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:
bchanot committed 2026-10-21 16:50:47 +02:00
1 parent d3635b6c33
commit a7d747c65f
10 files changed
+73 -26

No files matched your search

+7 -6
View File
@@ -83,8 +83,8 @@ inherits silently: typed agents run on their model-router row, their
| Agent | Model | Tier | | Agent | Model | Tier |
|---|---|---| |---|---|---|
| feater, hotfixer, bugfixer | sonnet (pinned) | executors — code from a closed plan (feat), fix from a closed diagnosis (bugfix), fix-bundle appliers | | feater, hotfixer, bugfixer | sonnet (pinned) | executors — code from a closed plan (feat), fix from a closed diagnosis (bugfix), fix-bundle appliers |
| verifier | sonnet (pinned) | fresh gate (≤3×/loop) | | verifier | Fable (`audit` row: best/xhigh, opus frontmatter floor) | fresh gate (≤3×/loop) |
| security-auditor | opus (judge row: opus/xhigh, the user's first-use decision; frontmatter floor aligned) | fresh gate (≤3×/loop) | | security-auditor | Fable (`audit` row: best/xhigh, opus frontmatter floor) | fresh gate (≤3×/loop) |
| commit-changer, release-executor, code-cleaner | sonnet (pinned) | dispatched execution — grouping+commit / release spans / approved cleanup (audit + approval gates stay in the dispatcher) | | commit-changer, release-executor, code-cleaner | sonnet (pinned) | dispatched execution — grouping+commit / release spans / approved cleanup (audit + approval gates stay in the dispatcher) |
| onboarder, scaffolder, refactorer, validator-analyzer, plugin-probe | sonnet (pinned) | workers — config generation, scaffold, refactor, deterministic W3C/WCAG runner, mechanical plugin probe | | onboarder, scaffolder, refactorer, validator-analyzer, plugin-probe | sonnet (pinned) | workers — config generation, scaffold, refactor, deterministic W3C/WCAG runner, mechanical plugin probe |
| status-reporter | haiku (pinned) | mechanical collector | | status-reporter | haiku (pinned) | mechanical collector |
@@ -109,12 +109,13 @@ Second axis of the same table: how hard each phase thinks. Session default
model-router mod (below): the phase table and one phase row per repo skill model-router mod (below): the phase table and one phase row per repo skill
and agent, each phase naming a tier and an effort level and agent, each phase naming a tier and an effort level
(`plan` best/xhigh, `reflect` best/high, `orchestrate` best/medium, (`plan` best/xhigh, `reflect` best/high, `orchestrate` best/medium,
`escalate` best/max, `judge` big/xhigh, `implement` work/medium, `write` `escalate` best/max, `judge` big/xhigh, `audit` best/xhigh, `implement` work/medium, `write`
work/high, `verify` work/xhigh, `explore` work/medium, `apply` work/low, work/high, `verify` work/xhigh, `explore` work/medium, `apply` work/low,
`mechanical` cheap/low). The `model:` and `effort:` frontmatter of every `mechanical` cheap/low). The `model:` and `effort:` frontmatter of every
typed agent and user-invoked skill stays as the off-state floor, kept equal typed agent and user-invoked skill stays as the off-state floor, kept equal
to the rows by the census `lib/tests/effort-routing.test.sh` (a row to the rows by the census `lib/tests/effort-routing.test.sh` (a best-tier
changed through the first-use dialog passes with a `WARN floor drift` line row floors on the tier's second alias, opus, since Fable is credit-gated; a
row changed through the first-use dialog passes with a `WARN floor drift` line
until its frontmatter follows): low until its frontmatter follows): low
appliers, medium executors, high writers, xhigh judgment and gates (none appliers, medium executors, high writers, xhigh judgment and gates (none
on haiku, which rejects the parameter); `/status` low … `/ship-feature` on haiku, which rejects the parameter); `/status` low … `/ship-feature`
@@ -132,7 +133,7 @@ effort, never version. Transcript audit `python3 lib/effort-audit.py`.
`mods/model-router/` is a Claude Code mod (a function-hooks plugin) that applies this table per request. It loads in every session through the tracked symlink `skills/model-router`, as `model-router@skills-dir`. `mods/model-router/` is a Claude Code mod (a function-hooks plugin) that applies this table per request. It loads in every session through the tracked symlink `skills/model-router`, as `model-router@skills-dir`.
