Files
boocode/apps/server/src/routes/chats.ts
indifferentketchup 13c3aa5b4e v1.13.1-B: read-path flip from tool_calls/tool_results JSON columns to message_parts
- schema.sql: new messages_with_parts view. tool_calls aggregates parts
  with kind='tool_call' as a jsonb array of {id, name, args}; tool_results
  picks the single sequence=0 part with kind='tool_result' as a jsonb
  {tool_call_id, output, truncated, error?}. COALESCE against the legacy
  jsonb columns means pre-v1.13.0 history (no parts rows) still reads
  correctly via the fallback, and fresh inserts (where parts dual-write
  follows the row INSERT) hit the legacy columns until the parts land.
- reasoning_parts column added to the view but not selected by any caller
  yet — v1.13.1-C extends the Message type and pulls it into the model
  payload alongside the type extension.
- Read sites switched to FROM messages_with_parts:
  - routes/chats.ts:427 (chat history GET)
  - routes/messages.ts:95 (session history GET)
  - routes/ws.ts:27 (WS snapshot on session connect, resume path)
  - services/inference/payload.ts (loadContext for model assembly)
  - services/compaction.ts (compaction's payload assembly)
- chats.ts:394 (discard_stale UPDATE RETURNING) unchanged — UPDATEs target
  messages directly and the returned shape is for a freshly-modified row
  where the legacy column is dual-written and correct.
- messages.ts:478/549 (ask_user_input correlation) intentionally not
  migrated — those query a different shape, ported in v1.13.1-C.
- Writes still target `messages` directly; the view is read-only.

Smoke verified against the live container:
- Equivalence: 5/5 messages with both legacy column and parts row return
  identical tool_calls jsonb between FROM messages and FROM messages_with_parts.
- Perf: EXPLAIN ANALYZE on the 42-message stress chat returns in ~1ms
  (50ms threshold). Bitmap Index Scan on message_parts_msg_seq_idx
  carries the parts lookups.
- API contract: GET /api/chats/:id/messages returns identical
  {id, name, args} tool_calls and {tool_call_id, output, truncated, error}
  tool_results shapes to frontend consumers — no UI changes needed.
- Inference path: sent a view_file prompt; assistant turn 1 emitted the
  tool_call, tool message captured the result, follow-up assistant turn
  read the result back via loadContext (now view-backed) and answered
  correctly. End-to-end loop intact.

v1.13.2 drops the dual-write + the JSON columns + simplifies the view
to just SELECT FROM message_parts.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-22 06:22:47 +00:00

439 lines
15 KiB
TypeScript

import type { FastifyInstance } from 'fastify';
import { z } from 'zod';
import type { Sql } from '../db.js';
import type { Broker } from '../services/broker.js';
import type { Chat, Message } from '../types/api.js';
import { getModelContext } from '../services/model-context.js';
const CreateBody = z.object({
name: z.string().min(1).max(200).optional(),
});
const PatchBody = z.object({
name: z.string().min(1).max(200),
});
const ForkBody = z.object({
message_id: z.string().uuid(),
name: z.string().min(1).max(200).optional(),
});
const DiscardStaleBody = z.object({
message_id: z.string().uuid(),
});
const STALE_MIN_AGE_SECONDS = 60;
export function registerChatRoutes(
app: FastifyInstance,
sql: Sql,
broker: Broker
): void {
app.get<{ Params: { id: string }; Querystring: { status?: string } }>(
'/api/sessions/:id/chats',
async (req, reply) => {
const session = await sql`SELECT id FROM sessions WHERE id = ${req.params.id}`;
if (session.length === 0) {
reply.code(404);
return { error: 'session not found' };
}
const status = req.query.status === 'archived' ? 'archived' : 'open';
// Enriched list: computed per-chat fields via LATERAL joins.
