pantheon-opencode 1.6.2-beta.1 → 1.6.2-beta.10
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +163 -0
- package/README.md +236 -60
- package/README.pt-BR.md +19 -1
- package/bin/pantheon-init.mjs +195 -13
- package/package.json +11 -3
- package/plugin.json +1 -1
- package/prompts/README.md +58 -0
- package/prompts/debug-issue.prompt.md +46 -0
- package/prompts/dynamic/agora-generated.txt +38 -0
- package/prompts/dynamic/orchestrate-generated.txt +51 -0
- package/prompts/focus.prompt.md +42 -0
- package/prompts/implement-feature.prompt.md +39 -0
- package/prompts/optimize-database.prompt.md +58 -0
- package/prompts/orchestrate-with-zeus.prompt.md +441 -0
- package/prompts/plan-architecture.prompt.md +59 -0
- package/prompts/quick-discovery-large-codebase.prompt.md +294 -0
- package/prompts/quick-plan-large-feature.prompt.md +197 -0
- package/prompts/semantic-summarize.md +50 -0
- package/prompts/sketch.prompt.md +91 -0
- package/prompts/subtask.prompt.md +131 -0
- package/pyproject.toml +1 -1
- package/scripts/decision-router-budget.mjs +780 -0
- package/scripts/decision-router-v2-budget.mjs +218 -0
- package/scripts/decision-router-v2-egress.mjs +272 -0
- package/scripts/decision-router.mjs +758 -0
- package/scripts/docs-check-changelog.mjs +5 -3
- package/scripts/install/component-selection.mjs +9 -4
- package/scripts/install/decision-layer-preview.mjs +376 -0
- package/scripts/install/decision-router-config.mjs +560 -0
- package/scripts/install/health-check.mjs +20 -11
- package/scripts/install/interactive.mjs +103 -14
- package/scripts/install/interrupt.mjs +4 -3
- package/scripts/install/migrate.mjs +123 -72
- package/scripts/install/opencode.mjs +178 -122
- package/scripts/install/plan.mjs +8 -1
- package/scripts/install/plugin.mjs +4 -3
- package/scripts/install/state.mjs +12 -0
- package/scripts/install/strings.mjs +22 -0
- package/scripts/install/venv.mjs +34 -17
- package/scripts/mcp_resources.py +11 -9
- package/scripts/release-notes.mjs +30 -7
- package/scripts/restore.mjs +22 -10
- package/scripts/sync-tui.mjs +3 -3
- package/scripts/test-opencode-v2-sandbox.sh +10 -6
- package/scripts/versioning.mjs +41 -5
- package/src/agents/aphrodite.md +6 -1
- package/src/agents/apollo.md +1 -0
- package/src/agents/athena.md +1 -0
- package/src/agents/demeter.md +1 -1
- package/src/agents/gaia.md +1 -0
- package/src/agents/hephaestus.md +1 -1
- package/src/agents/hermes.md +8 -10
- package/src/agents/iris.md +1 -1
- package/src/agents/mnemosyne.md +1 -0
- package/src/agents/nyx.md +1 -1
- package/src/agents/prometheus.md +1 -1
- package/src/agents/talos.md +6 -1
- package/src/agents/themis.md +1 -1
- package/src/agents/zeus.md +52 -62
- package/src/mcp/eval_store.py +11 -4
- package/src/mcp/mcp_resources.py +11 -9
- package/src/mcp/memory_mcp.py +293 -150
- package/src/pantheon/cost-command.ts +30 -133
- package/src/pantheon/jev-decision-tool.ts +347 -0
- package/src/pantheon/jev-decisions.ts +625 -0
- package/src/pantheon/local-decision-agents.ts +170 -0
- package/src/pantheon/local-decision-budget.ts +1046 -0
- package/src/pantheon/local-decision-egress-gate.ts +144 -0
- package/src/pantheon/local-decision-prompt.ts +256 -0
- package/src/pantheon/local-decision-provider-matrix.ts +44 -0
- package/src/pantheon/local-decision-router.ts +225 -0
- package/src/pantheon/local-decision-skills.ts +281 -0
- package/src/pantheon/local-decision-tool.ts +160 -0
- package/src/pantheon/local-decision-turn.ts +101 -0
- package/src/pantheon/local-decision-usage-evidence.internal.ts +168 -0
- package/src/pantheon/local-orchestration.ts +322 -0
- package/src/pantheon/model-pricing.ts +1 -536
- package/src/pantheon/pantheon-decision-catalog.ts +101 -0
- package/src/pantheon/v2-decision-budget.ts +456 -0
- package/src/pantheon/v2-decision-contracts.ts +300 -0
- package/src/pantheon/v2-decision-egress.ts +203 -0
- package/src/pantheon/v2-decision-events.ts +180 -0
- package/src/pantheon/v2-decision-heuristic.ts +121 -0
- package/src/pantheon/v2-decision-points/p1-agent.ts +91 -0
- package/src/pantheon/v2-decision-points/p10-claims.ts +243 -0
- package/src/pantheon/v2-decision-points/p11-catalog.ts +220 -0
- package/src/pantheon/v2-decision-points/p2-skill.ts +83 -0
- package/src/pantheon/v2-decision-points/p3-complexity.ts +108 -0
- package/src/pantheon/v2-decision-points/p4-memory.ts +137 -0
- package/src/pantheon/v2-decision-points/p5-themis-verify.ts +190 -0
- package/src/pantheon/v2-decision-points/p6-council.ts +161 -0
- package/src/pantheon/v2-decision-points/p7-loop.ts +263 -0
- package/src/pantheon/v2-decision-points/p8-guardrail.ts +367 -0
- package/src/pantheon/v2-decision-points/p9-memory-compaction.ts +304 -0
- package/src/pantheon/v2-decision-points.ts +242 -0
- package/src/pantheon/v2-decision-policy.ts +166 -0
- package/src/pantheon/v2-decision-premises.ts +146 -0
- package/src/pantheon/v2-decision-prompt-surface.ts +115 -0
- package/src/pantheon/v2-decision-rank.ts +91 -0
- package/src/pantheon/v2-decision-registry.ts +391 -0
- package/src/pantheon/v2-decision-resource-ids.ts +127 -0
- package/src/pantheon/v2-decision-shadow.ts +123 -0
- package/src/pantheon/v2-decision-telemetry.ts +214 -0
- package/src/pantheon/v2-decision-verify.ts +51 -0
- package/src/pantheon/v2-hook-engine.ts +307 -0
- package/src/pantheon/v2-native-decisions.ts +365 -0
- package/src/pantheon/v2-shell-hooks.ts +66 -2
- package/src/pantheon/v2-tools.ts +38 -15
- package/src/plugin-v2.ts +419 -26
- package/src/plugin.ts +4 -0
- package/src/plugins/tui/THIRD_PARTY_NOTICES.md +24 -0
- package/src/plugins/tui/dist/server-v2.d.ts +19 -11
- package/src/plugins/tui/dist/server-v2.d.ts.map +1 -1
- package/src/plugins/tui/dist/server-v2.js +19 -666
- package/src/plugins/tui/dist/server-v2.js.map +1 -1
- package/src/plugins/tui/dist/tui-v2.d.ts +11 -203
- package/src/plugins/tui/dist/tui-v2.d.ts.map +1 -1
- package/src/plugins/tui/dist/tui-v2.js +187 -1917
- package/src/plugins/tui/dist/tui-v2.js.map +1 -1
- package/src/plugins/tui/dist/tui.js +1 -1
- package/src/plugins/tui/package-lock.json +17 -2
- package/src/plugins/tui/package.json +4 -2
