diff --git a/benchmarks/harbor-buzz-orchestra/manifests/tb-meli-solo-cloudflare.yaml b/benchmarks/harbor-buzz-orchestra/manifests/tb-meli-solo-cloudflare.yaml new file mode 100644 index 000000000..db53d8dbd --- /dev/null +++ b/benchmarks/harbor-buzz-orchestra/manifests/tb-meli-solo-cloudflare.yaml @@ -0,0 +1,39 @@ +# Meli solo cell, take 2: same Tyler-picked persona (buzz-benchmarking thread +# 74a65a09) on deepseek/deepseek-v4-flash-0731 via OpenRouter, now pinned to +# the cloudflare/fp8 upstream (Tyler, event 857619b8) instead of gmicloud/fp8. +# +# Identical to tb-meli-solo.yaml except the pinned provider and its listed +# rates. Runs on the post-merge harness (PR #5145 head), which carries the +# #4896 vision-input recovery and the #5136 explicit-mention task post that +# the first solo run predated. The pin itself lives in +# testbed/endpoints/openrouter-live.json (OPENROUTER_PROVIDER_ORDER). +schema_version: "1" +condition: tb-meli-solo-cloudflare +roster: + - id: meli + kind: orchestrator + role: solo + count: 1 + endpoint: deepseek/deepseek-v4-flash-0731 + model_revision: deepseek/deepseek-v4-flash-20260731 + prompt: + path: personas/bench/meli-solo.md + sha256: de6330190fe22cb4b58cd5c2ca1cb7fc080e9b7f97b298c8960e08854e7a7a8b + generation: + thinking_effort: high +prices: + deepseek/deepseek-v4-flash-0731: + # cloudflare/fp8 listed rates (OpenRouter endpoints API, 2026-08-07): + # prompt $0.14/M, completion $0.28/M. + input_per_million_usd: 0.14 + cached_input_per_million_usd: 0.14 + output_per_million_usd: 0.28 + cache_read_rate: 0.0 +trial_budget: + # Identical to every other TB solo cell. + timeout_seconds: 36000 + +environment: + # Identical in every condition -- see tb-solo-luna.yaml for the reasoning. + override_cpus: 4 + override_memory_mb: 8192 diff --git a/benchmarks/harbor-buzz-orchestra/testbed/endpoints/openrouter-cloudflare.json b/benchmarks/harbor-buzz-orchestra/testbed/endpoints/openrouter-cloudflare.json new file mode 100644 index 000000000..57d360671 --- /dev/null +++ b/benchmarks/harbor-buzz-orchestra/testbed/endpoints/openrouter-cloudflare.json @@ -0,0 +1,9 @@ +{ + "deepseek/deepseek-v4-flash-0731": { + "provider": "openrouter", + "api_key_env": "OPENROUTER_API_KEY", + "env": { + "OPENROUTER_PROVIDER_ORDER": "cloudflare/fp8" + } + } +}