([#1300](https://github.com/vercel-labs/agent-browser/issues/1300)).
 - 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).
 
 ## UX/reliability decisions from 2026-05-29 agent feedback
@@ -52,24 +52,26 @@ Current summary:
 | RQ-0134 | Upstream `agent-browser 0.32.0` rebaseline hardens domain containment, fixes completed-page waits, and adds a separate eve extension package; wrapper launch policy and docs cover the relevant behavior. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0320-rebaseline) |
 | RQ-0135 | Upstream `agent-browser 0.32.2` rebaseline updates eve packaging only and closes the wrapper's prior missing `read [url]` inventory/presentation contract. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0322-rebaseline) |
 | RQ-0136 | Wrapper regression fix keeps helper subprocess launch environments stable, refreshes active tab state after `tab close`, and makes ordinary document-direction scrolling deterministic before upstream fallback. | [`docs/ARCHITECTURE.md`](ARCHITECTURE.md), [`docs/TOOL_CONTRACT.md`](TOOL_CONTRACT.md#details) |
+| RQ-0137 | Upstream `agent-browser 0.32.4` rebaseline adds HAR `--content` body modes, the `derive-client` skill, and fixed `find role` implicit-ARIA/name matching with locator-detail misses; wrapper classifier/argv/docs cover those surfaces. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0330-rebaseline) |
+| RQ-0138 | Upstream `agent-browser 0.33.0` rebaseline adds `a11y` axe-core audits and discarded-tab revival on tab switch; wrapper documents/presents `a11y` and samples the new help surface. | [`docs/COMMAND_REFERENCE.md`](COMMAND_REFERENCE.md#upstream-0330-rebaseline) |
 
 ## Verification evidence
 
-Re-run the gates below before each release; this table records what the closure audit exercised. The 0.32.2 / Pi 0.80.10 local rebaseline gates passed on 2026-07-18; the prior 0.32.0 / Pi 0.80.9 release-composition and platform rows remain explicitly historical evidence.
+Re-run the gates below before each release; this table records what the closure audit exercised. The 0.33.0 / package 0.2.72 local rebaseline gates passed on 2026-07-23.
 
 | Gate | Evidence | Status |
 | --- | --- | --- |
-| Default local gate | `npm run verify` checks generated playbook drift, clean-builds generated `dist/`, runs `tsc --noEmit`, unit/fake tests, generated command-reference blocks, and live command-reference sampling. | **Current for 0.32.2 / Pi 0.80.10:** pass on 2026-07-18 (590 passed, 2 opt-in skips; live command-reference verification passed). |
-| Pre-PR local gate | `npm run verify -- pre-pr` composes the default gate with package-content verification. Use before larger local handoffs or PR-ready claims when lifecycle/platform/live dogfood cost is not warranted. | **Current for 0.32.0:** covered by the stronger passing release composition on 2026-07-16; orchestration remains locked by `test/project-verify.test.ts`. |
-| Real upstream contract | `npm run verify -- real-upstream` runs the localhost fixture matrix against the real installed `agent-browser` matching the baseline. | **Current for 0.32.2:** pass on 2026-07-18 (2/2 real-upstream tests), including snapshot-ref native select, stable-id/label tab switching, active-target refresh after `tab close`, and visible `read` content against the localhost contract fixture. |
-| Packaged Pi smoke | `npm run verify -- package-pi` validates package contents, loads the packaged `agent_browser` tool without requiring optional Brave config, and executes fake-upstream `--version`. | **Current for package 0.2.71 / Pi 0.80.10:** pass on 2026-07-18 (116 packed entries; exactly one packaged `agent_browser`; invocation passed). |
+| Default local gate | `npm run verify` checks generated playbook drift, clean-builds generated `dist/`, runs `tsc --noEmit`, unit/fake tests, generated command-reference blocks, and live command-reference sampling. | **Current for 0.33.0:** pass on 2026-07-23 (590 passed, 2 opt-in skips; live command-reference verification passed). |
+| Pre-PR local gate | `npm run verify -- pre-pr` composes the default gate with package-content verification. Use before larger local handoffs or PR-ready claims when lifecycle/platform/live dogfood cost is not warranted. | **Current for 0.33.0:** covered by the stronger passing release composition on 2026-07-23; orchestration remains locked by `test/project-verify.test.ts`. |
+| Real upstream contract | `npm run verify -- real-upstream` runs the localhost fixture matrix against the real installed `agent-browser` matching the baseline. | **Current for 0.33.0:** pass on 2026-07-23 (2/2 real-upstream tests). |
+| Packaged Pi smoke | `npm run verify -- package-pi` validates package contents, loads the packaged `agent_browser` tool without requiring optional Brave config, and executes fake-upstream `--version`. | **Current for package 0.2.72:** pass on 2026-07-23 inside `npm run verify -- release`. |
 | Startup profile | `npm run verify -- startup-profile --samples <n>` clean-builds generated `dist/`, records direct package entrypoint import/factory timing in fresh Node processes, and writes `.artifacts/startup-profile/latest.json`. It must not launch Pi, tmux, mise, npm, browsers, or `agent-browser`; full Pi TUI ready-prompt profiling is intentionally excluded after it proved too invasive for routine verification. Run this opt-in evidence when package layout, the compiled entrypoint, top-level imports, schema registration, or prompt/config startup logic changes. | **Current for compiled entrypoint:** pass on 2026-07-18 (`npm run verify -- startup-profile --samples 3`; median 49.1 ms, maximum 50.1 ms, below the 250 ms budget). Full-Pi startup numbers from the unsafe tmux profiler are not accepted as ongoing release evidence. |
-| Deterministic dogfood smoke | `npm run verify -- dogfood` (`scripts/verify-agent-browser-dogfood.ts`) drives the native wrapper against a local file fixture through top-level `qa`, `semanticAction`, constrained `job`, screenshot artifact verification, and session close with the real `agent-browser` on `PATH`. | **Current for 0.32.2:** pass on 2026-07-18; checkout-loaded Artificial Analysis/React/GitHub dogfood also passed snapshot-ref interactions, document scroll, and multi-tab close/reuse without background restarts or tab resets. |
+| Deterministic dogfood smoke | `npm run verify -- dogfood` (`scripts/verify-agent-browser-dogfood.ts`) drives the native wrapper against a local file fixture through top-level `qa`, `semanticAction`, constrained `job`, screenshot artifact verification, and session close with the real `agent-browser` on `PATH`. | **Current for 0.33.0:** covered by Crabbox `browser-dogfood-smoke` on macOS/Ubuntu/Windows inside `npm run verify -- release` on 2026-07-23. |
 | WebGPU and restore autosave | Live 0.31.2 feature probes validate the new upstream paths independently from ordinary browser dogfood. | **macOS:** `doctor --webgpu` passed Apple Metal render/readback and headless red-pixel screenshot checks; the official Hello Triangle sample exposed the Metal adapter and produced a verified non-black screenshot. **Ubuntu image:** `doctor --webgpu --headed --json` passed SwiftShader render/readback and red-pixel screenshot checks with the baked Vulkan/Mesa/Xvfb dependencies. **Restore autosave:** an idle page timer changed localStorage and the namespaced restore file contained the new value before close; test state was removed. **Windows interactive desktop:** post-release validation on 2026-07-15 used a disposable clone of snapshot `57cc3c0d-7d7c-4a4c-9c57-8270d4174679`, a logged-in console session, `agent-browser 0.31.2`, and Edge 150. The headed doctor WebGPU render/readback subcheck passed in 0.99s and its decoded screenshot subcheck passed with `rgb(255,0,0)`; a separate `--webgpu --headed` launch opened the proof page and the Parallels console capture visibly recorded the red triangle (553,500 bright-red pixels; SHA-256 `f5a28f5336cbdfeb0ff557af9425458bddc6b266d3cc6b946de7b101a0b43288`). The full doctor remained nonzero only for the unrelated absence of a separately installed Chrome binary; the explicit Edge executable completed the launch and both WebGPU probes. Local evidence is under `.artifacts/windows-webgpu-interactive/20260715T150903Z/summary.json`; the disposable clone and temporary account were deleted afterward. |
 | Efficiency benchmark | `npm run verify -- benchmark` runs deterministic browser workflow accounting plus focused benchmark tests, including JSONL sampling fixtures and job/qa/sourceLookup/networkSourceLookup/Electron scenario coverage. | **Current:** pass on 2026-07-18 (`npm run verify -- benchmark`; 13/13 deterministic scenarios passed). |
-| Crabbox platform smoke | `npm run check:platform-smoke` syntax-checks the harness and cheap invariants. `npm run smoke:platform:ubuntu-image` builds the project-owned Linux image, `npm run smoke:platform:doctor` checks Crabbox 0.26.0+ and local target readiness, and `npm run smoke:platform:all` runs doctor first, then fast target-local `platform-build` (`npm run verify -- platform-target`, pack, clean Pi install) plus `browser-dogfood-smoke` on Crabbox `macos`, `ubuntu`, and `windows-native`; see [`platform-smoke.md`](platform-smoke.md). Target artifacts include Crabbox/provider/work-root metadata, and release review also checks provider-specific `crabbox list` commands for leftover leases/clones. | **Current for 0.32.2 / Pi 0.80.10:** pass on 2026-07-18 inside `npm run verify -- release`; evidence roots are `run-1784406200583-yaojql` (macOS), `run-1784406200585-fyulk0` (Ubuntu), and `run-1784406200586-w1nkt1` (native Windows). All platform-build, browser-dogfood, and lease-cleanup summaries passed; no release-owned leases/clones remained. |
-| `verify -- release` / `prepublishOnly` | `npm run verify -- release` chains the default gate with the configured-source lifecycle harness, packaged Pi smoke, and the release-blocking Crabbox platform matrix (`verifySteps` `release` in [`scripts/project.mjs`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/scripts/project.mjs)). `package.json` `prepublishOnly` runs that compose before `npm pack --dry-run` during `npm publish`. It intentionally omits standalone real-upstream, host-only dogfood, and benchmark modes—see [`RELEASE.md`](RELEASE.md#pre-release-checks). | **Current for 0.32.2 / package 0.2.71 / Pi 0.80.10:** pass on 2026-07-18, including 590 passing default tests, live command-reference sampling, lifecycle, packaged Pi smoke, and the required macOS/Ubuntu/native-Windows matrix. |
