Tests: cover agents and fix web defaults

Co-authored-by: RealSid08 <RealSid08@users.noreply.github.com>
This commit is contained in:
Peter Steinberger
2025-12-02 10:56:10 +00:00
parent f31e89d5af
commit ed080ae988
17 changed files with 285 additions and 82 deletions

118
src/agents/agents.test.ts Normal file
View File

@@ -0,0 +1,118 @@
import { describe, expect, it } from "vitest";
import { CLAUDE_IDENTITY_PREFIX } from "../auto-reply/claude.js";
import { OPENCODE_IDENTITY_PREFIX } from "../auto-reply/opencode.js";
import { claudeSpec } from "./claude.js";
import { codexSpec } from "./codex.js";
import { opencodeSpec } from "./opencode.js";
import { piSpec } from "./pi.js";
describe("agent buildArgs + parseOutput helpers", () => {
it("claudeSpec injects flags and identity once", () => {
const argv = ["claude", "hi"];
const built = claudeSpec.buildArgs({
argv,
bodyIndex: 1,
isNewSession: true,
sessionId: "sess",
sendSystemOnce: false,
systemSent: false,
identityPrefix: undefined,
format: "json",
});
expect(built).toContain("--output-format");
expect(built).toContain("json");
expect(built).toContain("-p");
expect(built.at(-1)).toContain(CLAUDE_IDENTITY_PREFIX);
const builtNoIdentity = claudeSpec.buildArgs({
argv,
bodyIndex: 1,
isNewSession: false,
sessionId: "sess",
sendSystemOnce: true,
systemSent: true,
identityPrefix: undefined,
format: "json",
});
expect(builtNoIdentity.at(-1)).not.toContain(CLAUDE_IDENTITY_PREFIX);
});
it("opencodeSpec adds format flag and identity prefix when needed", () => {
const argv = ["opencode", "body"];
const built = opencodeSpec.buildArgs({
argv,
bodyIndex: 1,
isNewSession: true,
sessionId: "sess",
sendSystemOnce: false,
systemSent: false,
identityPrefix: undefined,
format: "json",
});
expect(built).toContain("--format");
expect(built).toContain("json");
expect(built.at(-1)).toContain(OPENCODE_IDENTITY_PREFIX);
});
it("piSpec parses final assistant message and preserves usage meta", () => {
const stdout = [
'{"type":"message_start","message":{"role":"assistant"}}',
'{"type":"message_end","message":{"role":"assistant","content":[{"type":"text","text":"hello world"}],"usage":{"input":10,"output":5},"model":"pi-1","provider":"inflection","stopReason":"end"}}',
].join("\n");
const parsed = piSpec.parseOutput(stdout);
expect(parsed.text).toBe("hello world");
expect(parsed.meta?.provider).toBe("inflection");
expect((parsed.meta?.usage as { output?: number })?.output).toBe(5);
});
it("codexSpec parses agent_message and aggregates usage", () => {
const stdout = [
'{"type":"item.completed","item":{"type":"agent_message","text":"hi there"}}',
'{"type":"turn.completed","usage":{"input_tokens":50,"output_tokens":10,"cached_input_tokens":5}}',
].join("\n");
const parsed = codexSpec.parseOutput(stdout);
expect(parsed.text).toBe("hi there");
const usage = parsed.meta?.usage as {
input?: number;
output?: number;
cacheRead?: number;
total?: number;
};
expect(usage?.input).toBe(50);
expect(usage?.output).toBe(10);
expect(usage?.cacheRead).toBe(5);
expect(usage?.total).toBe(65);
});
it("opencodeSpec parses streamed events and summarizes meta", () => {
const stdout = [
'{"type":"step_start","timestamp":0}',
'{"type":"text","part":{"text":"hi"}}',
'{"type":"step_finish","timestamp":1200,"part":{"cost":0.002,"tokens":{"input":100,"output":20}}}',
].join("\n");
const parsed = opencodeSpec.parseOutput(stdout);
expect(parsed.text).toBe("hi");
expect(parsed.meta?.extra?.summary).toContain("duration=1200ms");
expect(parsed.meta?.extra?.summary).toContain("cost=$0.0020");
expect(parsed.meta?.extra?.summary).toContain("tokens=100+20");
});
it("codexSpec buildArgs enforces exec/json/sandbox defaults", () => {
const argv = ["codex", "hello world"];
const built = codexSpec.buildArgs({
argv,
bodyIndex: 1,
isNewSession: true,
sessionId: "sess",
sendSystemOnce: false,
systemSent: false,
identityPrefix: undefined,
format: "json",
});
expect(built[1]).toBe("exec");
expect(built).toContain("--json");
expect(built).toContain("--skip-git-repo-check");
expect(built).toContain("read-only");
});
});

