@tea-agent/loop-agent 0.39.0-beta.0 → 0.39.0-beta.10

package/dist/executors/pi-executor.js

@@ -1012,6 +1012,13 @@ export function classifyPiFailure(input) {
     if (input.exitCode === 0 && input.assistantText.trim())
         return "success";
     const combined = `${input.stderr}\n${input.stdout}`.toLowerCase();
+    // Context overflow (400 request-too-large / context window exceeded).
+    // Must be detected BEFORE the generic rate-limit/quota phrases: an overflow
+    // error often contains "too many tokens" / "maximum context" which would
+    // otherwise be misread as rate-limit or quota. Kept in sync with
+    // CONTEXT_OVERFLOW_PHRASES in commands/client-recovery.ts.
+    if (/请求上下文过大|context_length_exceeded|context overflow|context length overflow|too many tokens|maximum context|prompt is too long|request_too_large|context window/.test(combined))
+        return "context-overflow";
     // Prefer explicit rate-limit / HTTP 429 before generic "limit" quota phrases.
     // Chinese gateways often say "请求频率已达到限制" without English "rate limit".
     if (/rate.?limit|too many requests|\b429\b|请求频率|频率.*限制|rpm|tpm/.test(combined))

package/dist/executors/pi-extension-resolver.js

@@ -0,0 +1,233 @@
+import { existsSync, readdirSync, readFileSync, statSync } from "node:fs";
+import os from "node:os";
+import path from "node:path";
+/**
+ * Pi extension allowlist for backend implementation DAGs (plan D2/D3).
+ * DAG specs carry these frozen short ids; the executor resolves them against
+ * the Pi agent settings package inventory at run time.
+ */
+export const DAG_PI_EXTENSION_IDS = ["pi-codegraph", "pi-lens"];
+/**
+ * Alias table: one DAG short id may resolve to multiple published package
+ * names. The first settings spec whose de-`npm:`-prefixed package name is in
+ * the alias set wins (project settings override user settings).
+ */
+export const DAG_PI_EXTENSION_PACKAGE_ALIASES = {
+    "pi-codegraph": [
+        "@estebanforge/pi-codegraph-enhanced",
+        "@vndv/pi-codegraph",
+        "pi-codegraph",
+    ],
+    "pi-lens": ["pi-lens"],
+};
+/**
+ * Extension tools that must never be activated as extras on any node (D5):
+ * they mutate files without the writer path policy. Writer nodes keep only
+ * policy-wrapped edit/write; read nodes keep only navigation tools.
+ */
+export const DAG_PI_EXTENSION_WRITE_TOOL_DENY = new Set([
+    "ast_grep_replace",
+]);
+/** Builtin tool names extensions must never replace (D5). */
+export const DAG_PI_EXTENSION_PROTECTED_BUILTIN_TOOLS = new Set(["read", "edit", "write", "bash", "grep", "find", "ls"]);
+/** Deny surface extensions must never activate (D5). */
+export const DAG_PI_EXTENSION_DENIED_TOOL_IDS = new Set([
+    "apply_patch",
+    "apply-patch",
+    "full-tools",
+    "full_tools",
+    "coding-chat",
+    "coding_chat",
+    "shell",
+]);
+export function isDagPiExtensionId(value) {
+    return DAG_PI_EXTENSION_IDS.includes(value);
+}
+function getPiAgentDir() {
+    const envDir = process.env.PI_CODING_AGENT_DIR;
+    if (envDir)
+        return envDir;
+    return path.join(os.homedir(), ".pi", "agent");
+}
+function readSettingsPackages(settingsPath) {
+    try {
+        if (!existsSync(settingsPath))
+            return undefined;
+        const parsed = JSON.parse(readFileSync(settingsPath, "utf8"));
+        if (!Array.isArray(parsed.packages))
+            return undefined;
+        return parsed.packages.filter((spec) => typeof spec === "string");
+    }
+    catch {
+        return undefined;
+    }
+}
+/** Strip an `npm:` prefix from a settings package spec, e.g. `npm:pi-lens`. */
+export function packageNameFromSpec(spec) {
+    return spec.startsWith("npm:") ? spec.slice(4) : spec;
+}
+function loadPackageInventories(repoRoot) {
+    const agentDir = getPiAgentDir();
+    const userSpecs = readSettingsPackages(path.join(agentDir, "settings.json"));
+    const projectSpecs = readSettingsPackages(path.join(repoRoot, ".pi", "settings.json"));
+    const inventories = [];
+    if (userSpecs) {
+        inventories.push({
+            specs: userSpecs,
+            nodeModulesRoot: path.join(agentDir, "npm", "node_modules"),
+        });
+    }
+    if (projectSpecs) {
+        inventories.push({
+            specs: projectSpecs,
+            nodeModulesRoot: path.join(repoRoot, "node_modules"),
+        });
+    }
+    return inventories;
+}
+const EXTENSION_FILE_RE = /\.(?:ts|js|mjs|cjs)$/;
+/**
+ * Resolve a package's `pi.extensions` entries to absolute entry paths.
