Skip to content

📐 fix: Align Summarization Trigger Schema with Documented and Runtime-Supported Types #12735

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
danny-avila merged 8 commits into from
Apr 20, 2026
Merged

📐 fix: Align Summarization Trigger Schema with Documented and Runtime-Supported Types #12735

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
072d224
🐛 fix: accept documented `summarization.trigger.type` values
danny-avila Apr 18, 2026
599c0fe
🧹 fix: bound `token_ratio` trigger value to (0, 1]
danny-avila Apr 18, 2026
bc4e2c8
🧹 fix: accept `token_ratio: 0` per documented 0.0–1.0 inclusive range
danny-avila Apr 18, 2026
1aba326
🐛 fix: preserve `token_ratio` trigger when `value: 0`
danny-avila Apr 18, 2026
a2731a9
🧹 fix: reject non-finite trigger values at schema level
danny-avila Apr 18, 2026
7521b7e
🧹 fix: integer counts + targeted token_count migration warning
danny-avila Apr 18, 2026
3d11e26
🧹 fix: accurate fallback wording + bare-string trigger test
danny-avila Apr 18, 2026
617e166
🔇 fix: cast `raw.trigger.type` to inspect legacy value past narrowed …
danny-avila Apr 18, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions packages/api/src/agents/__tests__/run-summarization.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -218,7 +218,7 @@ describe('summarizationConfig field passthrough', () => {
const agents = await callAndCapture({
summarizationConfig: {
enabled: true,
trigger: { type: 'token_count', value: 8000 },
trigger: { type: 'token_ratio', value: 0.8 },
provider: 'anthropic',
model: 'claude-3-haiku',
parameters: { temperature: 0.2 },
Expand All @@ -233,7 +233,7 @@ describe('summarizationConfig field passthrough', () => {
// `enabled` is not forwarded to the agent-level config — it is resolved
// into the separate `summarizationEnabled` boolean on the agent input.
expect(agents[0].summarizationEnabled).toBe(true);
expect(config.trigger).toEqual({ type: 'token_count', value: 8000 });
expect(config.trigger).toEqual({ type: 'token_ratio', value: 0.8 });
expect(config.provider).toBe('anthropic');
expect(config.model).toBe('claude-3-haiku');
expect(config.parameters).toEqual({ temperature: 0.2 });
Expand Down
76 changes: 76 additions & 0 deletions packages/data-provider/specs/config-schemas.spec.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,8 @@ import {
interfaceSchema,
fileStorageSchema,
fileStrategiesSchema,
summarizationTriggerSchema,
summarizationConfigSchema,
} from '../src/config';
import { tModelSpecPresetSchema, EModelEndpoint } from '../src/schemas';
import { FileSources } from '../src/types/files';
Expand Down Expand Up @@ -502,3 +504,77 @@ describe('interfaceSchema', () => {
expect(result.modelSelect).toBe(false);
});
});

describe('summarizationTriggerSchema', () => {
it.each([
['token_ratio', 0.8],
['remaining_tokens', 500],
['messages_to_refine', 4],
] as const)('accepts documented trigger type "%s" with a sensible value', (type, value) => {
const result = summarizationTriggerSchema.safeParse({ type, value });
expect(result.success).toBe(true);
});

it('rejects the legacy/typoed "token_count" trigger type', () => {
const result = summarizationTriggerSchema.safeParse({
type: 'token_count',
value: 8000,
});
expect(result.success).toBe(false);
});

it('rejects unknown trigger types', () => {
const result = summarizationTriggerSchema.safeParse({
type: 'never_heard_of_it',
value: 1,
});
expect(result.success).toBe(false);
});

it('rejects zero or negative values', () => {
expect(summarizationTriggerSchema.safeParse({ type: 'token_ratio', value: 0 }).success).toBe(
false,
);
expect(summarizationTriggerSchema.safeParse({ type: 'token_ratio', value: -0.5 }).success).toBe(
false,
);
expect(
summarizationTriggerSchema.safeParse({ type: 'remaining_tokens', value: 0 }).success,
).toBe(false);
expect(
summarizationTriggerSchema.safeParse({ type: 'messages_to_refine', value: 0 }).success,
).toBe(false);
});

