v1.14.0-outer-loop: explicit while loop replaces inference recursion

Converts the ad-hoc executeToolPhase → runAssistantTurn recursion into an
explicit while (stepNumber < effectiveCap) loop. A step is one stream-and-
tool-execute iteration; the loop terminates on non-tool finish, step-cap hit,
doom-loop, budget exhaustion, abort, or synthesis success.

MAX_STEPS = 200 hard ceiling (4x old effective limit from budget). Per-agent
steps: field in AGENTS.md frontmatter sets tighter caps (Refactorer: 5,
Architect: 20, others: unset = bounded only by MAX_STEPS). Resolution:
effectiveCap = Math.min(agent.steps ?? Infinity, MAX_STEPS).

executeToolPhase no longer recurses — returns ToolPhaseResult struct
(action: 'continue' | 'paused' | 'synthesis_done') so the caller decides
whether to continue or break. steps: 0 handled as "no tool calls allowed"
via runTextOnlyTurn (one text-only stream phase, tool calls ignored with
warn log).

Step-cap hits produce a sentinel summary (reuses cap_hit kind so
CapHitSentinel.tsx renders without frontend changes; text distinguishes
"Step limit reached" from "Tool budget exhausted"). Doom-loop check migrated
to top of loop body — same predicate, same threshold (3), break instead of
return.

step_start parts are in the schema CHECK but not emitted as message_parts —
writing before the stream phase creates a sequence-0 collision with
partsFromAssistantMessage. Structured log line emitted instead. Adversarial
review caught the collision pre-deploy.

332/332 server tests passing. No frontend changes. No schema changes.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-23 20:29:21 +00:00
parent 211e903620
commit f4a97808ad
14 changed files with 756 additions and 204 deletions