View File

@@ -3,16 +3,11 @@ import path from "node:path";
import {
CLAUDE_BIN,
CLAUDE_IDENTITY_PREFIX,
type ClaudeJsonParseResult,
parseClaudeJson,
summarizeClaudeMetadata,
type ClaudeJsonParseResult,
} from "../auto-reply/claude.js";
import type {
AgentMeta,
AgentParseResult,
AgentSpec,
BuildArgsContext,
} from "./types.js";
import type { AgentMeta, AgentSpec } from "./types.js";
function toMeta(parsed?: ClaudeJsonParseResult): AgentMeta | undefined {
if (!parsed?.parsed) return undefined;
@@ -22,10 +17,11 @@ function toMeta(parsed?: ClaudeJsonParseResult): AgentMeta | undefined {
export const claudeSpec: AgentSpec = {
kind: "claude",
isInvocation: (argv) => argv.length > 0 && path.basename(argv[0]) === CLAUDE_BIN,
isInvocation: (argv) =>
argv.length > 0 && path.basename(argv[0]) === CLAUDE_BIN,
buildArgs: (ctx) => {
// Work off a split of "before body" and "after body" so we don't lose the
// body index when inserting flags.
// Split around the body so we can inject flags without losing the body
// position. This keeps templated prompts intact even when we add flags.
const argv = [...ctx.argv];
const body = argv[ctx.bodyIndex] ?? "";
const beforeBody = argv.slice(0, ctx.bodyIndex);
@@ -34,14 +30,18 @@ export const claudeSpec: AgentSpec = {
const wantsOutputFormat = typeof ctx.format === "string";
if (wantsOutputFormat) {
const hasOutputFormat = argv.some(
(part) => part === "--output-format" || part.startsWith("--output-format="),
(part) =>
part === "--output-format" || part.startsWith("--output-format="),
);
if (!hasOutputFormat) {
beforeBody.push("--output-format", ctx.format!);
const outputFormat = ctx.format ?? "json";
beforeBody.push("--output-format", outputFormat);
}
}
const hasPrintFlag = argv.some((part) => part === "-p" || part === "--print");
const hasPrintFlag = argv.some(
(part) => part === "-p" || part === "--print",
);
if (!hasPrintFlag) {
beforeBody.push("-p");
}

View File

@@ -1,6 +1,6 @@
import path from "node:path";
import type { AgentMeta, AgentParseResult, AgentSpec, BuildArgsContext } from "./types.js";
import type { AgentMeta, AgentParseResult, AgentSpec } from "./types.js";
function parseCodexJson(raw: string): AgentParseResult {
const lines = raw.split(/\n+/).filter((l) => l.trim().startsWith("{"));
@@ -9,11 +9,25 @@ function parseCodexJson(raw: string): AgentParseResult {
for (const line of lines) {
try {
const ev = JSON.parse(line) as { type?: string; item?: { type?: string; text?: string }; usage?: unknown };
if (ev.type === "item.completed" && ev.item?.type === "agent_message" && typeof ev.item.text === "string") {
const ev = JSON.parse(line) as {
type?: string;
item?: { type?: string; text?: string };
usage?: unknown;
};
// Codex streams multiple events; capture the last agent_message text and
// the final turn usage for cost/telemetry.
if (
ev.type === "item.completed" &&
ev.item?.type === "agent_message" &&
typeof ev.item.text === "string"
) {
text = ev.item.text;
}
if (ev.type === "turn.completed" && ev.usage && typeof ev.usage === "object") {
if (
ev.type === "turn.completed" &&
ev.usage &&
typeof ev.usage === "object"
) {
const u = ev.usage as {
input_tokens?: number;
cached_input_tokens?: number;
@@ -63,4 +77,3 @@ export const codexSpec: AgentSpec = {
},
parseOutput: parseCodexJson,
};

View File

@@ -16,4 +16,3 @@ export function getAgentSpec(kind: AgentKind): AgentSpec {
}
export { AgentKind, AgentMeta, AgentParseResult } from "./types.js";

