Files
AgentCompany/tests/eval/assertion-judge.ts
T
ZacharyZhang-NY 9a5823b242 C4 follow-up #4: add message_does_not_contain_substring assertion kind + pin C4 invariants
Closes the fourth ask from the C4 cross-review (docs/proposals/C4-followup.md
Item 4). The eval harness previously had no way to assert the absence of a
pattern in a trace — only positive `message_contains_substring`. That meant
the C4 "no more node -e / bash+fetch from CEO" invariant was only
demonstrated by the diff between two commits, not by any running assertion
that future regressions would trip.

Three changes:

1. Extend the Assertion union in tests/eval/types.ts with
   `message_does_not_contain_substring` (role + substring). Symmetric to
   the positive kind; fails on first match with a specific reason.

2. Add the case in assertion-judge.ts. Same traversal as the positive
   branch but inverted exit condition.

3. Add two harness self-tests covering pass + fail, so the new kind is
   exercised even when the fixtures directory is empty.

4. Pin two C4-regression assertions onto the recorded ceo-bootstrap-empty
   fixture: the assistant response must NOT contain "node -e" OR
   "/api/companies". Any future regression that reintroduces the
   HTTP-path-in-prompt pattern or the bash+node -e shell fallback will
   now fail pnpm test:eval instead of living in the fixture silently.

typecheck green, test:eval up from 8 → 10 tests (2 new self-tests), all
passing.
2026-04-20 14:53:24 -04:00

214 lines
6.9 KiB
TypeScript

/**
* Assertion judge for B5 eval harness.
*
* Evaluates a list of structural `Assertion` records against a recorded
* fixture trace. This is the cheap, deterministic tier — it understands tool
* call names, counts, order, and substrings. Semantic judgment (tone, plan
* quality) is out of scope and handled by the LLM-as-judge tier described in
* B5.1.
*
* Design notes:
* - Pure function of (assertions, turns) → AssertionResult[]. No I/O.
* - Never throws. Every assertion either passes or fails with a `reason`.
* The runner aggregates these into a single `EvalResult`.
* - `tool_call_arg_matches.arg_path` supports dotted paths through nested
* objects and numeric indexes through arrays (`items.0.name`). If the path
* misses or resolves to a non-string, the assertion fails with a reason.
*/
import type { ToolCall } from "@mariozechner/pi-ai";
import type {
Assertion,
AssertionResult,
AssistantTurn,
TraceTurn,
} from "./types.js";
interface ToolCallOccurrence {
toolCall: ToolCall;
/** Ordinal index among all tool calls across the full trace. */
ordinal: number;
}
function collectToolCalls(turns: TraceTurn[]): ToolCallOccurrence[] {
const occurrences: ToolCallOccurrence[] = [];
for (const turn of turns) {
if (turn.role !== "assistant") continue;
const assistantTurn = turn as AssistantTurn;
for (const block of assistantTurn.content) {
if (block.type === "toolCall") {
occurrences.push({
toolCall: block,
ordinal: occurrences.length,
});
}
}
}
return occurrences;
}
function resolveArgPath(root: unknown, path: string): unknown {
const parts = path.split(".");
let cursor: unknown = root;
for (const part of parts) {
if (cursor === null || cursor === undefined) return undefined;
if (typeof cursor !== "object") return undefined;
cursor = (cursor as Record<string, unknown>)[part];
}
return cursor;
}
function evaluateOne(
assertion: Assertion,
turns: TraceTurn[],
toolCalls: ToolCallOccurrence[],
): AssertionResult {
switch (assertion.kind) {
case "tool_called": {
const matches = toolCalls.filter(
(occ) => occ.toolCall.name === assertion.name,
);
const minCount = assertion.min_count ?? 1;
if (matches.length < minCount) {
return {
assertion,
passed: false,
reason: `expected at least ${minCount} call(s) to "${assertion.name}", saw ${matches.length}`,
};
}
if (assertion.max_count !== undefined && matches.length > assertion.max_count) {
return {
assertion,
passed: false,
reason: `expected at most ${assertion.max_count} call(s) to "${assertion.name}", saw ${matches.length}`,
};
}
if (assertion.order !== undefined) {
const match = matches.find((occ) => occ.ordinal === assertion.order);
if (!match) {
const seenOrdinals = matches.map((occ) => occ.ordinal).join(",");
return {
assertion,
passed: false,
reason: `expected "${assertion.name}" at ordinal ${assertion.order}, matching calls at [${seenOrdinals}]`,
};
}
}
return { assertion, passed: true };
}
case "no_tool_called": {
const matches = toolCalls.filter(
(occ) => occ.toolCall.name === assertion.name,
);
if (matches.length > 0) {
return {
assertion,
passed: false,
reason: `expected no call to "${assertion.name}", saw ${matches.length}`,
};
}
return { assertion, passed: true };
}
case "message_contains_substring": {
for (const turn of turns) {
if (turn.role !== assertion.role) continue;
// UserTurn and AssistantTurn both expose .content; the `role` guard
// above restricts us to those variants, so no cast is needed.
const content = turn.content;
if (!Array.isArray(content)) continue;
for (const block of content) {
if (
block &&
typeof block === "object" &&
(block as { type?: string }).type === "text" &&
typeof (block as { text?: unknown }).text === "string" &&
((block as { text: string }).text).includes(assertion.substring)
) {
return { assertion, passed: true };
}
}
}
return {
assertion,
passed: false,
reason: `no ${assertion.role} message contained substring "${assertion.substring}"`,
};
}
case "message_does_not_contain_substring": {
for (const turn of turns) {
if (turn.role !== assertion.role) continue;
const content = turn.content;
if (!Array.isArray(content)) continue;
for (const block of content) {
if (
block &&
typeof block === "object" &&
(block as { type?: string }).type === "text" &&
typeof (block as { text?: unknown }).text === "string" &&
((block as { text: string }).text).includes(assertion.substring)
) {
return {
assertion,
passed: false,
reason: `a ${assertion.role} message contained forbidden substring "${assertion.substring}"`,
};
}
}
}
return { assertion, passed: true };
}
case "tool_call_arg_matches": {
const matches = toolCalls.filter(
(occ) => occ.toolCall.name === assertion.name,
);
if (matches.length === 0) {
return {
assertion,
passed: false,
reason: `no tool call named "${assertion.name}" to match arg against`,
};
}
let regex: RegExp;
try {
regex = new RegExp(assertion.matches_regex);
} catch (error) {
const detail = error instanceof Error ? error.message : String(error);
return {
assertion,
passed: false,
reason: `invalid regex "${assertion.matches_regex}": ${detail}`,
};
}
for (const occurrence of matches) {
const value = resolveArgPath(occurrence.toolCall.arguments, assertion.arg_path);
if (typeof value === "string" && regex.test(value)) {
return { assertion, passed: true };
}
}
return {
assertion,
passed: false,
reason: `no "${assertion.name}" call had arg "${assertion.arg_path}" matching /${assertion.matches_regex}/`,
};
}
case "trace_max_turns": {
if (turns.length > assertion.max) {
return {
assertion,
passed: false,
reason: `trace has ${turns.length} turns, max allowed is ${assertion.max}`,
};
}
return { assertion, passed: true };
}
}
}
export function judgeAssertions(
assertions: Assertion[],
turns: TraceTurn[],
): AssertionResult[] {
const toolCalls = collectToolCalls(turns);
return assertions.map((assertion) => evaluateOne(assertion, turns, toolCalls));
}