steve/majordomo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(llamaswap): llama-swap provider + canonical imagegen interface #3

Merged
steve merged 3 commits from feat/llama-swap-provider into main 2026-06-27 20:14:01 +00:00
Conversation 10 Commits 3 Files Changed 14
+1037 -9
3 Commits
Author SHA1 Message Date
steveandClaude Opus 4.8 64642c43c4 fix(llamaswap): address Gadfly review findings
CI / Tidy (pull_request) Successful in 9m25s
Details
CI / Build & Test (pull_request) Successful in 10m15s
Details 
- Unload: reject model ids containing path separators (/?#) so a model name
  can't redirect the request to another endpoint; ":" (common in ids) stays
  verbatim.
- doJSON: take a model arg so image/management HTTP errors carry the target id
  (was always ""); add a base-URL guard so management methods fail clearly
  instead of building a bare-path request; cap the success-path JSON decode with
  io.LimitReader (64 MiB) and drain the body when out is nil for conn reuse.
- image: reject negative Request.N before sending.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
 2026-06-27 16:04:23 -04:00
steve 3ba2dbefae Merge remote-tracking branch 'origin/main' into feat/llama-swap-provider
CI / Build & Test (pull_request) Successful in 10m15s
Details
CI / Tidy (pull_request) Successful in 10m20s
Details
Adversarial Review (Gadfly) / review (pull_request) Successful in 18m24s
Details
2026-06-27 15:13:07 -04:00
steveandClaude Opus 4.8 96c612e707 feat(llamaswap): add llama-swap provider + canonical imagegen interface
CI / Tidy (pull_request) Successful in 9m25s
Details
CI / Build & Test (pull_request) Successful in 10m15s
Details 
Add provider/llamaswap, a tailored provider for llama-swap (the model-swapping
proxy over llama.cpp / stable-diffusion.cpp). Its chat path delegates to
provider/openai at {base}/v1 — no duplicated wire client (ADR-0007) — with
legacy max_tokens, a Bearer no-key placeholder for keyless local instances, and
a timeout-free client so cold model swaps rely on context deadlines. The
"tailored" surface is concrete management methods (ListModels / Running /
Unload) that don't belong on the canonical llm.Provider interface. The
llama-swap:// DSN scheme builds an http base URL (local-first); a no-URL
built-in errors clearly on use, mirroring foreman.

Add imagegen, a new canonical text-to-image interface separate from llm
(Request/Result/Model/Provider; Image = llm.ImagePart so generated images feed
straight back into chat). First backend is llama-swap via OpenAI
/v1/images/generations (b64_json, bytes-only). Re-exported from the root. v1 is
txt2img only.

Hermetic httptest coverage for chat delegation, management endpoints, image
decode, and scheme wiring. ADR-0015 + ADR-0016, README support matrix +
image-gen section, CLAUDE.md package map, and progress.md updated in the same
commit.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
 2026-06-27 15:01:54 -04:00