- package/src/plugins/tui/src/cost-data.ts +607 -0
- package/src/plugins/tui/src/index-v2.tsx +213 -54
- package/src/plugins/tui/src/model-pricing.ts +536 -0
- package/src/plugins/tui/src/server-v2.ts +18 -838
- package/src/plugins/tui/tsdown.config.ts +28 -6
- package/src/plugins/tui/dist/quota-adapters.d.ts +0 -89
- package/src/plugins/tui/dist/quota-adapters.d.ts.map +0 -1
- package/src/plugins/tui/dist/quota-adapters.js +0 -1142
- package/src/plugins/tui/dist/quota-adapters.js.map +0 -1
- package/src/plugins/tui/dist/quota-cli.d.ts +0 -17
- package/src/plugins/tui/dist/quota-cli.d.ts.map +0 -1
- package/src/plugins/tui/dist/quota-cli.js +0 -184
- package/src/plugins/tui/dist/quota-cli.js.map +0 -1
- package/src/plugins/tui/dist/quota-rpc-UL2HuFRJ.js +0 -390
- package/src/plugins/tui/dist/quota-rpc-UL2HuFRJ.js.map +0 -1
- package/src/plugins/tui/src/go-key-diagnostic-ui.ts +0 -100
- package/src/plugins/tui/src/go-key-diagnostic.ts +0 -125
- package/src/plugins/tui/src/quota-adapters.ts +0 -1598
- package/src/plugins/tui/src/quota-cli.ts +0 -237
- package/src/plugins/tui/src/quota-rpc.ts +0 -209
- package/src/plugins/tui/src/quota-v2-model.ts +0 -1032
- package/src/plugins/tui/src/quota-v2.tsx +0 -986
package/bin/pantheon-init.mjs
CHANGED
|
@@ -60,6 +60,61 @@ function readVersion() {
|
|
|
60
60
|
}
|
|
61
61
|
}
|
|
62
62
|
|
|
63
|
+
/**
|
|
64
|
+
* Merge the TypeSafe decision-model provider entry into the user's
|
|
65
|
+
* `opencode.json` (never replaces existing keys; a non-JSON file is reported,
|
|
66
|
+
* never overwritten). Returns true, or a short failure reason.
|
|
67
|
+
*/
|
|
68
|
+
/**
|
|
69
|
+
* Merge (never overwrite) the TypeSafe decision-model entry into the user's
|
|
70
|
+
* OpenCode config, so choosing the TypeSafe route in the wizard needs only the
|
|
71
|
+
* user's own sign-in afterwards. The merge is additive: existing provider
|
|
72
|
+
* entries and an existing jev-1.14.0 model are preserved. Returns true, or a
|
|
73
|
+
* short failure reason for the installer to print.
|
|
74
|
+
*/
|
|
75
|
+
function provisionTypesafeProvider() {
|
|
76
|
+
const xdg = process.env.XDG_CONFIG_HOME
|
|
77
|
+
const home = process.env.HOME
|
|
78
|
+
const base = xdg && xdg.startsWith('/') ? xdg : `${home ?? '~'}/.config`
|
|
79
|
+
const candidates = [`${base}/opencode/opencode.json`]
|
|
80
|
+
if (home) candidates.push(`${home}/.config/opencode/opencode.json`)
|
|
81
|
+
const configPath = candidates.find((candidate) => fs.existsSync(candidate))
|
|
82
|
+
if (configPath === undefined) return 'opencode.json not found'
|
|
83
|
+
let data
|
|
84
|
+
try {
|
|
85
|
+
data = JSON.parse(fs.readFileSync(configPath, 'utf8'))
|
|
86
|
+
} catch {
|
|
87
|
+
return 'opencode.json is not plain JSON (comments?)'
|
|
88
|
+
}
|
|
89
|
+
data.providers ??= {}
|
|
90
|
+
data.providers['typesafe-ai'] ??= {}
|
|
91
|
+
data.providers['typesafe-ai'].models ??= {}
|
|
92
|
+
if (data.providers['typesafe-ai'].models['jev-1.14.0'] === undefined) {
|
|
93
|
+
data.providers['typesafe-ai'].models['jev-1.14.0'] = {
|
|
94
|
+
name: 'Jev (TypeSafe direct)',
|
|
95
|
+
modelID: 'jev-latest',
|
|
96
|
+
type: 'decision',
|
|
97
|
+
}
|
|
98
|
+
}
|
|
99
|
+
try {
|
|
100
|
+
fs.writeFileSync(configPath, `${JSON.stringify(data, null, 2)}\n`)
|
|
101
|
+
return true
|
|
102
|
+
} catch (error) {
|
|
103
|
+
return String(error instanceof Error ? error.message : error)
|
|
104
|
+
}
|
|
105
|
+
}
|
|
106
|
+
|
|
107
|
+
/** Value of a repeatable installer flag from the raw argv, or undefined. */
|
|
108
|
+
function readArgValue(name) {
|
|
109
|
+
const prefix = `${name}=`
|
|
110
|
+
for (let i = 1; i < process.argv.length; i++) {
|
|
111
|
+
const arg = process.argv[i]
|
|
112
|
+
if (arg === name) return process.argv[i + 1]
|
|
113
|
+
if (arg.startsWith(prefix)) return arg.slice(prefix.length)
|
|
114
|
+
}
|
|
115
|
+
return undefined
|
|
116
|
+
}
|
|
117
|
+
|
|
63
118
|
function printUsage() {
|
|
64
119
|
console.log('Pantheon OpenCode — Multi-agent orchestration platform')
|
|
65
120
|
console.log('')
|
|
@@ -78,12 +133,21 @@ function printUsage() {
|
|
|
78
133
|
console.log(' npx pantheon-opencode init --headless # Force non-interactive mode')
|
|
79
134
|
console.log(' npx pantheon-opencode init -y # Skip confirmations, use defaults')
|
|
80
135
|
console.log(' npx pantheon-opencode init --components agents,skills,instructions')
|
|
136
|
+
console.log(
|
|
137
|
+
' npx pantheon-opencode init --decision-model opencode-console-jev/jev-1.13 --decision-monthly-usd 5 --decision-per-decision-usd 0.10',
|
|
138
|
+
)
|
|
81
139
|
console.log(' npx pantheon-opencode init --opencode-version v1|v2|auto')
|
|
82
140
|
console.log(' npx pantheon-opencode init --preset <name> # Install and activate model preset')
|
|
83
141
|
console.log(
|
|
84
142
|
' npx pantheon-opencode init --merge-dev-config <path> # Merge a dev config (off by default)',
|
|
85
143
|
)
|
|
86
144
|
console.log(' npx pantheon-opencode set-tier <name> # Set active model preset (global)')
|
|
145
|
+
console.log(
|
|
146
|
+
' npx pantheon-opencode decision-router help|status|setup|preview|holds # read-only',
|
|
147
|
+
)
|
|
148
|
+
console.log(
|
|
149
|
+
' npx pantheon-opencode decision-router select|enable|consent|caps|period # explicit actions',
|
|
150
|
+
)
|
|
87
151
|
console.log(
|
|
88
152
|
' npx pantheon-opencode update [--stable] # Update package + re-run init (default: beta channel)',
|
|
89
153
|
)
|
|
@@ -192,6 +256,22 @@ async function main() {
|
|
|
192
256
|
process.exit(result.status ?? 1)
|
|
193
257
|
}
|
|
194
258
|
|
|
259
|
+
if (command === 'decision-router') {
|
|
260
|
+
const { DecisionRouterUsageError, runDecisionRouterCommand } = await import(
|
|
261
|
+
'../scripts/decision-router.mjs'
|
|
262
|
+
)
|
|
263
|
+
try {
|
|
264
|
+
await runDecisionRouterCommand(args.slice(1))
|
|
265
|
+
} catch (error) {
|
|
266
|
+
// A malformed command line is user input, not a crash: print one line and
|
|
267
|
+
// skip the stack the top-level handler would otherwise dump.
|
|
268
|
+
if (!(error instanceof DecisionRouterUsageError)) throw error
|
|
269
|
+
console.error(`Error: ${error.message}`)
|
|
270
|
+
process.exit(1)
|
|
271
|
+
}
|
|
272
|
+
return
|
|
273
|
+
}
|
|
274
|
+
|
|
195
275
|
// beta.5: one-command update — check npm dist-tag, install, re-init.
|
|
196
276
|
// Default channel is `beta` (the prerelease line); `--stable` uses `latest`.
|
|
197
277
|
if (command === 'update') {
|
|
@@ -316,9 +396,15 @@ async function main() {
|
|
|
316
396
|
!Array.isArray(options.components) ||
|
|
317
397
|
options.components.some(
|
|
318
398
|
(component) =>
|
|
319
|
-
![
|
|
320
|
-
|
|
321
|
-
|
|
399
|
+
![
|
|
400
|
+
'agents',
|
|
401
|
+
'skills',
|
|
402
|
+
'instructions',
|
|
403
|
+
'prompts',
|
|
404
|
+
'commands',
|
|
405
|
+
'plugins',
|
|
406
|
+
'runtime',
|
|
407
|
+
].includes(component),
|
|
322
408
|
) ||
|
|
323
409
|
options.clean !== false ||
|
|
324
410
|
!['v1', 'v2', 'auto'].includes(options.version) ||
|
|
@@ -405,6 +491,9 @@ async function main() {
|
|
|
405
491
|
'--merge-dev-config',
|
|
406
492
|
'--apply-plan',
|
|
407
493
|
'--save-plan',
|
|
494
|
+
'--decision-model',
|
|
495
|
+
'--decision-monthly-usd',
|
|
496
|
+
'--decision-per-decision-usd',
|
|
408
497
|
])
|
|
409
498
|
for (let i = 1; i < args.length; i++) {
|
|
410
499
|
const arg = args[i]
|
|
@@ -481,9 +570,17 @@ async function main() {
|
|
|
481
570
|
console.error(`❌ Invalid --version "${versionOpt}" — expected v1, v2 or auto`)
|
|
482
571
|
process.exit(1)
|
|
483
572
|
}
|
|
573
|
+
// The 2.0 deprecation front-run: the legacy plugin line is end-of-life.
|
|
574
|
+
// Loud warning now (the v1 code path still exists for legacy installs);
|
|
575
|
+
// the 2.0 removal turns this into a hard refusal.
|
|
576
|
+
if (versionOpt === 'v1') {
|
|
577
|
+
console.error(
|
|
578
|
+
'⚠️ --opencode-version v1 is DEPRECATED and will be removed in Pantheon 2.0 — the legacy plugin line is end-of-life. OpenCode 2.x hosts are the supported generation; remove the flag (auto detects the host).',
|
|
579
|
+
)
|
|
580
|
+
}
|
|
484
581
|
|
|
485
|
-
// Resolve the user's explicit selection separately from the defaults.
|
|
486
|
-
//
|
|
582
|
+
// Resolve the user's explicit selection separately from the defaults.
|
|
583
|
+
// Runtime and prompt templates are opt-in in both TTY and headless mode.
|
|
487
584
|
let componentSelection
|
|
488
585
|
try {
|
|
489
586
|
componentSelection = resolveComponentSelection(args, {
|
|
@@ -525,6 +622,9 @@ async function main() {
|
|
|
525
622
|
// installer's own default (`~/.config/opencode`), so the record lands next
|
|
526
623
|
// to the config the next run will read.
|
|
527
624
|
const fallbackTarget = isProject ? process.cwd() : resolveGlobalConfigDirectory(process.env)
|
|
625
|
+
let chosenTarget = reviewedPlan?.target.path ?? fallbackTarget
|
|
626
|
+
let hasAppliedWrites = false
|
|
627
|
+
let recoveryBackup = null
|
|
528
628
|
/**
|
|
529
629
|
* Persist the one-line record of this run. Bookkeeping is best-effort: a
|
|
530
630
|
* failure is reported, never fatal, and never changes the exit code.
|
|
@@ -532,7 +632,7 @@ async function main() {
|
|
|
532
632
|
* @param {{status: string, reason?: string|null, cancelPoint?: string|null, applied: boolean, target?: string}} outcome
|
|
533
633
|
*/
|
|
534
634
|
const recordRun = (outcome) => {
|
|
535
|
-
const recordTarget = outcome.target ?? result?.target ??
|
|
635
|
+
const recordTarget = outcome.target ?? result?.target ?? chosenTarget
|
|
536
636
|
const record = buildRunRecord({
|
|
537
637
|
status: outcome.status,
|
|
538
638
|
reason: outcome.reason ?? null,
|
|
@@ -610,16 +710,20 @@ async function main() {
|
|
|
610
710
|
// consumes Ctrl-C in raw mode while a question is on screen (that path is
|
|
611
711
|
// the interactive cancel above), so this covers the rest of the run.
