v0.10.0

v0.10.0 — Release notes draft

Range: v0.9.6 → main (201 commits, 2026-01-21 → today)

Highlights

• Reasoning UI: per-model reasoning toggle, configurable reasoning effort for capable models, streaming reasoning in a fixed-height fade viewport (#2252, #2259, #2262, #2263).
• Image viewer: fullscreen lightbox for chat images, with pinch-zoom and pan gestures (#2261).
• Per-model inference provider selection: pick the provider per model, with provider icons in the model list, settings nav, and next to the model name; powered by a bits-ui Select.
• Mobile polish: larger header tap targets, no mobile-specific text shrinking, smarter haptic feedback (incl. a streaming haptic burst on first token), iOS Safari thinking-block fix.
• Conversation flow: ChatGPT-style scroll positioning for new messages, instant scroll on conversation switch, immediate stop on abort, copy button on user messages, inline title editing via double-click, nav item kebab dropdown.
• MCP & tools: configurable MCP_TOOL_TIMEOUT_MS, DNS-level SSRF protection on MCP endpoints, MCP examples for any tools-enabled model (not just router), Exa crawling tool, timezone-aware tool prompts, refined search-tool prompt.

Features

• Reasoning effort configuration for capable models (#2252)
• Streaming reasoning in fixed-height fade viewport (#2262), mobile cap (#2263)
• Per-model reasoning toggle in model settings
• Fullscreen lightbox + pinch-zoom/pan for chat images (#2261)
• Per-model inference provider selection with icons (settings + model list + chat header)
• Copy button on user messages; inline title edit on double-click in sidebar
• Page title on model pages; link username to HF profile in sidebar (HuggingChat)
• Smooth/anchored scroll on new messages; instant scroll between conversations
• Kebab dropdown for nav item edit/delete (#2246)
• Per-model system-prompt enable/disable toggle (#2231)
• Timezone support in tool prompts (#2233)
• Configurable MCP_TOOL_TIMEOUT_MS (#2063)
• Exa crawling MCP tool enabled; MCP prompt guidance for HTML apps
• Iframe embedding restricted to huggingface.co (#2053)
• Haptic feedback for mobile web (incl. burst on first token)
• New router models: DeepSeek‑V4‑Pro, Kimi‑K2.6, MiniMax‑M2.7, Molmo‑8B, Qwen3‑Coder‑Next, plus descriptions for GLM‑5.1, Gemma 4, Qwen 3.5 medium, etc.

Bugfixes

• Respect USE_USER_TOKEN in OpenAI endpoint (#2187)
• sameSite cookie default now follows secure flag — fixes HTTP deployments (#2249)
• Defer to router for model tool/multimodal capability on HuggingChat (#2251)
• DNS-level SSRF protection on MCP endpoints (#2195)
• Abort streaming immediately on stop; preserve partial output; treat APIUserAbortError correctly
• Re-apply interrupted flag after invalidateAll on abort; fix stale UUID errors
• Fix </think> tag leaking in MCP tool flow for reasoning models
• Skip empty prose wrapper before tool blocks; truncate long tool names on one line
• Off-by-one in spacer activation + tighter scroll threshold
• iOS Safari: collapsed thinking blocks no longer take full height
• Safari: line-clamp applied to reasoning toggle button
• Default value for PUBLIC_APP_ASSETS prevents undefined asset paths
• Tools/multimodal toggles fall back to model capability

Performance & infrastructure

• Optimize conversation stats aggregation (#2079)
• Add MongoDB missing indexes; MongoDB read preference support (#2090)
• MONGODB-AWS auth (#2200)
• Refactor: native SvelteKit API routes (replace Elysia)
• Extract conversation write path into service + projector (§2)
• Bump deps: svelte, kit, ajv, devalue, hono, qs, uuid, fast-uri, MCP SDK 1.25.2, undici, etc.

