feat(model-router): audit phase puts the verifier and security-auditor on Fable
New best-tier phase audit (xhigh) carries both merge gates; their opus frontmatter stays the outage floor, since inTier never writes below a tier head. The census floors best-tier rows on the second alias, and the citers now name the audit row.
This commit is contained in:
1 parent
d3635b6c33
commit
a7d747c65f
10 files changed
+73
-26
No files matched your search
@@ -69,6 +69,7 @@ const baseRouting = (): Rec => ({
|
||||
orchestrate: { tier: 'best', effort: 'medium' },
|
||||
escalate: { tier: 'best', effort: 'max' },
|
||||
judge: { tier: 'big', effort: 'xhigh' },
|
||||
audit: { tier: 'best', effort: 'xhigh' },
|
||||
implement: { tier: 'work', effort: 'medium' },
|
||||
write: { tier: 'work', effort: 'high' },
|
||||
verify: { tier: 'work', effort: 'xhigh' },
|
||||
@@ -1290,6 +1291,32 @@ test('agent row: opus and fable down, no write and one log line', async (
|
||||
])
|
||||
})
|
||||
|
||||
const auditWorld = () => newWorld({
|
||||
edit: f => { (f.agents as Rec)['security-auditor'] = 'audit' },
|
||||
})
|
||||
|
||||
test('audit row: fable down, no write, frontmatter runs', async (
|
||||
$, on) => {
|
||||
const logs = recordLogs(on)
|
||||
const rig = await bootRun($, on, FABLE, auditWorld())
|
||||
await switchTo($, FABLE, SONNET, 'auto')
|
||||
await $.agent.spawn(spawnOf('security-auditor'))
|
||||
expect(rig.specs).toEqual([undefined])
|
||||
const down = logs.filter(l => l.includes('frontmatter model kept'))
|
||||
expect(down).toEqual([
|
||||
'model-router: security-auditor tier best down, frontmatter model kept',
|
||||
])
|
||||
})
|
||||
|
||||
test('audit row: first spawn dies on fable, the retry lands on the floor',
|
||||
async ($, on) => {
|
||||
const rig = await bootRun($, on, FABLE, auditWorld())
|
||||
await $.agent.spawn(spawnOf('security-auditor'))
|
||||
await failWith($, 'rate_limit', 'a1')
|
||||
await $.agent.spawn(spawnOf('security-auditor'))
|
||||
expect(rig.specs).toEqual([FABLE, undefined])
|
||||
})
|
||||
|
||||
test('agent row: explicit model, explicit effort and fork win', async (
|
||||
$, on) => {
|
||||
const rig = await bootRun($, on)
|
||||
@@ -2552,7 +2579,7 @@ test('/route pending lists what is not confirmed, asked first', async (
|
||||
await bootRun($, on, FABLE, w)
|
||||
await typeFeat($)
|
||||
const lines = (await route($, 'pending')).split('\n')
|
||||
expect(lines[0]).toBe('pending confirmation: 19')
|
||||
expect(lines[0]).toBe('pending confirmation: 20')
|
||||
expect(lines[1]).toBe('asked this session: skills:feat')
|
||||
expect(lines[2]).toContain('agents:feater')
|
||||
expect(lines[2]).toContain('phases:plan')
|
||||
@@ -2564,7 +2591,7 @@ test('/route pending drops a confirmed row', async ($, on) => {
|
||||
await bootRun($, on, FABLE, w)
|
||||
await typeFeat($)
|
||||
const text = await route($, 'pending')
|
||||
expect(text).toContain('pending confirmation: 17')
|
||||
expect(text).toContain('pending confirmation: 18')
|
||||
expect(text).not.toContain('phases:reflect')
|
||||
})
|
||||
|
||||
|
||||
@@ -278,6 +278,7 @@ const DEFAULT_CONFIG: Config = {
|
||||
orchestrate: { tier: 'best', effort: 'medium' },
|
||||
escalate: { tier: 'best', effort: 'max' },
|
||||
judge: { tier: 'big', effort: 'xhigh' },
|
||||
audit: { tier: 'best', effort: 'xhigh' },
|
||||
implement: { tier: 'work', effort: 'medium' },
|
||||
write: { tier: 'work', effort: 'high' },
|
||||
verify: { tier: 'work', effort: 'xhigh' },
|
||||
|
||||
@@ -23,7 +23,12 @@
|
||||
"judge": {
|
||||
"tier": "big",
|
||||
"effort": "xhigh",
|
||||
"about": "independent judgment of work: audits, challenges and verdicts"
|
||||
"about": "independent judgment of work: challenges, analyses and reviews"
|
||||
},
|
||||
"audit": {
|
||||
"tier": "best",
|
||||
"effort": "xhigh",
|
||||
"about": "the fresh gates: contract verdict and security scan; dispatched agents, not a main-loop phase"
|
||||
},
|
||||
"implement": {
|
||||
"tier": "work",
|
||||
@@ -38,7 +43,7 @@
|
||||
"verify": {
|
||||
"tier": "work",
|
||||
"effort": "xhigh",
|
||||
"about": "checking a result against its spec: tests, security review, gates"
|
||||
"about": "checking a result against its spec: tests and suites"
|
||||
},
|
||||
"explore": {
|
||||
"tier": "work",
|
||||
@@ -138,17 +143,17 @@
|
||||
"release-executor": "apply",
|
||||
"plugin-probe": "apply",
|
||||
"validator-analyzer": "apply",
|
||||
"verifier": "verify",
|
||||
"security-auditor": "judge",
|
||||
"verifier": "audit",
|
||||
"security-auditor": "audit",
|
||||
"status-reporter": "mechanical"
|
||||
},
|
||||
"projects": {},
|
||||
"confirmed": {
|
||||
"agents": {
|
||||
"verifier": "verify",
|
||||
"verifier": "audit",
|
||||
"feater": "implement",
|
||||
"doc-syncer": "write",
|
||||
"security-auditor": "judge",
|
||||
"security-auditor": "audit",
|
||||
"plan-challenger": "judge",
|
||||
"analyzer": "judge",
|
||||
"hotfixer": "apply",
|
||||
|
||||
Reference in new issue
Block a user