pi-openai-toolkit 0.14.4 → 0.14.6

package/package.json

@@ -1,127 +1,127 @@
-{
-  "name": "pi-openai-toolkit",
-  "version": "0.14.4",
-  "private": false,
-  "type": "module",
-  "engines": {
-    "node": ">=22.19.0"
-  },
-  "description": "OpenAI toolkit for Pi: Codex Remote Context windows, remote compaction v2, hosted Web Search, image gen, auto mode.",
-  "author": "awoaCrim and contributors",
-  "license": "MIT",
-  "repository": {
-    "type": "git",
-    "url": "git+https://github.com/awoaCrim/pi-openai-toolkit.git"
-  },
-  "bugs": {
-    "url": "https://github.com/awoaCrim/pi-openai-toolkit/issues"
-  },
-  "homepage": "https://github.com/awoaCrim/pi-openai-toolkit#readme",
-  "publishConfig": {
-    "access": "public",
-    "registry": "https://registry.npmjs.org/"
-  },
-  "keywords": [
-    "pi-package",
-    "pi-extension",
-    "openai",
-    "compaction",
-    "web-search",
-    "image-generation",
-    "auto-mode",
-    "codex",
-    "responses"
-  ],
-  "pi": {
-    "extensions": [
-      "./extensions/compaction.ts",
-      "./extensions/web-search.ts",
-      "./extensions/image-generation.ts",
-      "./extensions/auto-mode.ts",
-      "./extensions/codex-astra.ts"
-    ]
-  },
-  "files": [
-    "extensions/compaction.ts",
-    "extensions/web-search.ts",
-    "extensions/image-generation.ts",
-    "extensions/auto-mode.ts",
-    "src/compact-client.ts",
-    "src/config.ts",
-    "src/debug.ts",
-    "src/details-store.ts",
-    "src/deferred-tool-carryover.ts",
-    "src/extension-runtime.ts",
-    "src/context-management/types.ts",
-    "src/context-management/messages.ts",
-    "src/context-management/window-budget.ts",
-    "src/context-management/window-request.ts",
-    "src/context-management/window-manager.ts",
-    "src/context-management/codex-provider.ts",
-    "src/context-management/history-notes.ts",
-    "src/context-management/tools.ts",
-    "src/context-management/namespace-tools.ts",
-    "src/context-management/tool-contract.ts",
-    "src/image-generation/artifacts.ts",
-    "src/image-generation/client.ts",
-    "src/image-generation/eligibility.ts",
-    "src/image-generation/extension.ts",
-    "src/image-generation/protocol.ts",
-    "src/image-generation/references.ts",
-    "src/image-generation/render.ts",
-    "src/image-generation/service.ts",
-    "src/image-generation/types.ts",
-    "src/auto-mode/extension.ts",
-    "src/auto-mode/policy.ts",
-    "src/auto-mode/prompt.ts",
-    "src/auto-mode/transcript.ts",
-    "src/auto-mode/reviewer.ts",
-    "src/auto-mode/classifier.ts",
-    "src/auto-mode/types.ts",
-    "extensions/codex-astra.ts",
-    "src/codex-astra/effort-planner.ts",
-    "src/codex-astra/extension.ts",
-    "src/model-scope.ts",
-    "src/native-fallback.ts",
-    "src/payload-rewrite.ts",
-    "src/provider-headers.ts",
-    "src/responses-headers.ts",
-    "src/remote-v2-client.ts",
-    "src/request-context-cache.ts",
-    "src/runtime.ts",
-    "src/serializer.ts",
-    "src/supported-environment.ts",
-    "src/types.ts",
-    "src/web-search/extension.ts",
-    "src/web-search/payload.ts",
-    "src/web-search/prompt.ts",
-    "src/web-search/types.ts",
-    "docs/internals.md",
-    "README.md",
-    "README.zh.md",
-    "LICENSE",
-    "NOTICE",