+ * - A file entry maps to itself.
+ * - A directory entry expands to every extension file directly inside it
+ *   (e.g. `@estebanforge/pi-codegraph-enhanced` ships `./extensions` holding
+ *   `codegraph.ts`).
+ * No `pi.extensions` declaration, or a declaration whose paths do not exist,
+ * yields no entries (caller records `no-entry`) — no heuristic scanning
+ * outside declared paths.
+ */
+export function resolvePackageEntryPaths(packageDir) {
+    let manifest;
+    try {
+        manifest = JSON.parse(readFileSync(path.join(packageDir, "package.json"), "utf8"));
+    }
+    catch {
+        return { entryPaths: [], reason: "no-entry" };
+    }
+    const declared = manifest.pi?.extensions;
+    if (!Array.isArray(declared)) {
+        return { entryPaths: [], reason: "no-entry" };
+    }
+    const entryPaths = [];
+    for (const entry of declared) {
+        if (typeof entry !== "string" || entry.length === 0)
+            continue;
+        const resolved = path.resolve(packageDir, entry);
+        if (!existsSync(resolved))
+            continue;
+        let isDirectory = false;
+        try {
+            isDirectory = statSync(resolved).isDirectory();
+        }
+        catch {
+            continue;
+        }
+        if (!isDirectory) {
+            entryPaths.push(resolved);
+            continue;
+        }
+        let names;
+        try {
+            names = readdirSync(resolved);
+        }
+        catch {
+            continue;
+        }
+        for (const name of names.sort()) {
+            if (!EXTENSION_FILE_RE.test(name))
+                continue;
+            entryPaths.push(path.join(resolved, name));
+        }
+    }
+    if (entryPaths.length === 0) {
+        return { entryPaths: [], reason: "no-entry" };
+    }
+    return { entryPaths };
+}
+/**
+ * Resolve frozen DAG short ids against the Pi settings package inventory
+ * (user `~/.pi/agent/settings.json`, then project `.pi/settings.json` — a
+ * later match on the same alias wins). Pure synchronous read; never throws.
+ */
+export function resolveDagPiExtensions(input) {
+    const inventories = loadPackageInventories(input.repoRoot);
+    const resolved = [];
+    const missing = [];
+    for (const id of input.ids) {
+        if (!isDagPiExtensionId(id)) {
+            missing.push({
+                id,
+                reason: "package-unreadable",
+                detail: `unknown pi extension id: ${id}`,
+            });
+            continue;
+        }
+        const aliases = DAG_PI_EXTENSION_PACKAGE_ALIASES[id];
+        let matched;
+        // Later inventories (project) override earlier (user).
+        for (const inventory of inventories) {
+            for (const spec of inventory.specs) {
+                const packageName = packageNameFromSpec(spec);
+                if (!aliases.includes(packageName))
+                    continue;
+                const packageDir = path.join(inventory.nodeModulesRoot, ...packageName.split("/"));
+                if (!existsSync(packageDir))
+                    continue;
+                try {
+                    const manifest = JSON.parse(readFileSync(path.join(packageDir, "package.json"), "utf8"));
+                    if (typeof manifest.version !== "string")
+                        continue;
+                    matched = { packageDir, packageName, version: manifest.version };
+                }
+                catch {
+                    // unreadable manifest: skip this candidate
+                }
+            }
+        }
+        if (!matched) {
+            missing.push({ id, reason: "not-installed" });
+            continue;
+        }
+        const entries = resolvePackageEntryPaths(matched.packageDir);
+        if (entries.entryPaths.length === 0) {
+            missing.push({
+                id,
+                reason: entries.reason === "no-entry" ? "no-entry" : "package-unreadable",
+            });
+            continue;
+        }
+        resolved.push({
+            id,
+            packageName: matched.packageName,
+            version: matched.version,
+            entryPaths: entries.entryPaths,
+        });
+    }
+    return { resolved, missing };
+}
+/**
+ * Compute extension tool names that may join a node's active tool allowlist
+ * after session creation (D5): new tool names registered by the loaded
+ * extensions, minus protected builtins, the deny surface, and write-capable
+ * extension tools (both buckets — writer writes stay policy-wrapped only).