const rows = await sql<Chat[]>`
SELECT
c.id, c.session_id, c.name, c.status, c.created_at, c.updated_at,
COALESCE(mc.cnt, 0)::int AS message_count,
lp.preview AS last_message_preview,
ec.tokens AS effective_context_tokens
FROM chats c
LEFT JOIN LATERAL (
SELECT COUNT(*) AS cnt FROM messages WHERE chat_id = c.id
) mc ON TRUE
LEFT JOIN LATERAL (
SELECT LEFT(BTRIM(REGEXP_REPLACE(content, E'[\\n\\r]+', ' ', 'g')), 80) AS preview
FROM messages
WHERE chat_id = c.id AND kind = 'message' AND content <> ''
ORDER BY created_at DESC
LIMIT 1
) lp ON TRUE
LEFT JOIN LATERAL (
SELECT ctx_used AS tokens
FROM messages
WHERE chat_id = c.id AND kind = 'message' AND role = 'assistant'
AND status = 'complete' AND ctx_used IS NOT NULL
ORDER BY created_at DESC
LIMIT 1
) ec ON TRUE
WHERE c.session_id = ${req.params.id} AND c.status = ${status}
ORDER BY c.updated_at DESC
`;
// v1.11.5: enrich each chat with its model's context window so the
// ContextBar can render a zero-state (and the auto-compaction threshold
// tooltip) before the first assistant message lands. All chats in a
// session share the session's model, so we do ONE getModelContext
// lookup and apply the result to the whole list. Failed lookups
// (model unknown, llama-swap down) yield null and the frontend falls
// through to the "model context unknown" placeholder.
const sessRow = await sql<{ model: string | null }[]>`
SELECT model FROM sessions WHERE id = ${req.params.id}
`;
const sessionModel = sessRow[0]?.model ?? null;
const mctx = sessionModel ? await getModelContext(sessionModel) : null;
const modelContextLimit = mctx?.n_ctx ?? null;
return rows.map((r) => ({ ...r, model_context_limit: modelContextLimit }));
}
);
app.post<{ Params: { id: string } }>(
'/api/sessions/:id/chats',
async (req, reply) => {
const parsed = CreateBody.safeParse(req.body ?? {});
if (!parsed.success) {
reply.code(400);
return { error: 'invalid body', details: parsed.error.flatten() };
}
const session = await sql`SELECT id FROM sessions WHERE id = ${req.params.id}`;
if (session.length === 0) {
reply.code(404);
return { error: 'session not found' };
}
const [chat] = await sql<Chat[]>`
INSERT INTO chats (session_id, name, status)
VALUES (${req.params.id}, ${parsed.data.name ?? null}, 'open')
RETURNING id, session_id, name, status, created_at, updated_at
`;
broker.publishUser('default', {
type: 'chat_created',
chat: chat!,
session_id: req.params.id,
});
reply.code(201);
return chat;
}
);
app.patch<{ Params: { id: string } }>(
'/api/chats/:id',
async (req, reply) => {
const parsed = PatchBody.safeParse(req.body ?? {});
if (!parsed.success) {
reply.code(400);
return { error: 'invalid body', details: parsed.error.flatten() };
}
const rows = await sql<Chat[]>`
UPDATE chats
SET name = ${parsed.data.name},
updated_at = clock_timestamp()
WHERE id = ${req.params.id}
RETURNING id, session_id, name, status, created_at, updated_at
`;
if (rows.length === 0) {
reply.code(404);
return { error: 'chat not found' };
}
const chat = rows[0]!;
broker.publishUser('default', {
type: 'chat_updated',
chat_id: chat.id,
session_id: chat.session_id,
name: chat.name,
updated_at: chat.updated_at,
});
return chat;
}
);
// v1.9: bulk-archive every open chat in a session. Mirrors the single
// /chats/:id/archive shape — N chat_archived frames published, useSidebar
// reducer handles each via the existing case.
app.post<{ Params: { id: string } }>(
'/api/sessions/:id/chats/archive-all',
async (req, reply) => {
const session = await sql`SELECT id FROM sessions WHERE id = ${req.params.id}`;
if (session.length === 0) {
reply.code(404);
return { error: 'session not found' };
}
const rows = await sql<{ id: string }[]>`
UPDATE chats
SET status = 'archived', updated_at = clock_timestamp()
WHERE session_id = ${req.params.id} AND status = 'open'
RETURNING id
`;
const ids = rows.map((r) => r.id);
for (const id of ids) {
broker.publishUser('default', {
type: 'chat_archived',
chat_id: id,
session_id: req.params.id,
});
}
return { archived: ids.length, ids };
}
);
// v1.9: count helper for the confirm dialog.
app.get<{ Params: { id: string } }>(
'/api/sessions/:id/chats/open-count',
async (req, reply) => {
const session = await sql`SELECT id FROM sessions WHERE id = ${req.params.id}`;
if (session.length === 0) {
reply.code(404);
return { error: 'session not found' };
}
const rows = await sql<{ count: number }[]>`
SELECT COUNT(*)::int AS count
FROM chats
WHERE session_id = ${req.params.id} AND status = 'open'
`;
return { count: rows[0]?.count ?? 0 };
}
);
app.post<{ Params: { id: string } }>(
'/api/chats/:id/archive',
async (req, reply) => {
const rows = await sql<{ id: string; session_id: string }[]>`
UPDATE chats SET status = 'archived', updated_at = clock_timestamp()
WHERE id = ${req.params.id} AND status = 'open'
RETURNING id, session_id
`;
if (rows.length === 0) {
reply.code(404);
return { error: 'chat not found or already archived' };
}
const row = rows[0]!;
broker.publishUser('default', {
type: 'chat_archived',
chat_id: row.id,
session_id: row.session_id,
});
reply.code(204);
return null;
}
);
app.post<{ Params: { id: string } }>(
'/api/chats/:id/unarchive',
async (req, reply) => {
const rows = await sql<Chat[]>`
UPDATE chats SET status = 'open', updated_at = clock_timestamp()
WHERE id = ${req.params.id} AND status = 'archived'
RETURNING id, session_id, name, status, created_at, updated_at
`;
if (rows.length === 0) {
reply.code(404);
return { error: 'chat not found or not archived' };
}
const chat = rows[0]!;
broker.publishUser('default', { type: 'chat_unarchived', chat });
return chat;
}
);
app.delete<{ Params: { id: string } }>(
'/api/chats/:id',
async (req, reply) => {
const result = await sql<{ id: string; session_id: string }[]>`
DELETE FROM chats WHERE id = ${req.params.id}
RETURNING id, session_id
`;
if (result.length === 0) {
reply.code(404);
return { error: 'chat not found' };
}
const row = result[0]!;
broker.publishUser('default', {
type: 'chat_deleted',
chat_id: row.id,
session_id: row.session_id,
});
reply.code(204);
return null;
}
);
app.post<{ Params: { id: string } }>(
'/api/chats/:id/fork',
async (req, reply) => {
const parsed = ForkBody.safeParse(req.body ?? {});
if (!parsed.success) {
reply.code(400);
return { error: 'invalid body', details: parsed.error.flatten() };
}
const sourceRows = await sql<Chat[]>`
SELECT id, session_id, name, status, created_at, updated_at
FROM chats WHERE id = ${req.params.id}
`;
if (sourceRows.length === 0) {
reply.code(404);
return { error: 'chat not found' };
}
const source = sourceRows[0]!;
const targetRows = await sql<{ created_at: string; status: string }[]>`
SELECT created_at, status FROM messages
WHERE chat_id = ${source.id} AND id = ${parsed.data.message_id}
`;
if (targetRows.length === 0) {
reply.code(404);
return { error: 'message not found in chat' };
}
const target = targetRows[0]!;
if (target.status !== 'complete') {
reply.code(400);
return { error: 'can only fork from completed messages' };
}
const newName = parsed.data.name ?? `${source.name ?? 'Chat'} (fork)`;
const newChat = await sql.begin(async (tx) => {
const [chat] = await tx<Chat[]>`
INSERT INTO chats (session_id, name, status)
VALUES (${source.session_id}, ${newName}, 'open')
RETURNING id, session_id, name, status, created_at, updated_at
`;
await tx`
INSERT INTO messages (
session_id, chat_id, role, content, kind, tool_calls, tool_results,
status, tokens_used, ctx_used, ctx_max, started_at, finished_at,
created_at, metadata
)
SELECT
${source.session_id}, ${chat!.id}, role, content, kind,
tool_calls, tool_results, status,
tokens_used, ctx_used, ctx_max, started_at, finished_at,
clock_timestamp() + (
ROW_NUMBER() OVER (ORDER BY created_at ASC, id ASC) * INTERVAL '1 microsecond'
),
metadata
FROM messages
WHERE chat_id = ${source.id}
AND created_at <= ${target.created_at}::timestamptz
AND status = 'complete'
`;
// v1.13.0: clone message_parts for the forked messages. Source and
// destination preserve ordering (the INSERT above orders by created_at,
// id) so a ROW_NUMBER pairing maps source.id → dest.id deterministically.