-| Configured-source lifecycle | `npm run verify -- lifecycle` (`scripts/verify-lifecycle.mjs`) drives `/reload`, closes and relaunches Pi with the same exact `--session-id`, checks the JSONL session header id, session continuity, slash-command sentinel tokens (`v1` before reload and `v2` after full relaunch because compiled JS package modules are process-cached), persisted spill reachability, and real Pi `tool_result` failure-patch semantics for a QA reclassification with a fake upstream on `PATH`. Default Pi model is `zai/glm-5.2`; default per-step wait is **180000 ms** (`DEFAULT_TIMEOUT_MS`); override model with `--model <id>` and waits with `--timeout-ms <ms>`. Passthrough flags in [`scripts/project.mjs`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/scripts/project.mjs): `--keep-artifacts`, `--model`, `--verbose`, and `--timeout-ms` plus a value (for example `npm run verify -- lifecycle --model openai-codex/gpt-5.5:minimal --keep-artifacts --verbose --timeout-ms 600000`). | **Current for 0.32.2 / Pi 0.80.10:** pass on 2026-07-18 inside `npm run verify -- release`; reload/relaunch continuity, persisted spill reachability, and failure-patch assertions passed. |
+| Crabbox platform smoke | `npm run check:platform-smoke` syntax-checks the harness and cheap invariants. `npm run smoke:platform:ubuntu-image` builds the project-owned Linux image, `npm run smoke:platform:doctor` checks Crabbox 0.26.0+ and local target readiness, and `npm run smoke:platform:all` runs doctor first, then fast target-local `platform-build` (`npm run verify -- platform-target`, pack, clean Pi install) plus `browser-dogfood-smoke` on Crabbox `macos`, `ubuntu`, and `windows-native`; see [`platform-smoke.md`](platform-smoke.md). Target artifacts include Crabbox/provider/work-root metadata, and release review also checks provider-specific `crabbox list` commands for leftover leases/clones. | **Current for 0.33.0 / package 0.2.72:** pass on 2026-07-23 inside `npm run verify -- release`; evidence roots are `run-1784844609963-t3gs7f` (macOS), `run-1784844609966-jcdyhb` (Ubuntu), and `run-1784844609967-epvk68` (native Windows). Windows snapshot `crabbox-ready-ab-0.33.0`; Ubuntu image `node24-agent-browser0.33.0`. |
+| `verify -- release` / `prepublishOnly` | `npm run verify -- release` chains the default gate with the configured-source lifecycle harness, packaged Pi smoke, and the release-blocking Crabbox platform matrix (`verifySteps` `release` in [`scripts/project.mjs`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/scripts/project.mjs)). `package.json` `prepublishOnly` runs that compose before `npm pack --dry-run` during `npm publish`. It intentionally omits standalone real-upstream, host-only dogfood, and benchmark modes—see [`RELEASE.md`](RELEASE.md#pre-release-checks). | **Current for 0.33.0 / package 0.2.72:** pass on 2026-07-23, including 590 passing default tests, live command-reference sampling, lifecycle, packaged Pi smoke, and the required macOS/Ubuntu/native-Windows matrix. |
+| Configured-source lifecycle | `npm run verify -- lifecycle` (`scripts/verify-lifecycle.mjs`) drives `/reload`, closes and relaunches Pi with the same exact `--session-id`, checks the JSONL session header id, session continuity, slash-command sentinel tokens (`v1` before reload and `v2` after full relaunch because compiled JS package modules are process-cached), persisted spill reachability, and real Pi `tool_result` failure-patch semantics for a QA reclassification with a fake upstream on `PATH`. Default Pi model is `zai/glm-5.2`; default per-step wait is **180000 ms** (`DEFAULT_TIMEOUT_MS`); override model with `--model <id>` and waits with `--timeout-ms <ms>`. Passthrough flags in [`scripts/project.mjs`](https://github.com/fitchmultz/pi-agent-browser-native/blob/main/scripts/project.mjs): `--keep-artifacts`, `--model`, `--verbose`, and `--timeout-ms` plus a value (for example `npm run verify -- lifecycle --model openai-codex/gpt-5.5:minimal --keep-artifacts --verbose --timeout-ms 600000`). | **Current for 0.33.0:** pass on 2026-07-23 inside `npm run verify -- release`. |
 | Quick isolated Pi smoke | `pi --approve --no-extensions --no-skills -e . --tools agent_browser` from trusted repo root; native `agent_browser` only. | **Current for 0.32.2 / Pi 0.80.10:** pass on 2026-07-18 across isolated tmux runs using Artificial Analysis, React, GitHub, and a deterministic select/tab fixture. Snapshot-ref select/click, document scroll (0→700), stable-id/label tab switching, `tab close` target refresh, and post-close interaction passed with zero background restarts, `about:blank` resets, or spurious stale-ref failures; all disposable sessions/tmux/temp files were removed. |
 
