CHANGELOG.md

@@ -43,6 +43,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   OpenRouter, etc.; `openai` uses the official provider (real-OpenAI
   reasoning-model request shaping). Chosen explicitly rather than inferred from
   the base URL, since a custom URL can front real OpenAI too. (#175, #177)
+- **AI chat "Context window (tokens)" setting (`chatContextWindow`).** A new
+  admin field in AI settings that records the chat model's context-window size.
+  When set (> 0) it becomes the denominator of the header context-badge, which
+  now reads "used / max"; `0`/empty clears the limit and the badge shows only
+  the current context as before. There is no provider-independent way to read a
+  model's window automatically, so it is an explicit workspace-level value.
+  (#189)
 - **Per-MCP-server instructions in the agent prompt.** Each external MCP server
   now has an admin-authored `instructions` field ("how/when to use this server's
   tools") that is injected into the agent's system prompt next to that server's
@@ -61,6 +68,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   model's reasoning out of the box. An endpoint that is real OpenAI behind a
   custom base URL should set the new `chatApiStyle` "Protocol" to `openai`. (#177)
 
+- **AI chat header context-badge now shows "used / max".** When an admin sets
+  the new `chatContextWindow`, the badge displays the current context size over
+  the configured window (e.g. `120k / 200k`) instead of switching to a live
+  per-turn token counter during streaming. With no window configured the badge
+  keeps showing just the current context. (#189)
+
 - **Footnotes now reuse (Pandoc semantics).** Multiple `[^a]` references to the
   same id are ONE footnote — one number, one definition, several back-references
   — instead of being renamed to `a__2`, `a__3`. Duplicate `[^a]:` definitions are

apps/server/src/database/repos/workspace/workspace.repo.ts

@@ -256,11 +256,17 @@ export class WorkspaceRepo {
   ): Promise<Workspace> {
     const db = dbOrTx(this.db, trx);
     // Assemble the provider object IN SQL. Keys are fixed provider field names
-    // (sql.lit -> inlined literals, no injection); values are bound params cast
-    // to ::text — postgres.js sends bound params untyped, and jsonb_build_object's
-    // value args are polymorphic ("any"), so without the explicit ::text cast
-    // Postgres throws "could not determine data type of parameter $1". The result
-    // is a real jsonb object, never a double-encoded string. The CASE self-heals
+    // (sql.lit -> inlined literals, no injection); values are bound params with
+    // an explicit cast — postgres.js sends bound params untyped, and
+    // jsonb_build_object's value args are polymorphic ("any"), so without the
+    // cast Postgres throws "could not determine data type of parameter $1". The
+    // cast is branched by the JS runtime type so the value lands in jsonb with
+    // the matching JSON type: a number stays a JSON number (e.g.
+    // chatContextWindow → `{"chatContextWindow":200000}`, jsonb_typeof 'number'),
+    // a boolean a JSON boolean, everything else a JSON string. A plain `::text`
+    // for all would store a numeric field as the JSON STRING `"200000"`, which
+    // the client's `typeof === "number"` guards reject. The result is a real
+    // jsonb object, never a double-encoded string. The CASE self-heals
     // workspaces whose settings.ai.provider was previously corrupted into an
     // array/string.
     const entries = Object.entries(provider).filter(
@@ -268,7 +274,14 @@ export class WorkspaceRepo {
     );
     const patch = entries.length
       ? sql`jsonb_build_object(${sql.join(
-          entries.flatMap(([k, v]) => [sql.lit(k), sql`${v}::text`]),
+          entries.flatMap(([k, v]) => [
+            sql.lit(k),
+            typeof v === 'number'
+              ? sql`${v}::numeric`
+              : typeof v === 'boolean'
+                ? sql`${v}::boolean`
+                : sql`${v}::text`,
+          ]),
         )})`
       : sql`'{}'::jsonb`;
     return db

apps/server/test/integration/workspace-repo-ai-provider-settings.int-spec.ts

@@ -0,0 +1,91 @@
+import { Kysely, sql } from 'kysely';
+import { WorkspaceRepo } from '@docmost/db/repos/workspace/workspace.repo';
+import { getTestDb, destroyTestDb, createWorkspace } from './db';
+
+/**
+ * WorkspaceRepo.updateAiProviderSettings numeric round-trip (#189, #213).
+ *
+ * `chatContextWindow` is the first NUMERIC provider field routed through this
+ * generic SQL layer. The patch builder must cast a JS number so it lands in
+ * jsonb as a JSON NUMBER, not the JSON STRING `"200000"` — the client guards
+ * (`typeof === "number"`) reject a string, silently killing the `/ max` badge
+ * denominator. A plain `::text` cast (the prior code) regressed exactly this.
+ * These specs are real SQL and assert both the JS value type and the on-disk
+ * `jsonb_typeof`.
+ */
+describe('WorkspaceRepo.updateAiProviderSettings (numeric round-trip) [integration]', () => {
+  let db: Kysely<any>;
+  let repo: WorkspaceRepo;
+
+  beforeAll(() => {
+    db = getTestDb();
+    repo = new WorkspaceRepo(db as any);
+  });
+
+  afterAll(async () => {
+    await destroyTestDb();
+  });
+
+  it('stores chatContextWindow as a JSON number (not a "200000" string)', async () => {
+    const ws = await createWorkspace(db, { settings: undefined });
+
+    const updated = await repo.updateAiProviderSettings(ws.id, {
+      driver: 'openai',
+      chatModel: 'gpt-4o',
+      chatContextWindow: 200000,
+    });
+
+    // Returned row: the number survives as a real JS number, alongside the
+    // string fields which stay strings.
+    const provider = (updated.settings as any)?.ai?.provider;
+    expect(provider.chatContextWindow).toBe(200000);
+    expect(typeof provider.chatContextWindow).toBe('number');
+    expect(provider.driver).toBe('openai');
+    expect(provider.chatModel).toBe('gpt-4o');
+
+    // On disk: the jsonb value is typed 'number' (the must-fix assertion), and
+    // sibling string fields are typed 'string'.
+    const typed = await db
+      .selectFrom('workspaces')
+      .select([
+        sql<string>`jsonb_typeof(settings->'ai'->'provider'->'chatContextWindow')`.as(
+          'windowType',
+        ),
+        sql<string>`jsonb_typeof(settings->'ai'->'provider'->'chatModel')`.as(
+          'modelType',
+        ),
+      ])
+      .where('id', '=', ws.id)
+      .executeTakeFirstOrThrow();
+
+    expect(typed.windowType).toBe('number');
+    expect(typed.modelType).toBe('string');
+  });
+
+  it('re-reads chatContextWindow as a number after a partial-merge update', async () => {
+    const ws = await createWorkspace(db, {
+      settings: { ai: { provider: { driver: 'openai', chatModel: 'x' } } },
+    });
+
+    // Merge in only the numeric field; siblings must be preserved and the value
+    // must still be a JSON number, not a string.
+    await repo.updateAiProviderSettings(ws.id, { chatContextWindow: 128000 });
+
+    const row = await db
+      .selectFrom('workspaces')
+      .select([
+        'settings',
+        sql<string>`jsonb_typeof(settings->'ai'->'provider'->'chatContextWindow')`.as(
+          'windowType',
+        ),
+      ])
+      .where('id', '=', ws.id)
+      .executeTakeFirstOrThrow();
+
+    expect(row.windowType).toBe('number');
+    const provider = (row.settings as any)?.ai?.provider;
+    expect(provider.chatContextWindow).toBe(128000);
+    expect(provider.driver).toBe('openai');
+    expect(provider.chatModel).toBe('x');
+  });
+});