docs(readme): rebrand around the locus stack — drop "agent loop" framing#246
Merged
Conversation
d8c0ef9 to
e60fa19
Compare
- 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>
e60fa19 to
7d0bf51
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
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 asagent-loop.svg; Oracle wordmark top-left + on the 26ai banner.GoalFrame(intent · domain · complexity · risk) instead of leaning on "deterministic". Protocol selection is rule-based by default, but the opt-inLLMProtocolPicker(src/locus/router/picker.py) means strict "deterministic" framing was stale.docs/img/agent-loop.svgleft untouched: it still backs the focused per-loop deep-dive atdocs/concepts/agent-loop.md.Test plan
pre-commithooks pass (markdownlint, commitizen, codespell, secret-detect)/markdownAPI +github-markdown-cssgit grep -i "zero.*lang"returns nothing)