kenneth 682df6a573 fix(backend): disable reasoning and fallback to reasoning field
Set reasoning effort to none in the LLM client to reduce latency
and token usage. Fall back to the reasoning field when content is
absent in the response.

Co-authored-by: Ona <no-reply@ona.com>
2026-03-22 22:46:03 +00:00
2026-01-16 00:56:55 +00:00
2026-01-16 00:56:55 +00:00
2026-03-10 19:19:23 +00:00
2026-03-10 19:19:23 +00:00
2026-01-16 00:56:55 +00:00

aelis

To install dependencies:

bun install

Packages

@aelis/source-tfl

TfL (Transport for London) feed source for tube, overground, and Elizabeth line alerts.

Testing

cd packages/aelis-source-tfl
bun run test

Fixtures

Tests use fixture data from real TfL API responses stored in fixtures/tfl-responses.json.

To refresh fixtures:

bun run fetch-fixtures
Description
No description provided
Readme 15 MiB
Languages
TypeScript 97.2%
Shell 1%
CSS 0.9%
JavaScript 0.6%
Dockerfile 0.2%