.gitea/workflows/review-reusable.yml

@@ -13,7 +13,8 @@
 #       with: { allowed_users: "..." }   # config inputs are optional (see below)
 #
 # Inputs ship the DEFAULT swarm (see the inputs block): 3 cloud models + the
-# Claude Code engine, 5-lens suite (3 claude models concurrent, 5 lenses each). A consumer
+# Claude Code engine + a local 4090 Ti (qwen3.6-27b via llama-swap), 5-lens suite
+# (3 claude models concurrent / 5 lenses each; the 4090 Ti runs 1 model × 1 lens). A consumer
 # inherits it by omitting `with:` entirely, or overrides any field (e.g.
 # `models:` for a cloud-only / different-provider setup; "" falls back to the
 # image's built-in default). Secrets are DECLARED below (workflow_call.secrets) so a
@@ -35,9 +36,11 @@ on:
   workflow_call:
     # Inputs ship the DEFAULT Gadfly swarm so a consumer can just call this
     # workflow (no `with:` block) and inherit it. The default is opinionated —
-    # 3 strong cloud models + the Claude Code engine (sonnet/opus/opus:max), the
+    # 3 strong cloud models + the Claude Code engine (sonnet/opus/opus:max) + a
+    # local 4090 Ti (qwen3.6-27b via llama-swap at GADFLY_ENDPOINT_RAGNAROS), the
     # 5-lens suite, with all 3 claude models concurrent and each running its 5
-    # lenses at once. It needs OLLAMA_CLOUD_API_KEY and CLAUDE_CODE_OAUTH_TOKEN; a consumer
+    # lenses at once (the 4090 Ti runs 1 model × 1 lens — a single local GPU). It
+    # needs OLLAMA_CLOUD_API_KEY and CLAUDE_CODE_OAUTH_TOKEN; a consumer
     # with only one (or a different provider) overrides `models:` (and forwards
     # just the secrets it uses). Set any input to "" to fall back to the
     # image/entrypoint built-in default.
@@ -46,12 +49,12 @@ on:
     # (3 models × 5 lenses = up to 15 concurrent `claude -p` per pass). If you hit
     # subscription rate limits or runner load, dial claude-code down in either knob.
     inputs:
-      models:                    { type: string, default: "minimax-m3:cloud,glm-5.2:cloud,deepseek-v4-pro:cloud,claude-code/sonnet,claude-code/opus,claude-code/opus:max" }   # GADFLY_MODELS (csv)
+      models:                    { type: string, default: "minimax-m3:cloud,glm-5.2:cloud,deepseek-v4-pro:cloud,claude-code/sonnet,claude-code/opus,claude-code/opus:max,ragnaros/qwen3.6-27b" }   # GADFLY_MODELS (csv); ragnaros/* = the 4090 Ti via llama-swap (see GADFLY_ENDPOINT_RAGNAROS)
       specialists:               { type: string, default: "security,correctness,maintainability,performance,error-handling" }   # GADFLY_SPECIALISTS (5-lens default suite)
       provider:                  { type: string, default: "" }   # GADFLY_PROVIDER
       base_url:                  { type: string, default: "" }   # GADFLY_BASE_URL
-      provider_concurrency:      { type: string, default: "ollama-cloud=3,claude-code=3" }   # GADFLY_PROVIDER_CONCURRENCY (all 3 claude models at once)
-      provider_lens_concurrency: { type: string, default: "ollama-cloud=3,claude-code=5" }   # GADFLY_PROVIDER_LENS_CONCURRENCY (each claude runs all 5 lenses at once)
+      provider_concurrency:      { type: string, default: "ollama-cloud=3,claude-code=3,ragnaros=1" }   # GADFLY_PROVIDER_CONCURRENCY (claude all 3 at once; ragnaros 4090 Ti one model at a time)
+      provider_lens_concurrency: { type: string, default: "ollama-cloud=3,claude-code=5,ragnaros=1" }   # GADFLY_PROVIDER_LENS_CONCURRENCY (claude 5 lenses at once; ragnaros 1 lens at a time)
       timeout_secs:              { type: string, default: "600" }   # GADFLY_TIMEOUT_SECS (per lens)
       max_steps:                 { type: string, default: "14" }   # GADFLY_MAX_STEPS
       worker_model:              { type: string, default: "" }   # GADFLY_WORKER_MODEL
@@ -119,6 +122,12 @@ jobs:
           # reusable workflow can't enumerate arbitrary names.
           GADFLY_ENDPOINT_M1: ${{ secrets.GADFLY_ENDPOINT_M1 }}
           GADFLY_ENDPOINT_M5: ${{ secrets.GADFLY_ENDPOINT_M5 }}
+          # ragnaros = the 4090 Ti, reached over the LAN through its llama-swap
+          # proxy (lazy-loads models on demand). Plain https URL, no credential —
+          # set here so the default `ragnaros/qwen3.6-27b` model resolves for all
+          # consumers. Registers provider "ragnaros". NB: use the un-hyphenated
+          # `llamaswap` provider spelling — the pinned image accepts that form.
+          GADFLY_ENDPOINT_RAGNAROS: "llamaswap|https://llama-swap.ragnaros.dudenhoeffer.casa"
           # --- findings telemetry (optional) --------------------------------
           GADFLY_FINDINGS_URL: ${{ secrets.GADFLY_FINDINGS_URL }}
           GADFLY_FINDINGS_TOKEN: ${{ secrets.GADFLY_FINDINGS_TOKEN }}

CLAUDE.md

@@ -47,8 +47,9 @@ entrypoint.sh          container brains: trigger gating, PR clone, model loop (t
 Dockerfile             multi-stage; private-module creds via BuildKit secrets never reach the final image
 .gitea/workflows/build-image.yml   push main → :latest; tag v* → :<tag>+:latest; PR → build-only
 .gitea/workflows/review-reusable.yml  reusable (workflow_call) review job; ships the DEFAULT swarm as
-                       input defaults (3 cloud + Claude Code sonnet/opus/opus:max, 5-lens suite;
-                       3 claude models concurrent, 5 lenses each) so consumers inherit it by omitting `with:`. Consumers subscribe
+                       input defaults (3 cloud + Claude Code sonnet/opus/opus:max + a local 4090 Ti
+                       via llama-swap, 5-lens suite; 3 claude models concurrent / 5 lenses each, the
+                       4090 Ti 1 model × 1 lens) so consumers inherit it by omitting `with:`. Consumers subscribe
                        with an ~8-line caller forwarding only the secrets the reviewer needs (Phase 4);
                        gadfly's own adversarial-review.yml is a thin caller of it (dogfoods the path).
 examples/              copy-paste consumer stub workflows for different providers

README.md

@@ -40,7 +40,7 @@ it. Drop one file in your repo and set a couple of secrets/vars:
    your repo. Two flavors: the slim [`reusable.yml`](examples/reusable.yml) — a tiny caller of
    Gadfly's **reusable workflow** (`uses: steve/gadfly/.gitea/workflows/review-reusable.yml@…`,
    forwarding only the secrets the reviewer needs), which ships a **default swarm** (3 cloud models +
-   the Claude Code engine, 5-lens suite) you inherit by omitting `with:` or override per-input — or the full self-contained
+   the Claude Code engine + a local 4090 Ti via llama-swap, 5-lens suite) you inherit by omitting `with:` or override per-input — or the full self-contained
    [`adversarial-review.yml`](examples/adversarial-review.yml) (Ollama Cloud default, with inline
    notes for every provider / local Ollama / OpenAI-compatible / endpoint aliases). See the
    [examples index](examples/README.md).