View File

@@ -6,42 +6,50 @@ import {
parseOpencodeJson,
summarizeOpencodeMetadata,
} from "../auto-reply/opencode.js";
import type { AgentMeta, AgentParseResult, AgentSpec, BuildArgsContext } from "./types.js";
import type { AgentMeta, AgentSpec } from "./types.js";
function toMeta(parsed: ReturnType<typeof parseOpencodeJson>): AgentMeta | undefined {
function toMeta(
parsed: ReturnType<typeof parseOpencodeJson>,
): AgentMeta | undefined {
const summary = summarizeOpencodeMetadata(parsed.meta);
return summary ? { extra: { summary } } : undefined;
}
export const opencodeSpec: AgentSpec = {
kind: "opencode",
isInvocation: (argv) => argv.length > 0 && path.basename(argv[0]) === OPENCODE_BIN,
isInvocation: (argv) =>
argv.length > 0 && path.basename(argv[0]) === OPENCODE_BIN,
buildArgs: (ctx) => {
// Split around the body so we can insert flags without losing the prompt.
const argv = [...ctx.argv];
const body = argv[ctx.bodyIndex] ?? "";
const beforeBody = argv.slice(0, ctx.bodyIndex);
const afterBody = argv.slice(ctx.bodyIndex + 1);
const wantsJson = ctx.format === "json";
// Ensure format json for parsing
if (wantsJson) {
const hasFormat = argv.some(
const hasFormat = [...beforeBody, body, ...afterBody].some(
(part) => part === "--format" || part.startsWith("--format="),
);
if (!hasFormat) {
const insertBeforeBody = Math.max(argv.length - 1, 0);
argv.splice(insertBeforeBody, 0, "--format", "json");
beforeBody.push("--format", "json");
}
}
// Session args default to --session
// Identity prefix
// Opencode streams text tokens; we still seed an identity so the agent
// keeps context on first turn.
const shouldPrependIdentity = !(ctx.sendSystemOnce && ctx.systemSent);
if (shouldPrependIdentity && argv[ctx.bodyIndex]) {
const existingBody = argv[ctx.bodyIndex];
argv[ctx.bodyIndex] = [ctx.identityPrefix ?? OPENCODE_IDENTITY_PREFIX, existingBody]
.filter(Boolean)
.join("\n\n");
}
const bodyWithIdentity =
shouldPrependIdentity && body
? [ctx.identityPrefix ?? OPENCODE_IDENTITY_PREFIX, body]
.filter(Boolean)
.join("\n\n")
: body;
return argv;
return [...beforeBody, bodyWithIdentity, ...afterBody];
},
parseOutput: (rawStdout) => {
const parsed = parseOpencodeJson(rawStdout);

View File

@@ -1,6 +1,6 @@
import path from "node:path";
import type { AgentMeta, AgentParseResult, AgentSpec, BuildArgsContext } from "./types.js";
import type { AgentMeta, AgentParseResult, AgentSpec } from "./types.js";
type PiAssistantMessage = {
role?: string;
@@ -16,7 +16,11 @@ function parsePiJson(raw: string): AgentParseResult {
let lastMessage: PiAssistantMessage | undefined;
for (const line of lines) {
try {
const ev = JSON.parse(line) as { type?: string; message?: PiAssistantMessage };
const ev = JSON.parse(line) as {
type?: string;
message?: PiAssistantMessage;
};
// Pi emits a stream; we only care about the terminal assistant message_end.
if (ev.type === "message_end" && ev.message?.role === "assistant") {
lastMessage = ev.message;
}
@@ -50,14 +54,20 @@ export const piSpec: AgentSpec = {
if (!argv.includes("-p") && !argv.includes("--print")) {
argv.splice(argv.length - 1, 0, "-p");
}
if (ctx.format === "json" && !argv.includes("--mode") && !argv.some((a) => a === "--mode")) {
if (
ctx.format === "json" &&
!argv.includes("--mode") &&
!argv.some((a) => a === "--mode")
) {
argv.splice(argv.length - 1, 0, "--mode", "json");
}
// Session defaults
// Identity prefix optional; Pi usually doesn't need, but allow
// Identity prefix optional; Pi usually doesn't need it, but allow injection
if (!(ctx.sendSystemOnce && ctx.systemSent) && argv[ctx.bodyIndex]) {
const existingBody = argv[ctx.bodyIndex];
argv[ctx.bodyIndex] = [ctx.identityPrefix, existingBody].filter(Boolean).join("\n\n");
argv[ctx.bodyIndex] = [ctx.identityPrefix, existingBody]
.filter(Boolean)
.join("\n\n");
}
return argv;
},

View File

@@ -39,4 +39,3 @@ export interface AgentSpec {
buildArgs: (ctx: BuildArgsContext) => string[];
parseOutput: (rawStdout: string) => AgentParseResult;
}