-    "tsconfig.check.json"
-  ],
-  "scripts": {
-    "test": "bun test",
-    "test:coverage": "bun test --coverage --coverage-reporter=text --coverage-reporter=lcov && node ./scripts/check-lcov.mjs ./coverage/lcov.info",
-    "test:pi": "bun test ./test/pi-smoke.test.ts",
-    "typecheck": "tsc -p tsconfig.check.json"
-  },
-  "peerDependencies": {
-    "@earendil-works/pi-agent-core": ">=0.85.1",
-    "@earendil-works/pi-ai": ">=0.85.1",
-    "@earendil-works/pi-coding-agent": ">=0.85.1",
-    "@earendil-works/pi-tui": ">=0.85.1"
-  },
-  "devDependencies": {
-    "@earendil-works/pi-agent-core": "0.85.1",
-    "@earendil-works/pi-ai": "0.85.1",
-    "@earendil-works/pi-coding-agent": "0.85.1",
-    "@earendil-works/pi-tui": "0.85.1",
-    "@types/node": "24.12.4",
-    "bun": "1.2.23",
-    "typescript": "5.9.3"
-  }
-}
+{
+  "name": "pi-openai-toolkit",
+  "version": "0.14.6",
+  "private": false,
+  "type": "module",
+  "engines": {
+    "node": ">=22.19.0"
+  },
+  "description": "OpenAI toolkit for Pi: Codex Remote Context windows, remote compaction v2, hosted Web Search, image gen, auto mode.",
+  "author": "awoaCrim and contributors",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/awoaCrim/pi-openai-toolkit.git"
+  },
+  "bugs": {
+    "url": "https://github.com/awoaCrim/pi-openai-toolkit/issues"
+  },
+  "homepage": "https://github.com/awoaCrim/pi-openai-toolkit#readme",
+  "publishConfig": {
+    "access": "public",
+    "registry": "https://registry.npmjs.org/"
+  },
+  "keywords": [
+    "pi-package",
+    "pi-extension",
+    "openai",
+    "compaction",
+    "web-search",
+    "image-generation",
+    "auto-mode",
+    "codex",
+    "responses"
+  ],
+  "pi": {
+    "extensions": [
+      "./extensions/compaction.ts",
+      "./extensions/web-search.ts",
+      "./extensions/image-generation.ts",
+      "./extensions/auto-mode.ts",
+      "./extensions/codex-astra.ts"
+    ]
+  },
+  "files": [
+    "extensions/compaction.ts",
+    "extensions/web-search.ts",
+    "extensions/image-generation.ts",
+    "extensions/auto-mode.ts",
+    "src/compact-client.ts",
+    "src/config.ts",
+    "src/debug.ts",
+    "src/details-store.ts",
+    "src/deferred-tool-carryover.ts",
+    "src/extension-runtime.ts",
+    "src/context-management/types.ts",
+    "src/context-management/messages.ts",
+    "src/context-management/window-budget.ts",
+    "src/context-management/window-request.ts",
+    "src/context-management/window-manager.ts",
+    "src/context-management/codex-provider.ts",
+    "src/context-management/history-notes.ts",
+    "src/context-management/tools.ts",
+    "src/context-management/namespace-tools.ts",
+    "src/context-management/tool-contract.ts",
+    "src/image-generation/artifacts.ts",
+    "src/image-generation/client.ts",
+    "src/image-generation/eligibility.ts",
+    "src/image-generation/extension.ts",
+    "src/image-generation/protocol.ts",
+    "src/image-generation/references.ts",
+    "src/image-generation/render.ts",
+    "src/image-generation/service.ts",
+    "src/image-generation/types.ts",
+    "src/auto-mode/extension.ts",
+    "src/auto-mode/policy.ts",
+    "src/auto-mode/prompt.ts",
+    "src/auto-mode/transcript.ts",
+    "src/auto-mode/reviewer.ts",
+    "src/auto-mode/classifier.ts",