 Runtime floor note: package metadata keeps Pi core package peer ranges wildcard per installed Pi package docs, but `pi-agent-browser-doctor` / `npm run doctor` treats `pi --version` below 0.80.6 as a setup failure. `npm run doctor` passed against Pi 0.80.6 on 2026-07-11. This keeps package dependency shape aligned with Pi package loading while still making unsupported host Pi versions a release and first-run blocker.

package/docs/TOOL_CONTRACT.md

@@ -161,7 +161,7 @@ The extension always plans normal browser commands with `--json` prepended in `e
 - For batch chains that touch cookies, storage, auth, or other secret-bearing commands, use details.batchSteps for per-step artifacts, categories, spill paths, and full structured errors; top-level details.data on batch is only a compact redacted step matrix (success, argv-redacted command, redacted result or scrubbed error text) built from the same presentation rules as standalone calls.
 - For non-core families, pass current upstream commands through the native tool directly: network requests, network route <url>, network har start/stop [path], diff snapshot, diff screenshot --baseline <file>, diff url <u1> <u2>, trace start, trace stop [path], profiler start, profiler stop [path], record start <path>, record stop, console/errors [--clear], highlight <selector>, inspect, clipboard read, clipboard write <text>, clipboard copy/paste, stream enable/disable/status, dashboard start/stop, device list for iOS simulator inventory, and chat <message>. For compact network requests output, prefer details.nextActions for request detail, route-mock diagnostics, actionable failed-request networkSourceLookup, filtering, clearing the aggregate buffer before repro, or HAR capture follow-ups instead of guessing request-id syntax. Artifact-producing commands report details.artifacts and verification state; long-running starts such as stream, dashboard, trace/profiler, and record should be paired with the matching stop/disable command when the task is done; stream enable already-enabled outcomes are treated as idempotent success with status/disable follow-ups.
 - For Electron desktop apps, prefer top-level electron for wrapper-owned discovery, isolated launch, status, compact probe, and cleanup: list first, treat likely-sensitive annotations as hints rather than enforcement, launch with the default snapshot handoff unless handoff: "tabs" is the safer diagnostic starting point, use electron.probe or snapshot -i/qa.attached for current-session state, and always cleanup the returned launchId when done. electron.launch uses an isolated temporary profile; it does not reuse the app's normal signed-in profile or attach to an already-running authenticated app. For signed-in local app state, host-launch the normal app with --remote-debugging-port when appropriate, then use raw args connect <port|url>; after connect, inspect tab list, select the stable tab id such as tab t2, then run a condition wait or snapshot -i before using refs. close commands (`close`, `quit`, or `exit`) only close the browser/CDP session; leave manually launched app shutdown, profile cleanup, and explicit artifacts to the host owner.
-- For provider or specialized app workflows, load version-matched upstream guidance with skills get agentcore|electron|slack|dogfood|vercel-sandbox through the native tool; add --full when you need references/templates, and use skills get --all only for broad skill audits. Hosted sandbox workflows should use upstream @agent-browser/sandbox helpers outside this wrapper. Provider launches such as -p ios, --provider browserbase/kernel/browseruse/browserless/agentcore, and iOS --device are upstream-owned setup paths; use sessionMode fresh when switching providers and expect external credentials or local Appium/Xcode setup to be required.
+- For provider or specialized app workflows, load version-matched upstream guidance with skills get agentcore|electron|slack|dogfood|vercel-sandbox|derive-client through the native tool; add --full when you need references/templates, and use skills get --all only for broad skill audits. Use derive-client when recording HAR traffic to generate a standalone API client; prefer network har start (text bodies by default) or network har start --content all|none before multi-step capture. For accessibility audits use a11y or a11y --tags wcag2a,wcag2aa (CDP browsers only). Hosted sandbox workflows should use upstream @agent-browser/sandbox helpers outside this wrapper. Provider launches such as -p ios, --provider browserbase/kernel/browseruse/browserless/agentcore, and iOS --device are upstream-owned setup paths; use sessionMode fresh when switching providers and expect external credentials or local Appium/Xcode setup to be required.
 - For dialogs and frames, use dialog status/accept/dismiss and frame <selector|main> through native args; dialog commands and eval snippets that look like alert/confirm/prompt/dialog triggers are shorter-bounded than normal browser calls, and timed-out dialog-like interactions may add inspect-dialog-after-timeout, dismiss-dialog-after-timeout, or recover-fresh-session-after-dialog-timeout nextActions. When --confirm-actions produces a pending confirmation, use details.nextActions or exact confirm <id> / deny <id> calls instead of inventing ids.
 - If a session lands on the wrong page or tab, an interaction changes origin unexpectedly, or an open call returns blocked, blank, or otherwise unexpected results, use tab list / tab <tab-id-or-label> / snapshot -i to recover state before retrying different URLs or fallback strategies. For headed demos, put --headed on the first launch with sessionMode=fresh and verify with screenshot/tab/get-url evidence because tool success cannot prove the OS window is visible to the user. For desktop readiness, prefer real conditions first: wait --text, wait --url, wait --fn, wait --load <state>, wait --download, or qa.attached; for disappearance checks, use wait --fn predicates instead of stale upstream-help examples like wait <selector> --state hidden. Use electron.probe/status for wrapper-owned launch health or target mismatch. Fixed waits are a last resort: use explicit --timeout or top-level timeoutMs for legitimately slow waits, and treat a successful payload like "waited":"timeout" as elapsed time only—verify completion with an observed condition, fresh snapshot, or screenshot.
 - For feed, timeline, or inbox reading tasks, focus on the main timeline/list region and read the first item there rather than unrelated composer or sidebar content.
@@ -227,7 +227,7 @@ Examples:
 - supported actions: `click`, `fill`, `check`, `select`
 - supported locators for `click` / `fill` / `check`: `role`, `text`, `label`, `placeholder`, `alt`, `title`, `testid`
 - optional `selector` is accepted for direct `click`, `check`, and `fill` targets (including current `@refs`); do not combine it with `locator`, `value`, `role`, or `name`. For `fill`, `text` is still required.
-- `semanticAction` does not expose `uncheck` while upstream `find ... uncheck` is not runtime-supported; use raw `args: ["uncheck", <selector-or-ref>]` after a stable selector or current snapshot ref
+- `semanticAction` does not expose `uncheck` because upstream `find` actions are only `click, fill, check, hover, text`; use raw `args: ["uncheck", <selector-or-ref>]` after a stable selector or current snapshot ref
 - for locator actions, `value` is the locator argument (for example ARIA role token `"button"`, label text, or visible substring), must be a non-empty string after trim; for `locator: "role"`, callers may provide `role` instead of redundant `value`
 - `fill` requires non-empty `text` (compiled as the trailing value argument to `find`)
 - `select` requires non-empty `selector` plus either `value` (single option value) or `values` (non-empty array of option values). `select` does not accept `locator`, `role`, `name`, or `text`; upstream `find` does not expose a verified `select` action, so role/name/label dropdown targeting must first be resolved to a stable selector or current `@ref`.
@@ -780,7 +780,7 @@ 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`. 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.
+- Failure: the classifier walks a single ordered chain (first match wins): explicit `options.confirmationRequired` → upstream locator-detail misses (`selector-not-found`, including 0.32.4+ `Names seen:` / `No element found: getByRole(...)` / `Element not found: … Verify the selector, role, or name`) → text-derived `confirmation-required` → `timeout` → `missing-binary` → `parse-failure` → `aborted` → `policy-blocked` → `cleanup-failed` → explicit `options.validationError` → `tab-drift` → `stale-ref` (including “unknown ref” text and a narrow `@eN` plus “element not found” heuristic) → `selector-unsupported` → other `selector-not-found` shapes → `download-not-verified` (download / wait-download style failures) → default `upstream-error`. Locator-detail misses are classified before text-derived confirmation/timeout so an accessible name containing those phrases cannot suppress selector recovery. Wrapper-known missing artifact checks pass an explicit `artifact-missing` category rather than relying on this text classifier.
 - The main tool implementation merges these fields into Pi-facing `details` from `extensions/agent-browser/index.ts` and from `extensions/agent-browser/lib/results/presentation.ts` for presentation-time failures.
 