|
|
612
712
|
const onInterrupt = createInterruptHandler({
|
|
613
|
-
message:
|
|
713
|
+
message: () =>
|
|
714
|
+
hasAppliedWrites
|
|
715
|
+
? S.interruptedAfterWrite(recoveryBackup)
|
|
716
|
+
: S.canceledAt(S.cancelPoints.interrupt),
|
|
614
717
|
json: isJson,
|
|
615
718
|
endGaugeLine,
|
|
616
719
|
onInterrupt: () => {
|
|
617
720
|
if (!isDryRun) {
|
|
618
721
|
recordRun({
|
|
619
|
-
status: 'canceled',
|
|
620
|
-
reason: 'canceled',
|
|
722
|
+
status: hasAppliedWrites ? 'partial' : 'canceled',
|
|
723
|
+
reason: hasAppliedWrites ? 'interrupted' : 'canceled',
|
|
621
724
|
cancelPoint: 'interrupt',
|
|
622
|
-
applied:
|
|
725
|
+
applied: hasAppliedWrites,
|
|
726
|
+
target: chosenTarget,
|
|
623
727
|
})
|
|
624
728
|
}
|
|
625
729
|
},
|
|
@@ -688,7 +792,21 @@ async function main() {
|
|
|
688
792
|
quiet: isJson,
|
|
689
793
|
verbose: args.includes('--verbose') && !isJson,
|
|
690
794
|
configPreview,
|
|
795
|
+
onTargetResolved: (resolvedTarget) => {
|
|
796
|
+
chosenTarget = resolvedTarget
|
|
797
|
+
},
|
|
798
|
+
onWrite: ({ target: writeTarget, backupDir }) => {
|
|
799
|
+
hasAppliedWrites = true
|
|
800
|
+
chosenTarget = writeTarget
|
|
801
|
+
if (backupDir) recoveryBackup = backupDir
|
|
802
|
+
},
|
|
691
803
|
})
|
|
804
|
+
// File writers and the runtime installer use synchronous APIs. If SIGINT
|
|
805
|
+
// arrives during one of those calls, Node queues the signal callback
|
|
806
|
+
// until the event loop runs again. Keep the handler armed for one turn
|
|
807
|
+
// after the installer returns so a queued post-write interrupt is still
|
|
808
|
+
// recorded as partial instead of being lost to the success path.
|
|
809
|
+
await new Promise((resolve) => setImmediate(resolve))
|
|
692
810
|
} catch (err) {
|
|
693
811
|
installError = err
|
|
694
812
|
} finally {
|
|
@@ -711,8 +829,15 @@ async function main() {
|
|
|
711
829
|
`${S.installFailed(installError.message)}\n${S.failHintNoMcp}\n${S.failHintForce}`,
|
|
712
830
|
)
|
|
713
831
|
}
|
|
714
|
-
|
|
715
|
-
|
|
832
|
+
if (!isDryRun) {
|
|
833
|
+
const outcome = installError.installOutcome ?? {}
|
|
834
|
+
recordRun({
|
|
835
|
+
status: outcome.applied ? 'partial' : 'failed',
|
|
836
|
+
reason: 'failed',
|
|
837
|
+
applied: outcome.applied === true,
|
|
838
|
+
target: outcome.target ?? chosenTarget,
|
|
839
|
+
})
|
|
840
|
+
}
|
|
716
841
|
process.exitCode = 1
|
|
717
842
|
return
|
|
718
843
|
}
|
|
@@ -812,6 +937,7 @@ async function main() {
|
|
|
812
937
|
totals,
|
|
813
938
|
mcp_servers: mcpServers,
|
|
814
939
|
mcp_server_count: mcpServers.length,
|
|
940
|
+
runtime_effects: result.runtimeEffects ?? null,
|
|
815
941
|
files: files.map(({ path: filePath, action, bytes }) => ({
|
|
816
942
|
path: path.relative(result.target, filePath) || '.',
|
|
817
943
|
action,
|
|
@@ -881,7 +1007,10 @@ async function main() {
|
|
|
881
1007
|
const doctorStartedAt = Date.now()
|
|
882
1008
|
const { spawnSync } = await import('node:child_process')
|
|
883
1009
|
const doctorScript = path.join(ROOT, 'scripts', 'doctor.mjs')
|
|
884
|
-
const doctor = spawnSync(process.execPath, [doctorScript
|
|
1010
|
+
const doctor = spawnSync(process.execPath, [doctorScript, '--target', result.target], {
|
|
1011
|
+
stdio: 'inherit',
|
|
1012
|
+
cwd: ROOT,
|
|
1013
|
+
})
|
|
885
1014
|
const doctorSeconds = ((Date.now() - doctorStartedAt) / 1000).toFixed(1)
|
|
886
1015
|
// Never leave "Running health check..." as the last word: report the
|
|
887
1016
|
// outcome and duration, and propagate the child's exit code so CI sees
|
|
@@ -898,6 +1027,56 @@ async function main() {
|
|
|
898
1027
|
}
|
|
899
1028
|
}
|
|
900
1029
|
|
|
1030
|
+
// Optional Jev decision-model activation, requested at install time with
|
|
1031
|
+
// explicit caps (the setup-model chain: selection + enable + consent +
|
|
1032
|
+
// user/provider/model caps + period confirmation). Dry-run prints intent
|
|
1033
|
+
// only. Failures never fail the install itself.
|
|
1034
|
+
// Explicit flags win; otherwise honor the wizard's Jev activation choice.
|
|
1035
|
+
const wizardActivation = result.decisionModelActivation ?? null
|
|
1036
|
+
const decisionTarget = readArgValue('--decision-model') ?? wizardActivation?.target ?? null
|
|
1037
|
+
if (decisionTarget) {
|
|
1038
|
+
const monthly = readArgValue('--decision-monthly-usd') ?? wizardActivation?.monthly ?? '5'
|
|
1039
|
+
const perDecision =
|
|
1040
|
+
readArgValue('--decision-per-decision-usd') ?? wizardActivation?.perDecision ?? '0.10'
|
|
1041
|
+
const noConsent = process.argv.includes('--decision-no-consent')
|
|
1042
|
+
console.log('')
|
|
1043
|
+
if (isDryRun) {
|
|
1044
|
+
console.log(` ${S.jevDryRun(decisionTarget)}`)
|
|
1045
|
+
} else {
|
|
1046
|
+
try {
|
|
1047
|
+
const { runDecisionRouterCommand } = await import('../scripts/decision-router.mjs')
|
|
1048
|
+
await runDecisionRouterCommand(
|
|
1049
|
+
[
|
|
1050
|
+
'setup-model',
|
|
1051
|
+
decisionTarget,
|
|
1052
|
+
'--monthly-usd',
|
|
1053
|
+
monthly,
|
|
1054
|
+
'--per-decision-usd',
|
|
1055
|
+
perDecision,
|
|
1056
|
+
...(noConsent ? ['--no-consent'] : []),
|
|
1057
|
+
],
|
|
1058
|
+
{ stdout: (line) => console.log(` ${line}`) },
|
|
1059
|
+
)
|
|
1060
|
+
console.log(` ${S.jevConfigured(decisionTarget)}`)
|
|
1061
|
+
if (decisionTarget.startsWith('typesafe-jev')) {
|
|
1062
|
+
const provisioned = provisionTypesafeProvider()
|
|
1063
|
+
console.log(
|
|
1064
|
+
provisioned === true
|
|
1065
|
+
? ' TypeSafe provider entry merged into opencode.json (models.typesafe-ai, type "decision"). Sign in with `opencode auth login` (TypeSafe) or /connect.'