- Main loop: every request gets the route in force. A typed skill with a row routes the main loop to it; a best-tier row (`plan`, `reflect`, `orchestrate`, `escalate`) holds across turns in a run slot until `/route clear`, `/route off`, a user `/model` or a typed skill on a non-best row. A skill without a row leaves the route as it is. A rowed skill the model loads inside a best-tier run moves effort only when its row ranks below the run's model. Main routed onto a model whose context window the conversation outgrew returns to the session model. Before main runs on a model, the one it moves to or the one it keeps (the session's own model included), the mod probes it with one small completion bounded to 8 seconds; the step (and `/route show`, the route tool's answer) waits for it. A timeout or an error marks the model down (reason `probe`, held for `cooldownMinutes` like any breaker hold) and the decision is taken again once. A model already marked down is never probed, and a model that answered is not probed again, `/clear` included, until it is marked down. When a lower model stands in for its tier's head held down (Opus for Fable on a best-tier phase), the phase's own effort goes one notch up: `reflect` xhigh, `plan` max, `orchestrate` high, `escalate` stays max. An effort asked explicitly (`/route ... effort=`, the `route` tool's `effort`) or set by a floor is never raised. `/route show` and the route tool's answer print the level with `(opus stands in for fable)`; the verbose transition line names `stand-in` as a cause. - Main loop: every request gets the route in force. A typed skill with a row routes the main loop to it; a best-tier row (`plan`, `reflect`, `orchestrate`, `escalate`; `audit` is an agent row, never typed) holds across turns in a run slot until `/route clear`, `/route off`, a user `/model` or a typed skill on a non-best row. A skill without a row leaves the route as it is. A rowed skill the model loads inside a best-tier run moves effort only when its row ranks below the run's model. Main routed onto a model whose context window the conversation outgrew returns to the session model. Before main runs on a model, the one it moves to or the one it keeps (the session's own model included), the mod probes it with one small completion bounded to 8 seconds; the step (and `/route show`, the route tool's answer) waits for it. A timeout or an error marks the model down (reason `probe`, held for `cooldownMinutes` like any breaker hold) and the decision is taken again once. A model already marked down is never probed, and a model that answered is not probed again, `/clear` included, until it is marked down. When a lower model stands in for its tier's head held down (Opus for Fable on a best-tier phase), the phase's own effort goes one notch up: `reflect` xhigh, `plan` max, `orchestrate` high, `escalate` stays max. An effort asked explicitly (`/route ... effort=`, the `route` tool's `effort`) or set by a floor is never raised. `/route show` and the route tool's answer print the level with `(opus stands in for fable)`; the verbose transition line names `stand-in` as a cause.
- Sub-agents: a routed agent gets its row's model at spawn, within its tier and only upward from its frontmatter model, and the row's effort on every step. Explicit `model` / `effort` params on the Agent call win; a project-defined agent of the same name keeps its own definition. Built-ins: Explore runs on sonnet/medium, Plan on opus/xhigh. A built-in `general-purpose` agent that main spawns with no `model` param, while main runs below the session model (a downgrade or a breaker fallback), starts on the session model instead of inheriting the lower one; it is not pinned when the session model is marked down, for a fork, a workflow or a nested spawn, or when a project or user definition shadows the built-in. Other agent types are never pinned this way: the hook cannot see their frontmatter model. - Sub-agents: a routed agent gets its row's model at spawn, within its tier and only upward from its frontmatter model, and the row's effort on every step. Explicit `model` / `effort` params on the Agent call win; a project-defined agent of the same name keeps its own definition. Built-ins: Explore runs on sonnet/medium, Plan on opus/xhigh. A built-in `general-purpose` agent that main spawns with no `model` param, while main runs below the session model (a downgrade or a breaker fallback), starts on the session model instead of inheriting the lower one; it is not pinned when the session model is marked down, for a fork, a workflow or a nested spawn, or when a project or user definition shadows the built-in. Other agent types are never pinned this way: the hook cannot see their frontmatter model.
- Levers inside a run: `ultrathink` in a prompt sets the turn's minimum effort; `/route effort=max` holds until `/route clear`. The built-in `/effort` is not a lever inside a run, rows and routes outrank it. - Levers inside a run: `ultrathink` in a prompt sets the turn's minimum effort; `/route effort=max` holds until `/route clear`. The built-in `/effort` is not a lever inside a run, rows and routes outrank it.