 Additional structured fields can appear when relevant:

package/docs/platform-smoke.md

@@ -62,7 +62,7 @@ PLATFORM_SMOKE_MAC_PORT=22
 PLATFORM_SMOKE_UBUNTU_IMAGE="pi-agent-browser-native-platform:node24-agent-browser<baseline-version>"
 
 PLATFORM_SMOKE_WINDOWS_VM="pi-extension-windows-template"
-PLATFORM_SMOKE_WINDOWS_SNAPSHOT="crabbox-ready"
+PLATFORM_SMOKE_WINDOWS_SNAPSHOT="crabbox-ready-ab-0.33.0"
 PLATFORM_SMOKE_WINDOWS_USER="<windows-ssh-user>"
 PLATFORM_SMOKE_WINDOWS_WORK_ROOT="C:\\crabbox\\pi-agent-browser-native"
 
@@ -80,11 +80,11 @@ Crabbox does not install project runtime tools. The macOS host, Ubuntu image, an
 
 - Node/npm at or above the configured Node major baseline in [`platform-smoke.config.mjs`](../platform-smoke.config.mjs).
 - Git and `tar`.
-- Upstream `agent-browser` matching this wrapper’s capability baseline. The Ubuntu target gets it from [`scripts/platform-smoke/linux-image/Dockerfile`](../scripts/platform-smoke/linux-image/Dockerfile); the Windows template gets it from the shared `pi-extension-windows-template` / `crabbox-ready` snapshot.
+- Upstream `agent-browser` matching this wrapper’s capability baseline. The Ubuntu target gets it from [`scripts/platform-smoke/linux-image/Dockerfile`](../scripts/platform-smoke/linux-image/Dockerfile); the Windows template gets it from the shared `pi-extension-windows-template` snapshot named in [`platform-smoke.config.mjs`](../platform-smoke.config.mjs) (currently `crabbox-ready-ab-0.33.0`, a child of the shared `crabbox-ready` base used by other projects' linked clones).
 - Browser/runtime dependencies needed by upstream `agent-browser`.
 - Native PowerShell and OpenSSH Server on Windows.
 