+ */
+export function computeExtensionToolAllowlistExtras(sessionTools, baseline) {
+    const baselineLower = new Set(baseline.map((name) => name.toLowerCase()));
+    const extras = [];
+    for (const tool of sessionTools) {
+        const name = tool && typeof tool.name === "string" ? tool.name : undefined;
+        if (!name)
+            continue;
+        const lower = name.toLowerCase();
+        if (baselineLower.has(lower))
+            continue;
+        if (DAG_PI_EXTENSION_PROTECTED_BUILTIN_TOOLS.has(lower))
+            continue;
+        if (DAG_PI_EXTENSION_DENIED_TOOL_IDS.has(lower))
+            continue;
+        if (DAG_PI_EXTENSION_WRITE_TOOL_DENY.has(lower))
+            continue;
+        extras.push(name);
+    }
+    return extras;
+}

package/dist/executors/pi-playwright-cli-tool.js

@@ -4,7 +4,8 @@ import { appendFile, lstat, mkdir, readFile, realpath, stat, } from "node:fs/pro
 import path from "node:path";
 import { processTreeSpawnOptions, terminateProcessTree, } from "./process-tree.js";
 import { resolvePlaywrightCliLauncher } from "./playwright-cli-launcher.js";
-import { PLAYWRIGHT_CLI_ALLOWED_COMMANDS, isPlaywrightCliCommand, } from "../shared/playwright-cli-command-policy.js";
+import { PLAYWRIGHT_CLI_ALLOWED_COMMANDS, isPlaywrightCliCommand, parsePlaywrightCliFindMatchCount, } from "../shared/playwright-cli-command-policy.js";
+import { defaultFrontendTestLayout, escapeRegexLiteral, } from "../workflows/dag/frontend-test-layout.js";
 export { PLAYWRIGHT_CLI_ALLOWED_COMMANDS, isPlaywrightCliCommand, };
 /** Logical capability name only; execution always uses the verified JS launcher. */
 export const PLAYWRIGHT_CLI_EXECUTABLE = "playwright-cli";
@@ -111,6 +112,13 @@ export async function readPlaywrightCliReceipts(runDir, nodeId) {
     }
 }
 export function summarizePlaywrightCliReceipts(receipts) {
+    // Sequence numbers are assigned at dispatch time, which is the controller's
+    // causal order. Receipt lines are appended when each command COMPLETES, so
+    // concurrent commands (e.g. parallel find calls issued in one turn) persist
+    // out of sequence order. Judge chain contiguity on the dispatch order by
+    // sorting on `sequence` first; a genuinely missing receipt (gap) or a
+    // duplicated sequence still fails the contiguity check below.
+    const orderedReceipts = [...receipts].sort((a, b) => a.sequence - b.sequence);
     let hasSuccessfulOpen = false;
     let hasInteractionOrAssertion = false;
     let hasMeaningfulAssertion = false;
@@ -122,7 +130,7 @@ export function summarizePlaywrightCliReceipts(receipts) {
     let hasContiguousControllerSequence = true;
     let previousSequence = 0;
     const caseIds = new Set();
-    for (const receipt of receipts) {
+    for (const receipt of orderedReceipts) {
         caseIds.add(receipt.caseId);
         const succeeded = receipt.exitCode === 0 && !receipt.timedOut;
         const ordered = receipt.sequence === previousSequence + 1;
@@ -137,8 +145,10 @@ export function summarizePlaywrightCliReceipts(receipts) {
         if (PLAYWRIGHT_CLI_INTERACTION_COMMANDS.has(receipt.command) && succeeded) {
             hasInteractionOrAssertion = true;
         }
-        // A successful find is the only model-visible semantic assertion in v1.
-        if (receipt.command === "find" && succeeded) {
+        // A successful find (or find-unique, its semantic wrapper) is the only
+        // model-visible semantic assertion in v1.
