fix(ab-corpus): keep applying composite tags past per-shape failures
Codex stop-time review caught the previous commit (113bd55a) message overstating apply.ts's behavior — I claimed "scripts/ab-corpus/apply both catch per-shape and keep running the remaining tags" but the loop at line 55 had no inner try/catch. A single throw from any handleElementToolCall (e.g. the heading invalid-level reject 113bd55a just added) would bubble up through the outer try at line 40 and return early, dropping every remaining tag in a composite batch on the floor — gpt-5.4's 13-tag team-people-page response would lose tags 12-13 instead of just tag 12. Wraps each handleElementToolCall in its own try/catch + accumulates failures into a per-shape list. ELEMENT_TOOL_NAMES miss is also a push-and-continue (was a return). When `failures.length > 0` we return ok:false with a message listing every failed tag, AND the partial PenDocument that DID land — so M3 (role coverage) can still score the 11 tags that worked. M1 stays strict (any failure → false). Mirrors apps/web/src/services/ai/element-tools-dispatcher:: dispatchElementToolCalls's "collect-errors-keep-going" semantics — production already worked this way; ab-corpus now does too. 3772 vitest pass, format clean, tsc silent. Existing dry-run + live sweeps exercise the path; a focused apply.ts unit test would need pen-mcp setup that the harness's existing build-prompt test sidesteps, so leaving that as a followup.
This commit is contained in:
parent
39aeb0c30e
commit
bd370bd5b8
|
|
@ -41,18 +41,46 @@ export const applyToFreshDoc: ApplyFn = async (parsed: ParsedOutput): Promise<Ap
|
|||
if (parsed.kind === 'tool_calls') {
|
||||
// Apply every call into the same fresh doc, in emit order.
|
||||
// Composite prompts route here with N≥2 calls; obvious prompts
|
||||
// typically with N=1. Any single call failing aborts the row
|
||||
// (M1=false) — we don't partially apply.
|
||||
// typically with N=1. Per-shape try/catch keeps the batch going
|
||||
// past a single bad tag — matches production
|
||||
// (apps/web/src/services/ai/element-tools-dispatcher::dispatchElementToolCalls)
|
||||
// and prevents one invented arg (e.g. an unknown heading level
|
||||
// on tag 12 of 13, seen on gpt-5.4 in ab-v4) from dropping the
|
||||
// other 12 valid tags on the floor. M1 stays strict: any failure
|
||||
// → ok:false; the partial PenDocument is returned so M3 (role
|
||||
// coverage) can still score against whatever did land.
|
||||
const failures: string[] = [];
|
||||
for (let i = 0; i < parsed.calls.length; i += 1) {
|
||||
const call = parsed.calls[i];
|
||||
const tagLabel = `call ${i + 1}/${parsed.calls.length} (${call.name})`;
|
||||
if (!ELEMENT_TOOL_NAMES.has(call.name)) {
|
||||
return {
|
||||
ok: false,
|
||||
error: `unknown element tool "${call.name}" (call ${i + 1}/${parsed.calls.length})`,
|
||||
doc: null,
|
||||
};
|
||||
failures.push(`${tagLabel}: unknown element tool`);
|
||||
continue;
|
||||
}
|
||||
await handleElementToolCall(call.name, { ...call.arguments, filePath: fp });
|
||||
try {
|
||||
await handleElementToolCall(call.name, { ...call.arguments, filePath: fp });
|
||||
} catch (err) {
|
||||
const msg = err instanceof Error ? err.message : String(err);
|
||||
failures.push(`${tagLabel}: ${msg}`);
|
||||
}
|
||||
}
|
||||
if (failures.length > 0) {
|
||||
let partialDoc: PenDocument | null = null;
|
||||
try {
|
||||
const candidate = JSON.parse(readFileSync(fp, 'utf-8')) as PenDocument;
|
||||
const topLevel = (candidate.children ??
|
||||
candidate.pages?.[0]?.children ??
|
||||
[]) as unknown[];
|
||||
if (topLevel.length > 0) partialDoc = candidate;
|
||||
} catch {
|
||||
// File unreadable or empty (e.g. every tag failed before
|
||||
// the first element-tool wrote anything) — surface null.
|
||||
}
|
||||
return {
|
||||
ok: false,
|
||||
error: `${failures.length}/${parsed.calls.length} tag(s) failed: ${failures.join('; ')}`,
|
||||
doc: partialDoc,
|
||||
};
|
||||
}
|
||||
} else {
|
||||
const result = await handleBatchDesign({
|
||||
|
|
|
|||
Loading…
Reference in a new issue