@oh-my-pi/pi-coding-agent 15.10.10 → 15.10.11

package/src/autoresearch/prompt.md

@@ -11,17 +11,17 @@ Primary goal:
 There is no goal recorded for this session yet. Infer what to optimize from the latest user message and the conversation; capture the goal in your notes (`update_notes`) once it is clear.
 {{/if}}
 
-Session state and run artifacts are managed for you. The benchmark entrypoint is `bash autoresearch.sh` (committed during Phase 1). Do not edit `autoresearch.sh` mid-segment unless you intentionally bump segment via `init_experiment new_segment: true`. Do not create `autoresearch.md` or `.autoresearch/` in this repo.
+Session state and run artifacts are managed for you. The benchmark entrypoint is `bash autoresearch.sh` (committed during Phase 1). NEVER edit `autoresearch.sh` mid-segment unless you intentionally bump segment via `init_experiment new_segment: true`. NEVER create `autoresearch.md` or `.autoresearch/` in this repo.
 
 Working directory: `{{working_dir}}`
 {{#if has_branch}}Active branch: `{{branch}}`{{/if}}
 {{#if has_baseline_commit}}Baseline commit: `{{baseline_commit}}`{{/if}}
 
-You are running an autonomous experiment loop. Keep iterating until the user interrupts you or the configured maximum iteration count is reached.
+You are running an autonomous experiment loop. You MUST keep iterating until the user interrupts you or the configured maximum iteration count is reached.
 
 ### Available tools
 - `init_experiment` — open or reconfigure the session. Pass `new_segment: true` to start a fresh baseline within the current session.
-- `run_experiment` — run the benchmark (`bash autoresearch.sh`). Output is captured automatically and `METRIC name=value` / `ASI key=value` lines printed by the harness are parsed back to you. The command is fixed; if you need a different workload, edit `autoresearch.sh` and bump segment via `init_experiment new_segment: true`.
+- `run_experiment` — run the benchmark (`bash autoresearch.sh`). Output is captured automatically and `METRIC name=value` / `ASI key=value` lines printed by the harness are parsed back to you. The command is fixed.
 - `log_experiment` — record the result. On `keep`, modified files are committed for you; on `discard`/`crash`/`checks_failed`, the worktree is reverted. Pass `flag_runs` to mark earlier runs as suspect; flagged runs are excluded from baseline and best-metric math.
 - `update_notes` — replace the durable session playbook (`body`) or append to the ideas backlog (`append_idea`). The notes are injected into your system prompt every iteration.
 
@@ -97,7 +97,7 @@ Finish the `log_experiment` step before starting another benchmark.
 {{/if}}
 
 ### Guardrails
-- Do not game the benchmark.
-- Do not overfit to synthetic inputs if the real workload is broader.
-- Preserve correctness.
+- NEVER game the benchmark.
+- NEVER overfit to synthetic inputs if the real workload is broader.
+- MUST preserve correctness.
 - If the user sends another message while a run is in progress, finish the current run and logging cycle first, then address the new input in the next iteration.

package/src/capability/fs.ts

@@ -15,6 +15,16 @@ export async function readFile(filePath: string): Promise<string | null> {
 	}
 
 	try {
+		// Gate on the file type first: discovery scans foreign config dirs
+		// (~/.claude, ~/.cursor, project trees), and reading a FIFO/socket/char
+		// device with `.text()` blocks until EOF — i.e. forever — hanging
+		// startup with zero output. `stat` follows symlinks, so symlinked
+		// context files (CLAUDE.md -> AGENTS.md) still resolve.
+		const stats = await fs.promises.stat(abs);
+		if (!stats.isFile()) {
+			contentCache.set(abs, null);
+			return null;
+		}
 		const content = await Bun.file(abs).text();
 		contentCache.set(abs, content);
 		return content;

package/src/cli/args.ts

@@ -1,7 +1,7 @@
 /**
  * CLI argument parsing and help display
  */
-import { type Effort, THINKING_EFFORTS } from "@oh-my-pi/pi-ai/effort";
+import { type Effort, THINKING_EFFORTS } from "@oh-my-pi/pi-catalog/effort";
 import { APP_NAME, CONFIG_DIR_NAME, logger } from "@oh-my-pi/pi-utils";
 import chalk from "chalk";
 import { parseEffort } from "../thinking";