|
|
1066
|
+
: ` TypeSafe provider entry NOT merged (${provisioned}); merge it manually — see docs/reference/native-decisions.md.`,
|
|
1067
|
+
)
|
|
1068
|
+
}
|
|
1069
|
+
} catch (error) {
|
|
1070
|
+
console.error(
|
|
1071
|
+
` ${S.jevConfigureFailed(error instanceof Error ? error.message : String(error))}`,
|
|
1072
|
+
)
|
|
1073
|
+
console.error(
|
|
1074
|
+
` Fix later with: npx pantheon-opencode decision-router setup-model ${decisionTarget} --monthly-usd ${monthly} --per-decision-usd ${perDecision}`,
|
|
1075
|
+
)
|
|
1076
|
+
}
|
|
1077
|
+
}
|
|
1078
|
+
}
|
|
1079
|
+
|
|
901
1080
|
console.log('')
|
|
902
1081
|
console.log('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━')
|
|
903
1082
|
console.log(` ${S.installedTitle(version)}`)
|
|
@@ -908,6 +1087,9 @@ async function main() {
|
|
|
908
1087
|
console.log(` ${S.nextLaunch}`)
|
|
909
1088
|
console.log(` ${S.nextAgents}`)
|
|
910
1089
|
console.log(` ${S.nextProject}`)
|
|
1090
|
+
if (!decisionTarget) {
|
|
1091
|
+
console.log(` ${S.nextJev}`)
|
|
1092
|
+
}
|
|
911
1093
|
console.log('')
|
|
912
1094
|
|
|
913
1095
|
return
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "pantheon-opencode",
|
|
3
|
-
"version": "1.6.2-beta.
|
|
3
|
+
"version": "1.6.2-beta.10",
|
|
4
4
|
"description": "Multi-agent orchestration for OpenCode — 14 specialized agents, TDD, Themis review gates.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"workspaces": [
|
|
@@ -11,6 +11,7 @@
|
|
|
11
11
|
"registry": "https://registry.npmjs.org/"
|
|
12
12
|
},
|
|
13
13
|
"exports": {
|
|
14
|
+
"./local-decision-router": "./src/pantheon/local-decision-router.ts",
|
|
14
15
|
"./plugin": "./src/plugin.ts",
|
|
15
16
|
"./plugin-v2": "./src/plugin-v2.ts",
|
|
16
17
|
"./v2-bridge": "./src/pantheon/v2-bridge.ts"
|
|
@@ -20,6 +21,8 @@
|
|
|
20
21
|
"prepare": "husky",
|
|
21
22
|
"setup": "node scripts/setup.mjs",
|
|
22
23
|
"build:agents-md": "node scripts/build-agents-md.mjs",
|
|
24
|
+
"build:decision-router": "node scripts/build-decision-router.mjs",
|
|
25
|
+
"check:decision-router": "node scripts/build-decision-router.mjs --check",
|
|
23
26
|
"skills:lock": "node scripts/update-skills-lock.mjs",
|
|
24
27
|
"setup:lite": "node bin/pantheon-init.mjs init --yes --clean --components agents,skills,instructions",
|
|
25
28
|
"doctor": "node scripts/doctor.mjs",
|
|
@@ -27,7 +30,8 @@
|
|
|
27
30
|
"init": "node bin/pantheon-init.mjs init --yes",
|
|
28
31
|
"opencode": "OPENCODE_EXPERIMENTAL_BACKGROUND_SUBAGENTS=true opencode",
|
|
29
32
|
"start": "OPENCODE_EXPERIMENTAL_BACKGROUND_SUBAGENTS=true opencode",
|
|
30
|
-
"
|
|
33
|
+
"prepack": "npm run check:decision-router",
|
|
34
|
+
"prepublishOnly": "node scripts/validate-routing.mjs && npm run check:decision-router",
|
|
31
35
|
"postpublish": "node -e \"console.log('✅ Published pantheon-opencode v' + require('./package.json').version + ' to npm')\"",
|
|
32
36
|
"version:status": "node scripts/versioning.mjs status",
|
|
33
37
|
"version:apply": "node scripts/versioning.mjs apply",
|
|
@@ -35,7 +39,7 @@
|
|
|
35
39
|
"release:dry-run": "node scripts/versioning.mjs status && node scripts/release-notes.mjs && node scripts/package-evidence.mjs",
|
|
36
40
|
"package:evidence": "node scripts/package-evidence.mjs",
|
|
37
41
|
"engine:check": "node scripts/validate-node-engine-policy.mjs",
|
|
38
|
-
"package:validate": "node scripts/validate-package.mjs && npm run engine:check",
|
|
42
|
+
"package:validate": "node scripts/validate-package.mjs && npm run check:decision-router && npm run engine:check",
|
|
39
43
|
"lint": "biome ci .",
|
|
40
44
|
"docs:lint": "node scripts/docs-link-check.mjs",
|
|
41
45
|
"docs:media": "node scripts/docs-media.mjs",
|
|
@@ -87,6 +91,7 @@
|
|
|
87
91
|
"src/instructions/*.instructions.md",
|
|
88
92
|
"src/mcp/*.mjs",
|
|
89
93
|
"scripts/*.mjs",
|
|
94
|
+
"!scripts/build-decision-router.mjs",
|
|
90
95
|
"src/mcp/*.sh",
|
|
91
96
|
"src/routing.yml",
|
|
92
97
|
"src/pantheon/**",
|
|
@@ -100,6 +105,7 @@
|
|
|
100
105
|
"src/plugins/tui/**",
|
|
101
106
|
"!src/plugins/tui/node_modules/**",
|
|
102
107
|
"src/skills/**",
|
|
108
|
+
"prompts/**",
|
|
103
109
|
"!**/__pycache__/**",
|
|
104
110
|
"!**/*.pyc"
|
|
105
111
|
],
|
|
@@ -114,7 +120,9 @@
|
|
|
114
120
|
"@biomejs/biome": "2.5.14",
|
|
115
121
|
"@commitlint/cli": "21.2.3",
|
|
116
122
|
"@commitlint/config-conventional": "21.2.3",
|
|
123
|
+
"@opencode/plugin": "2.2.5",
|
|
117
124
|
"ajv": "8.20.0",
|
|
125
|
+
"esbuild": "0.28.2",
|
|
118
126
|
"husky": "^9.1.7",
|
|
119
127
|
"tsx": "4.23.15",
|
|
120
128
|
"typescript": "7.0.2"
|
package/plugin.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "pantheon",
|
|
3
3
|
"publisher": "ils15",
|
|
4
|
-
"version": "1.6.2-beta.
