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

tune(reusable): claude-code=3 models × 5 lenses (claude was the bottleneck) (#11)
Build & push image / build-and-push (push) Successful in 8s
Details

Browse Source
This commit was merged in pull request #11.
This commit is contained in:
steve
2026-06-28 04:02:17 +00:00
parent b02b11d691
commit 0d80ae73d8
2 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.gitea/workflows/review-reusable.yml
+6 -6
View File
@@ -13,7 +13,7 @@
# 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 (claude models serial, 5 lenses each). A consumer
# Claude Code engine, 5-lens suite (3 claude models concurrent, 5 lenses each). 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
@@ -35,21 +35,21 @@ on:
# 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
# 5-lens suite. Claude models run ONE at a time, but each runs all 5 lenses at
# once. It needs OLLAMA_CLOUD_API_KEY and CLAUDE_CODE_OAUTH_TOKEN; a consumer
# 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
# 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.
#
# Peak claude concurrency = provider_concurrency × provider_lens_concurrency
# (1 model × 5 lenses = up to 5 concurrent `claude -p` per pass) — friendly to
# a single subscription. Raise claude-code in either knob for more parallelism.
# (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)
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=1" } # GADFLY_PROVIDER_CONCURRENCY (claude models one at a time)
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)
timeout_secs: { type: string, default: "600" } # GADFLY_TIMEOUT_SECS (per lens)
max_steps: { type: string, default: "14" } # GADFLY_MAX_STEPS