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>

apps/server/src/services/inference/payload.ts

@@ -0,0 +1,155 @@
+import type { Sql } from '../../db.js';
+import type {
+  Agent,
+  Message,
+  Project,
+  Session,
+} from '../../types/api.js';
+import * as compaction from '../compaction.js';
+import { buildSystemPrompt } from '../system-prompt.js';
+import { isAnySentinel } from './sentinels.js';
+import type { InferenceContext } from '../inference.js';
+
+export interface OpenAiMessage {
+  role: 'system' | 'user' | 'assistant' | 'tool';
+  content: string | null;
+  tool_calls?: Array<{
+    id: string;
+    type: 'function';
+    function: { name: string; arguments: string };
+  }>;
+  tool_call_id?: string;
+}
+
+// v1.12: buildSystemPrompt lives in services/system-prompt.ts. It awaits the
+// container-guidance loader, so this function is async too and every call
+// site in inference.ts awaits the result.
+export async function buildMessagesPayload(
+  session: Session,
+  project: Project,
+  history: Message[],
+  agent: Agent | null = null
+): Promise<OpenAiMessage[]> {
+  const out: OpenAiMessage[] = [];
+  const systemPrompt = await buildSystemPrompt(project, session, agent);
+  out.push({ role: 'system', content: systemPrompt });
+
+  // Find the latest compact marker — only send messages from that point onwards
+  let startIdx = 0;
+  for (let i = history.length - 1; i >= 0; i--) {
+    if (history[i]!.kind === 'compact') {
+      startIdx = i;
+      break;
+    }
+  }
+
+  for (let i = startIdx; i < history.length; i++) {
+    const m = history[i]!;
+    if (m.kind === 'compact') {
+      out.push({ role: 'system', content: m.content });
+      continue;
+    }
+    // v1.8.2 / v1.11.6: cap-hit and doom-loop sentinels are UI-only — never
+    // send them to the LLM. The synthetic instruction note lives only inside
+    // the summary call's messages array and is never persisted, so on a
+    // follow-up turn the model resumes with a clean context.
+    if (isAnySentinel(m)) continue;
+    if (m.role === 'assistant' && m.status === 'streaming') continue;
+    if (m.role === 'assistant' && m.status === 'cancelled') continue;
+    if (m.role === 'tool') {
+      const tr = m.tool_results;
+      if (!tr) continue;
+      const outputText = tr.error
+        ? `error: ${tr.error}`
+        : typeof tr.output === 'string'
+          ? tr.output
+          : JSON.stringify(tr.output);
+      out.push({
+        role: 'tool',
+        content: outputText,
+        tool_call_id: tr.tool_call_id,
+      });
+      continue;
+    }
+    if (m.role === 'assistant') {
+      const msg: OpenAiMessage = {
+        role: 'assistant',
+        content: m.content && m.content.length > 0 ? m.content : null,
+      };
+      if (m.tool_calls && m.tool_calls.length > 0) {
+        msg.tool_calls = m.tool_calls.map((tc) => ({
+          id: tc.id,
+          type: 'function' as const,
+          function: { name: tc.name, arguments: JSON.stringify(tc.args) },
+        }));
+      }
+      out.push(msg);
+      continue;
+    }
+    out.push({ role: 'user', content: m.content });
+  }
+  return out;
+}
+
+export async function loadContext(
+  sql: Sql,
+  sessionId: string,
+  chatId: string
+): Promise<{ session: Session; project: Project; history: Message[] } | null> {
+  const sessionRows = await sql<Session[]>`
+    SELECT id, project_id, name, model, system_prompt, status, created_at, updated_at,
+           agent_id, web_search_enabled
+    FROM sessions WHERE id = ${sessionId}
+  `;
+  if (sessionRows.length === 0) return null;
+  const session = sessionRows[0]!;
+
+  const projectRows = await sql<Project[]>`
+    SELECT id, name, path, added_at, last_session_id, status, gitea_remote,
+           default_system_prompt, default_web_search_enabled
+    FROM projects WHERE id = ${session.project_id}
+  `;
+  if (projectRows.length === 0) return null;
+  const project = projectRows[0]!;
+
+  // v1.11: filter compacted messages out of the inference assembly. The GET
+  // /api/sessions/:id/messages endpoint still returns everything (so the UI
+  // can show history with the summary card inline); only LLM payloads skip
+  // compacted rows. compacted_at IS NULL keeps the active summary + tail.
+  const history = await sql<Message[]>`
+    SELECT id, session_id, chat_id, role, content, kind, tool_calls, tool_results, status, last_seq,
+           tokens_used, ctx_used, ctx_max, started_at, finished_at, created_at, metadata
+    FROM messages
+    WHERE chat_id = ${chatId} AND compacted_at IS NULL
+    ORDER BY created_at ASC, id ASC
+  `;
+
+  return { session, project, history };
+}
+
+// v1.11: shared helper used after both finalizeCompletion and executeToolPhase
+// persist their token counts. Reads tokens off the just-UPDATEd row (which
+// the caller returns from RETURNING), runs compaction.isOverflow, and flips
+// chats.needs_compaction. The next runAssistantTurn invocation acts on it.
+// Silent on missing tokens — llama-swap occasionally omits usage on truncated
+// streams, and we'd rather miss one overflow than crash the inference path.
+export async function maybeFlagForCompaction(
+  ctx: InferenceContext,
+  chatId: string,
+  updated: { tokens_used: number | null; ctx_used: number | null; ctx_max: number | null } | undefined,
+): Promise<void> {
+  if (!updated) return;
+  const promptTokens = updated.ctx_used;
+  const completionTokens = updated.tokens_used;
+  const contextLimit = updated.ctx_max;
+  if (typeof promptTokens !== 'number') return;
+  if (typeof completionTokens !== 'number') return;
+  if (typeof contextLimit !== 'number') return;
+  const overflow = compaction.isOverflow(
+    { prompt_tokens: promptTokens, completion_tokens: completionTokens },
+    contextLimit,
+  );
+  if (!overflow) return;
+  await ctx.sql`UPDATE chats SET needs_compaction = true WHERE id = ${chatId}`;
+  ctx.log.info({ chatId, promptTokens, completionTokens, contextLimit }, 'inference: flagged for compaction');
+}