View File

@@ -476,6 +476,202 @@ export async function runDoomLoopSummary(
);
}
// v1.14.0: step-cap wrap-up. Mirrors runCapHitSummary structurally — same
// in-flight-slot reuse, same tools-disabled streaming-summary call, same
// post-finalize sentinel insert + chat_status drop. Difference: the note
// text names the step limit rather than the tool budget. Sentinel reuses
// metadata.kind = 'cap_hit' so the frontend CapHitSentinel component
// renders it without changes.
const STEP_CAP_NOTE = (steps: number, cap: number) =>
`You've reached the step limit (${steps}/${cap} steps). Produce the best answer you can with what you have. Do not call more tools.`;
export async function runStepCapSummary(
ctx: InferenceContext,
args: TurnArgs,
session: Session,
project: Project,
history: Message[],
agent: Agent | null,
steps: number,
cap: number,
): Promise<void> {
const { sessionId, chatId, assistantMessageId, signal } = args;
const messages = await buildMessagesPayload(session, project, history, agent, ctx.log);
messages.push({ role: 'system', content: STEP_CAP_NOTE(steps, cap) });
const startedRow = await ctx.sql<{ started_at: string }[]>`
UPDATE messages
SET started_at = clock_timestamp()
WHERE id = ${assistantMessageId}
RETURNING started_at
`;
const startedAt = startedRow[0]?.started_at ?? null;
ctx.publish(sessionId, {
type: 'message_started',
message_id: assistantMessageId,
chat_id: chatId,
role: 'assistant',
});
let accumulated = '';
let pendingFlushTimer: NodeJS.Timeout | null = null;
let flushPromise: Promise<unknown> = Promise.resolve();
const flushNow = () => {
if (pendingFlushTimer) {
clearTimeout(pendingFlushTimer);
pendingFlushTimer = null;
}
const snapshot = accumulated;
flushPromise = flushPromise.then(() =>
ctx.sql`UPDATE messages SET content = ${snapshot} WHERE id = ${assistantMessageId}`
);
};
const scheduleFlush = () => {
if (pendingFlushTimer) return;
pendingFlushTimer = setTimeout(() => {
pendingFlushTimer = null;
flushNow();
}, DB_FLUSH_INTERVAL_MS);
};
let summaryOk = false;
let summarySoftCancelled = false;
let summaryError: string | null = null;
let result: StreamResult | null = null;
try {
result = await streamCompletion(
ctx,
session.model,
messages,
{ tools: null, temperature: agent?.temperature },
(delta) => {
accumulated += delta;
ctx.publish(sessionId, {
type: 'delta',
message_id: assistantMessageId,
chat_id: chatId,
content: delta,
});
scheduleFlush();
},
undefined,
signal,
);
summaryOk = true;
} catch (err) {
if (err instanceof Error && err.name === 'AbortError') {
summarySoftCancelled = true;
} else {
summaryError = err instanceof Error ? err.message : String(err);
}
} finally {
if (pendingFlushTimer) {
clearTimeout(pendingFlushTimer);
pendingFlushTimer = null;
}
await flushPromise;
}
if (summaryOk && result) {
const mctx = await modelContext.getModelContext(session.model);
const nCtx = mctx?.n_ctx ?? null;
const [updated] = await ctx.sql<
{ tokens_used: number | null; ctx_used: number | null; ctx_max: number | null; finished_at: string | null }[]
>`
UPDATE messages
SET content = ${result.content},
status = 'complete',
tokens_used = ${result.completionTokens},
ctx_used = ${result.promptTokens},
ctx_max = ${nCtx},
finished_at = clock_timestamp()
WHERE id = ${assistantMessageId}
RETURNING tokens_used, ctx_used, ctx_max, finished_at
`;
ctx.publish(sessionId, {
type: 'message_complete',
message_id: assistantMessageId,
chat_id: chatId,
tokens_used: updated?.tokens_used ?? null,
ctx_used: updated?.ctx_used ?? null,
ctx_max: updated?.ctx_max ?? null,
started_at: startedAt,
finished_at: updated?.finished_at ?? null,
model: session.model,
});
} else if (summarySoftCancelled) {
await ctx.sql`
UPDATE messages
SET content = ${accumulated},
status = 'cancelled',
finished_at = clock_timestamp()
WHERE id = ${assistantMessageId}
`;
ctx.publish(sessionId, {
type: 'message_complete',
message_id: assistantMessageId,
chat_id: chatId,
});
} else {
const errMeta: MessageMetadata = {
kind: 'error',
error_reason: 'summary_after_cap_failed',
error_text: summaryError ?? 'step-cap summary failed',
};
await ctx.sql`
UPDATE messages
SET content = ${accumulated},
status = 'failed',
finished_at = clock_timestamp(),
metadata = ${ctx.sql.json(errMeta as never)}
WHERE id = ${assistantMessageId}
`;
ctx.publish(sessionId, {
type: 'error',
message_id: assistantMessageId,
chat_id: chatId,
error: summaryError ?? 'step-cap summary failed',
reason: 'summary_after_cap_failed',
});
}
const [sessRow] = await ctx.sql<{ project_id: string; name: string; updated_at: string }[]>`
UPDATE sessions SET updated_at = clock_timestamp()
WHERE id = ${sessionId}
RETURNING project_id, name, updated_at
`;
ctx.publishUser({
type: 'session_updated',
session_id: sessionId,
project_id: sessRow!.project_id,
name: sessRow!.name,
updated_at: sessRow!.updated_at,
});
// Reuse cap_hit sentinel so the frontend CapHitSentinel component renders
// it without changes. The content text distinguishes step cap from budget.
await insertCapHitSentinel(ctx, sessionId, chatId, agent, cap);
if (summaryOk || summarySoftCancelled) {
ctx.publishUser({ type: 'chat_status', chat_id: chatId, status: 'idle', at: new Date().toISOString() });
} else {
ctx.publishUser({
type: 'chat_status',
chat_id: chatId,
status: 'error',
at: new Date().toISOString(),
reason: 'summary_after_cap_failed',
});
}
ctx.log.info(
{ sessionId, chatId, assistantMessageId, steps, cap, summaryOk, summaryCancelled: summarySoftCancelled },
'inference step-cap summary finished',
);
}
async function insertDoomLoopSentinel(
ctx: InferenceContext,
sessionId: string,