Skip to content

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

feat(quality): audit measured CI efficiency and stage placement

Adam Eivyf50d98fe4bae
diff --git a/server/lib/auditQuality.js b/server/lib/auditQuality.js
index 6ec822dd21..a1f8599acd 100644
--- a/server/lib/auditQuality.js
+++ b/server/lib/auditQuality.js
@@ -32,7 +32,7 @@ export const AUDIT_DISCOVERY = Object.freeze({
'better-dependency-freedom': 'Inventory manifests and actual imports across packages; rank dependency cost, advisory exposure and removable surface against the complexity of a concrete replacement.',
'better-test-quality': 'Inventory suites and public boundaries; search assertion-free tests, overmocking, tautologies and redundant cases, prioritizing suites that falsely protect critical behavior.',
'better-dev-environment': 'Diff host state around one bounded run of the dev commands (see the mission), then inventory the fixture, spawn, watcher and cache sites behind each change; rank by what accumulates per run times how often the loop runs.',
- infrastructure: 'Inventory infrastructure-as-code, container, orchestration, deployment and CI files; scan exposure, identity grants, secrets, pinning, resource limits and probes, ranking reachable production exposure and irreproducible deploys first.',
+ infrastructure: 'Inventory infrastructure-as-code, container, orchestration, deployment and CI files; scan exposure, identity grants, secrets, pinning, resource limits and probes, rank deployment risk alongside measured CI waste. Trace CI planners/runners; measure run frequency, job duration and critical path, then inspect trigger/path selection, duplicate work, dependencies, cache/artifact reuse, cancellation/concurrency and risk-based PR/MR versus merge/nightly/release placement. Coordinate test-value evidence with Test Quality; preserve essential correctness/security coverage.',
'data-integrity': 'Inventory every write path, ingestion entry point, consumer, batch/backfill job and stored data format; trace retry and redelivery behavior and multi-step writes, ranking silent duplication, loss and wrong results first.',
reliability: 'Inventory process entry points, signal handling, health endpoints, queues, workers and scheduled jobs; trace shutdown, restart, overload and multi-instance behavior, ranking dropped work and outage amplification first.',
privacy: 'Inventory personal and sensitive fields in schemas and payloads, then trace them to logs, errors, analytics, caches, exports, third-party calls and deletion paths; rank exposure already happening over missing governance.',
diff --git a/server/services/cosTaskGenerator.auditMode.test.js b/server/services/cosTaskGenerator.auditMode.test.js
index 70724e6f02..4db99a33c3 100644
--- a/server/services/cosTaskGenerator.auditMode.test.js
+++ b/server/services/cosTaskGenerator.auditMode.test.js
@@ -188,6 +188,41 @@ describe('issues-only audit dispatch never acquires code-shipping instructions (
}
});
+ it.each([true, false])('infrastructure renders measured CI efficiency and safe delivery with fileIssues=%s', async (fileIssues) => {
+ const { DEFAULT_TASK_PROMPTS } = await import('./taskPromptDefaults.js');
+ const { getTaskInterval } = await import('./taskSchedule.js');
+ promptTemplate.body = DEFAULT_TASK_PROMPTS.infrastructure;
+ getTaskInterval.mockResolvedValue({ type: 'on-demand', taskMetadata: { fileIssues, useWorktree: true, openPR: true } });
+ const task = await generate('infrastructure');
+ const prompt = renderPrompt(task);
+ for (const instruction of [
+ 'CI efficiency and placement', 'sample window and count', 'execution frequency',
+ 'summed runner time', 'critical path', 'measured avoidable runner time',
+ 'coverage/required-check failure', 'trigger/path selection', 'affected-test',
+ 'duplicate work', 'unnecessary serialization', 'cache hits/misses',
+ 'artifact upload/download cost', 'superseded-run', 'risk-based PR/MR',
+ 'stronger surviving coverage', 'A slow test is not a valueless test',