Other changes

• Dark-mode grays switched to high-contrast neutral palette; numerous style tweaks (nav, badge, tool chips, model settings header, mobile header)
• Theme button group replaced with a select dropdown in settings
• Markdown rendering refresh; shimmer on active labels; refined tool detail visuals
• Switch default multimodal model to zai-org/GLM-4.6V; switch task model to Llama-3.1-8B-Instruct
• Drop final streaming mode from settings; remove dead code & stale metrics

---

Generated locally — not committed, not tagged, not published. To publish:

gh release create v0.10.0 --title "v0.10.0" --notes-file release-notes-v0.10.0.md
# or, to use GitHub's auto-generated notes from .github/release.yml:
gh release create v0.10.0 --generate-notes

v0.9.6

What's Changed

Features

• refactor: new API & universal load functions by @nsarrazin in #1743

Other changes

• refactor: new API & universal load functions (pt. 2) by @nsarrazin in #1847
• refactor: api cleanup by @nsarrazin in #1849
• fix: Improve error handling in generateFromDefaultEndpoint by @calycekr in #1853
• build(deps-dev): bump brace-expansion from 1.1.11 to 1.1.12 by @dependabot[bot] in #1851
• fix: add tick() to prevent textarea height adjustment failures by @calycekr in #1854
• Fix broken documentation links to multimodal and tools in Cloudflare … by @VolodymyrBg in #1859
• feat: put export behind feature flag by @nsarrazin in #1862
• fix: reduce min pods following closure by @rtrompier in #1865
• docs: fix the llama-server README link ("examples" -> "tools") by @sgvictorino in #1869
• HuggingChat 2026 by @gary149 in #1875
• Update README.md by @gary149 in #1878
• Thumbnails by @gary149 in #1879
• Omni multimodality by @gary149 in #1880
• Add image attachment support to router examples by @gary149 in #1883
• Add background generation polling for conversation updates by @gary149 in #1882
• fix CI by @coyotte508 in #1884
• Add COUPLE_SESSION_WITH_COOKIE_NAME env var by @coyotte508 in #1881
• Store oauth token in DB + use it when doing API calls by @coyotte508 in #1885
• Automatic login by @coyotte508 in #1900
• Automatically refresh oauth token by @coyotte508 in #1913
• Abort by @gary149 in #1924
• Get pro by @gary149 in #1930
• Polling by @gary149 in #1932
• feat: update deploy conf by @rtrompier in #1933
• Add message trimming for router prompt construction by @gary149 in #1935
• App Settings: add target=blank to external links by @julien-c in #1937
• Remove alt text from model logo image by @krampstudio in #1936
• Oauth on welcome modal by @krampstudio in #1939
• fix: init plausible script by @rtrompier in #1946
• Add Poe as a provider by @garethpaul in #1943
• Prompt params by @gary149 in #1949
• Share convos by @krampstudio in #1942
• lint & ignore ts error on old migration scripts by @krampstudio in #1948
• Url attachments by @gary149 in #1950
• Add Prometheus metrics support with prom-client by @gary149 in #1934
• Link to provider by @julien-c in #1938
• Simplify login options by @krampstudio in #1953
• Disable the share button while generating by @krampstudio in #1958
• Refresh models by @gary149 in #1961
• allow guest on home and shared convo by @krampstudio in #1960
• Preserve and sanitize return path after login by @gary149 in #1959
• Redirect to shared conversation after login by @krampstudio in #1962
• Fix follow up message on shared conversation by @krampstudio in #1963
• Chore fix by @krampstudio in #1964
• Url attachments by @gary149 in #1965
• fix: allow com with huggingface by @rtrompier in #1966
• fix: structured logs by @rtrompier in #1967
• Shared conversation redirect by @krampstudio in #1968
• Plus UI dropdown by @gary149 in #1971
• feat: ephemeral env by @rtrompier in #1972
• fix: update OAuth redirect logic to include model thumbnail pages by @gary149 in #1977
• Improve opening a model from an URL by @krampstudio in #1979
• MCP by @gary149 in #1981
• MCP: Image refs by @gary149 in #1987
• mcp: tool results now properly rendered by @ServeurpersoCom in #1988
• Markdown rendering update by @gary149 in #1989
• Add CIMD support for automatic oauth app creation, and PKCE support by @coyotte508 in #1978
• Reset MCP timeout on Progress Notifications by @evalstate in #1992
• Add strict security headers to fetch-url endpoint by @gary149 in #1993
• Forward original MIME by @gary149 in #1994
• Login on focus by @krampstudio in #1969
• Org billing by @gary149 in #1995
• fix: remove redundant apt install that fails as non-root by @gary149 in #1996
• Fix double-click issue in navigation bar by @gary149 in #1999
• enabled base MCP servers by default by @gary149 in #2001
• Fix auto scroll behavior in message chat by @gary149 in #2000
• Mobile UI update by @gary149 in #2004
• New tools rendering by @gary149 in #2005
• Transcribe UI by @gary149 in #2006
• Disable zoom on mobile view by @gary149 in #2008
• filter out transcription returning ellipsis dots by @gary149 in #2009
• Replace welcome modal video with GIF for mobile compatibility by @gary149 in #2011
• fix(mcp): use logger by @rtrompier in #2014
• fix(log): use logger by @rtrompier in #2016
• Rename message field in logs by @rtrompier in #2015
• Require authentication before processing query params by @gary149 in #2017
• fix: improve logs by @rtrompier in #2018
• Contextual logs by @rtrompier in #2019
• feat(mcp): add direct Exa API integration to bypass slow mcp.exa.ai by @gary149 in #2021
• fix(mcp): reduce Exa API context size sent to LLM by @gary149 in #2026
• [Fix]: Hovering bug of close button in dark theme. by @nakul-py in #2034
• MCP Tool Progress Notifications and MCP SDK bump. by @evalstate in #2030
• fix(mcp): communicate tool errors to LLM to prevent hallucinated success by @gary149 in #2036
• feat(markdown): allow video and audio tags by @gary149 in #2037
• fix(markdown): use htmlparser2 instead of DOMPurify for Web Worker compatibility by @gary149 in #2039
• Adding tool-tip and updating color for sidebar toggle button. by @nakul-py in #2044
• feat: add PRO badge and credits modal for HuggingChat by @gary149 in #2048
• refactor: remove isPro from database schema by @gary149 in #2050
• Bump undici from 7.16.0 to 7.18.2 by @dependabot[bot] in #2047
• Bump @modelcontextprotocol/sdk from 1.25.1 to 1.25.2 by @dependabot[bot] in #2035
• feat: add descriptions for 8 new models from router by @gary149 in #2056
• Reduce unnecessary tool calls in model by @gary149 in #2057
• Allow X-HF-Bill-To header for all deployments by @gary149 in #2054
• Convert remaining server loads to universal loads for SPA/Capacitor support by @gary149 in https://github.com/huggingface/chat-ui/p...

