LLP 0290/0291: local inference is an out-of-tree lane; core owes a projector precedence contract - #956
Open
bgmcmullen wants to merge 1 commit into
Open
LLP 0290/0291: local inference is an out-of-tree lane; core owes a projector precedence contract#956bgmcmullen wants to merge 1 commit into
bgmcmullen wants to merge 1 commit into
Conversation
…ojector precedence contract Two docs drafted 2026-08-18, renumbered from their draft numbers 0266/0267 (both since claimed on master and by open PRs): - LLP 0290 (decision, Draft): capturing a local inference server (Ollama, LM Studio, llama.cpp, vLLM) is not bundled work; the hypaware.ai-gateway@2.0.0 capability and install path already support it out of tree. What core owes is the one thing a third-party adapter cannot secure for itself: a documented projector dispatch precedence, because today such a plugin's correctness rests on outranking an undocumented priority number inside @hypaware/codex. - LLP 0291 (plan, Draft): the three tasks that publish and pin that precedence band. The local-inference plugin itself is explicitly out of scope. Co-Authored-By: Claude Fable 5 <noreply@anthropic.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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What this is
The two local-inference LLP drafts from the 2026-08-18 working session, committed as-is on their own branch. Both are Status: Draft - this PR records them; nothing here is Accepted, so no agent work derives from it yet.
hypaware.ai-gateway@2.0.0capability names custom integrations as a consumer and the install path is complete, so the whole lane is buildable out of tree. What core owes is the one thing an out-of-tree author cannot secure for themselves: a documented projector dispatch precedence, because today such a plugin's correctness rests on outranking an undocumented priority number inside@hypaware/codex.Renumbering
The drafts were written as 0266/0267. Both numbers have since been claimed: 0266 by
cli-compatibility-rolloveron master, and open PRs claim through 0289, so the docs take 0290/0291. All internal cross-references (headers,Related:lines,@refmentions, relative links and anchors) are updated to match; no content changes otherwise.🤖 Generated with Claude Code