Demiurge The Single 31f519b9b0 fix(models): expose combo model token limits (#4189) ...

Integrated into release/v3.8.29. Thanks @megamen32! Reconciled on your branch: the branch had drifted behind release and would have reverted the centralized vision detection (#4072), the no-thinking gateway variants (#4145) and #4164's auto/* loop — those are kept, and your genuine improvement is applied on top: each auto/* /v1/models entry now carries advertised context/output limits + capabilities (createBuiltinAutoCombo, with a fallback to the minimal entry on resolve failure). Added a regression test (Rule #18) and bumped the catalog.ts file-size baseline 1440→1463 with justification.

2026-06-18 16:00:27 -03:00

..

_setup

Release v3.8.28 (#4053)

2026-06-17 19:26:32 -03:00

benchmarks

Release v3.8.2 (#2503)

2026-05-23 01:46:59 -03:00

e2e

Release v3.8.28 (#4053)

2026-06-17 19:26:32 -03:00

fixtures

fix(antigravity): default includeThoughts for modern Gemini models (#4180)

2026-06-18 14:16:59 -03:00

golden-set

feat(compression): expand caveman parity and MCP metadata compression

2026-05-03 09:14:20 -03:00

helpers

Fase 8 · Bloco B — suíte de correção (property + golden + SSE-correctness) (#3808)

2026-06-14 18:02:51 -03:00

integration

feat(sse): transparent stream recovery (free-claude-code port, Fase 4, opt-in) (#4131)

2026-06-18 00:22:05 -03:00

live

fix(security): resolve CodeQL ReDoS + URL sanitization alerts

2026-05-17 07:43:32 -03:00

llm-security

Fase 8 · Bloco D — injection-guard em todas as rotas LLM + red-team (#3857)

2026-06-14 18:02:18 -03:00

load

Fase 8 · Bloco C — resiliência runtime (chaos + heap-growth + k6 soak) (#3854)

2026-06-14 18:02:08 -03:00

manual

Release v3.8.20 (#3547)

2026-06-10 13:49:08 -03:00

security

feat: OmniRoute v1.0.0 — Intelligent AI Gateway & Universal LLM Proxy

2026-02-18 00:02:15 -03:00

snapshots/translation

fix(antigravity): default includeThoughts for modern Gemini models (#4180)

2026-06-18 14:16:59 -03:00

translator

chore: apply PR 1495 and update changelog

2026-04-21 21:12:29 -03:00

unit

fix(models): expose combo model token limits (#4189)

2026-06-18 16:00:27 -03:00

e2e-tool-calls.sh

Release v3.8.24 (#3747)

2026-06-13 17:27:40 -03:00

scratch_test.mjs

refactor: implement path utilities, add custom date formatting, improve type safety, and unify database imports

2026-04-21 21:10:48 -03:00

theoldllm-stress.test.ts

feat(provider): add The Old LLM (theoldllm) — free Playwright-backed provider (#3217)

2026-06-05 11:45:24 -03:00