v0.9.5

Doing a release with the latest changes before merging the API refactor

New Contributors

• @krjoha made their first contribution in #1555
• @StuartMesham made their first contribution in #1575
• @bot08 made their first contribution in #1602
• @guspan-tanadi made their first contribution in #1616
• @KeganHollern made their first contribution in #1618
• @drewtoto made their first contribution in #1568
• @northern-64bit made their first contribution in #1634
• @tarekbecker made their first contribution in #1629
• @ethayu made their first contribution in #1322
• @calycekr made their first contribution in #1643
• @laurentlb made their first contribution in #1651
• @lgarbarini made their first contribution in #1686
• @ishatalkin made their first contribution in #1690
• @vvnsrzn made their first contribution in #1709
• @brians1196 made their first contribution in #1717
• @JeanBaptiste-dlb made their first contribution in #1730
• @yousefelkilany made their first contribution in #1748
• @benglewis made their first contribution in #1739
• @slmagus made their first contribution in #1738
• @keligggg made their first contribution in #1787
• @IAmStoxe made their first contribution in #1764
• @dhruv1710 made their first contribution in #1760
• @oOraph made their first contribution in #1814
• @natikgadzhi made their first contribution in #1818
• @zvun made their first contribution in #1824
• @jwt625 made their first contribution in #1834
• @hongantran3804 made their first contribution in #1823
• @crStiv made their first contribution in #1839
• @vijay2904 made their first contribution in #1841