+    "src/auto-mode/types.ts",
+    "extensions/codex-astra.ts",
+    "src/codex-astra/effort-planner.ts",
+    "src/codex-astra/extension.ts",
+    "src/model-scope.ts",
+    "src/native-fallback.ts",
+    "src/payload-rewrite.ts",
+    "src/provider-headers.ts",
+    "src/responses-headers.ts",
+    "src/remote-v2-client.ts",
+    "src/request-context-cache.ts",
+    "src/runtime.ts",
+    "src/serializer.ts",
+    "src/supported-environment.ts",
+    "src/types.ts",
+    "src/web-search/extension.ts",
+    "src/web-search/payload.ts",
+    "src/web-search/prompt.ts",
+    "src/web-search/types.ts",
+    "docs/internals.md",
+    "README.md",
+    "README.zh.md",
+    "LICENSE",
+    "NOTICE",
+    "tsconfig.check.json"
+  ],
+  "scripts": {
+    "test": "bun test",
+    "test:coverage": "bun test --coverage --coverage-reporter=text --coverage-reporter=lcov && node ./scripts/check-lcov.mjs ./coverage/lcov.info",
+    "test:pi": "bun test ./test/pi-smoke.test.ts",
+    "typecheck": "tsc -p tsconfig.check.json"
+  },
+  "peerDependencies": {
+    "@earendil-works/pi-agent-core": ">=0.85.1",
+    "@earendil-works/pi-ai": ">=0.85.1",
+    "@earendil-works/pi-coding-agent": ">=0.85.1",
+    "@earendil-works/pi-tui": ">=0.85.1"
+  },
+  "devDependencies": {
+    "@earendil-works/pi-agent-core": "0.85.1",
+    "@earendil-works/pi-ai": "0.85.1",
+    "@earendil-works/pi-coding-agent": "0.85.1",
+    "@earendil-works/pi-tui": "0.85.1",
+    "@types/node": "24.12.4",
+    "bun": "1.2.23",
+    "typescript": "5.9.3"
+  }
+}

package/src/auto-mode/classifier.ts

@@ -1,165 +1,165 @@
-import type { Api, Model } from "@earendil-works/pi-ai";
-import type { ModelRegistry } from "@earendil-works/pi-coding-agent";
-import { parseModelSpec } from "../runtime";
-import { CLASSIFIER_SYSTEM_PROMPT } from "./prompt";
-import { boundReviewText, type ClassifierRisk, type FastDecisionReason } from "./types";
-
-/** One completed classification of the trajectory, tagged to a tool-call position. */
-export type ScoreRecord = {
-	risk: ClassifierRisk;
-	/** Tool-call counter value when the sample was taken. */
-	scoredAtCall: number;
-	/** Fingerprint of the user turns the score was based on. */
-	authorizationVersion: string;
-	sampledAt: number;
-};
-
-/**
- * Mutable per-session tracker for the non-blocking pre-scorer.
- *
- * The counters reproduce Codex's staleness rule: the agent keeps running while a
- * classification is in flight, so a score is only trustworthy if it is recent
- * enough and nothing the user said has changed underneath it.
- */
-export type ScoreTracker = {
-	latestCallIndex: number;
-	latestScoredIndex: number;
-	latestFailedIndex: number;
-	score?: ScoreRecord;
-};
-
-export function createScoreTracker(): ScoreTracker {
-	return { latestCallIndex: 0, latestScoredIndex: 0, latestFailedIndex: 0 };
-}
-
-/** Reset everything: a new turn or a disengaged mode invalidates prior scoring. */
-export function resetScoreTracker(tracker: ScoreTracker): void {
-	tracker.latestCallIndex = 0;
-	tracker.latestScoredIndex = 0;
-	tracker.latestFailedIndex = 0;
-	tracker.score = undefined;
-}
-
-/**
- * Fingerprint of the user-authored conversation. Any new or edited user turn makes
- * an existing score stale, because the score's authorization premise changed.
