Skip to content

feat: phase 1 provider axis — local-openai, per-entry records, ADR-0028 (F-28/F-29/F-30) - #143

Merged
pacphi merged 3 commits into
developfrom
feat/phase-1-provider-axis
Aug 15, 2026
Merged

feat: phase 1 provider axis — local-openai, per-entry records, ADR-0028 (F-28/F-29/F-30)#143
pacphi merged 3 commits into
developfrom
feat/phase-1-provider-axis

Conversation

@pacphi

@pacphi pacphi commented Aug 15, 2026

Copy link
Copy Markdown
Owner

Phase 1 of the consistency roadmap, built and reviewed in the same swarm discipline as #142: per-entry provider records with a deep-equality pin (F-28), the generic local-openai provider row per ADR-0028 with structural AQE/claude exclusions, the registry-driven ak status info row for local non-AQE bindings (F-29), and ADR-0028 accepted in-tree with the api_mode correction (F-30), crediting @adrianco's PR #131 proposal. Full gate green at build time (1,538 tests).

First increment into develop for the Phase 2/3 program.

🤖 Generated with Claude Code

pacphi added 3 commits August 14, 2026 20:30
…r row

Phase 1 provider axis (ADR-0028, F-28): providerEntries is six explicit
records — capabilities live on each entry instead of being derived from
identity comparisons, matching hostEntries; the five pre-existing providers
are pinned deep-equal to the old construction. local-openai names any
OpenAI-compatible server the user runs: billing local, no credentials, the
openai-compatible transport only, projections ruflo/codex/opencode (no aqe —
AQE's provider set is upstream's; no claude — that projection expects an
anthropic-compatible surface), no discovery claims, no builtin bindings.
Remote-endpoint policy pinned: local is a billing claim, not topology —
https off-box is legal, plain http stays loopback-only.
Phase 1 provider axis (F-29): when kit.json declares a binding whose provider
is local and not AQE-projected, status prints one info row naming provider,
host, and endpoint with the not-an-AQE-provider-type fact. Registry-driven
(billing + projections), so ollama never triggers it and a future provider of
the same shape gets the same treatment; no bindings means no new output.
…openai recipe

Proposed by adrianco in PR #131; accepted with the api_mode citation
annotated as invalid per Hermes v0.20.0 source and the ollama/local-openai
AQE-projection asymmetry stated as an intentional decision. PROVIDERS.md adds
a brief current-state section on declaring a local-openai binding.
@pacphi
pacphi merged commit 941071e into develop Aug 15, 2026
14 checks passed
@pacphi
pacphi deleted the feat/phase-1-provider-axis branch August 15, 2026 03:35
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant