bench: record the tb2-quick proxy-lane baseline

bench: record the tb2-quick proxy-lane baseline

First proxy-lane row in bench-results/. Suite tb2-quick on lane proxy with
model gpt-5.6-luna: 2 of 2 trials accepted, success rate 1.000 over 2 graded
trials, 0 ungraded, wall clock 221.9s. Gate tb2-quick PASSED on all four
criteria, report exit 0.

Cost is null (cost_unknown): gpt-5.6-luna is deliberately unpriced in the
forge model catalog, so 0 of 2 trials could be priced and a figure here
would launder an unmeasured lane into a free one.

Harbor job 97f3415f-3b17-49f9-adc0-8828e223280a, Gym run
3f053327-6618-4e6e-bf52-77f55c0b4427 (graded), CLI 0.4.0 packed from the
working tree with pnpm.

The three existing rows are byte-identical and the deliberate qwen3:0.6b
regression row is untouched; this is a single appended line, verified with
effectiveness:compare before and after rebase.

Refs #118

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01K7q2vA5LJroLTR6ZFbRq6j

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01K7q2vA5LJroLTR6ZFbRq6j

Deploy story

What this commit did to the running system — joined from the forge receipt chain, the part a commit page elsewhere cannot show.

Not deployed through the forge lane

No push, promotion, build, or deploy receipt references this commit (receipts are scanned over a bounded recent window). Changes shipped by full node replacement carry their proof in the release gate receipt instead.