- Prompt classifier: a plain prompt typed in the composer (12 characters or more, not a slash command) that no keyword rule, skill, run slot, `/route` or floor covers is sent to the engine's small fast model, one call, bounded to 3 seconds (the prompt waits for it, typically under a second). The label (`design`, `analysis`, `coding`, `bookkeeping`, `chat`) maps to plan, reflect, implement or apply (`chat` routes nothing), and the turn takes that phase's route: its effort becomes the turn's default, and its model may move the main loop, never above the session model. A `coding` or `bookkeeping` guess moves main down only when `mainModelSwitch` is on and the cold read fits `downgradeMaxTokens`; an `ultrathink` floor in the same turn keeps its own model. No dialog opens and no file is written. The route is gone at the end of the turn, a later route call or typed skill replaces it, and a `/effort` you type between turns drops the guess for that turn only. A typed best-tier skill holds its run slot across turns, so nothing is classified there until `/route clear`. Long prompts are sampled (first 500 and last 1500 code points), so pasted text at the end can steer one turn's route. Three failures in a row pause it for `cooldownMinutes` (one toast, `classifier: paused` in the status line). Never in a sub-agent, mid-turn or under `-p`. Off per session with `/route classify off`, per machine with `"classify": false`. The status line reads `route: classifier <phase>`; `/route verbose on` adds the transition line. - Prompt classifier: a plain prompt typed in the composer (12 characters or more, not a slash command) that no keyword rule, skill, run slot, `/route` or floor covers is sent to the engine's small fast model, one call, bounded to 3 seconds (the prompt waits for it, typically under a second). The label (`design`, `analysis`, `coding`, `bookkeeping`, `chat`) maps to plan, reflect, implement or apply (`chat` routes nothing), and the turn takes that phase's route: its effort becomes the turn's default, and its model may move the main loop, never above the session model. A `coding` or `bookkeeping` guess moves main down only when `mainModelSwitch` is on and the cold read fits `downgradeMaxTokens`; an `ultrathink` floor in the same turn keeps its own model. No dialog opens and no file is written. The route is gone at the end of the turn, a later route call or typed skill replaces it, and a `/effort` you type between turns drops the guess for that turn only. A typed best-tier skill holds its run slot across turns, so nothing is classified there until `/route clear`. Long prompts are sampled (first 500 and last 1500 code points), so pasted text at the end can steer one turn's route. Three failures in a row pause it for `cooldownMinutes` (one toast, `classifier: paused` in the status line). Never in a sub-agent, mid-turn or under `-p`. Off per session with `/route classify off`, per machine with `"classify": false`. The status line reads `route: classifier <phase>`; `/route verbose on` adds the transition line.
+6 -4
View File
@@ -107,10 +107,12 @@ the MAIN loop, never here):
(correctness / robustness / simplicity), each blind to the others. (correctness / robustness / simplicity), each blind to the others.
- MODEL (BDR-076, supersedes the BDR-066 inherit): plan critique is AUDIT - MODEL (BDR-076, supersedes the BDR-066 inherit): plan critique is AUDIT
JUDGMENT, not a procedural gate — the challenger is routed to the `judge` JUDGMENT, not a procedural gate — the challenger is routed to the `judge`
row (opus) by the model-router, the `model: opus` frontmatter being the off-state floor (big row (opus) by the model-router, the `model: opus` frontmatter being the
tier; the session model stays on the inline loop). Never `model: "sonnet"` — off-state floor (big tier; the session model stays on the inline loop).
a silent judgment downgrade. (Contrast the verifier on its `verify` row and Never `model: "sonnet"` — a silent judgment downgrade. (Contrast the
the executors on their `implement` row, both sonnet, oracle-anchored to a contract.) executors on their `implement` row, sonnet, oracle-anchored to a contract;
the verifier and security-auditor sit on the `audit` row, Fable with an
opus floor.)
