fix(infra): remove group order

chore: add internal (#1828)

fix(hchat): `deepseek-ai/DeepSeek-R1-Distill-Qwen-32B` endpoint url

New `InferenceClient` endpoint type (#1813)

fix(cohere): 404 due to org rename (#1815)

fix(huggingchat): sed api-inference (#1814)

fix: correct typo in prompt example in prod.yaml

feat: update banner

feat: new model 29-04-25 (#1808)

fix: config bits

feat(huggingchat): update available models

feat: add Mistral-Small-3.1-24B-Instruct-2503 model and Phi-4 (#1806)

fix: prod config

feat: rework example layout to work better on mobile

feat: allow storing env variable in DB (#1802)

feat: admin CLI login (#1789)

fix(chart): add config checksum (#1738)

fix(hchat): update endpoint for qwq

fix: add missing examples in prod config

fix: duplicate endpoints in task model

Revert "Revert "feat(config): add gemma 3 to prod config (#1753)""

feat: improve task model tool calling (#1755)

Revert "feat(config): add gemma 3 to prod config (#1753)"

feat(config): add gemma 3 to prod config (#1753)

fix: improve tasks performance

feat(model): configure Llama-3.1-8B-Instruct with OpenAI-compatible endpoint

feat(tasks): use tools for tasks if available (#1749)

feat(hchat): add QwQ-32B to prod HuggingChat config (#1746)

fix(prod): model config

fix(huggingchat): add additional stop token for model configuration

fix(hchat): update internal endpoint (#1716)

refactor: remove deprecated EXPOSE_API environment variable

fix: handle no beginToken for token based reasoning models (#1713)

feat(hchat): move Llama 3.3 70B as the default model

feat(chart): use inference proxy (#1688)

Update prod.yaml

feat(hchat): Add additional network policy allowed blocks (#1679)

fix(chart): use dedicated nodes (#1675)

feat(hchat): update banners

feat: add `deepseek-ai/DeepSeek-R1-Distill-Qwen-32B` to HuggingChat config (#1660)

fix: update name of task model

feat: show login modal if login is required for creating assistants & tools (#1640)

feat: new tool UI (#1630)

fix: add banner for 3.3

config(hchat): model update 06-12-24 (#1617)

feat: improve tool calling & add tools to qwen 2.5 72b (#1615)

Revert "Remove unneeded QwQ System prompt (#1610)"

Remove unneeded QwQ System prompt (#1610)

feat: UI for advanced reasoning models (#1605)

feat(hchat): add examples to QwQ config and a banner update