-For Windows, reuse `pi-extension-windows-template` with the shared canonical `crabbox-ready` power-off snapshot configured in [`platform-smoke.config.mjs`](../platform-smoke.config.mjs). Do not create one-off project VMs or run tests directly on the source VM. If a reusable tool is missing, update the shared template, verify from a fresh SSH session, remove caches/secrets/checkouts, shut down cleanly, and promote a known-good power-off snapshot.
+For Windows, reuse `pi-extension-windows-template` with the power-off snapshot configured in [`platform-smoke.config.mjs`](../platform-smoke.config.mjs). Do not create one-off project VMs or run tests directly on the source VM. If a reusable tool is missing, update the shared template from the current base snapshot, verify from a fresh SSH session, remove caches/secrets/checkouts, shut down cleanly, and promote a known-good power-off snapshot (a child snapshot is fine when other projects still hold linked clones of an older base).
 
 ## What the suites prove
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-agent-browser-native",
-  "version": "0.2.71",
+  "version": "0.2.72",
   "description": "pi extension that exposes agent-browser as a native tool for browser automation",
   "type": "module",
   "author": "Mitch Fultz (https://github.com/fitchmultz)",

package/platform-smoke.config.mjs

@@ -22,7 +22,9 @@ export default {
 	ubuntuContainerImage: PLATFORM_SMOKE_UBUNTU_IMAGE,
 	windowsParallels: {
 		sourceVm: "pi-extension-windows-template",
-		snapshot: "crabbox-ready",
+		// Shared template snapshot with agent-browser 0.33.0 (+ Chrome 151 for the SSH user).
+		// Parent crabbox-ready remains for other projects' linked clones.
+		snapshot: "crabbox-ready-ab-0.33.0",
 	},
 	nodeValidationMajor: 22,
 	agentBrowserVersion: PLATFORM_SMOKE_AGENT_BROWSER_VERSION,

package/scripts/agent-browser-capability-baseline.mjs

@@ -14,14 +14,18 @@ export const COMMAND_REFERENCE_BASELINE_BLOCK_IDS = Object.freeze(["upstream-bas
 