- FAIL-SAFE — never fail open: a malformed/empty verdict, a missing `PROOF`, or - FAIL-SAFE — never fail open: a malformed/empty verdict, a missing `PROOF`, or
a dead challenger → retry ONCE fresh; a 2nd failure → escalate to the human and a dead challenger → retry ONCE fresh; a 2nd failure → escalate to the human and
NAME the lens. Never report "plan challenged" on a silently dropped lens (same NAME the lens. Never report "plan challenged" on a silently dropped lens (same
+1 -1
View File
@@ -2,7 +2,7 @@
name: verifier name: verifier
description: Fresh independent verifier — reads a CONTRACT file from disk and renders a structured verdict (CONFORME / ECARTS / ERROR) on the implemented diff. Report-only, never fixes. Dispatched fresh at every iteration; receives no iteration history. description: Fresh independent verifier — reads a CONTRACT file from disk and renders a structured verdict (CONFORME / ECARTS / ERROR) on the implemented diff. Report-only, never fixes. Dispatched fresh at every iteration; receives no iteration history.
tools: Read, Grep, Glob, Bash tools: Read, Grep, Glob, Bash
model: sonnet model: opus
effort: xhigh effort: xhigh
--- ---
+2 -1
View File
@@ -47,7 +47,8 @@ JUDGMENT — the challengers are routed to the `judge` row (opus) by the model-r
the `model: opus` frontmatter being the off-state floor: a big tier, off the `model: opus` frontmatter being the off-state floor: a big tier, off
the session model. The session model (Fable) the session model. The session model (Fable)
keeps only this loop — synthesis, RE-THINK, gate. Never sonnet: that would keeps only this loop — synthesis, RE-THINK, gate. Never sonnet: that would
silently downgrade the judgment. (The executor gates stay sonnet.) silently downgrade the judgment. (The executors stay sonnet; the two merge
gates sit on the `audit` row, Fable with an opus floor.)
**Lens framing by `KIND`** (the agent's three lenses, read against the artifact): **Lens framing by `KIND`** (the agent's three lenses, read against the artifact):
- `build-plan` — will it WORK / will it BREAK / is it needlessly COMPLEX. - `build-plan` — will it WORK / will it BREAK / is it needlessly COMPLEX.
+12 -2
View File
@@ -52,12 +52,19 @@ code_phase() {
awk '/^ phases: \{/{f=1;next} f&&/^ \},?$/{f=0} f' "$REG" \ awk '/^ phases: \{/{f=1;next} f&&/^ \},?$/{f=0} f' "$REG" \
| sed -nE "s/^ *$1: \{ tier: '([a-z]+)', effort: '([a-z]+)' \},?$/\1 \2/p" | sed -nE "s/^ *$1: \{ tier: '([a-z]+)', effort: '([a-z]+)' \},?$/\1 \2/p"
} }
# tier_floor <file> <tier> -> the model: floor of a tier's agents
# a best-tier row floors on its 2nd alias: inTier keeps the frontmatter when the head is down (Fable credits, BLK-030); a fable floor would spawn the gates on a dead model
tier_floor() {
if [ "$2" != best ]; then tier_head "$1" "$2"; return; fi
awk '/^ tiers: \{/{f=1;next} f&&/^ \},?$/{f=0} f' "$1" \
| sed -nE "s/^ *best: \['[a-z]+', '([a-z]+)'.*$/\1/p"
}
# field_of <dump> <phase> <effort|model> -> that phase's frontmatter value # field_of <dump> <phase> <effort|model> -> that phase's frontmatter value
field_of() { field_of() {
local pe tier local pe tier
pe="$(phase_effort "$1" "$2")" pe="$(phase_effort "$1" "$2")"
if [ "$3" = effort ]; then printf '%s\n' "${pe#* }"; return; fi if [ "$3" = effort ]; then printf '%s\n' "${pe#* }"; return; fi
tier="${pe% *}"; tier_head "$REG" "$tier" tier="${pe% *}"; tier_floor "$REG" "$tier"
} }
# verdict <dump> <kind> <name> <effort|model> <got> <phase>: ok when the # verdict <dump> <kind> <name> <effort|model> <got> <phase>: ok when the
# frontmatter equals the row's phase; warn when the row was changed through # frontmatter equals the row's phase; warn when the row was changed through
@@ -87,6 +94,7 @@ RD="$(dump "$RJ")"