v0.9.4

What's Changed

Features

• feat: Update featured workflow to allow user to submit featured requests by @nsarrazin in #1510
• feat: lazy stream conversations load function by @nsarrazin in #1553

Bugfixes

• fix: upload of files on multimodal assistant on first message by @nsarrazin in #1513

Other changes

• feat: commit id in settings by @nsarrazin in #1507
• fix: Remove ; in Vertex AI example configuration in Readme.md and add model_version as config by @SebSchroen in #1508
• feat(endpoints): Add conv ID to headers passed to TGI by @nsarrazin in #1511
• feat(review): add force feature option & change label on make private option by @nsarrazin in #1519
• feat(security): add flag for allowing iframes by @nsarrazin in #1518
• feat(security): add cookie samesite & security settings by @nsarrazin in #1517
• [vertex] Add PDF/plein texts support by @ArthurGoupil in #1520
• nemotron: add examples by @gary149 in #1528
• [fix] Fix typo in Vertex by @ArthurGoupil in #1531
• fix(infra): new token name by @rtrompier in #1530
• fix: show file upload button when assistant has tool with file support by @nsarrazin in #1532
• feat: add confirmation popup before deleting content by @nsarrazin in #1534
• feat: use model id as fallback for finding a tokenizer by @nsarrazin in #1535
• fix: make sure transformers.js sees HF_TOKEN by @nsarrazin in #1536
• fix(modal): fix freeze after modal close by @neven4 in #1538
• [feat] Add support for endpoint web sources by @ArthurGoupil in #1544
• fix(ui): swap delete confirmation buttons for better UX (#1546) by @flash1729 in #1547
• feat: Add a model config option to disable system prompts by @Mounayer in #1539
• feat: paste long context as plaintext files by @nsarrazin in #1549
• feat: add sources for websearch by @nsarrazin in #1551
• [fix] Add placeholder param for sources icon by @ArthurGoupil in #1554

New Contributors

• @flash1729 made their first contribution in #1547
• @Mounayer made their first contribution in #1539

Full Changelog: v0.9.3...v0.9.4

v0.9.3

What's Changed

Features

• Community tools by @nsarrazin in #1250
• feat(media): support audio & video files by @nsarrazin in #1408
• feat(assistants): use community tools in assistants by @nsarrazin in #1421
• feat(settings): add indicator when custom instructions are active by @nsarrazin in #1438
• feat: add support for multimodal in Vertex by @ArthurGoupil in #1338
• feat(conv): let user switch models on conversations with deprecated models by @nsarrazin in #1462
• fix(assistants): remove websearch from assistant tool options, add websearch in backend logic by @nsarrazin in #1465
• fix(tools): tool call name must be a valid python variable name by @nsarrazin in #1466
• fix(endpoints): make bedrock import optional by @nsarrazin in #1468
• feat(tools): add toggle to see unfeatured tools for admins by @nsarrazin in #1474
• feat: add link to API playground for compatible models by @nsarrazin in #1488
• feat(tools): Basic tool support for OpenAI models by @gladish in #1447

Bugfixes

• fix(featureflags): use correct env vars by @nsarrazin in #1405
• fix(config): test setup update by @nsarrazin in #1430
• Fix typo by @julien-c in #1450
• fix(assistants): only enable websearch on assistants with RAG by @nsarrazin in #1452
• fix(continue): fix continue feature by @nsarrazin in #1459
• pluralize by @julien-c in #1469
• fix(websearch): fix webSearch flag use for model with tool use by @nsarrazin in #1480
• fix: multimodal on TGI endpoint type by @nsarrazin in #1491
• fix: prevent empty submits by @nsarrazin in #1501
• fix(docker): pin mongo version to latest 7 by @nsarrazin in #1504