Changed files

modified bench-results/tb2-quick.jsonl

Diff

1 file changed, +1 -0

1	1		{"schema":"openagents.bench_result.v2","recordedAt":"2026-08-25T22:57:20.862Z","suite":"tb2-quick","lane":"local","runDigest":"effectiveness:64ec65020e7d342258678d6f1da6c352aecdf83db0a58647beb31187d1e0cf85","suiteKey":"suite:9595eb324cb51585c773fe693cec8540a6e705881f8ea83fa8b3de00fce7fdaf","jobId":"3db2ad8e-6324-4a3b-b922-795d0698b2e6","suiteId":"tb2-quick","suiteDigest":"suite-manifest:b418d40416b197791d4f148758c9d78680783bcd05bf8c011c1d460b25ea6125","tier":"score","models":["qwen3.8:27b-mtp-q8_0"],"agentVersions":["0.4.0"],"rateCatalogVersion":"openagents.coder-rate-catalog.2026-08-25","tasks":["openssl-selfsigned-cert","regex-log"],"trialsTotal":2,"accepted":1,"rejected":1,"ungraded":0,"graded":2,"successRate":0.5,"ungradedRatio":0,"costPerAcceptedOutcomeUsd":null,"costDisposition":"cost_unknown","totalCostUsd":null,"costCoverage":"unknown","rateBasis":null,"promptTokens":null,"completionTokens":null,"cachedInputTokens":0,"toolCalls":null,"wallClockSeconds":1395.848,"gateStatus":"passed","thresholdsId":"tb2-quick","previousReceipt":null,"receipt":"receipt:94f09429a15a1b731ecaa31132962c5dee3f269e410f486a817e7b31093a556c"}
2	2		{"schema":"openagents.bench_result.v2","recordedAt":"2026-08-25T23:27:15.789Z","suite":"tb2-quick","lane":"local","runDigest":"effectiveness:64ec65020e7d342258678d6f1da6c352aecdf83db0a58647beb31187d1e0cf85","suiteKey":"suite:9595eb324cb51585c773fe693cec8540a6e705881f8ea83fa8b3de00fce7fdaf","jobId":"b0fb4134-23f2-4395-9d42-c334e2a03c3f","suiteId":"tb2-quick","suiteDigest":"suite-manifest:b418d40416b197791d4f148758c9d78680783bcd05bf8c011c1d460b25ea6125","tier":"score","models":["qwen3.8:27b-mtp-q8_0"],"agentVersions":["0.4.0"],"rateCatalogVersion":"openagents.coder-rate-catalog.2026-08-25","tasks":["openssl-selfsigned-cert","regex-log"],"trialsTotal":2,"accepted":1,"rejected":1,"ungraded":0,"graded":2,"successRate":0.5,"ungradedRatio":0,"costPerAcceptedOutcomeUsd":null,"costDisposition":"cost_unknown","totalCostUsd":null,"costCoverage":"unknown","rateBasis":null,"promptTokens":null,"completionTokens":null,"cachedInputTokens":0,"toolCalls":null,"wallClockSeconds":1589.478,"gateStatus":"passed","thresholdsId":"tb2-quick","previousReceipt":"receipt:94f09429a15a1b731ecaa31132962c5dee3f269e410f486a817e7b31093a556c","receipt":"receipt:554644f440ce789d596720026f8bbfde24aa93097f3d3f601a6b024485bf1f21"}
3	3		{"schema":"openagents.bench_result.v2","recordedAt":"2026-08-25T23:33:52.382Z","suite":"tb2-quick","lane":"local","runDigest":"effectiveness:abce8e4e80d93c387df25ae78ef722d369ae9514e0922ca7de38409c371ee92e","suiteKey":"suite:9595eb324cb51585c773fe693cec8540a6e705881f8ea83fa8b3de00fce7fdaf","jobId":"7e9371ab-7f30-4394-8d10-f153cea80e3b","suiteId":"tb2-quick","suiteDigest":"suite-manifest:b418d40416b197791d4f148758c9d78680783bcd05bf8c011c1d460b25ea6125","tier":"score","models":["qwen3:0.6b"],"agentVersions":["0.4.0"],"rateCatalogVersion":"openagents.coder-rate-catalog.2026-08-25","tasks":["openssl-selfsigned-cert","regex-log"],"trialsTotal":2,"accepted":0,"rejected":2,"ungraded":0,"graded":2,"successRate":0,"ungradedRatio":0,"costPerAcceptedOutcomeUsd":null,"costDisposition":"no_accepted_outcomes","totalCostUsd":null,"costCoverage":"unknown","rateBasis":null,"promptTokens":377891,"completionTokens":24452,"cachedInputTokens":0,"toolCalls":23,"wallClockSeconds":143.91,"gateStatus":"failed","thresholdsId":"tb2-quick","previousReceipt":"receipt:554644f440ce789d596720026f8bbfde24aa93097f3d3f601a6b024485bf1f21","receipt":"receipt:accea92e82f5dfe4c79030941d5086bd5e3808a8937acc2464a77a1c46a03cf5"}
	4	+	{"schema":"openagents.bench_result.v2","recordedAt":"2026-08-26T13:41:54.207Z","suite":"tb2-quick","lane":"proxy","runDigest":"effectiveness:4fedb44245a87ec7e9fe14f38128ffc8689f8635897f8e057c0609def257e4ae","suiteKey":"suite:9595eb324cb51585c773fe693cec8540a6e705881f8ea83fa8b3de00fce7fdaf","jobId":"97f3415f-3b17-49f9-adc0-8828e223280a","suiteId":"tb2-quick","suiteDigest":"suite-manifest:b418d40416b197791d4f148758c9d78680783bcd05bf8c011c1d460b25ea6125","tier":"score","models":["gpt-5.6-luna"],"agentVersions":["0.4.0"],"rateCatalogVersion":"openagents.coder-rate-catalog.2026-08-25","tasks":["openssl-selfsigned-cert","regex-log"],"trialsTotal":2,"accepted":2,"rejected":0,"ungraded":0,"graded":2,"successRate":1,"ungradedRatio":0,"costPerAcceptedOutcomeUsd":null,"costDisposition":"cost_unknown","totalCostUsd":null,"costCoverage":"unknown","rateBasis":null,"promptTokens":335740,"completionTokens":9913,"cachedInputTokens":0,"toolCalls":19,"wallClockSeconds":221.909,"gateStatus":"passed","thresholdsId":"tb2-quick","previousReceipt":"receipt:accea92e82f5dfe4c79030941d5086bd5e3808a8937acc2464a77a1c46a03cf5","receipt":"receipt:6c1fd3ed9b5449cc35d60e5b82d85d3ee535c64018f6f200a07a6d88ba96c739"}