FIX="$(mktemp -d)"; trap 'rm -rf "$FIX"' EXIT FIX="$(mktemp -d)"; trap 'rm -rf "$FIX"' EXIT
cat > "$FIX/reg.ts" <<'FX' cat > "$FIX/reg.ts" <<'FX'
tiers: { tiers: {
best: ['fable', 'opus', 'sonnet'],
big: ['opus', 'fable'], big: ['opus', 'fable'],
}, },
FX FX
@@ -110,6 +118,8 @@ FD="$(dump "$FIX/routing.json")"
[ "$(phase_effort "$FD" judge)" = "big xhigh" ] && ok || ko "flip: phase" [ "$(phase_effort "$FD" judge)" = "big xhigh" ] && ok || ko "flip: phase"
[ -z "$(phase_effort "$FD" nothere)" ] && ok || ko "flip: ghost phase" [ -z "$(phase_effort "$FD" nothere)" ] && ok || ko "flip: ghost phase"
[ "$(tier_head "$FIX/reg.ts" big)" = "opus" ] && ok || ko "flip: tier head" [ "$(tier_head "$FIX/reg.ts" big)" = "opus" ] && ok || ko "flip: tier head"
[ "$(tier_floor "$FIX/reg.ts" best)" = opus ] && ok || ko "flip: best floors on its 2nd alias"
[ "$(tier_floor "$FIX/reg.ts" big)" = opus ] && ok || ko "flip: big floors on its head"
[ "$(changed_of "$FD" skills feat)" = "reflect implement" ] && ok || ko "flip: changed entry" [ "$(changed_of "$FD" skills feat)" = "reflect implement" ] && ok || ko "flip: changed entry"
[ -z "$(changed_of "$FD" skills doc)" ] && ok || ko "flip: ghost changed entry" [ -z "$(changed_of "$FD" skills doc)" ] && ok || ko "flip: ghost changed entry"
# the drift verdicts (high = reflect's effort, medium = implement's) # the drift verdicts (high = reflect's effort, medium = implement's)
@@ -147,7 +157,7 @@ check_skill() {
while IFS= read -r f; do check_skill "$f"; done < <( while IFS= read -r f; do check_skill "$f"; done < <(
cd "$R" && git ls-files 'skills/*/SKILL.md' 'skills-external/*/SKILL.md') cd "$R" && git ls-files 'skills/*/SKILL.md' 'skills-external/*/SKILL.md')
# ── (c) tracked agents with a row: tier head == model:, effort == effort: ─ # ── (c) tracked agents with a row: tier floor == model:, effort == effort: ─
NO_ROW_AGENTS=" interviewer client-handover-writer " NO_ROW_AGENTS=" interviewer client-handover-writer "
check_agent() { check_agent() {
local f="$1" name phase local f="$1" name phase
+2 -2
View File
@@ -20,8 +20,8 @@ done
# 3) executor + gate pins # 3) executor + gate pins
has "agents/feater.md" 'model: sonnet' has "agents/feater.md" 'model: sonnet'
has "agents/hotfixer.md" 'model: sonnet' has "agents/hotfixer.md" 'model: sonnet'
has "agents/verifier.md" 'model: sonnet' has "agents/verifier.md" 'model: opus' # audit row (best tier, opus = outage floor; BLK-032 policy 2026-10-21)
has "agents/security-auditor.md" 'model: opus' # judge row since 2026-10-11 (user first-use decision) has "agents/security-auditor.md" 'model: opus' # audit row since 2026-10-21 (was judge since 2026-10-11)
has "agents/analyzer.md" 'model: opus' has "agents/analyzer.md" 'model: opus'
# 4) /feat executor shape # 4) /feat executor shape
has "skills/feat/SKILL.md" 'subagent_type="feater"' has "skills/feat/SKILL.md" 'subagent_type="feater"'
+29 -2
View File
@@ -69,6 +69,7 @@ const baseRouting = (): Rec => ({
orchestrate: { tier: 'best', effort: 'medium' }, orchestrate: { tier: 'best', effort: 'medium' },
escalate: { tier: 'best', effort: 'max' }, escalate: { tier: 'best', effort: 'max' },
judge: { tier: 'big', effort: 'xhigh' }, judge: { tier: 'big', effort: 'xhigh' },
audit: { tier: 'best', effort: 'xhigh' },
implement: { tier: 'work', effort: 'medium' }, implement: { tier: 'work', effort: 'medium' },
write: { tier: 'work', effort: 'high' }, write: { tier: 'work', effort: 'high' },
verify: { tier: 'work', effort: 'xhigh' }, 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 ( test('agent row: explicit model, explicit effort and fork win', async (
$, on) => { $, on) => {
const rig = await bootRun($, 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 bootRun($, on, FABLE, w)
await typeFeat($) await typeFeat($)