Other changes

• Add steps to install from source for llama.cpp by @Vaibhavs10 in #1396
• Fix "Copy" button styling. Relates to issue 1387 by @evalstate in #1403
• feat(tools): use gradio ETA for tools by @nsarrazin in #1411
• chores(deps): update Transformers to latest version and remove chat templates for all models by @nsarrazin in #1414
• fix(huggingchat): remove app banners by @nsarrazin in #1426
• Websearch using Bing API by @harisyammnv in #1420
• Configurable websearch timeout by @ABarLT in #1427
• build(deps): bump micromatch from 4.0.7 to 4.0.8 by @dependabot in #1431
• fix(openai): do not throw "Generation failed" when finish_reason="length" by @llllvvuu in #1429
• Dynamic credential resolution for AWS endpoints by @nason in #1419
• Maintain Conversation Tree State on Refresh or Share by @kramosss in #1397
• Add start chat button on models & assistants. by @nsarrazin in #963
• Let users access the API using their HF token by @nsarrazin in #1216
• feat(tools): specify either space namespace or huggingface.co URL by @nsarrazin in #1435
• Add support for Anthropic models via AWS Bedrock by @ABarLT in #1413
• feat(assistants): better distinction between my own assistants and other people's assistants by @nsarrazin in #1437
• extend user count by @gary149 in #1455
• build(deps-dev): bump svelte from 4.2.18 to 4.2.19 by @dependabot in #1442
• Move Google GenAI API key to env file instead by @altbdoor in #1448
• feat(models): add transferTo property on old models by @nsarrazin in #1453
• Update prod.yaml by @gary149 in #1460
• feat(tools): add thumbnail by @nsarrazin in #1470
• feat(tools): remove feature flag for tools and use env variable instead by @nsarrazin in #1433
• fix(front): add better responsive design to tools & assistants by @nsarrazin in #1473
• fix(share): use copy link on desktop by @nsarrazin in #1477
• build(deps): bump express from 4.19.2 to 4.20.0 by @dependabot in #1478
• build(deps): bump send and express by @dependabot in #1479
• build(deps): bump rollup by @dependabot in #1482
• feat(front): add multimodal icon on model page by @nsarrazin in #1493
• Fix: Cohere Endpoint - Add Support for Tools by @dvirmor in #1490
• Added enter to insert new line on mobile instead of default. by @natecard in #1475
• feat: allow custom message to guest users. by @samehkhattab in #1441
• fix(front): fix clipboard copy on chrome by @nsarrazin in #1497
• Add support for model version in Vertex AI by @pocman in #1496
• Feature - Scroll to Previous Message by @evalstate in #1440
• feat: add content disposition to file endpoint by @nsarrazin in #1500
• Remove right margin from custom scrollbar by @rotemdan in #1498

New Contributors

• @Vaibhavs10 made their first contribution in #1396
• @evalstate made their first contribution in #1403
• @harisyammnv made their first contribution in #1420
• @ABarLT made their first contribution in #1427
• @llllvvuu made their first contribution in #1429
• @nason made their first contribution in #1419
• @kramosss made their first contribution in #1397
• @altbdoor made their first contribution in #1448
• @dvirmor made their first contribution in #1490
• @natecard made their first contribution in #1475
• @samehkhattab made their first contribution in #1441
• @pocman made their first contribution in #1496
• @rotemdan made their first contribution in #1498
• @gladish made their first contribution in #1447