 const sourceEvidence = Object.freeze({
   repository: "vercel-labs/agent-browser",
-  upstreamHead: "6ede7a9470ac4b681cabf838af8668b9aa99e957",
-  upstreamPackageVersion: "0.32.2",
+  upstreamHead: "1ed371f3af472cc0d6cd8fdaea75d1a085ff7534",
+  upstreamPackageVersion: "0.33.0",
   inspectedSources: Object.freeze([
     "agent-browser --version",
     "agent-browser --help",
     "selected agent-browser <command> --help output",
+    "agent-browser a11y --help",
     "agent-browser mcp --help",
     "agent-browser plugin --help",
+    "agent-browser skills list",
+    "agent-browser skills get core --full",
+    "agent-browser skills get derive-client --full",
     "README.md",
     "CHANGELOG.md",
     "agent-browser.schema.json",
@@ -30,8 +34,17 @@ const sourceEvidence = Object.freeze({
     "cli/src/read.rs",
     "cli/src/doctor/webgpu.rs",
     "cli/src/native/actions.rs",
+    "cli/src/native/a11y/mod.rs",
+    "cli/src/native/browser.rs",
     "cli/src/native/daemon.rs",
+    "cli/src/output.rs",
     "docs/src/app/webgpu/page.mdx",
+    "docs/src/app/network/page.mdx",
+    "docs/src/app/selectors/page.mdx",
+    "docs/src/app/skills/page.mdx",
+    "docs/src/app/commands/page.mdx",
+    "skill-data/derive-client/SKILL.md",
+    "skill-data/core/SKILL.md",
     "packages/@agent-browser/eve/README.md",
     "packages/@agent-browser/eve/package.json",
     "packages/@agent-browser/eve/test/extension.test.mjs",
@@ -100,6 +113,7 @@ const helpCommands = Object.freeze([
   helpCommand("record help", ["record", "--help"]),
   helpCommand("console help", ["console", "--help"]),
   helpCommand("errors help", ["errors", "--help"]),
+  helpCommand("a11y help", ["a11y", "--help"]),
   helpCommand("clipboard help", ["clipboard", "--help"]),
   helpCommand("tap help", ["tap", "--help"]),
   helpCommand("swipe help", ["swipe", "--help"]),
@@ -127,6 +141,7 @@ const inventorySections = Object.freeze([
       "skills get dogfood",
       "skills get vercel-sandbox",
       "skills get agentcore",
+      "skills get derive-client",
       "@agent-browser/sandbox",
       "installSystemDependencies: false",
       "skills path [name]",
@@ -143,11 +158,14 @@ const inventorySections = Object.freeze([
       ["skills list", "dogfood"],
       ["skills list", "vercel-sandbox"],
       ["skills list", "agentcore"],
+      ["skills list", "derive-client"],
       ["vercel sandbox skill full", "@agent-browser/sandbox"],
       ["vercel sandbox skill full", "installSystemDependencies: false"],
       ["core skill full", "agent-browser frame @e3"],
       ["core skill full", "agent-browser dialog accept"],
       ["core skill full", "agent-browser --session \"$SESSION\" --restore open https://app.example.com"],
+      ["core skill full", "network har start --content all"],
+      ["core skill full", "implicit roles work"],
     ],
   ),
   section(
@@ -229,6 +247,7 @@ const inventorySections = Object.freeze([
       "find last <sel>",
       "find nth <n> <sel>",
       "find role <role> --name <name>",
+      "find role heading text --name",
       "find ... --exact",
       "mouse <action> [args]",
       "set <setting> [value]",
@@ -308,6 +327,8 @@ const inventorySections = Object.freeze([
       ["find help", "nth <index> <selector>"],
       ["find help", "--name <name>"],
       ["find help", "--exact"],
+      ["find help", "case-insensitive"],
+      ["find help", "click, fill, check, hover, text"],
       root("Mouse:  agent-browser mouse <action> [args]"),
       root("Browser Settings:  agent-browser set <setting> [value]"),
       ["set help", "media [dark|light]"],
@@ -383,6 +404,9 @@ const inventorySections = Object.freeze([
       "network requests [--clear] [--filter <pattern>] [--type <csv>] [--method <method>] [--status <code|range>]",
       "network request <requestId>",
       "network har start",
+      "network har start --content all",
+      "network har start --content none",
+      "network har start --content text",
       "network har stop [path]",
       "cookies [get|set|clear]",
       "cookies set <name> <value> --url <url> --domain <domain> --path <path> --httpOnly --secure --sameSite <Strict|Lax|None> --expires <timestamp>",
@@ -419,6 +443,9 @@ const inventorySections = Object.freeze([
       "react suspense [--only-dynamic] [--json]",
       "vitals [url] [--json]",
       "web-vitals [url] [--json]",
+      "a11y [url]",
+      "a11y --tags wcag2a,wcag2aa",
+      "a11y --selector \"#main\"",
       "removeinitscript <id>",
     ],
     [
@@ -426,6 +453,8 @@ const inventorySections = Object.freeze([
       root("--resource-type <csv>"),
       ["network help", "unroute [url]"],
       ["network help", "network har start"],
+      ["network help", "network har start --content all"],
+      ["network help", "--content <mode>"],
       ["network help", "network har stop ./capture.har"],
       root("cookies [get|set|clear]"),
       root("cookies set --curl <file>"),
@@ -455,6 +484,11 @@ const inventorySections = Object.freeze([
       root("react renders stop [--json]"),
       root("react suspense [--only-dynamic] [--json]"),
       root("vitals [url] [--json]"),
+      root("a11y [url] [--tags <t1,t2>] [--selector <css>] [--json]"),
+      ["a11y help", "a11y [url]"],
+      ["a11y help", "--tags <tag1,tag2>"],
+      ["a11y help", "-s, --selector <css>"],
+      ["core skill full", "agent-browser a11y"],
       root("removeinitscript <id>"),
       ["network help", "requests [options]"],
       ["network help", "--type <types>"],
@@ -810,7 +844,7 @@ const inventorySections = Object.freeze([
 ]);
 
 export const CAPABILITY_BASELINE = Object.freeze({
-  targetVersion: "0.32.2",
+  targetVersion: "0.33.0",
   sourceEvidence,
   helpCommands,
   inventorySections,