package/src/cli/auth-gateway-cli.ts

@@ -24,14 +24,12 @@ import {
 	type CredentialCompletionResult,
 	completeSimple,
 	DEFAULT_AUTH_GATEWAY_BIND,
-	type GeneratedProvider,
-	getBundledModels,
-	getBundledProviders,
 	type Model,
 	RemoteAuthCredentialStore,
 	type SnapshotResponse,
 	startAuthGateway,
 } from "@oh-my-pi/pi-ai";
+import { type GeneratedProvider, getBundledModels, getBundledProviders } from "@oh-my-pi/pi-catalog/models";
 import { getConfigRootDir, isEnoent, VERSION } from "@oh-my-pi/pi-utils";
 import chalk from "chalk";
 import { type AuthBrokerClientConfig, resolveAuthBrokerConfig } from "../session/auth-broker-config";

package/src/cli/dry-balance-cli.ts

@@ -12,10 +12,10 @@ import type {
 	SimpleStreamOptions,
 } from "@oh-my-pi/pi-ai";
 import { streamSimple } from "@oh-my-pi/pi-ai";
+import type { CanonicalModelVariant } from "@oh-my-pi/pi-catalog/identity";
 import { replaceTabs, truncateToWidth } from "@oh-my-pi/pi-tui";
 import { formatDuration, getProjectDir } from "@oh-my-pi/pi-utils";
 import chalk from "chalk";
-import type { CanonicalModelVariant } from "../config/model-equivalence";
 import { type CanonicalModelQueryOptions, ModelRegistry } from "../config/model-registry";
 import {
 	formatModelString,

package/src/cli/gallery-cli.ts

@@ -104,7 +104,7 @@ export async function renderGalleryState(
 	state: GalleryState,
 	width: number,
 	expanded = false,
-): Promise<string[]> {
+): Promise<readonly string[]> {
 	if (fixture.renderState) {
 		return await fixture.renderState(state, width, expanded);
 	}

package/src/cli/gallery-fixtures/fs.ts

@@ -56,7 +56,7 @@ function addGroupedReadArgs(component: ReadToolGroupComponent): void {
 	component.updateArgs({ path: groupedReadRepeatedRanges }, "read-ranges");
 }
 
-function renderReadGroupFixtureState(state: GalleryFixtureState, width: number, expanded: boolean): string[] {
+function renderReadGroupFixtureState(state: GalleryFixtureState, width: number, expanded: boolean): readonly string[] {
 	const component = new ReadToolGroupComponent();
 	component.setExpanded(expanded);
 

package/src/cli/gallery-fixtures/types.ts

@@ -22,7 +22,11 @@ export interface GalleryFixture {
 	 * Custom gallery-only renderer for fixtures that are not one ToolExecutionComponent
 	 * (for example the read-group transcript component).
 	 */
-	renderState?: (state: GalleryFixtureState, width: number, expanded: boolean) => string[] | Promise<string[]>;
+	renderState?: (
+		state: GalleryFixtureState,
+		width: number,
+		expanded: boolean,
+	) => readonly string[] | Promise<readonly string[]>;
 	/**
 	 * Set for tools whose real `AgentTool` attaches `renderCall`/`renderResult`
 	 * directly on the instance (e.g. `task`). The harness then attaches

package/src/cli/list-models.ts

@@ -1,7 +1,8 @@
 /**
  * List available models with optional fuzzy search
  */
-import { type Api, getSupportedEfforts, type Model } from "@oh-my-pi/pi-ai";
+import type { Api, Model } from "@oh-my-pi/pi-ai";
+import { getSupportedEfforts } from "@oh-my-pi/pi-catalog/model-thinking";
 import { fuzzyFilter } from "@oh-my-pi/pi-tui";
 import { formatNumber } from "@oh-my-pi/pi-utils";
 import type { ModelRegistry } from "../config/model-registry";