await tx`
WITH src AS (
SELECT id, ROW_NUMBER() OVER (ORDER BY created_at ASC, id ASC) AS rn
FROM messages
WHERE chat_id = ${source.id}
AND created_at <= ${target.created_at}::timestamptz
AND status = 'complete'
),
dst AS (
SELECT id, ROW_NUMBER() OVER (ORDER BY created_at ASC, id ASC) AS rn
FROM messages
WHERE chat_id = ${chat!.id}
)
INSERT INTO message_parts (message_id, sequence, kind, payload)
SELECT dst.id, p.sequence, p.kind, p.payload
FROM message_parts p
JOIN src ON p.message_id = src.id
JOIN dst ON dst.rn = src.rn
`;
return chat!;
});
broker.publishUser('default', {
type: 'chat_created',
chat: newChat,
session_id: source.session_id,
});
reply.code(201);
return newChat;
}
);
// v1.12.3: explicit recovery from a stuck-streaming assistant row. The
// frontend gates this behind a 60s no-token-activity timer; the server
// re-checks the age and current status for safety. Non-streaming rows
// return 409 (frontend race; idempotent retry is fine).
app.post<{ Params: { id: string } }>(
'/api/chats/:id/discard_stale',
async (req, reply) => {
const parsed = DiscardStaleBody.safeParse(req.body ?? {});
if (!parsed.success) {
reply.code(400);
return { error: 'invalid body', details: parsed.error.flatten() };
}
const rows = await sql<{
id: string;
session_id: string;
chat_id: string;
status: string;
age_seconds: number;
}[]>`
SELECT id, session_id, chat_id, status,
EXTRACT(EPOCH FROM (clock_timestamp() - created_at))::int AS age_seconds
FROM messages
WHERE id = ${parsed.data.message_id} AND chat_id = ${req.params.id}
`;
if (rows.length === 0) {
reply.code(404);
return { error: 'message not found in chat' };
}
const msg = rows[0]!;
if (msg.status !== 'streaming') {
reply.code(409);
return { error: 'message is no longer streaming', current_status: msg.status };
}
if (msg.age_seconds < STALE_MIN_AGE_SECONDS) {
reply.code(409);
return { error: 'message is not stale yet', age_seconds: msg.age_seconds };
}
const updated = await sql<Message[]>`
UPDATE messages
SET status = 'failed',
content = COALESCE(content, ''),
finished_at = clock_timestamp()
WHERE id = ${msg.id} AND status = 'streaming'
RETURNING 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, summary, tail_start_id, compacted_at
`;
if (updated.length === 0) {
// Race: the row flipped out of 'streaming' between our SELECT and UPDATE.
reply.code(409);
return { error: 'message status changed mid-request' };
}
broker.publishUser('default', {
type: 'chat_status',
chat_id: msg.chat_id,
status: 'idle',
at: new Date().toISOString(),
});
broker.publish(msg.session_id, {
type: 'message_complete',
message_id: msg.id,
chat_id: msg.chat_id,
});
return updated[0];
}
);
app.get<{ Params: { id: string } }>(
'/api/chats/:id/messages',
async (req, reply) => {
const chat = await sql`SELECT id FROM chats WHERE id = ${req.params.id}`;
if (chat.length === 0) {
reply.code(404);
return { error: 'chat not found' };
}
// v1.13.1-B: reads tool_calls/tool_results via the parts-merged view.
const rows = 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,
summary, tail_start_id, compacted_at
FROM messages_with_parts
WHERE chat_id = ${req.params.id}
ORDER BY created_at ASC, id ASC
`;
return rows;
}
);
}