v1.3.0

What's Changed

• fix(ci): use --no-project in SDK Makefile to avoid circular dependency during release by @leseb in #6273
• feat(inference): add Meta AI remote inference provider by @raghotham in #6275
• feat(inference, meta): inject network/TLS config into Meta provider HTTP clients by @mattf in #6277
• refactor(inference, messages): extract shared SSE passthrough stream helper for Anthropic-compatible providers by @mattf in #6269
• fix(containers): pass --insecure to entrypoint to restore starter image boot by @derekhiggins in #6288
• chore: remove unused prompt_for_config by @mattf in #6286
• fix(inference): strip duplicate /v1 prefix in vLLM Anthropic message URLs by @nathan-weinberg in #6294
• feat(inference, messages): add anthropic_count_tokens to OpenAIMixin via translation by @mattf in #6268
• fix(ci): generate ogx-client in-repo instead of cloning external repo by @cdoern in #6297
• chore: fix type annotations in core by @mattf in #6296
• fix(ci): publish ogx-client-typescript now that its release branches exist by @cdoern in #6301
• docs: add OpenAI-compatible gateway example with DaoXE by @seven7763 in #6298
• docs(blog): add multi-tenant capabilities blog post by @leseb in #6129
• feat(vector-io): Add the Neo4j vector provider by @franciscojavierarceo in #6274
• fix(vector_io): prevent duplicate libomp crash when importing faiss on macOS by @leseb in #6304
• fix(server): warn at startup when authentication is not configured by @nathan-weinberg in #6307
• chore: clean up inference provider type annotations and remove exclusions by @mattf in #6313
• fix(inference): remove duplicate per-provider model id resolution by @mattf in #6324
• fix(inference): return requested model id in streamed completion chunks by @sohumt123 in #6320
• fix(ui): improve vector store and citation workflows by @franciscojavierarceo in #6325
• chore: bump fallback_version to 1.2.1.dev0 by @cdoern in #6276
• chore(github-deps): bump actions/stale from 10.3.0 to 10.4.0 by @dependabot[bot] in #6281
• chore(python-deps): bump sentence-transformers from 5.5.1 to 5.6.0 by @dependabot[bot] in #6282
• refactor: run starter as non-root by @rhdedgar in #6319
• chore(api-deps): bump opentelemetry-exporter-otlp-proto-http from 1.43.0 to 1.44.0 in /src/ogx_api by @dependabot[bot] in #6322
• fix: bump pyasn1 for CVE-2026-59885 by @cdoern in #6330
• chore(python-deps): bump mcp from 1.27.1 to 1.28.1 by @dependabot[bot] in #6310
• chore(python-deps): bump torch from 2.12.0 to 2.13.0 by @dependabot[bot] in #6317
• feat(inference): add Mistral remote inference provider by @NishchayMahor in #6239
• fix(inference, anthropic): default json_schema.strict to true by @derekhiggins in #6024
• fix(responses): only dedup user messages when function_call_outputs are present by @derekhiggins in #6022
• fix(responses): populate file_citation annotations when models don't cite inline by @elinacse in #6292
• feat(inference): add DeepSeek remote inference provider by @NishchayMahor in #6240
• fix(responses): delimit untrusted web_search/file_search tool output before feeding it back to the model by @mittalpk in #6337
• fix(inference): add _enforce_credentials=False to passthrough AsyncOpenAI client by @NickGagan in #6344
• feat(inference): expose httpx connection pool limits via network config by @elinacse in #6306
• feat(bedrock): auto-discover models via ListFoundationModels and mantle API by @Artemon-line in #6315
• docs: fix Gemini provider auth docs to match mutually-exclusive behavior by @Aawegg in #6341
• test(inference): update the Cerebras model ID by @ryanl-cerebras in #6366
• feat(cli): rename 'ogx letsgo' to 'ogx go' with backward-compatible alias by @mattf in #5815
• refactor: clean up reasoning implementation by @robinnarsinghranabhat in #5429
• chore: remove remote::passthrough inference provider by @mattf in #6368
• fix(inference, anthropic): emit tool messages before user text in translation by @LuShadowX in #6367
• fix: remove sklearn dep by @mattf in #6359
• feat(vector_io): add classifier reranker type for post-retrieval chunk filtering by @varshaprasad96 in #5890
• feat: durable out-of-process job scheduling for file_processors by @cdoern in #6160
• chore: updated discord invite link by @dominikkawka in #6374
• fix: bump aiohttp for CVE-2026-69244 by @cdoern in #6375
• fix: make AsyncOgxClient functional by inheriting from sync ApiClient by @aegeiger in #6372

New Contributors

• @seven7763 made their first contribution in #6298
• @sohumt123 made their first contribution in #6320
• @NishchayMahor made their first contribution in #6239
• @mittalpk made their first contribution in #6337
• @Aawegg made their first contribution in #6341
• @ryanl-cerebras made their first contribution in #6366
• @LuShadowX made their first contribution in #6367
• @dominikkawka made their first contribution in #6374

Full Changelog: v1.2.2...v1.3.0