Skip to content

docs(readme): rebrand around the locus stack — drop "agent loop" framing#246

Merged
fede-kamel merged 1 commit into
mainfrom
docs/readme-rebrand-locus-stack
May 20, 2026
Merged

docs(readme): rebrand around the locus stack — drop "agent loop" framing#246
fede-kamel merged 1 commit into
mainfrom
docs/readme-rebrand-locus-stack

Conversation

@fede-kamel
Copy link
Copy Markdown
Contributor

Summary

  • New top-of-fold diagram (docs/img/locus-stack.svg) showing the five layers: PRISM cognitive router → 8 orchestration shapes → agent loop → foundations → Oracle Database 26ai. Same Oracle FY26 palette and card-shadow style as agent-loop.svg; Oracle wordmark top-left + on the 26ai banner.
  • Section heading "The agent loop" → "Inside locus — the stack, not just the loop", with bullets walking each layer. The agent loop is repositioned as the inner engine of a broader stack, not the whole story.
  • Both PRISM blurbs (the standalone section and the new stack bullet) now lead with the LLM classifier filling a typed GoalFrame (intent · domain · complexity · risk) instead of leaning on "deterministic". Protocol selection is rule-based by default, but the opt-in LLMProtocolPicker (src/locus/router/picker.py) means strict "deterministic" framing was stale.
  • Removed the "zero LangChain / LangGraph dependency" boast from the four places it lived (header em-tag, new stack bullet, "Backed by 26ai" paragraph, primitives footer). Descriptive interop notes (LangGraph-shape checkpoint saver, langgraph-oracledb parity aliases) intentionally kept — they're API-shape callouts, not bragging.
  • Existing docs/img/agent-loop.svg left untouched: it still backs the focused per-loop deep-dive at docs/concepts/agent-loop.md.

Test plan

  • pre-commit hooks pass (markdownlint, commitizen, codespell, secret-detect)
  • SVG validated as well-formed XML and visually verified at full width
  • README renders cleanly via GitHub's /markdown API + github-markdown-css
  • All four "zero LangChain / LangGraph" mentions removed from README (git grep -i "zero.*lang" returns nothing)

@oracle-contributor-agreement oracle-contributor-agreement Bot added the OCA Verified All contributors have signed the Oracle Contributor Agreement. label May 20, 2026
@fede-kamel fede-kamel force-pushed the docs/readme-rebrand-locus-stack branch from d8c0ef9 to e60fa19 Compare May 20, 2026 16:04
- New top-of-fold diagram (docs/img/locus-stack.svg) showing the five
  layers: PRISM cognitive router → 8 orchestration shapes → agent loop
  → foundations → Oracle Database 26ai. Same Oracle FY26 palette and
  card-shadow style as agent-loop.svg; Oracle wordmark top-left + on
  the 26ai banner.
- Section heading "The agent loop" → "Inside locus — the stack, not
  just the loop", with bullets walking each layer.
- Both PRISM blurbs now lead with the LLM classifier filling a typed
  GoalFrame (intent · domain · complexity · risk), instead of leaning
  on "deterministic" — protocol selection is rule-based by default but
  LLM tie-break is opt-in (picker.py), so "deterministic" was stale.
- Removed the "zero LangChain / LangGraph dependency" boast from the
  four places it lived. Descriptive interop notes (LangGraph-shape
  checkpoint saver, langgraph-oracledb parity aliases) kept.

Signed-off-by: Federico Kamelhar <federico.kamelhar@oracle.com>
@fede-kamel fede-kamel force-pushed the docs/readme-rebrand-locus-stack branch from e60fa19 to 7d0bf51 Compare May 20, 2026 17:31
@fede-kamel fede-kamel merged commit 0d0e953 into main May 20, 2026
10 checks passed
@fede-kamel fede-kamel deleted the docs/readme-rebrand-locus-stack branch May 20, 2026 17:36
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

OCA Verified All contributors have signed the Oracle Contributor Agreement.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant