Sync main with internal feature work (16 MRs)#5
Merged
Conversation
Pulls orahub/main's tree onto github/main as a single sync commit. Two histories diverged at the public release; this lands all the work merged on orahub today on the public mirror so the docs site deploys to GitHub Pages. Feature-level summary (each landed as its own MR on orahub): - feat(structured-output): output_schema= on Agent, parsed/parsed_as on AgentResult, response_format on OpenAI/OCI, tool-use translation on Anthropic, validate-and-repair retries, StructuredStream partial parsing - feat(termination): wire AgentConfig.termination into the agent loop - feat(idempotent): apply @tool(idempotent=True) dedup in Agent.run() - feat(playbooks): PlaybookEnforcerHook + Agent(playbook=...) auto-install - feat(agent): wire auxiliary_model into max-iterations summary + grounding eval - feat(graph): real intermediate-event streaming in StateGraph.stream() via async-queue sink + emit_custom + StreamMode.CUSTOM - feat(server): GET / DELETE /threads/{tid} with principal scoping - fix(imports): from locus import Reflexion + hook re-exports - test(integration): live coverage across OCI v1, OCI native SDK, OpenAI direct, Anthropic direct - test(tutorials): every tutorial_NN_*.py runs against a real model - docs: full Material-themed website with multi-agent patterns, provider pages, observability, etc. - docs: walk back fabricated claims Tone tweak on the homepage: replace "agent stack you'd actually let near a credit card" with production-grade language Oracle customers will recognise.
oracle-contributor-agreement
Bot
added
the
OCA Verified
3 tasks
fede-kamel
added a commit
that referenced
this pull request
May 4, 2026
Two threads in one commit (small enough to cohabitate):
1) Subtitle: drop "Orchestrator" everywhere — locus is the
"Multi-Agent Reasoning SDK". Updated docs/img/logo.svg,
docs/stylesheets/locus.css (CSS-injected docs header subtitle),
sandbox/web/index.html brand-tag, and the playwright assertion
in sandbox/e2e/tests/sandbox.spec.ts so the e2e test still passes.
2) Six things you can ship — swap two weak sections for two
genuinely-shipped, peer-differentiated tutorials:
- "Claims grounded …" (Reflexion+Grounding) → "Map-reduce a
code-review crew" (tutorial 42). Send fan-out is shorter than
LangGraph's routing function + targets dict; this is locus's
most ergonomically-distinct primitive.
- "Agent meshes across teams …" (A2A, niche audience) → "An
incident runbook in one graph.execute()" (tutorial 46) — Send
scatter to 3 investigators, severity gate, interrupt() for
human approval, typed Postmortem.
- "Day-one production deployment" (Agent Server) → "Voice in.
Voice out." (tutorial 50) — multimodal gpt-audio in one
chat-completions round-trip; net-new vs every peer SDK.
Kept #2 idempotent tools, #3 handoff (now linking tutorial 45 too
for the meatier HITL example), and #5 termination algebra
verbatim — those three are the genuine differentiators the audit
surfaced.
The reflexion=True example was honest as code (the validator now
coerces correctly post-d18d52f) but advertised result.grounding_score
that the SDK doesn't surface that cleanly today; pulling it out of
the marquee until the surface stabilises.
Signed-off-by: Federico Kamelhar <federico.kamelhar@oracle.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Pulls the internal repo's main tree onto github/main as a single sync commit. Two histories diverged at the public release; this lands all the work that's been merged internally so the docs site deploys to GitHub Pages.
What's included
output_schema=on Agent,parsed/parsed_ason AgentResult, nativeresponse_formaton OpenAI / OCI, tool-use translation on Anthropic, validate-and-repair retries,StructuredStreampartial parsing.AgentConfig.terminationinto the agent loop (|/&algebra).@tool(idempotent=True)dedup inAgent.run();ToolExecution.idempotent_cache_hit.PlaybookEnforcerHook+Agent(playbook=...)auto-install.auxiliary_modelinto max-iterations summary + grounding eval.StateGraph.stream(); newemit_customAPI +StreamMode.CUSTOM.GET/DELETE /threads/{tid}with bearer-principal scoping.from locus import Reflexion+ModelRetryHook/SteeringHookre-exports.Verification
Tone tweak on the homepage: replaced "agent stack you'd actually let near a credit card" with production-grade language Oracle customers will recognise.