feat(concurrency): provider-wide lens budget, drop the model cap
Build & push image / build-and-push (pull_request) Successful in 4s
Gadfly review (reusable) / review (pull_request) Successful in 14m47s
Adversarial Review (Gadfly) / review (pull_request) Successful in 14m47s

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]>
This commit is contained in:
2026-07-18 12:22:11 -04:00
co-authored by Claude Opus 4.8
parent 0d51879450
commit 74831368ab
9 changed files with 333 additions and 95 deletions
+6 -4
View File
@@ -44,7 +44,7 @@ on:
#
# Owner-set user-scope variables (see README "Central config via variables"):
# GADFLY_DEFAULT_MODELS, GADFLY_DEFAULT_SPECIALISTS,
# GADFLY_DEFAULT_PROVIDER_CONCURRENCY, GADFLY_DEFAULT_PROVIDER_LENS_CONCURRENCY,
# GADFLY_DEFAULT_PROVIDER_LENS_CONCURRENCY (the provider-wide lens budget),
# GADFLY_ENDPOINT_NETHERSTORM (the local GPU box endpoint).
# An unset variable + no input → the image default (one model, default suite),
# so a public consumer with neither still gets a sane minimal review.
@@ -53,8 +53,8 @@ on:
specialists: { type: string, default: "" } # GADFLY_SPECIALISTS — empty falls back to user var GADFLY_DEFAULT_SPECIALISTS
provider: { type: string, default: "" } # GADFLY_PROVIDER
base_url: { type: string, default: "" } # GADFLY_BASE_URL
provider_concurrency: { type: string, default: "" } # GADFLY_PROVIDER_CONCURRENCY — empty falls back to user var GADFLY_DEFAULT_PROVIDER_CONCURRENCY
provider_lens_concurrency: { type: string, default: "" } # GADFLY_PROVIDER_LENS_CONCURRENCY — empty falls back to user var GADFLY_DEFAULT_PROVIDER_LENS_CONCURRENCY
provider_concurrency: { type: string, default: "" } # DEPRECATED / ignored — the per-provider MODEL cap was removed; the lens budget below is the single throttle. Kept so existing callers don't error.
provider_lens_concurrency: { type: string, default: "" } # GADFLY_PROVIDER_LENS_CONCURRENCY — the per-provider lens budget (shared across the provider's models); empty falls back to user var GADFLY_DEFAULT_PROVIDER_LENS_CONCURRENCY
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
@@ -151,7 +151,9 @@ jobs:
GADFLY_SPECIALISTS: ${{ inputs.specialists || vars.GADFLY_DEFAULT_SPECIALISTS }}
GADFLY_PROVIDER: ${{ inputs.provider }}
GADFLY_BASE_URL: ${{ inputs.base_url }}
GADFLY_PROVIDER_CONCURRENCY: ${{ inputs.provider_concurrency || vars.GADFLY_DEFAULT_PROVIDER_CONCURRENCY }}
# NB: GADFLY_PROVIDER_CONCURRENCY (the old model cap) is intentionally no
# longer forwarded — entrypoint.sh ignores it. The lens budget is the one
# throttle now, shared across a provider's models.
GADFLY_PROVIDER_LENS_CONCURRENCY: ${{ inputs.provider_lens_concurrency || vars.GADFLY_DEFAULT_PROVIDER_LENS_CONCURRENCY }}
GADFLY_TIMEOUT_SECS: ${{ inputs.timeout_secs }}
GADFLY_MAX_STEPS: ${{ inputs.max_steps }}