it('rejects token_ratio values > 1 to catch the "80 meant as 80%" mistake', () => {
expect(summarizationTriggerSchema.safeParse({ type: 'token_ratio', value: 80 }).success).toBe(
false,
);
expect(summarizationTriggerSchema.safeParse({ type: 'token_ratio', value: 1.01 }).success).toBe(
false,
);
});

it('accepts token_ratio value at the upper bound of 1', () => {
expect(summarizationTriggerSchema.safeParse({ type: 'token_ratio', value: 1 }).success).toBe(
true,
);
});

it('allows remaining_tokens and messages_to_refine values above 1 (token/message counts)', () => {
expect(
summarizationTriggerSchema.safeParse({ type: 'remaining_tokens', value: 2000 }).success,
).toBe(true);
expect(
summarizationTriggerSchema.safeParse({ type: 'messages_to_refine', value: 20 }).success,
).toBe(true);
});

it('parses inside the full summarization config', () => {
const result = summarizationConfigSchema.safeParse({
enabled: true,
trigger: { type: 'token_ratio', value: 0.8 },
});
expect(result.success).toBe(true);
});
});
18 changes: 14 additions & 4 deletions packages/data-provider/src/config.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1020,10 +1020,20 @@ export const memorySchema = z.object({

export type TMemoryConfig = DeepPartial<z.infer<typeof memorySchema>>;

export const summarizationTriggerSchema = z.object({
type: z.enum(['token_count']),
value: z.number().positive(),
});
export const summarizationTriggerSchema = z.discriminatedUnion('type', [
z.object({
type: z.literal('token_ratio'),
value: z.number().positive().max(1),
Copy link
Copy Markdown

@chatgpt-codex-connector chatgpt-codex-connector Bot Apr 18, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Allow documented token_ratio: 0 trigger threshold

The new token_ratio branch rejects value: 0 because it uses .positive().max(1), but the published trigger range is 0.0–1.0; this means a documented configuration now fails schema validation and can stop startup when configSchema.strict().safeParse(...) runs in config loading. This regression only appears when admins intentionally set trigger.type: "token_ratio" with value: 0 (e.g., to force immediate summarization), and the fix is to include 0 in the accepted lower bound for that variant.

Useful? React with 👍 / 👎.

Copy link
Copy Markdown
Owner Author

@danny-avila danny-avila Apr 18, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Addressed in bc4e2c8 — switched token_ratio from .positive().max(1) to .min(0).max(1) to match the documented inclusive 0.0–1.0 range. 0 is a valid extreme that means "summarize on every pruning event" per the SDK's usedRatio >= 0 check. remaining_tokens and messages_to_refine keep .positive() — 0 on either is semantically no-op given the SDK's messagesToRefineCount <= 0 early return.

}),
z.object({
type: z.literal('remaining_tokens'),
value: z.number().positive(),
Copy link
Copy Markdown

@chatgpt-codex-connector chatgpt-codex-connector Bot Apr 18, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Disallow Infinity in count-based trigger values

The new remaining_tokens/messages_to_refine branches validate value with z.number().positive(), which in Zod still accepts Infinity (e.g., YAML .inf). That means config validation can succeed, but the summarization runtime rejects non-finite trigger values and returns false, so summarization silently never fires even though the server starts cleanly. This mismatch is user-visible whenever trigger.value becomes infinite and should be blocked at schema level (e.g., .finite()) to keep validation and runtime behavior aligned.

Useful? React with 👍 / 👎.

Copy link
Copy Markdown
Owner Author

@danny-avila danny-avila Apr 18, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Addressed in a2731a9 — added .finite() to every trigger value. z.number().positive() accepts Infinity (and z.number() accepts NaN), which would pass validation and then silently no-op because the agents SDK guards every path with Number.isFinite(...). .finite() is applied uniformly (even to token_ratio where .max(1) already rules out Infinity but not NaN).

}),
z.object({
type: z.literal('messages_to_refine'),
value: z.number().positive(),
}),
]);

export const contextPruningSchema = z.object({
enabled: z.boolean().optional(),
Expand Down
Loading