discourse-ai/spec/lib
Sam 37dbd48513
FIX: implement max_output tokens (anthropic/openai/bedrock/gemini/open router) (#1447)
* FIX: implement max_output tokens (anthropic/openai/bedrock/gemini/open router)

Previously this feature existed but was not implemented
Also updates a bunch of models to in our preset to point to latest

* implementing in base is safer, simpler and easier to manage

* anthropic 3.5 is getting older, lets use 4.0 here and fix spec
2025-06-19 16:00:11 +10:00
..
completions FIX: implement max_output tokens (anthropic/openai/bedrock/gemini/open router) (#1447) 2025-06-19 16:00:11 +10:00
discord/bot REFACTOR: Move personas into its own module. (#1233) 2025-03-31 14:42:33 -03:00
discourse_automation FIX: persona triage should be logged to automation (#1326) 2025-05-08 12:51:36 +10:00
inference FEATURE: configurable embeddings (#1049) 2025-01-21 12:23:19 -03:00
inferred_concepts FIX: Proper default LLM detection for inferred concepts (#1392) 2025-06-02 17:56:47 -03:00
modules FIX: never block spam scanning user (#1437) 2025-06-17 14:51:27 +10:00
personas FEATURE: add context and llm controls to researcher, fix username filter (#1401) 2025-06-04 16:39:43 +10:00
translation DEV: Prevent multiple translation per post (#1443) 2025-06-18 13:24:02 +08:00
utils DEV: Log AI related configuration to staff action log (#1416) 2025-06-12 12:39:58 -07:00
guardian_extensions_spec.rb FIX: Restore gists previous group access behavior. (#1247) 2025-04-07 12:04:30 -03:00