indifferentketchup/boocode
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

v1.13.1-C: port ask_user_input correlation to parts + wire reasoning_parts end-to-end

Browse Source 
Pass 1 — ask_user_input correlation port (messages.ts:478, :549):

- The two correlation queries that backed the elicitation flow used to scan
  messages.tool_calls and messages.tool_results JSON columns directly. They
  now JOIN message_parts on payload->>'id' (for the caller assistant) and
  payload->>'tool_call_id' (for the pending tool row). Semantics preserved:
  ORDER BY m.created_at DESC LIMIT 1 still picks the latest issuance, the
  already-answered 409 guard now reads payload.output, and the UPDATE +
  parts replace inside sql.begin is unchanged from v1.13.0.
- Pre-v1.13.0 history has no parts rows and is unreachable to this lookup
  path (404). Acceptable per dispatch decision — no pending elicitation
  from before v1.13.0 will still be open. JSON-column fallback can land as
  a hotfix if it ever surfaces.

Pass 2 — reasoning_parts wired end-to-end:

- types.ts/StreamResult gains `reasoning: string`. stream-phase.ts accumulates
  reasoning-delta text per stream (replacing the v1.13.1-A counter-only
  diagnostic) and returns it on the result.
- parts.ts/partsFromAssistantMessage gains an optional `reasoning` param.
  When present it emits a kind='reasoning' part at sequence 0, ahead of
  the text and tool_call parts.
- error-handler.ts/finalizeCompletion and tool-phase.ts/executeToolPhase
  both thread result.reasoning into the dual-write call so reasoning-channel
  models (qwen3.6) get persistent reasoning rows.
- payload.ts: loadContext SELECT pulls reasoning_parts from the v1.13.1-B
  view; OpenAiMessage gains an optional `reasoning` field; buildMessagesPayload
  collapses reasoning_parts into a single string per assistant message.
- stream-phase.ts/toModelMessages converts assistant messages with reasoning
  into an AI SDK ModelMessage content array starting with a ReasoningPart,
  matching the @ai-sdk/provider-utils AssistantContent union. Reasoning
  models can now replay prior reasoning context across tool-call boundaries.
- types/api.ts and apps/web/src/api/types.ts Message interface gain
  reasoning_parts (optional, nullable). Frontend doesn't render this yet —
  field reserved for a v1.14 UI surface.

Tests: 2 new in parts.test.ts cover reasoning-at-sequence-0 with and
without text content. 172 tests pass (170 prior + 2 new).

Smoke verified against the live container:
- A reasoning-prompt ("walk through 17 × 23 step by step") produced one
  message with kind='reasoning' (361 chars) at sequence 0 and kind='text'
  (429 chars) at sequence 1. Adapter log confirmed reasoning capture.
- The new correlation SQL was validated against existing tool_call /
  tool_result parts: returns the expected message_id + payload shape with
  pending state correctly identified via payload.output IS NULL.
- ask_user_input end-to-end through the UI is Sam's smoke — the Prompt
  Builder agent does not always trigger ask_user_input for these prompts,
  so synthetic verification via SQL substituted for traffic-driven cover.

Annotation: the v1.13.1-A abort-throw site in stream-phase.ts got a
one-liner comment ("AI SDK v6 fullStream returns normally on abort; check
signal explicitly.") to prevent a future refactor removing it.

v1.13.2 drops the dual-write + the JSON columns + collapses the view.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
indifferentketchup
2026-05-22 06:34:10 +00:00
parent 13c3aa5b4e
commit ac1a71f583
10 changed files with 169 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
apps/server/src/services/inference/stream-phase.ts
View File

@@ -49,20 +49,28 @@ function toModelMessages(messages: OpenAiMessage[]): ModelMessage[] {
}
if (m.role === 'assistant') {
const hasTools = m.tool_calls && m.tool_calls.length > 0;
if (!hasTools) {
const hasReasoning = typeof m.reasoning === 'string' && m.reasoning.length > 0;
if (!hasTools && !hasReasoning) {
// Bare text assistant (string content). null content + no tool_calls
// is degenerate but harmless to forward.
out.push({ role: 'assistant', content: m.content ?? '' });
continue;
}
// v1.13.1-C: AI SDK ReasoningPart precedes text + tool-calls in the
// assistant content array. Reasoning models (qwen3.6) consume their
// prior reasoning context to resume mid-thought across tool boundaries.
const parts: Array<
| { type: 'reasoning'; text: string }
| { type: 'text'; text: string }
| { type: 'tool-call'; toolCallId: string; toolName: string; input: unknown }
> = [];
if (hasReasoning) {
parts.push({ type: 'reasoning', text: m.reasoning! });
}
if (m.content && m.content.length > 0) {
parts.push({ type: 'text', text: m.content });
}
for (const tc of m.tool_calls!) {
for (const tc of m.tool_calls ?? []) {
let input: unknown = {};
try {
input = tc.function.arguments.length > 0 ? JSON.parse(tc.function.arguments) : {};
@@ -141,7 +149,11 @@ export async function streamCompletion(
const aiTools = hasTools ? buildAiTools(opts.tools!) : undefined;
const startedAt = Date.now();
let reasoningDeltaCount = 0;
// v1.13.1-C: accumulate reasoning text across reasoning-delta parts.
// qwen3.6 emits these on a separate channel from text content; we capture
// them per stream so finalizeCompletion can dual-write a 'reasoning' part.
// Replaces the v1.13.1-A counter-only diagnostic.
let reasoningAccumulated = '';
const result = streamText({
model: upstreamModel(ctx.config.LLAMA_SWAP_URL, model),
@@ -218,10 +230,11 @@ export async function streamCompletion(
break;
}
case 'reasoning-delta': {
// v1.13.1-A: reasoning parts are dropped for now. v1.13.1-C will
// persist them as `kind='reasoning'` rows in message_parts. Counter
// is logged at finish so we know whether qwen3.6 actually emits any.
reasoningDeltaCount += 1;
// v1.13.1-C: accumulate; finalizeCompletion / executeToolPhase
// dual-write the resulting text as a kind='reasoning' part.
if (typeof part.text === 'string') {
reasoningAccumulated += part.text;
}
break;
}
case 'finish': {
@@ -254,11 +267,10 @@ export async function streamCompletion(
pendingBuffer = '';
}
// v1.13.1-A: AI SDK v6 swallows the abort signal — the fullStream iterator
// exits cleanly and we'd otherwise return a successful StreamResult, which
// makes executeStreamPhase call finalizeCompletion and write status='complete'.
// Detect post-iteration abort and throw an AbortError so handleAbortOrError
// owns the row instead, matching v1.12.x stop-button behavior.
// AI SDK v6 fullStream returns normally on abort; check signal explicitly.
// Without this throw the row would land as status='complete' with partial
// content instead of going through handleAbortOrError → status='cancelled'.
// Smoke D caught this in v1.13.1-A — don't refactor it away.
if (signal?.aborted) {
const abortErr = new Error('aborted');
abortErr.name = 'AbortError';
@@ -281,14 +293,21 @@ export async function streamCompletion(
onUsage(promptTokens, completionTokens);
}
if (reasoningDeltaCount > 0) {
if (reasoningAccumulated.length > 0) {
ctx.log.debug(
{ reasoningDeltaCount, model, elapsed_ms: Date.now() - startedAt },
'streamCompletion: reasoning deltas dropped (captured in v1.13.1-C)',
{ reasoningChars: reasoningAccumulated.length, model, elapsed_ms: Date.now() - startedAt },
'streamCompletion: captured reasoning',
);
}
return { finishReason, content, toolCalls, promptTokens, completionTokens };
return {
finishReason,
content,
toolCalls,
promptTokens,
completionTokens,
reasoning: reasoningAccumulated,
};
}
export async function executeStreamPhase(