Full Changelog: v0.9.2...v0.9.3

v0.9.2

What's Changed

Features

• Fix max upload size in huggingchat by @nsarrazin in #1251
• Add createdAt filter on messageEvents by @nsarrazin in #1256
• Add "disable streaming tokens" settings & remove media query by @nsarrazin in #1299
• Add Google Gemini API Support by @toandev95 in #1330
• feat(upload): Enable multi-file in dropzone by @nsarrazin in #1347
• feat(auth): Add admin & early access flags based on orgs membership by @nsarrazin in #1365
• Add support to @cf models with cloudflare.com by @wgcv in #1378
• feat(confirm): add confirm on deleting branch & sharing conversation by @nsarrazin in #1381
• Major bump to sveltekit & node-adapter versions by @nsarrazin in #1395

Bugfixes

• fix: increase body size limit in docker image by @nsarrazin in #1280
• Standardize llama.cpp endpoint with baseURL by @nsarrazin in #1305
• fix(disclaimer): only show disclaimer if PUBLIC_APP_DISCLAIMER is 1 by @nsarrazin in #1360
• fix(ui): fix cut off buttons in chat message by @dlavrenuek in #1373
• fix(cohere): pass toolResults only when needed to cohere endpoint type by @nsarrazin in #1382

Other changes

• feat(chart): service account by @rtrompier in #1252
• chore(dependencies): add aws4 to enable mongo passwordless auth by @rtrompier in #1253
• chore(dependencies): add @aws-sdk/credential-providers to enable mong… by @rtrompier in #1255
• Refactor logger error messages for consistency. by @dnzzzl in #1257
• feat(ci): add trufflehog secrets detection by @McPatate in #1259
• fix(ci): remove unnecessary permissions by @McPatate in #1260
• Add body size limit to prod env by @nsarrazin in #1265
• Add BODY_SIZE_LIMIT to build step by @nsarrazin in #1266
• Use bytes for body size limit by @nsarrazin in #1268
• Add BODY_SIZE_LIMIT to Dockerfile ARGs by @nsarrazin in #1269
• chore(deps): update major versions on svelte, sveltekit & node by @nsarrazin in #1281
• fix(scrape parser): Cannot read properties of 'undefined' during page parsing by @neven4 in #1274
• chore(deps): bump braces from 3.0.2 to 3.0.3 by @dependabot in #1267
• feat(chart): use infisical by @rtrompier in #1276
• fix(chart): infisical secret name by @rtrompier in #1284
• feat(chart): auto reload when secrets change by @rtrompier in #1285
• chore(deps): bump ws from 8.13.0 to 8.17.1 by @dependabot in #1291
• fix(screen-reader): disable FileDropZone area-label for models without file upload by @neven4 in #1295
• add files in the conversation[id] api by @alak in #1300
• Auto open app by @itsbhatt in #1294
• fix(env): change env var typo by @neven4 in #1307
• Fix "login" button text wrap on mobile by @neven4 in #1315
• Add CSP protection on uploaded files by @nsarrazin in #1304
• feat: allow disabling metrics server, consolidate exit handlers by @saghen in #1201
• Move stats to their own job by @nsarrazin in #1324
• feat: playwright-adblocked toggle #1298 by @krakenftw in #1301
• add new parameter in model and conversation api by @alak in #1325
• add messages updates in the conversation.messages api by @alak in #1327
• perf: add prod deployment resources by @jcudit in #1333
• remove-internal registry by @XciD in #1336
• remove dead code by @nsarrazin in #1339
• fix: prod registry repository by @jcudit in #1340
• Improve sanitization of model output by @nsarrazin in #1341
• fix(models): Update tokenizer on command R+ by @nsarrazin in #1345
• UX: Dropzone by @gary149 in #1350
• fix(tools): improve json parsing by @nsarrazin in #1356
• feat(config): improve sampling params for llama 3.1 by @nsarrazin in #1357
• fix(env) enable LLM_SUMMARIZATION by @zhang-yi-chi in #1379
• fix(assistant): add correct steps to repetition penalty by @nsarrazin in #1389
• feat(android): disable tools on android app by @nsarrazin in #1390

New Contributors

• @dnzzzl made their first contribution in #1257
• @McPatate made their first contribution in #1259
• @itsbhatt made their first contribution in #1294
• @jcudit made their first contribution in #1333
• @toandev95 made their first contribution in #1330
• @dlavrenuek made their first contribution in #1373
• @zhang-yi-chi made their first contribution in #1379
• @wgcv made their first contribution in #1378

Full Changelog: v0.9.1...v0.9.2

v0.9.1

What's Changed

Features

• Enable dropzone on tools by @nsarrazin in #1211
• Enable auth using trusted header by @lijunle in #1128
• Add super basic admin feature by @nsarrazin in #1213
• Add support for SearchApi API by @SebastjanPrachovskij in #1196
• Send ollama pull request if model is not available locally by @nsarrazin in #1227
• Add sampling parameter support to cloudflare by @nsarrazin in #1233
• Feat: Delete branch #1210 by @krakenftw in #1240
• Add support for ?q query parameter to start a conversation by @nsarrazin in #1232

Bugfixes

• fix websearch on assistants by @nsarrazin in #1244
• Hide upload button when tools are not available by @nsarrazin in #1245
• Handle errors gracefully in building PlaywrightBlocker by @nsarrazin in #1248

Other changes

• [readme] Bring back full readme by @mishig25 in #1207
• feat: request model be concise on tool image outputs by @saghen in #1202
• Assistants: add reset to default model button by @gary149 in #1200
• fix: tool error not updating in UI by @saghen in #1203
• Revamp llama.cpp docs by @mishig25 in #1214
• [docs] Fix errors by @mishig25 in #1218
• Fix migration object id by @nsarrazin in #1215
• feat: support file pasting in chat input by @saghen in #1206
• Remove gendered pronoun by @everypizza1 in #1219
• feat: skip tools when all disabled by @saghen in #1205
• Improve docs by @mishig25 in #1223
• [docs] fix css by @mishig25 in #1224
• feat: mime types on tools, show upload btn on demand by @saghen in #1204
• Trim trailing comma on tool calls by @saghen in #1229
• Fix error logging by @wdhorton in #1228
• Update README.md by @kodster28 in #1226
• Fix: tools in endpointVertex now optional by @SebSchroen in #1234
• Npm: Remove updateProdEnv from script from package.json by @rodrigobdz in #1243

New Contributors

• @cihancinar made their first contribution in #1209
• @lijunle made their first contribution in #1128
• @SebastjanPrachovskij made their first contribution in #1196
• @wdhorton made their first contribution in #1228
• @kodster28 made their first contribution in #1226
• @SebSchroen made their first contribution in #1234
• @rodrigobdz made their first contribution in #1243
• @krakenftw made their first contribution in #1240

Full Changelog: v0.9.0...v0.9.1

v0.9.0 - Tools release!

What's Changed

Features

• Fix OpenAI Embeddings Auth Issue by @adhishthite in #1077
• feat: add support for anthropic on vertex by @cheahjs in #958
• Extend endpointOai.ts to allow usage of extra sampling parameters by @taeminlee in #1032
• Web Search: Playwright, spatial parsing, markdown by @saghen in #1094
• Generic Multimodal Support by @saghen in #1021
• Generic Multimodal Support Fixed by @saghen in #1147
• add assistantId in the conversation API by @alak in #1154
• add missing assistantId param by @alak in #1156
• Function calling by @nsarrazin in #996
• Add error message for tools by @saghen in #1163
• Disable text streaming if user prefers reduced animation by @neven4 in #1131
• Add metrics for models, tools, websearch by @nsarrazin in #1186
• Bypass spaces tools rate limit by @mishig25 in #1167
• Log parsing failures, drop from UI by @saghen in #1189
• Reduce message update size returned by websearch by @nsarrazin in #1179
• Simplify tool error handling by @saghen in #1168
• Misc tools release by @gary149 in #1192
• Add a loading bar for tools by @nsarrazin in #1188