- */
-export function authorizationVersion(userText: string): string {
-	const bounded = boundReviewText(userText, 8_000);
-	let hash = 2166136261;
-	for (let index = 0; index < bounded.length; index += 1) {
-		hash ^= bounded.charCodeAt(index);
-		hash = Math.imul(hash, 16777619);
-	}
-	return `${bounded.length}:${(hash >>> 0).toString(36)}`;
-}
-
-export function recordScoredCall(tracker: ScoreTracker, score: ScoreRecord): void {
-	tracker.score = score;
-	tracker.latestScoredIndex = Math.max(tracker.latestScoredIndex, score.scoredAtCall);
-}
-
-export function recordFailedCall(tracker: ScoreTracker, scoredAtCall: number): void {
-	tracker.latestFailedIndex = Math.max(tracker.latestFailedIndex, scoredAtCall);
-}
-
-export type FastDecisionInput = {
-	tracker: ScoreTracker;
-	/** Tool-call counter value for the call being gated. */
-	currentCallIndex: number;
-	authorizationVersion: string;
-	maxLag: number;
-	/** Retries after a denial and widened gates must not take the fast path. */
-	requiresSynchronousReview?: boolean;
-};
-
-/**
- * Decide whether a cached classification can satisfy this gated call without
- * running the blocking reviewer. Anything other than `low_risk` defers to the
- * synchronous review; the classifier never denies an action on its own.
- */
-export function fastApprovalEligible(input: FastDecisionInput): {
-	eligible: boolean;
-	reason: FastDecisionReason;
-} {
-	const defer = (reason: FastDecisionReason) => ({ eligible: false, reason });
-
-	if (input.requiresSynchronousReview) return defer("requires_synchronous_review");
-	if (input.tracker.latestFailedIndex > input.tracker.latestScoredIndex) return defer("scoring_failure");
-
-	const score = input.tracker.score;
-	if (!score) return defer("missing_score");
-
-	const lag = input.currentCallIndex - score.scoredAtCall;
-	if (lag > input.maxLag) return defer("stale_score");
-	if (score.authorizationVersion !== input.authorizationVersion) return defer("authorization_changed");
-	if (score.risk === "low") return { eligible: true, reason: "low_risk" };
-	return defer("elevated_risk");
-}
-
-export type ClassificationResult =
-	| { kind: ClassifierRisk; model: string }
-	| { kind: "failed"; reason: string };
-
-/**
- * Run one non-blocking classification. Output is a single token; anything else is a
- * failed sample rather than a verdict, so a confused classifier costs a review and
- * never an approval or a denial.
- */
-export async function classifyTrajectory(params: {
-	registry: Pick<ModelRegistry, "find" | "complete">;
-	modelSpec: string;
-	prompt: string;
-	timeoutMs: number;
-	signal?: AbortSignal;
-}): Promise<ClassificationResult> {
-	const parsed = parseModelSpec(params.modelSpec);
-	if (!parsed) {
-		return { kind: "failed", reason: `autoMode.classifier.model "${params.modelSpec}" is not provider/model-id.` };
-	}
-	const model = params.registry.find(parsed.provider, parsed.modelId) as Model<Api> | undefined;
-	if (!model) {
-		return { kind: "failed", reason: `Classifier model ${params.modelSpec} is not available.` };
-	}
-	const label = boundReviewText(`${model.provider}/${model.id}`, 256);
-
-	const controller = new AbortController();
-	const abortFromCaller = () => controller.abort();
-	if (params.signal?.aborted) controller.abort();
-	else params.signal?.addEventListener("abort", abortFromCaller);
-	const timer = setTimeout(() => controller.abort(), params.timeoutMs);
-
-	try {
-		const response = await params.registry.complete(
-			model,
-			{
-				systemPrompt: CLASSIFIER_SYSTEM_PROMPT,
-				messages: [
-					{
-						role: "user",
-						content: [{ type: "text", text: params.prompt }],
-						timestamp: Date.now(),
-					},
-				],
-			},
-			{ signal: controller.signal, cacheRetention: "none" },
-		);
-		if (response.stopReason === "error" || response.stopReason === "aborted") {
