Self-hosted, Self-Improving, Federated Everything App — dev management, agent orchestration, persistent mind, digital twin, second brain, and creative pipeline from a single dashboard over Tailscale to port the user into the OS
JavaScript ai-agentsdashboarddeveloper-toolsdigital-twinquantified-selfsecond-brainself-hostedtailscale
test: preserve calibration guards and verify model judgements after rebase (#11403)
[._.]/ Adam Eivy6bf3c6dd5662
diff --git a/server/services/codeReview.js b/server/services/codeReview.jsindex b026ca5286..cac6ea1e73 100644--- a/server/services/codeReview.js+++ b/server/services/codeReview.js@@ -1222,16 +1222,6 @@ export async function runLocalCodeReview({ backend, model, diff, effort = null,diagnostics: reviewFailureDiagnostics({ reason, finishReason: result.finishReason, responseLengthChars: result.responseLengthChars }),error: `${backend} returned no usable code-review verdict: incomplete or contradictory review output.`,}- // Preserve the fail-only production floor from the contextual-catch- // calibration. Focused model checks above cannot waive proven contradictions.- if (backfillAudit && verdict.verdict !== 'rethink') {- const findings = backfillAccountingFindings(trimmedObjective, trimmedDiff)- if (findings.length) Object.assign(verdict, normalizeGoalFidelityVerdict({- ...verdict, verdict: 'fix-first',- missing: [...new Set([...findings, ...verdict.missing])],- }))- }-return {ok: true,backend,diff --git a/server/services/codeReview.test.js b/server/services/codeReview.test.jsindex 3d015388f2..cc103152a1 100644--- a/server/services/codeReview.test.js+++ b/server/services/codeReview.test.js@@ -67,6 +67,7 @@ import {} from './codeReview.js'import { MODEL_SELECTABLE_REVIEWERS, EFFORT_SELECTABLE_REVIEWERS, codeReviewSettingsSchema } from '../lib/cosValidation.js'import { taskObjective } from '../lib/goalFidelity.js'+import { extractJson } from '../lib/jsonExtract.js'import { updateSettingsWith } from './settings.js'// Preserve the real transport for the explicitly requested local-model evaluation.@@ -1501,8 +1502,10 @@ describe('codeReview helpers', () => {}return completion(shipVerdict)})- expect(await runLocalGoalFidelityReview({ backend: 'ollama', model: 'example-model', objective: backfillCase.objective, diff }))- .toMatchObject({ ok: true, ...shipVerdict })+ const result = await runLocalGoalFidelityReview({ backend: 'ollama', model: 'example-model', objective: backfillCase.objective, diff })+ const contradicted = ['failed writes counted as successes', 'failure summary remains info'].includes(name)+ expect(result).toMatchObject({ ok: true, verdict: contradicted ? 'fix-first' : 'ship', evidence: shipVerdict.evidence })+ if (contradicted) expect(result.missing.join(' ')).toMatch(/backfillFromHistory.*(?:count|summary)/)expect(productionReviewed).toBe(true) // Even when primary ship ignores a mutant.})@@ -1524,8 +1527,9 @@ describe('codeReview helpers', () => {}return completion(shipVerdict)})- expect(await runLocalGoalFidelityReview({ backend: 'ollama', model: 'example-model', objective: backfillCase.objective, diff }))- .toMatchObject({ verdict: 'fix-first', missing: [missing], evidence: shipVerdict.evidence })+ const result = await runLocalGoalFidelityReview({ backend: 'ollama', model: 'example-model', objective: backfillCase.objective, diff })+ expect(result).toMatchObject({ verdict: 'fix-first', evidence: shipVerdict.evidence })+ expect(result.missing).toContain(missing)expect(global.fetch).toHaveBeenCalledTimes(4)})@@ -1588,11 +1592,24 @@ describe('codeReview helpers', () => {})// Opt-in actual judgements, never an ordinary CI provider call.