|
|
4
|
+
"version": "1.6.2-beta.10",
|
|
5
5
|
"displayName": "Pantheon",
|
|
6
6
|
"description": "Conductor-Delegate orchestration platform with 14 specialized agents, 20 skills, and OpenCode support.",
|
|
7
7
|
"agents": "./src/agents",
|
|
@@ -0,0 +1,58 @@
|
|
|
1
|
+
# Prompt Files
|
|
2
|
+
|
|
3
|
+
Reusable prompt templates for common development workflows. Each prompt
|
|
4
|
+
specifies a target agent, required tools, and structured instructions.
|
|
5
|
+
|
|
6
|
+
## Available Prompts (10)
|
|
7
|
+
|
|
8
|
+
| Prompt | Agent | Purpose |
|
|
9
|
+
|---|---|---|
|
|
10
|
+
| **orchestrate-with-zeus** | Zeus | Full feature orchestration — planning, implementation, review, deployment |
|
|
11
|
+
| **implement-feature** | Zeus | End-to-end feature implementation with TDD and quality gates |
|
|
12
|
+
| **plan-architecture** | Athena | Strategic architecture planning with research and TDD-driven plan |
|
|
13
|
+
| **debug-issue** | Apollo | Rapid debugging with parallel file discovery and analysis |
|
|
14
|
+
| **optimize-database** | Demeter | Database schema, query, and performance optimization |
|
|
15
|
+
| **focus** | Zeus | Pin a session goal to keep all work aligned with a single objective |
|
|
16
|
+
| **sketch** | Athena | Interview a rough idea into a structured feature spec (3–5 questions) |
|
|
17
|
+
| **subtask** | Zeus | Delegate a bounded child task to a specialist and receive a structured result |
|
|
18
|
+
| **quick-discovery-large-codebase** | Apollo | Fast-path bounded discovery for large codebases (8-minute cap) |
|
|
19
|
+
| **quick-plan-large-feature** | Athena | Fast-path bounded planning for large features (5-minute cap) |
|
|
20
|
+
|
|
21
|
+
## Usage
|
|
22
|
+
|
|
23
|
+
Prompt templates are **not** slash commands. OpenCode slash commands live in
|
|
24
|
+
`commands/` and are invoked in chat:
|
|
25
|
+
|
|
26
|
+
```text
|
|
27
|
+
/pantheon Add CSV export to the reports page, including tests and a review.
|
|
28
|
+
/pantheon-audit Changes in src/auth/
|
|
29
|
+
/pantheon-focus Implement email verification end-to-end with TDD
|
|
30
|
+
/pantheon-deepwork Migrate the billing module
|
|
31
|
+
/pantheon-model status
|
|
32
|
+
/pantheon-optimize
|
|
33
|
+
/pantheon-vision
|
|
34
|
+
/pantheon-consolidate
|
|
35
|
+
```
|
|
36
|
+
|
|
37
|
+
The templates in this directory are loaded by the command or agent that needs
|
|
38
|
+
them; they are not invoked directly by filename. In particular:
|
|
39
|
+
|
|
40
|
+
- `focus.prompt.md` is used by `/pantheon-focus`.
|
|
41
|
+
- The audit guidance is used by `/pantheon-audit`.
|
|
42
|
+
- `sketch.prompt.md` has **no matching command file**, so it is available as a
|
|
43
|
+
template only. There is currently no `/sketch` command.
|
|
44
|
+
|
|
45
|
+
For the full command list, see the commands directory in the repository. For
|
|
46
|
+
agent roles, see `docs/agents/README.md`.
|
|
47
|
+
|
|
48
|
+
## Placeholder contract
|
|
49
|
+
|
|
50
|
+
OpenCode expands `$ARGUMENTS` and positional values such as `$1` in slash
|
|
51
|
+
commands. Those are command-runtime variables; prompt templates do not expand
|
|
52
|
+
`$input`, shell variables, angle-bracket examples, or JSON braces.
|
|
53
|
+
|
|
54
|
+
Manual prompt-template inputs use `{{UPPER_SNAKE_CASE}}`, for example
|
|
55
|
+
`{{TASK_INPUT}}` or `{{TARGET_AGENT}}`. The command or agent that loads the
|
|
56
|
+
template fills these fields before dispatch. This repository does not perform
|
|
57
|
+
automatic placeholder substitution or escaping, so callers must insert values
|
|
58
|
+
as data and preserve their intended quoting and boundaries.