+        if ((receipt.command === "find" || receipt.command === "find-unique") &&
+            succeeded) {
             hasMeaningfulAssertion = true;
             if (ordered && sawOpen)
                 sawMeaningfulAssertionAfterOpen = true;
@@ -258,7 +268,8 @@ function validateOpenArgs(args, baseUrl) {
 }
 function resolveEvidenceRelative(rawPath, ctx) {
     const evidenceDir = normalizePosix(ctx.evidenceDir).replace(/\/$/, "");
-    const evidencePrefix = `testcase/frontend/evidence/${ctx.caseId}`;
+    const layout = ctx.layout ?? defaultFrontendTestLayout();
+    const evidencePrefix = `${layout.evidenceDir}/${ctx.caseId}`;
     if (!(evidenceDir === evidencePrefix ||
         evidenceDir.startsWith(`${evidencePrefix}/`))) {
         throw new PlaywrightCliPolicyError("evidence-dir-invalid", `evidenceDir must be under ${evidencePrefix}`);
@@ -282,7 +293,7 @@ function resolveEvidenceRelative(rawPath, ctx) {
     if (candidate.startsWith(`${evidenceDir}/`) || candidate === evidenceDir) {
         return candidate;
     }
-    if (candidate.startsWith("testcase/frontend/evidence/") &&
+    if (candidate.startsWith(`${layout.evidenceDir}/`) &&
         !candidate.startsWith(`${evidencePrefix}/`)) {
         throw new PlaywrightCliPolicyError("path-cross-case", "output path escapes current case evidenceDir");
     }
@@ -463,11 +474,12 @@ function assertInputPathAllowed(rawPath, ctx) {
     if (!isSafeRelativePosix(candidate)) {
         throw new PlaywrightCliPolicyError("input-path-unsafe", `unsafe input path: ${rawPath}`);
     }
+    const layout = ctx.layout ?? defaultFrontendTestLayout();
     const allowedPrefixes = [
-        `testcase/frontend/evidence/${ctx.caseId}/`,
-        "testcase/frontend/cases/",
-        "testcase/frontend/rag/",
-        "testcase/frontend/fixtures/",
+        `${layout.evidenceDir}/${ctx.caseId}/`,
+        `${layout.casesDir}/`,
+        `${layout.ragDir}/`,
+        `${layout.fixturesDir}/`,
     ];
     if (!allowedPrefixes.some((prefix) => candidate === prefix.slice(0, -1) || candidate.startsWith(prefix)) &&
         !candidate.startsWith(normalizePosix(ctx.evidenceDir) + "/")) {
@@ -523,6 +535,17 @@ export function preparePlaywrightCliArgv(input, ctx) {
     else if (command === "pdf" || command === "snapshot") {
         args = normalizePdfOrSnapshotArgs(command, rawArgs, ctx);
     }
+    else if (command === "find-unique") {
+        // find-unique is a controller-side semantic wrapper: the underlying CLI
+        // only knows `find`; uniqueness (matchCount === 1) is judged by the
+        // executor after parsing the find output. Require exactly one text
+        // literal — a unique-control assertion is meaningless with multiple.
+        const literals = rawArgs.filter((arg) => !arg.startsWith("-"));
+        if (rawArgs.length !== 1 || literals.length !== 1) {
+            throw new PlaywrightCliPolicyError("find-unique-args", "find-unique requires exactly one text literal and no flags");
+        }
+        args = literals;
+    }
     else {
         args = rewriteArgsForPaths(command, rawArgs, ctx);
     }
@@ -609,8 +632,8 @@ async function validatePlaywrightCliOutputPath(command, args, ctx) {
     if (!outputFilename)
         return;
     const repoRoot = path.resolve(ctx.repoRoot);
-    const caseEvidenceRoot = path.resolve(repoRoot, "testcase", "frontend", "evidence", ctx.caseId);
-    const evidenceDir = path.resolve(repoRoot, ctx.evidenceDir);
+    const caseEvidenceRoot = path.resolve(repoRoot, ctx.evidenceDir);
+    const evidenceDir = caseEvidenceRoot;
     const target = path.resolve(repoRoot, outputFilename);
     if (!pathIsContained(repoRoot, caseEvidenceRoot) ||
         !pathIsContained(caseEvidenceRoot, evidenceDir) ||
@@ -818,7 +841,10 @@ export async function executePlaywrightCliCommand(input, ctx, signal) {
         };
     }
     let executable = PLAYWRIGHT_CLI_EXECUTABLE;
-    let argv = [command, ...args];
+    // find-unique executes as the underlying CLI `find` command; uniqueness is
+    // a controller-side judgment on the parsed match count.
+    const cliCommand = command === "find-unique" ? "find" : command;
+    let argv = [cliCommand, ...args];
     try {
         await validatePlaywrightCliOutputPath(command, args, ctx);
         await validatePlaywrightCliInputFiles(command, args, ctx);
@@ -827,7 +853,7 @@ export async function executePlaywrightCliCommand(input, ctx, signal) {
         if (!ctx.runCommand) {
             const launcher = resolvePlaywrightCliLauncher(ctx.repoRoot);
             executable = launcher.executable;
-            argv = [...launcher.argvPrefix, command, ...args];
+            argv = [...launcher.argvPrefix, cliCommand, ...args];
         }
     }
     catch (error) {
@@ -887,6 +913,19 @@ export async function executePlaywrightCliCommand(input, ctx, signal) {
     }
     const finishedAt = new Date();
     const combined = `${runResult.stdout}\n${runResult.stderr}`;
+    // find-family commands report their match count in stdout with exit code
+    // 0 even on zero matches — parse the count so receipts carry the real
+    // assertion signal for finalize-side audits.
