steveandClaude Opus 4.8
74831368ab
Concurrency was two multiplicative gates in two processes: entrypoint.sh capped MODELS-at-once per provider (GADFLY_PROVIDER_CONCURRENCY) while each model's binary separately capped its own lenses (GADFLY_LENS_CONCURRENCY). A model therefore held its whole model-slot until its LAST lens finished, stalling the next model even with idle lens capacity. Collapse to one throttle: a provider-wide lens budget shared across all of that provider's models. entrypoint now runs every model in a lane at once and seeds a single cross-process permit pool per lane (a dir of N flock files, sized by GADFLY_PROVIDER_LENS_CONCURRENCY -> GADFLY_LENS_CONCURRENCY). Each lens pass (review+recheck) acquires a permit before it runs and releases it after, so a model winding down immediately yields its freed permits to another model's queued lenses. flock auto-releases on process death, so a killed/crashed model can't leak budget. - cmd/gadfly/lenssem.go: the flock permit pool (+ lenssem_test.go). - main.go: runSpecialists holds a shared permit per lens; fanout sized to the budget so a lone model can use all of it. Falls back to the in-process limit when no pool is set (local runs, tests). - entrypoint.sh: drop provider_cap/DEFAULT_CONC; run_lane runs all models and seeds the per-lane pool. - GADFLY_PROVIDER_CONCURRENCY / GADFLY_CONCURRENCY are now ignored; the reusable workflow marks provider_concurrency deprecated and stops forwarding it. Docs (README, CLAUDE.md, examples) updated per the maintenance rule. Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
Example consumer workflows
Each file here is a complete, copy-paste stub workflow. Pick the one that matches your
setup, copy it to .gitea/workflows/adversarial-review.yml in the repo you want reviewed, and
set the secrets/vars it references. Gadfly is advisory only — it never blocks a merge.
| File | Backend | Needs |
|---|---|---|
reusable.yml |
slimmest stub — calls Gadfly's reusable workflow and inherits its default swarm (3 cloud + Claude Code, 5-lens suite), forwarding only the secrets it needs (least privilege, not secrets: inherit); the stub keeps a cloud-only models: override so it runs with just the Ollama key (drop it + add the Claude token to get the full default) |
secret OLLAMA_CLOUD_API_KEY |
adversarial-review.yml |
Ollama Cloud (default) + inline notes for every provider; full self-contained stub | secret OLLAMA_CLOUD_API_KEY |
local-ollama.yml |
a local/LAN Ollama daemon | nothing (or GADFLY_BASE_URL for a remote host) |
openai-compatible.yml |
any OpenAI-compatible endpoint (local Ollama /v1, gateway, vLLM, OpenRouter…) |
GADFLY_BASE_URL (+ a key for most gateways) |
endpoint-aliases.yml |
several named backends at once (one comment each) | repo vars GADFLY_ENDPOINT_<NAME> |
claude-code.yml |
the bundled Claude Code CLI engine (claude-code/<model>) |
secret CLAUDE_CODE_OAUTH_TOKEN (or ANTHROPIC_API_KEY) |
opencode.yml |
the bundled OpenCode CLI engine (opencode/<model>) driving an ollama-cloud model — benchmark it against the majordomo loop on the same model |
secret OLLAMA_CLOUD_API_KEY |
.gadfly.yml |
per-repo specialist config (not a workflow — goes at your repo root) | — |
Common to all:
- Triggers: new/reopened/ready non-draft PR (auto),
@gadfly reviewcomment (allowed users), or manualworkflow_dispatchwith apr_number. GITEA_TOKENis provided automatically; comments post asgitea-actions.- Tested backends are the Ollama ones; OpenAI/Anthropic/Google are wired via majordomo but untested. See the repo README for the full config reference and the honest tested/untested status.
Gitea note: repo
vars/secretsare not auto-exposed as env — anything you reference via${{ vars.X }}/${{ secrets.X }}must appear in the step'senv:block (already wired in these examples).