-			return { kind: "failed", reason: response.errorMessage ?? `Classifier stopped: ${response.stopReason}` };
-		}
-		const text = response.content
-			.filter((block): block is { type: "text"; text: string } => block.type === "text")
-			.map((block) => block.text)
-			.join("")
-			.trim()
-			.toLowerCase();
-		if (/^high\b/.test(text)) return { kind: "high", model: label };
-		if (/^low\b/.test(text)) return { kind: "low", model: label };
-		return { kind: "failed", reason: `Classifier returned unreadable output: ${boundReviewText(text, 80)}` };
-	} catch (error) {
-		return { kind: "failed", reason: error instanceof Error ? error.message : String(error) };
-	} finally {
-		clearTimeout(timer);
-		params.signal?.removeEventListener("abort", abortFromCaller);
-	}
-}
+import type { Api, Model } from "@earendil-works/pi-ai";
+import type { ModelRegistry } from "@earendil-works/pi-coding-agent";
+import { parseModelSpec } from "../runtime";
+import { CLASSIFIER_SYSTEM_PROMPT } from "./prompt";
+import { boundReviewText, type ClassifierRisk, type FastDecisionReason } from "./types";
+
+/** One completed classification of the trajectory, tagged to a tool-call position. */
+export type ScoreRecord = {
+	risk: ClassifierRisk;
+	/** Tool-call counter value when the sample was taken. */
+	scoredAtCall: number;
+	/** Fingerprint of the user turns the score was based on. */
+	authorizationVersion: string;
+	sampledAt: number;
+};
+
+/**
+ * Mutable per-session tracker for the non-blocking pre-scorer.
+ *
+ * The counters reproduce Codex's staleness rule: the agent keeps running while a
+ * classification is in flight, so a score is only trustworthy if it is recent
+ * enough and nothing the user said has changed underneath it.
+ */
+export type ScoreTracker = {
+	latestCallIndex: number;
+	latestScoredIndex: number;
+	latestFailedIndex: number;
+	score?: ScoreRecord;
+};
+
+export function createScoreTracker(): ScoreTracker {
+	return { latestCallIndex: 0, latestScoredIndex: 0, latestFailedIndex: 0 };
+}
+
+/** Reset everything: a new turn or a disengaged mode invalidates prior scoring. */
+export function resetScoreTracker(tracker: ScoreTracker): void {
+	tracker.latestCallIndex = 0;
+	tracker.latestScoredIndex = 0;
+	tracker.latestFailedIndex = 0;
+	tracker.score = undefined;
+}
+
+/**
+ * Fingerprint of the user-authored conversation. Any new or edited user turn makes
+ * an existing score stale, because the score's authorization premise changed.
+ */
+export function authorizationVersion(userText: string): string {
+	const bounded = boundReviewText(userText, 8_000);
+	let hash = 2166136261;
+	for (let index = 0; index < bounded.length; index += 1) {
+		hash ^= bounded.charCodeAt(index);
+		hash = Math.imul(hash, 16777619);
+	}
+	return `${bounded.length}:${(hash >>> 0).toString(36)}`;
+}
+
+export function recordScoredCall(tracker: ScoreTracker, score: ScoreRecord): void {
+	tracker.score = score;
+	tracker.latestScoredIndex = Math.max(tracker.latestScoredIndex, score.scoredAtCall);
+}
+
+export function recordFailedCall(tracker: ScoreTracker, scoredAtCall: number): void {
+	tracker.latestFailedIndex = Math.max(tracker.latestFailedIndex, scoredAtCall);
+}
+
+export type FastDecisionInput = {
+	tracker: ScoreTracker;
+	/** Tool-call counter value for the call being gated. */
+	currentCallIndex: number;
+	authorizationVersion: string;
+	maxLag: number;
+	/** Retries after a denial and widened gates must not take the fast path. */
+	requiresSynchronousReview?: boolean;
+};
+
+/**
+ * Decide whether a cached classification can satisfy this gated call without
+ * running the blocking reviewer. Anything other than `low_risk` defers to the
+ * synchronous review; the classifier never denies an action on its own.
+ */
+export function fastApprovalEligible(input: FastDecisionInput): {
+	eligible: boolean;
+	reason: FastDecisionReason;
+} {
+	const defer = (reason: FastDecisionReason) => ({ eligible: false, reason });
+
+	if (input.requiresSynchronousReview) return defer("requires_synchronous_review");
+	if (input.tracker.latestFailedIndex > input.tracker.latestScoredIndex) return defer("scoring_failure");
+
+	const score = input.tracker.score;
+	if (!score) return defer("missing_score");
+
+	const lag = input.currentCallIndex - score.scoredAtCall;
+	if (lag > input.maxLag) return defer("stale_score");
+	if (score.authorizationVersion !== input.authorizationVersion) return defer("authorization_changed");
+	if (score.risk === "low") return { eligible: true, reason: "low_risk" };
+	return defer("elevated_risk");
+}
+
+export type ClassificationResult =
+	| { kind: ClassifierRisk; model: string }
+	| { kind: "failed"; reason: string };
+
+/**
+ * Run one non-blocking classification. Output is a single token; anything else is a
+ * failed sample rather than a verdict, so a confused classifier costs a review and
+ * never an approval or a denial.
+ */
+export async function classifyTrajectory(params: {
+	registry: Pick<ModelRegistry, "find" | "complete">;
+	modelSpec: string;
+	prompt: string;
+	timeoutMs: number;
+	signal?: AbortSignal;
+}): Promise<ClassificationResult> {
+	const parsed = parseModelSpec(params.modelSpec);
+	if (!parsed) {
+		return { kind: "failed", reason: `autoMode.classifier.model "${params.modelSpec}" is not provider/model-id.` };
+	}
+	const model = params.registry.find(parsed.provider, parsed.modelId) as Model<Api> | undefined;
+	if (!model) {
+		return { kind: "failed", reason: `Classifier model ${params.modelSpec} is not available.` };
+	}
+	const label = boundReviewText(`${model.provider}/${model.id}`, 256);
+
+	const controller = new AbortController();
+	const abortFromCaller = () => controller.abort();
+	if (params.signal?.aborted) controller.abort();
+	else params.signal?.addEventListener("abort", abortFromCaller);
+	const timer = setTimeout(() => controller.abort(), params.timeoutMs);
+
+	try {
+		const response = await params.registry.complete(
+			model,
+			{
+				systemPrompt: CLASSIFIER_SYSTEM_PROMPT,
+				messages: [
+					{
+						role: "user",
+						content: [{ type: "text", text: params.prompt }],
+						timestamp: Date.now(),
+					},
+				],
+			},
+			{ signal: controller.signal, cacheRetention: "none" },
+		);
+		if (response.stopReason === "error" || response.stopReason === "aborted") {
+			return { kind: "failed", reason: response.errorMessage ?? `Classifier stopped: ${response.stopReason}` };
+		}
+		const text = response.content
+			.filter((block): block is { type: "text"; text: string } => block.type === "text")
+			.map((block) => block.text)
+			.join("")
+			.trim()
+			.toLowerCase();
+		if (/^high\b/.test(text)) return { kind: "high", model: label };
+		if (/^low\b/.test(text)) return { kind: "low", model: label };
+		return { kind: "failed", reason: `Classifier returned unreadable output: ${boundReviewText(text, 80)}` };
+	} catch (error) {
+		return { kind: "failed", reason: error instanceof Error ? error.message : String(error) };
+	} finally {
+		clearTimeout(timer);
+		params.signal?.removeEventListener("abort", abortFromCaller);
+	}
+}