- it.runIf(Boolean(process.env.GOAL_FIDELITY_EVAL_MODEL)).each(backfillCases)('judges backfill accounting and warning outcomes with a real local model: %s', async (name, diff, expected, missingOutcome) => {- global.fetch = nativeFetch+ it.runIf(Boolean(process.env.GOAL_FIDELITY_EVAL_MODEL)).each([+ ...backfillCases,+ ['original broad audit scope', backfillObservabilityCase.diff, 'ship', null, backfillObservabilityCase.objective],+ ['explicit catch repair scope', backfillObservabilityCase.diff, 'ship', null, backfillRequirement],+ ])('judges backfill accounting and warning outcomes with a real local model: %s', async (name, diff, expected, missingOutcome, objective = backfillCase.objective) => {+ const focusedJudgements = []+ global.fetch = async (url, init) => {+ const response = await nativeFetch(url, init)+ const messages = JSON.parse(init.body).messages+ if (/^You check only/.test(messages[0].content)) {+ const content = (await response.clone().json()).choices?.[0]?.message?.content+ focusedJudgements.push({ focus: messages[0].content, verdict: extractJson(content || '').value })+ }+ return response+ }const result = await runLocalGoalFidelityReview({backend: 'ollama', model: process.env.GOAL_FIDELITY_EVAL_MODEL,- objective: backfillCase.objective, diff, timeoutMs: 180_000,+ objective, diff, timeoutMs: 180_000,})console.log(`🔍 Backfill evaluation ${name}: ${JSON.stringify(result)}`)expect(result.ok, result.error).toBe(true)@@ -1602,6 +1619,13 @@ describe('codeReview helpers', () => {expect(result.missing.length + (expected === 'rethink' ? result.unrequested.length : 0), JSON.stringify(result)).toBeGreaterThan(0)if (missingOutcome) expect(result.missing.join(' ')).toMatch(missingOutcome)}+ // The incoming fail-only floor must not hide a model false approval.+ if (missingOutcome && name !== 'missing per-record logging') {+ const focus = name.startsWith('failed writes') ? 'success-accounting' : 'warning-summary'+ const judged = focusedJudgements.find(row => row.focus.includes(focus))?.verdict+ expect(['fix-first', 'rethink'], JSON.stringify(focusedJudgements)).toContain(judged?.verdict)+ expect(judged.missing.join(' ')).toMatch(missingOutcome)+ }// A diff carries coverage, never a passing test execution result.if (expected === 'ship') expect(result.evidence).toMatch(/(?:execution|executed|test.run|test result|tests? (?:ran|run|passed))/i)expect(result.evidence).not.toMatch(/tests? (?:have |were |was |are )?(?:run|ran|passed|passing)|verified by (?:the )?(?:passing )?tests/i)@@ -1666,28 +1690,9 @@ describe('codeReview helpers', () => {expect(result).toMatchObject({ ok: true, verdict: expected })if (expected === 'ship') expect(result.missing).toEqual([])else expect(result.missing.join(' ')).toMatch(/backfillFromHistory.*(?:count|summary)/)- expect(global.fetch).toHaveBeenCalledTimes(2)+ expect(global.fetch).toHaveBeenCalledTimes(4)})- // Actual judgement pin: explicitly opt-in so ordinary CI makes zero provider calls.- it.runIf(Boolean(process.env.GOAL_FIDELITY_EVAL_MODEL)).each(backfillObservabilityCases)('judges the backfill catch replacement with a real local model: %s', async (_name, objective, diff, expected) => {- global.fetch = nativeFetch- const result = await runLocalGoalFidelityReview({- backend: 'ollama', model: process.env.GOAL_FIDELITY_EVAL_MODEL,- objective: taskObjective({ description: objective }), diff, timeoutMs: 180_000,- })- console.log(`🔍 Backfill evaluation ${_name}: ${JSON.stringify(result)}`)- expect(result.ok, result.error).toBe(true)- if (expected === 'ship') expect(result, JSON.stringify(result)).toMatchObject({ verdict: 'ship', missing: [], unrequested: [] })- else {- expect(['fix-first', 'rethink'], JSON.stringify(result)).toContain(result.verdict)- expect(expected === 'rethink' ? result.missing.length + result.unrequested.length : result.missing.length, JSON.stringify(result)).toBeGreaterThan(0)- }- if (expected === 'rethink') expect(result.verdict).toBe('rethink')- if (_name.startsWith('failed records still counted')) expect(result.missing.join(' ')).toMatch(/count|success/i)- if (_name.startsWith('failure summary still reports info')) expect(result.missing.join(' ')).toMatch(/warn|summary|level/i)- }, 190_000)-// Actual judgement pin: explicitly opt-in so ordinary CI makes zero provider calls.it.runIf(Boolean(process.env.GOAL_FIDELITY_EVAL_MODEL)).each(observabilityCases)('judges the one-finding observability audit with a real local model: %s', async (_name, objective, diff, expected) => {global.fetch = nativeFetch