+    const matchCount = command === "find" || command === "find-unique"
+        ? parsePlaywrightCliFindMatchCount(runResult.stdout || "")
+        : undefined;
+    // find-unique fails closed unless exactly one match was found (including
+    // zero and unparseable outputs).
+    const findUniqueFailed = command === "find-unique" && matchCount !== 1 && !runResult.timedOut;
+    const effectiveExitCode = findUniqueFailed && runResult.exitCode === 0 ? 1 : runResult.exitCode;
+    const effectiveStderr = findUniqueFailed
+        ? `${runResult.stderr}${runResult.stderr ? "\n" : ""}find-unique: expected exactly 1 match, got ${matchCount === undefined ? "unparseable output" : `${matchCount}`}`
+        : runResult.stderr;
     const receipt = {
         schemaVersion: 1,
         caseId: ctx.caseId,
@@ -895,25 +934,28 @@ export async function executePlaywrightCliCommand(input, ctx, signal) {
         argsRedacted: redactPlaywrightCliArgs(command, args),
         startedAt: startedAt.toISOString(),
         finishedAt: finishedAt.toISOString(),
-        exitCode: runResult.exitCode,
+        exitCode: effectiveExitCode,
         durationMs: finishedAt.getTime() - startedAt.getTime(),
         outputSha256: createHash("sha256").update(combined).digest("hex"),
         toolVersion: ctx.toolVersion ?? "unknown",
         timedOut: runResult.timedOut || undefined,
+        ...(matchCount !== undefined ? { matchCount } : {}),
         errorClass: runResult.timedOut
             ? "timeout"
             : runResult.signal === "abort"
                 ? "abort"
-                : runResult.exitCode === 0
+                : effectiveExitCode === 0
                     ? undefined
-                    : "nonzero-exit",
+                    : findUniqueFailed
+                        ? "find-unique-count-mismatch"
+                        : "nonzero-exit",
     };
     await appendReceipt(ctx, receipt);
     return {
-        ok: runResult.exitCode === 0 && !runResult.timedOut,
-        exitCode: runResult.exitCode,
+        ok: effectiveExitCode === 0 && !runResult.timedOut,
+        exitCode: effectiveExitCode,
         stdout: runResult.stdout,
-        stderr: runResult.stderr,
+        stderr: effectiveStderr,
         timedOut: runResult.timedOut,
         receipt,
         errorClass: receipt.errorClass,
@@ -985,22 +1027,26 @@ export async function createPlaywrightCliTool(ctx) {
 export const PI_COMMAND_CAPABILITY_REGISTRY = {
     "playwright-cli": createPlaywrightCliTool,
 };
-export function resolveCaseIdFromWriteSet(writeSet) {
+export function resolveCaseIdFromWriteSet(writeSet, layout = defaultFrontendTestLayout()) {
+    const prefix = layout.evidenceDir.replace(/\/$/, "");
+    const escaped = escapeRegexLiteral(prefix);
+    const exact = new RegExp(`^${escaped}/([^/]+)(?:/\\*\\*)?$`);
+    const nested = new RegExp(`^${escaped}/([^/]+)/`);
     for (const entry of writeSet ?? []) {
         const normalized = normalizePosix(entry);
-        const match = normalized.match(/^testcase\/frontend\/evidence\/([^/]+)(?:\/\*\*)?$/);
+        const match = normalized.match(exact);
         if (match?.[1] && match[1] !== "**" && match[1] !== "*") {
             return match[1];
         }
-        const nested = normalized.match(/^testcase\/frontend\/evidence\/([^/]+)\//);
-        if (nested?.[1])
-            return nested[1];
+        const nestedMatch = normalized.match(nested);
+        if (nestedMatch?.[1])
+            return nestedMatch[1];
     }
     return undefined;
 }
-export function resolveEvidenceDirFromWriteSet(writeSet) {
-    const caseId = resolveCaseIdFromWriteSet(writeSet);
+export function resolveEvidenceDirFromWriteSet(writeSet, layout = defaultFrontendTestLayout()) {
+    const caseId = resolveCaseIdFromWriteSet(writeSet, layout);
     if (!caseId)
         return undefined;
-    return `testcase/frontend/evidence/${caseId}`;
+    return `${layout.evidenceDir}/${caseId}`;
 }