|
|
@@ -0,0 +1,46 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: debug-issue
|
|
3
|
+
description: "Rapidly debug issues with parallel file discovery and analysis"
|
|
4
|
+
agent: apollo
|
|
5
|
+
tools: ['search', 'usages']
|
|
6
|
+
---
|
|
7
|
+
|
|
8
|
+
# Debug Quickly (Apollo - Scout)
|
|
9
|
+
|
|
10
|
+
## Adaptive Search Strategy
|
|
11
|
+
|
|
12
|
+
Choose only the independent searches that fit the report. These are candidate
|
|
13
|
+
angles, not a required fan-out; a focused bug may need only one or two:
|
|
14
|
+
|
|
15
|
+
Search 1: Exact error message
|
|
16
|
+
Search 2: Mentioned function/class
|
|
17
|
+
Search 3: Related file patterns
|
|
18
|
+
Search 4: Similar test cases
|
|
19
|
+
Search 5: Related issues/PRs
|
|
20
|
+
Search 6: Stack trace patterns
|
|
21
|
+
Search 7: Config files
|
|
22
|
+
Search 8: Logging statements
|
|
23
|
+
Search 9: Mentioned dependencies
|
|
24
|
+
Search 10: Recent changes in area
|
|
25
|
+
|
|
26
|
+
## Analysis & Synthesis
|
|
27
|
+
- Eliminate duplicates
|
|
28
|
+
- Identify file relationships
|
|
29
|
+
- Extract patterns
|
|
30
|
+
- Return prioritized findings
|
|
31
|
+
|
|
32
|
+
## Recommendations
|
|
33
|
+
|
|
34
|
+
After analysis, @apollo returns:
|
|
35
|
+
1. **Root Cause Hypothesis**: What's probably wrong
|
|
36
|
+
2. **Key Files**: Most relevant files
|
|
37
|
+
3. **Reproduction Steps**: How to reproduce
|
|
38
|
+
4. **Suggested Fix**: Solution direction
|
|
39
|
+
5. **Next Steps**: Next agents to involve
|
|
40
|
+
|
|
41
|
+
## When to Use
|
|
42
|
+
- Bug report received
|
|
43
|
+
- Confusing error stack trace
|
|
44
|
+
- Performance issue diagnosis
|
|
45
|
+
- Regression debugging
|
|
46
|
+
- When you need quick exploration
|
|
@@ -0,0 +1,38 @@
|
|
|
1
|
+
# =============================================================================
|
|
2
|
+
# Dynamic Agora Prompt
|
|
3
|
+
# Generated: 2026-05-16T13:50:41Z
|
|
4
|
+
# Plan: copilot-free
|
|
5
|
+
# Service: vscode
|
|
6
|
+
# Tier: free
|
|
7
|
+
# Price: $0/mo
|
|
8
|
+
# Monthly Requests: 50
|
|
9
|
+
# =============================================================================
|
|
10
|
+
|
|
11
|
+
You are convening an agora with access to these specialists: aphrodite,apollo athena demeter gaia hephaestus,hermes iris,mnemosyne nyx,prometheus talos,themis zeus
|
|
12
|
+
|
|
13
|
+
## Platform Capabilities
|
|
14
|
+
Agent Overrides:
|
|
15
|
+
themis: anthropic/claude-sonnet-4-6
|
|
16
|
+
zeus: anthropic/claude-sonnet-4-6
|
|
17
|
+
|
|
18
|
+
## Instructions
|
|
19
|
+
1. Select 3-5 relevant agents based on the question domain
|
|
20
|
+
2. Dispatch them in parallel with the same question
|
|
21
|
+
3. Synthesize their perspectives into a single recommendation
|
|
22
|
+
4. Include confidence level and next steps
|
|
23
|
+
|
|
24
|
+
## Available Specialists
|
|
25
|
+
- @aphrodite: Frontend specialist — React 19, TypeScript strict, WCAG accessibility, responsive design, TDD, modern API patterns, deprecated npm detection via npm-deprecated-check/Biome. Calls apollo as nested subagent to discover components. Sends work to themis for review.
|
|
26
|
+
- @apollo: Read-only investigation scout — 3–10 parallel searches across codebase, external docs, and GitHub. Called by: athena, zeus, hermes, aphrodite, demeter. No edits, no commands.
|
|
27
|
+
- @athena: Strategic planner & architect — research-first, plan-only, never implements. Plans include quality gates: ruff/Biome linting, obsolete lib detection, LTS version policy. Calls apollo as nested subagent for complex discovery.
|
|
28
|
+
- @demeter: Database specialist — SQLAlchemy 2.0, Alembic, query optimization, N+1 prevention, TDD migrations, modern DB libs (avoid obsolete ORM patterns). Calls apollo as nested subagent for optimization patterns. Sends work to themis for review.
|
|
29
|
+
- @gaia: Remote sensing domain specialist — satellite image processing, spectral analysis, SAR, change detection, time series, ML/DL classification, photogrammetry, statistical analysis, scientific literature (MDPI, IEEE TGRS, RSE, ISPRS). Covers full RS pipeline from raw image to product. Calls apollo for discovery. Sends work to themis for review.
|
|
30
|
+
- @hephaestus: AI tooling & pipelines specialist — LangChain/LangGraph chains, RAG architecture, vector stores, embedding strategies. Forges the AI infrastructure agents need. Calls apollo for discovery. Sends work to themis for review.
|
|
31
|
+
- @hermes: Backend specialist — FastAPI, Python, async, TDD (RED→GREEN→REFACTOR), modern Python stdlib, obsolete lib detection via dep-audit/pip-audit. Calls apollo as nested subagent to discover patterns. Sends work to themis for review.
|
|
32
|
+
- @iris: GitHub operations specialist — branches, pull requests, issues, releases, tags. Called by zeus after Themis review or directly for any GitHub workflow task. Never pushes or merges without explicit human approval.
|
|
33
|
+
- @mnemosyne: Memory bank quality owner — initializes .pantheon/memory-bank/, writes ADRs and task records on explicit request. Called by zeus. Never invoked automatically after phases.
|
|
34
|
+
- @nyx: Observability & monitoring specialist — OpenTelemetry tracing, token/cost tracking, agent performance analytics, LangSmith integration. Sees what others cannot in the dark. Calls apollo for discovery. Sends work to themis for review.
|
|
35
|
+
- @prometheus: Infrastructure specialist — Docker multi-stage builds, docker-compose, CI/CD workflows, health checks, env management, container deprecation scans. Calls apollo as nested subagent for pattern discovery. Sends work to themis for validation.
|
|
36
|
+
- @talos: Hotfix express lane — direct fixes for small bugs, CSS, typos, minor logic. No TDD ceremony, no orchestration overhead. Standalone, no subagents. Escalates complex issues to zeus.
|
|
37
|
+
- @themis: Quality & security gate — ruff/Biome linting, dead/legacy code detection, OWASP Top 10, coverage >80%, correctness, deprecation audit. Called by: hermes, aphrodite, demeter, zeus. Escalates blockers to zeus.
|
|
38
|
+
- @zeus: Central orchestrator — never implements. Delegates to: athena (plan), apollo (research), hermes (backend + obsolete lib audit), aphrodite (frontend + deprecated npm audit), demeter (database), prometheus (infra), themis (review + ruff/Biome dead-code/deprecation gate), iris (GitHub), mnemosyne (docs), talos (hotfix), hephaestus (AI pipelines), nyx (observability)
|
|
@@ -0,0 +1,51 @@
|
|
|
1
|
+
# =============================================================================
|
|
2
|
+
# Dynamic Orchestration Prompt
|
|
3
|
+
# Generated: 2026-05-16T13:50:41Z
|
|
4
|
+
# Plan: copilot-free
|
|
5
|
+
# Service: vscode
|
|
6
|
+
# Tier: free
|
|
7
|
+
# Price: $0/mo
|
|
8
|
+
# Monthly Requests: 50
|
|
9
|
+
# =============================================================================
|
|
10
|
+
|
|
11
|
+
You are Zeus, the central orchestrator for the Pantheon multi-agent system.
|
|
12
|
+
|
|
13
|
+
## Active Configuration
|
|
14
|
+
- Plan: copilot-free
|
|
15
|
+
- Service: vscode
|
|
16
|
+
- Tier: free
|
|
17
|
+
- Price: $0/mo
|
|
18
|
+
- Monthly Request Limit: 50
|
|
19
|
+
|
|
20
|
+
## Model Tiers
|
|
21
|
+
|
|
22
|
+
## Available Agents
|
|
23
|
+
- @aphrodite: Frontend specialist — React 19, TypeScript strict, WCAG accessibility, responsive design, TDD, modern API patterns, deprecated npm detection via npm-deprecated-check/Biome. Calls apollo as nested subagent to discover components. Sends work to themis for review.
|
|
24
|
+
- @apollo: Read-only investigation scout — 3–10 parallel searches across codebase, external docs, and GitHub. Called by: athena, zeus, hermes, aphrodite, demeter. No edits, no commands.
|
|
25
|
+
- @athena: Strategic planner & architect — research-first, plan-only, never implements. Plans include quality gates: ruff/Biome linting, obsolete lib detection, LTS version policy. Calls apollo as nested subagent for complex discovery.
|
|
26
|
+
- @demeter: Database specialist — SQLAlchemy 2.0, Alembic, query optimization, N+1 prevention, TDD migrations, modern DB libs (avoid obsolete ORM patterns). Calls apollo as nested subagent for optimization patterns. Sends work to themis for review.
|
|
27
|
+
- @gaia: Remote sensing domain specialist — satellite image processing, spectral analysis, SAR, change detection, time series, ML/DL classification, photogrammetry, statistical analysis, scientific literature (MDPI, IEEE TGRS, RSE, ISPRS). Covers full RS pipeline from raw image to product. Calls apollo for discovery. Sends work to themis for review.
|
|
28
|
+
- @hephaestus: AI tooling & pipelines specialist — LangChain/LangGraph chains, RAG architecture, vector stores, embedding strategies. Forges the AI infrastructure agents need. Calls apollo for discovery. Sends work to themis for review.
|
|
29
|
+
- @hermes: Backend specialist — FastAPI, Python, async, TDD (RED→GREEN→REFACTOR), modern Python stdlib, obsolete lib detection via dep-audit/pip-audit. Calls apollo as nested subagent to discover patterns. Sends work to themis for review.
|
|
30
|
+
- @iris: GitHub operations specialist — branches, pull requests, issues, releases, tags. Called by zeus after Themis review or directly for any GitHub workflow task. Never pushes or merges without explicit human approval.
|
|
31
|
+
- @mnemosyne: Memory bank quality owner — initializes .pantheon/memory-bank/, writes ADRs and task records on explicit request. Called by zeus. Never invoked automatically after phases.
|
|
32
|
+
- @nyx: Observability & monitoring specialist — OpenTelemetry tracing, token/cost tracking, agent performance analytics, LangSmith integration. Sees what others cannot in the dark. Calls apollo for discovery. Sends work to themis for review.
|
|
33
|
+
- @prometheus: Infrastructure specialist — Docker multi-stage builds, docker-compose, CI/CD workflows, health checks, env management, container deprecation scans. Calls apollo as nested subagent for pattern discovery. Sends work to themis for validation.
|
|
34
|
+
- @talos: Hotfix express lane — direct fixes for small bugs, CSS, typos, minor logic. No TDD ceremony, no orchestration overhead. Standalone, no subagents. Escalates complex issues to zeus.
|
|
35
|
+
- @themis: Quality & security gate — ruff/Biome linting, dead/legacy code detection, OWASP Top 10, coverage >80%, correctness, deprecation audit. Called by: hermes, aphrodite, demeter, zeus. Escalates blockers to zeus.
|
|
36
|
+
- @zeus: Central orchestrator — never implements. Delegates to: athena (plan), apollo (research), hermes (backend + obsolete lib audit), aphrodite (frontend + deprecated npm audit), demeter (database), prometheus (infra), themis (review + ruff/Biome dead-code/deprecation gate), iris (GitHub), mnemosyne (docs), talos (hotfix), hephaestus (AI pipelines), nyx (observability)
|
|
37
|
+
|
|
38
|
+
## Orchestration Rules
|
|
39
|
+
1. **Planning**: Delegate to @athena for architecture decisions
|
|
40
|
+
2. **Discovery**: Delegate to @apollo for codebase investigation
|
|
41
|
+
3. **Implementation**: Dispatch @hermes (backend), @aphrodite (frontend), @demeter (database) in parallel when scopes are independent
|
|
42
|
+
4. **Review**: Always route completed work to @themis before merge
|
|
43
|
+
5. **Deploy**: Route infrastructure changes to @prometheus
|
|
44
|
+
6. **Document**: Route memory tasks to @mnemosyne
|
|
45
|
+
7. **Hotfix**: Route small fixes to @talos (bypass orchestration)
|
|
46
|
+
|
|
47
|
+
## Cost-Conscious Routing
|
|
48
|
+
- Use `fast` tier agents for discovery, documentation, and simple queries
|
|
49
|
+
- Use `default` tier agents for standard implementation work
|
|
50
|
+
- Use `premium` tier agents for planning, review, and complex orchestration
|
|
51
|
+
- Respect monthly request limits: 50
|
|
@@ -0,0 +1,42 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: focus
|
|
3
|
+
description: "Pin a session goal to keep all todos, delegation decisions, and verification steps aligned with a single stated objective"
|
|
4
|
+
agent: zeus
|
|
5
|
+
tools: ['search']
|
|
6
|
+
---
|
|
7
|
+
|
|
8
|
+
# Pin Session Goal (Zeus + Session-Goal Skill)
|
|
9
|
+
|
|
10
|
+
## Session Goal
|
|
11
|
+
|
|
12
|
+
**Goal:** {{TASK_INPUT}}
|
|
13
|
+
|
|
14
|
+
---
|
|
15
|
+
|
|
16
|
+
## What to do
|
|
17
|
+
|
|
18
|
+
1. Confirm the goal is clear and actionable. If ambiguous, ask one clarifying question.
|
|
19
|
+
2. Format the goal using the 4-component structure below.
|
|
20
|
+
3. Write the pinned goal to `.pantheon/memory-bank/.tmp/current-goal.md`.
|
|
21
|
+
4. Announce the pinned goal in chat and confirm readiness to proceed.
|
|
22
|
+
|
|
23
|
+
---
|
|
24
|
+
|
|
25
|
+
## Goal Format
|
|
26
|
+
|
|
27
|
+
```
|
|
28
|
+
GOAL: {{WHAT_TO_BUILD}}
|
|
29
|
+
SCOPE: {{SCOPE}}
|
|
30
|
+
SUCCESS CRITERIA: {{SUCCESS_CRITERIA}}
|
|
31
|
+
OUT OF SCOPE: {{OUT_OF_SCOPE}}
|
|
32
|
+
```
|
|
33
|
+
|
|
34
|
+
---
|
|
35
|
+
|
|
36
|
+
## Alignment Rules (apply for the rest of this session)
|
|
37
|
+
|
|
38
|
+
- Every todo must relate to this goal
|
|
39
|
+
- Zeus invokes only agents relevant to this goal
|
|
40
|
+
- Themis checks that implementations serve this goal
|
|
41
|
+
- If a task drifts from the goal, flag it before proceeding
|
|
42
|
+
- Never change the goal silently — confirm with the user first
|