+ 'representative', 'required-check behavior', 'do not invent savings',
+ 'preserve essential correctness/security coverage',
+ ]) expect(prompt).toContain(instruction);
+ expect(prompt).not.toContain('{modeInstructions}');
+ if (fileIssues) {
+ expectNoCodeDelivery(prompt, 'infrastructure');
+ expect(prompt).toContain('Mode: file issues, change nothing');
+ } else {
+ expect(task.metadata.fileIssues).toBe(false);
+ expect(task.metadata.noCodeOutput).not.toBe(true);
+ expect(prompt).toContain('Mode: audit and fix');
+ expect(prompt).toContain('## Completion Workflow');
+ }
+ });
+
+ it('keeps CI-efficiency discovery in customized infrastructure prompts', async () => {
+ const task = await generate('infrastructure');
+ expect(renderPrompt(task)).toContain('measure run frequency, job duration and critical path');
+ expect(renderPrompt(task)).toContain('preserve essential correctness/security coverage');
+ });
+
it('bails out before generating an audit that cannot apply, advancing the cadence', async () => {
applicability.inapplicable = { 'mobile-responsive': 'no user interface found in this repository' };
const { recordExecution } = await import('./taskSchedule.js');
diff --git a/server/services/taskPromptDefaults/integrity.snapshot.json b/server/services/taskPromptDefaults/integrity.snapshot.json
index 7f638a04d8..2087771a3c 100644
--- a/server/services/taskPromptDefaults/integrity.snapshot.json
+++ b/server/services/taskPromptDefaults/integrity.snapshot.json
@@ -30,7 +30,7 @@
"error-handling": "137b371f38398042c0a2c7e2279c92ce",
"feature-completeness": "00d8916cc6032e74817657375375115b",
"feature-ideas": "804f62f1dadadbfa8a0bcd4aff16b2e8",
- "infrastructure": "b4ad755eb115b82679c601a0df1ffd7b",
+ "infrastructure": "bd31db72a371136f6c32d119d76c0281",
"issue-reconcile": "716c87476d77d7e4f98613dadc06f228",
"jira-sprint-manager": "3e63c8a3bdf0d5a05a30faaa2dc07980",
"jira-status-report": "9d374a9d8ccb92c5c8fd0aa9899e79a5",
@@ -94,7 +94,7 @@
"error-handling": 3,
"feature-completeness": 1,
"feature-ideas": 11,
- "infrastructure": 1,
+ "infrastructure": 2,
"issue-reconcile": 8,
"jira-sprint-manager": 1,
"jira-status-report": 1,
@@ -341,6 +341,9 @@
"0741418bd275b8953131155f8bc89460",
"d3282f16da29efe2d53595b3b34778bc"
],
+ "infrastructure": [
+ "b4ad755eb115b82679c601a0df1ffd7b"
+ ],
"issue-reconcile": [
"6f33db6ad0b57c36909229694b78891a",
"c57a39aaa118173a496f030f5878bfc1",
diff --git a/server/services/taskPromptDefaults/prompts.js b/server/services/taskPromptDefaults/prompts.js
index fe8d767a60..f958517ff7 100644
--- a/server/services/taskPromptDefaults/prompts.js
+++ b/server/services/taskPromptDefaults/prompts.js
@@ -1906,6 +1906,46 @@ the project's documented deployment model decides which exposure is intended.
reads it) that disagree about a port, a variable, or a resource, so the first
deploy to the other one fails.
+## CI efficiency and placement
+
+This is part of the audit, alongside deployment safety. Trace workflow files
+through their planner, runners, scripts and required-check rules; YAML alone
+may hide what actually runs.
+
+- **Measure before changing.** Sample recent representative PR/MR, merge,
+ nightly and release runs, including a small change and a broad-risk change.
+ Record run links/commit SHAs, sample window and count, execution frequency,
+ per-job/step durations, queue time, summed runner time and the dependency
+ critical path. Separate measured data from estimates and explain missing
+ telemetry; estimate savings per run and at the observed cadence.
+- **Select work by risk.** Inspect event triggers, path filters, affected-test
+ selection and full-suite fallbacks. Check that small unrelated changes do
+ not select expensive work without a reason, and relevant changes cannot skip
+ required coverage. Evaluate PR/MR versus merge, nightly, release and opt-in
+ placement against the failures each check catches and when detection is
+ needed. Preserve required status reporting and fail closed on uncertain scope.
+- **Remove demonstrated duplicate work.** Trace overlapping workflows, matrix
+ jobs, installs, builds, test processes and setup. Inspect job dependencies for
+ unnecessary serialization or repeated prerequisites. Distinguish runner-time
+ savings from critical-path latency; more parallelism can increase total cost.
+- **Reuse safely.** Check cache hits/misses, keys and invalidation, restore cost,
+ artifact upload/download cost, retention and same-input build reuse. Preserve
+ platform/toolchain compatibility, provenance and untrusted-PR isolation.
+- **Bound obsolete work.** Inspect concurrency groups, superseded-run
+ cancellation, failure cancellation, retries and timeouts. Keep release work,
+ required gates and failure diagnostics reliable; do not trade waste for
+ missing results or restart loops.
+- **Prove test value.** Coordinate with Test Quality for redundant or vacuous
+ tests: identify the stronger surviving coverage or use a bounded mutation
+ probe, reverted before commit. A slow test is not a valueless test. Improve
+ fixtures, imports or setup before removing useful correctness/security checks.
+
+For a CI finding, give the measured baseline, exact selection/dependency change,
+expected savings, retained risk coverage and validation. Test representative
+changed-path/event cases and required-check behavior, then compare equivalent
+before/after runs where available. If access prevents measurement, report that
+limit; do not invent savings or weaken essential coverage to obtain green CI.
+
## Not yours
Application-code vulnerabilities belong to the security work; package version
@@ -1917,7 +1957,8 @@ reliability work. Name the overlap if it is the cause, then leave it to its owne
Every finding names the file and line, the environment it affects, and the
concrete consequence: who can reach what, what a leaked credential grants, or
-which deploy breaks. Redact before you publish — describe a secret's location
+which deploy breaks, measured avoidable runner time or critical-path delay,
+or a coverage/required-check failure. Redact before you publish — describe a secret's location
and shape, never its value, and never paste account ids, hostnames, or addresses.`,
'data-integrity': `[Improvement: {appName}] Data integrity and pipeline audit
diff --git a/server/services/taskPromptDefaults/versions.js b/server/services/taskPromptDefaults/versions.js
index 007b5f7628..d5ec4a6c21 100644
--- a/server/services/taskPromptDefaults/versions.js
+++ b/server/services/taskPromptDefaults/versions.js
@@ -68,7 +68,7 @@ export const PROMPT_VERSIONS = {
'better-structural-drift': 1, // v1: derived artifacts as a second source of truth, position-keyed records, hand-synced registries, incidental-layout coupling — carved out of code-quality v3.
'better-runtime-safety': 3, // v3: adds cross-module contract breaks in untyped code (missing members, missing named exports, dropped wrapper arguments) with a guard-test fix. Previous version: Framework-neutral UI lifecycle overlap. Previous version: v1: latent defects (floating promises, unowned rejections, unguarded access, sentinel confusion, races, leaks) requiring a concrete failure scenario.
'better-dependency-freedom': 1, // v1: dependency NECESSITY (the do:depfree lens) — classify, prove usage, size the replacement. Distinct from dependency-updates, which bumps what stays.
- 'infrastructure': 1, // v1: IaC/container/orchestration/CI audit — exposure, identity grants, secrets, pinning, runtime guardrails, state config, CI supply chain, environment drift. Net-new type. Mode injected at dispatch.
+ 'infrastructure': 2, // v2: measured CI efficiency, risk-based stage placement and test-value evidence. v1: IaC/container/orchestration/CI audit — exposure, identity grants, secrets, pinning, runtime guardrails, state config, CI supply chain, environment drift. Net-new type. Mode injected at dispatch.
'data-integrity': 1, // v1: runtime data-correctness audit — idempotency under redelivery, partial writes, lost updates, boundary validation, schema evolution, semantic corruption, pagination, retention, transfer checks. Net-new type.
'reliability': 1, // v1: service reliability audit — shutdown draining, truthful health checks, backpressure, job leasing/checkpoints, startup fragility, mixed-version deploys. Net-new type.
'privacy': 1, // v1: personal/sensitive-data audit — operational exposure, third-party minimization, API over-exposure, retention, erasure reach, real data in fixtures. Honors the project's documented sharing model. Net-new type.