21 Commits

Author SHA1 Message Date
Aiden Cline 7ccaec154e fix(sync): move inline comments to file top so they survive sync rewrites
The daily model sync rewrites synced provider TOMLs by parsing and
re-serializing them, which discards every comment except a leading header
block (the preservation added in f07ac11f only re-attaches the top-of-file
comment run). Any comment authored between sections was silently deleted on
every rewrite that touched the file — e.g. sync PR #3004 stripped Venice's
"# Live /models ..." citation from before [[reasoning_options]].

Rather than teach the serializer to track inline comments, move every
existing inline comment to the top of its file (a one-time data migration)
and document the rule in AGENTS.md. The existing leading-header
preservation then keeps them across rewrites.

Migrated 82 model files across Venice, Baseten, OVHcloud, and Cloudflare
Workers AI. Verified: every file parses to identical data before and after
(0 data mismatches), and round-tripping all 1000 synced files through the
existing formatToml + leadingComments preservation loses 0 comments.

No code change.
2026-07-03 03:11:46 -05:00
Adam 5c281e4feb feat: model descriptions 2026-07-01 14:16:49 -05:00
Aiden Cline 4e85eac00a docs: document provider reasoning request formats 2026-06-26 09:37:21 -05:00
github-actions[bot] 3f1d1575b6 chore(sync): update OVHcloud AI Endpoints model catalog 2026-06-26 03:26:07 +00:00
Aiden Cline fc4a781c2f fix(ovhcloud): complete reasoning controls 2026-06-10 23:16:08 -05:00
Aiden Cline c4650219c3 fix(sync): drop stale reasoning options 2026-06-10 23:13:06 -05:00
Aiden Cline 9fb0474d1c feat(ovhcloud): add reasoning options 2026-06-10 23:13:06 -05:00
Elias TOURNEUX ee71ea7181 feat(ovhcloud): Add qwen 3.6 27b 2026-06-01 11:57:58 +02:00
Elias TOURNEUX b038f40b64 feat(ovhcloud): Add OVHcloud sync mode 2026-06-01 10:28:46 +02:00
Elias TOURNEUX 4b7bdd9692 feat(ovhcloud): Add new Qwen models 2026-06-01 10:16:54 +02:00
Jaime de Aquino 2d142f920c Add Qwen3.5-9B model configuration file 2026-04-27 16:46:04 +02:00
aadhondt bb1c08dd41 chore(ovhcloud): remove 3 models no longer available in AI Endpoints
- deepseek-r1-distill-llama-70b
- mixtral-8x7b-instruct-v0.1
- qwen2.5-coder-32b-instruct

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-17 22:38:35 +02:00
Elias TOURNEUX 67d192dd9c Update OVHcloud AI Endpoints models 2026-01-21 08:17:47 -05:00
Aiden Cline bcb7182f67 tweak 2026-01-13 20:07:18 -06:00
Aiden Cline 1008f394ee wip 2026-01-13 18:33:02 -06:00
Aaron Iker 6fafd70000 fix: reorder some provider logos 2025-12-21 22:38:00 +01:00
Aaron Iker d35af033d0 fix: visually align provider logos 2025-12-21 22:08:18 +01:00
Adam 8de746edab feat: model family 2025-12-14 03:41:22 -06:00
Elias TOURNEUX 3b52def3fc Add OVHcloud AI Endpoints reasoning models 2025-11-14 15:28:25 -05:00
Elias TOURNEUX 8b98367b8b Update of OVHcloud AI Endpoints prices 2025-11-13 09:34:53 -05:00
Elias TOURNEUX 6623724f21 Add OVHcloud AI Endpoints provider 2025-11-12 13:36:04 -05:00