Praveen K Palaniswamy 6d4c4843e9 fix(ollama): route models by advertised capability (#11087) — port of #11088 to the release line (#11271) ...

Validated on the combined 8-PR board: ollama-local-capabilities-routing 3/3, managed-model-import 9/9 (including the integration with the carried Gemini-3.5-Flash cleanup from #11259), 88/88 across the board's focused suites, typecheck:core + dashboard-typecheck clean, gates within baseline. This brings #11088 to the release line — it had squash-merged to main by base error (mine) — AND fixes the two defects the port caught: the global filter drop that leaked image/video models into OpenAI chat selections (now scoped to self-hosted providers) and the unregistered hard-lease credential site. Exemplary port discipline: byte-identical carry + the corrections in a separate reviewable commit + the superpowers docs deliberately left out. main still needs the same two-line fix. Thank you @yourspraveen!

2026-08-23 18:11:21 -03:00

..

config

fix(providers): clamp reasoning_effort to the declared vocabulary of models that expose one (#11274)

2026-08-23 18:10:21 -03:00

executors

fix(providers): clamp reasoning_effort to the declared vocabulary of models that expose one (#11274)

2026-08-23 18:10:21 -03:00

handlers

Integration: security tier + self-hosted operator blockers (rebased onto v3.8.51) (#10952)

2026-08-23 16:51:25 -03:00

lib

Release v3.8.4 (#2678)

2026-05-26 23:51:47 -03:00

mcp-server

feat(search): add context7 as a library-docs search and fetch provider (#11140)

2026-08-23 02:24:01 -03:00

services

fix(ollama): route models by advertised capability (#11087) — port of #11088 to the release line (#11271)

2026-08-23 18:11:21 -03:00

shared

Release v3.8.46

2026-07-07 13:14:06 -03:00

transformer

fix(sse): strip corrupted request_id from upstream SSE responses (#10223) (#10666)

2026-08-20 13:21:03 -03:00

translator

fix(sse): append synthetic user turn for GLM-family upstreams (400 [1214]) (#11209)

2026-08-23 09:47:07 -03:00

utils

Integration: security tier + self-hosted operator blockers (rebased onto v3.8.51) (#10952)

2026-08-23 16:51:25 -03:00

vendor/codex-chatgpt-web

fix(quality): green release/v3.8.50 base-reds round 2 (#9985) (#10131)

2026-08-12 16:09:34 -03:00

index.ts

[Part 1/3]refactor(qwen): replace legacy Qwen Code and remove OAuth provider (#7866)

2026-07-20 17:53:04 -03:00

package.json

fix(build): remove misleading open-sse/package.json facade and add workspace typecheck gate (#8781)

2026-08-07 18:07:50 -03:00

tsconfig.json

chore(sse): drop deprecated baseUrl from open-sse tsconfig for TS 7.0 (#8473)

2026-07-25 02:53:01 -03:00

types.d.ts

feat(api): add per-key prompt compression bypass (#10001)

2026-08-11 09:20:41 -03:00