Bugfixes

• Fix context of logger by @jorado in #1112
• Remove trim on user input by @nsarrazin in #1122
• [fix] Assistant websearch text/markdown source by @mishig25 in #1129
• Clear playwright singleton on close by @saghen in #1170
• Always close playwright page by @saghen in #1171
• Fix message update migration not applying by @saghen in #1164
• Ony call tools if model.tools is true by @nsarrazin in #1172
• fix streaming not updating on front-end by @nsarrazin in #1173
• Fix reduced motion mode causing 500 on ssr by @nsarrazin in #1177
• fix: parse ISS if returned in OIDC flow by @muscionig in #1162
• Fix Playwright leak and use multiple contexts by @saghen in #1187
• Generic tool error msg "Error occurred" by @mishig25 in #1193
• Fix display websearch when using tools by @nsarrazin in #1197
• Fix issue with system preprompt and tools by @nsarrazin in #1198

New Contributors

• @adhishthite made their first contribution in #1077
• @jorado made their first contribution in #1112
• @cheahjs made their first contribution in #958
• @taeminlee made their first contribution in #1032
• @xianbaoqian made their first contribution in #1150
• @neven4 made their first contribution in #1131
• @wilfriedroset made their first contribution in #1144
• @muscionig made their first contribution in #1162

Full Changelog: v0.8.4...v0.9.0

v0.8.4

What's Changed

Features

• Add ALLOW_INSECURE_COOKIES feature flag by @nsarrazin in #1076
• Use pino for logs by @nsarrazin in #1086
• Add the simplest healthcheck route by @nsarrazin in #1089
• Move vars to dynamic, add metrics by @nsarrazin in #1085
• [VertexAI] Add support for tools parameter by @ArthurGoupil in #1065

Bugfixes

• 🎨 Add color for copy icon by @damianpumar in #1070
• set sameSite to lax when allowing insecure cookies by @nsarrazin in #1078

Other changes

• Sort by Trending to default by @KingNishHF in #1082
• retry text area height by @gary149 in #1091
• Kubernetes infra by @rtrompier in #1088
• fix(chart): update service metrics port name by @rtrompier in #1101
• fix(github): docker deploy version by @rtrompier in #1102
• fix(github): docker deploy version by @rtrompier in #1103

New Contributors

• @damianpumar made their first contribution in #1070
• @gugarosa made their first contribution in #1081
• @KingNishHF made their first contribution in #1082
• @rtrompier made their first contribution in #1088
• @ArthurGoupil made their first contribution in #1065

Full Changelog: v0.8.3...v0.8.4

v0.8.3

What's Changed

Features

• add an endpoint to api to get an assistant by id by @alak in #1020
• Move featured assistant check behind REQUIRE_FEATURED_ASSISTANTS by @nsarrazin in #1043
• Support Gemini 1.5 Pro from Vertex AI by @flexchar in #1041

Bugfixes

• Allow websearch if assistant has dynamic prompts by @nsarrazin in #1017
• Add assistant instructions to first system message by @nsarrazin in #1023
• fix: See all your assistants regardless of usercount by @nsarrazin in #1053
• Only require featured assistants for other users' assistants by @nsarrazin in #1054
• Final fix to assistants display logic by @nsarrazin in #1056
• add createdAt and udpatedAt to new messages by @nsarrazin in #1062
• add default value for description and examples in the API route for models by @alak in #1063
• return only valid models in the API by @alak in #1064

Other changes

• Add logs to tokenizer fetch by @nsarrazin in #1030
• return empty if error on hfapi endpoint by @nsarrazin in #1038
• Use user in docker image for spaces by @nsarrazin in #1045
• Docker chown change by @nsarrazin in #1046
• Always dispose of pipeline for embeddings after use by @nsarrazin in #1048
• Bump version to 0.8.3 by @nsarrazin in #1068

Full Changelog: v0.8.2...v0.8.3