const lines = (await route($, 'pending')).split('\n') const lines = (await route($, 'pending')).split('\n')
expect(lines[0]).toBe('pending confirmation: 19') expect(lines[0]).toBe('pending confirmation: 20')
expect(lines[1]).toBe('asked this session: skills:feat') expect(lines[1]).toBe('asked this session: skills:feat')
expect(lines[2]).toContain('agents:feater') expect(lines[2]).toContain('agents:feater')
expect(lines[2]).toContain('phases:plan') expect(lines[2]).toContain('phases:plan')
@@ -2564,7 +2591,7 @@ test('/route pending drops a confirmed row', async ($, on) => {
await bootRun($, on, FABLE, w) await bootRun($, on, FABLE, w)
await typeFeat($) await typeFeat($)
const text = await route($, 'pending') const text = await route($, 'pending')
expect(text).toContain('pending confirmation: 17') expect(text).toContain('pending confirmation: 18')
expect(text).not.toContain('phases:reflect') expect(text).not.toContain('phases:reflect')
}) })
+1
View File
@@ -278,6 +278,7 @@ const DEFAULT_CONFIG: Config = {
orchestrate: { tier: 'best', effort: 'medium' }, orchestrate: { tier: 'best', effort: 'medium' },
escalate: { tier: 'best', effort: 'max' }, escalate: { tier: 'best', effort: 'max' },
judge: { tier: 'big', effort: 'xhigh' }, judge: { tier: 'big', effort: 'xhigh' },
audit: { tier: 'best', effort: 'xhigh' },
implement: { tier: 'work', effort: 'medium' }, implement: { tier: 'work', effort: 'medium' },
write: { tier: 'work', effort: 'high' }, write: { tier: 'work', effort: 'high' },
verify: { tier: 'work', effort: 'xhigh' }, verify: { tier: 'work', effort: 'xhigh' },
+11 -6
View File
@@ -23,7 +23,12 @@
"judge": { "judge": {
"tier": "big", "tier": "big",
"effort": "xhigh", "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": { "implement": {
"tier": "work", "tier": "work",
@@ -38,7 +43,7 @@
"verify": { "verify": {
"tier": "work", "tier": "work",
"effort": "xhigh", "effort": "xhigh",
"about": "checking a result against its spec: tests, security review, gates" "about": "checking a result against its spec: tests and suites"
}, },
"explore": { "explore": {
"tier": "work", "tier": "work",
@@ -138,17 +143,17 @@
"release-executor": "apply", "release-executor": "apply",
"plugin-probe": "apply", "plugin-probe": "apply",
"validator-analyzer": "apply", "validator-analyzer": "apply",
"verifier": "verify", "verifier": "audit",
"security-auditor": "judge", "security-auditor": "audit",
"status-reporter": "mechanical" "status-reporter": "mechanical"
}, },
"projects": {}, "projects": {},
"confirmed": { "confirmed": {
"agents": { "agents": {
"verifier": "verify", "verifier": "audit",
"feater": "implement", "feater": "implement",
"doc-syncer": "write", "doc-syncer": "write",
"security-auditor": "judge", "security-auditor": "audit",
"plan-challenger": "judge", "plan-challenger": "judge",
"analyzer": "judge", "analyzer": "judge",
"hotfixer": "apply", "hotfixer": "apply",
+2 -2
View File
@@ -80,8 +80,8 @@ Model discipline (the user-fixed invariant behind this mode):
carries this skill's reflection (fix decisions, convergence calls); it carries this skill's reflection (fix decisions, convergence calls); it
must never be pinned down to an executor tier. must never be pinned down to an executor tier.
- Inside a runner, every dispatched agent keeps the tier this skill - Inside a runner, every dispatched agent keeps the tier this skill
already defines: security-auditor (sonnet frontmatter), the Phase B already defines: security-auditor (`audit` row: Fable, opus floor), the
audit (analyzer opus pin or `model="opus"`), doc-syncer (audit on Phase B audit (analyzer opus pin or `model="opus"`), doc-syncer (audit on
`model="opus"`, patch on its sonnet frontmatter — BDR-077). `model="opus"`, patch on its sonnet frontmatter — BDR-077).
Runner dispatch, one per project: Runner dispatch, one per project: