v1.12.4-rc2: extract payload + error-handler from inference.ts

- payload.ts: buildMessagesPayload (re-exported), loadContext,
  maybeFlagForCompaction
- error-handler.ts: handleAbortOrError, finalizeCompletion

Both new files type-import InferenceContext/StreamResult/TurnArgs from
inference.ts; ESM elides type imports so there's no runtime cycle.
handleAbortOrError turned out not to call the summary functions, so
no back-edge needed.

inference.ts shrinks from ~1676 to ~1401 LoC.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-21 22:09:50 +00:00
parent ea468ca7fb
commit 8fa7b7fce9
3 changed files with 320 additions and 292 deletions

View File

@@ -0,0 +1,148 @@
import type { MessageMetadata, Session } from '../../types/api.js';
import * as modelContext from '../model-context.js';
import { maybeFlagForCompaction } from './payload.js';
import type { InferenceContext, StreamResult, TurnArgs } from '../inference.js';
export async function handleAbortOrError(
ctx: InferenceContext,
args: TurnArgs,
accumulated: string,
err: unknown
): Promise<void> {
const { sessionId, chatId, assistantMessageId } = args;
const isAbort = err instanceof Error && err.name === 'AbortError';
const finalStatus = isAbort ? 'cancelled' : 'failed';
const errMsg = err instanceof Error ? err.message : String(err);
// v1.8.2: persist a structured error metadata blob on genuine failures so
// the bubble can render the reason on reload without re-deriving from the
// (one-shot) WS error frame. User-initiated abort skips this — there's no
// "reason" to surface for a stop the user already explicitly chose.
const errorMetadata: MessageMetadata | null = isAbort
? null
: { kind: 'error', error_reason: 'llm_provider_error', error_text: errMsg };
if (errorMetadata) {
await ctx.sql`
UPDATE messages
SET status = ${finalStatus},
content = ${accumulated},
finished_at = clock_timestamp(),
metadata = ${ctx.sql.json(errorMetadata as never)}
WHERE id = ${assistantMessageId}
`;
} else {
await ctx.sql`
UPDATE messages
SET status = ${finalStatus},
content = ${accumulated},
finished_at = clock_timestamp()
WHERE id = ${assistantMessageId}
`;
}
const [failSessRow] = await ctx.sql<{ project_id: string; name: string; updated_at: string }[]>`
UPDATE sessions SET updated_at = clock_timestamp()
WHERE id = ${sessionId}
RETURNING project_id, name, updated_at
`;
ctx.publishUser({ type: 'session_updated', session_id: sessionId, project_id: failSessRow!.project_id, name: failSessRow!.name, updated_at: failSessRow!.updated_at });
// v1.8 mobile-tabs: cancellation is a user-initiated stop, treat as idle;
// genuine errors flip the dot red. v1.8.2: error path also carries a
// machine-readable `reason` so the UI can render specifics inline.
if (isAbort) {
// v1.12.1: defensive cancellation write. The status=${finalStatus} UPDATE
// above already sets 'cancelled' for the AbortError case, but a row can
// leak as 'streaming' when the abort fires between the post-tool-phase
// INSERT (executeToolPhase) and the next runAssistantTurn's stream setup,
// bypassing the try/catch around executeStreamPhase. The status guard
// makes this a no-op when the earlier write already landed.
await ctx.sql`
UPDATE messages
SET status = 'cancelled', content = ${accumulated}, finished_at = clock_timestamp()
WHERE id = ${args.assistantMessageId} AND status = 'streaming'
`;
ctx.publishUser({ type: 'chat_status', chat_id: chatId, status: 'idle', at: new Date().toISOString() });
ctx.publish(sessionId, {
type: 'message_complete',
message_id: assistantMessageId,
chat_id: chatId,
});
ctx.log.info({ sessionId, chatId, assistantMessageId }, 'inference cancelled');
} else {
ctx.publishUser({
type: 'chat_status',
chat_id: chatId,
status: 'error',
at: new Date().toISOString(),
reason: 'llm_provider_error',
});
ctx.publish(sessionId, {
type: 'error',
message_id: assistantMessageId,
chat_id: chatId,
error: errMsg,
reason: 'llm_provider_error',
});
ctx.log.error({ err, sessionId, assistantMessageId }, 'inference failed');
}
}
export async function finalizeCompletion(
ctx: InferenceContext,
args: TurnArgs,
result: StreamResult,
startedAt: string | null,
session: Session
): Promise<void> {
const { sessionId, chatId, assistantMessageId } = args;
const { content, finishReason, promptTokens, completionTokens } = result;
// v1.11.3: see executeToolPhase for the rationale.
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 = ${content},
status = 'complete',
tokens_used = ${completionTokens},
ctx_used = ${promptTokens},
ctx_max = ${nCtx},
finished_at = clock_timestamp()
WHERE id = ${assistantMessageId}
RETURNING tokens_used, ctx_used, ctx_max, finished_at
`;
// v1.11: flag for compaction on the terminal turn too. Catches the common
// case of a turn that hit the limit without invoking tools.
await maybeFlagForCompaction(ctx, chatId, updated);
const [completeSessRow] = 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: completeSessRow!.project_id, name: completeSessRow!.name, updated_at: completeSessRow!.updated_at });
ctx.publishUser({ type: 'chat_status', chat_id: chatId, status: 'idle', at: new Date().toISOString() });
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,
});
ctx.log.info(
{
sessionId,
chatId,
assistantMessageId,
finishReason,
chars: content.length,
tokens_used: updated?.tokens_used,
ctx_used: updated?.ctx_used,
},
'inference complete'
);
}