Code Factory

6 mandatory audit lanes. 136 coded rejection conditions. One human-owned release decision.

Your code passed. But did it pass the right tests?

An AI agent—or a human developer—can write the code, write the tests, and set the rules used to approve its own work. Everything can turn green while the result still misses the request, leaks another tenant's data, breaks during a retry, damages a migration, or slows down in production.

Code Factory is an engineering audit and orchestration system: the independent review layer between “the build passed” and “a person should approve this.”

It seals the original intent before work begins, observes what changed, challenges the implementation and its tests, and connects every decision to inspectable evidence. If evidence is missing, contradictory, stale, or based on a weakened rule, the result does not quietly become a pass.

One review path, six questions

Audit lane	The practical question it answers
Stateful workflows	Do business rules still hold after real sequences such as create, cancel, retry, and refund?
Authorization and tenant isolation	Can one customer, session, export, cache, or background job reach another customer's data?
Failure and recovery	What happens during duplicate requests, timeouts, partial writes, worker crashes, and retries?
API and consumer compatibility	Will this change silently break an older app, SDK, integration, or service?
Migration and data integrity	Can the system upgrade without losing, corrupting, or stranding data?
Performance and resources	Did latency, queries, memory, connections, or other resources regress against an approved baseline?

Those lanes contain 81 lane-specific and 55 cross-cutting coded rejection conditions. The source-bound inventory recomputes the total from the implementation; it is not a claim that every project executes 136 tests.

What the Code Factory upgrade improves

Code Factory is the core audit and orchestration system. FactoryLine is one CLI/IDE/MCP surface for using it; the performance gains below come from the CF workflow itself, not from a JetBrains-specific adapter:

• Less repeated work: the dependency-aware proof DAG routes each change to RUN, REUSE, SKIP, or BLOCK, then compares the incremental route with a full baseline when that comparison is required.
• Fewer wasted agent retries: Proof-Delta stops a loop when the candidate did not change or fresh evidence did not improve the result, instead of spending another repair cycle on the same idea.
• Faster review orientation: hash-bound receipts, Graph Ops, and the failure briefing keep the exact diff, proof gap, consequence, evidence, and next action together instead of making a reviewer reconstruct them from agent chat and scattered logs.
• Bounded resource cost: evidence reads, workspace measurements, and process-bound replays have explicit limits and fresh-workspace rules, so the audit does not silently scan or mutate an entire project.
• Clear agent accountability: the proof-coupled Junie handoff records the known tool, changed-file rationale, hashes, and explicit unknowns against a taxonomy digest, so an agent receives credit only for evidence a reviewer can inspect.

These are workflow-efficiency improvements, not a promise that application code or tests execute faster. Actual time or cost savings remain unknown until your project supplies a baseline and an evidence window.

Built for the way you work

• Solo developers and vibe coders: get a second opinion before a plausible AI-generated change becomes your problem in production.
• Engineering teams: compare the request, code delta, independent checks, repair evidence, and remaining unknowns in one reviewable handoff.
• Enterprise teams: keep policy provenance, exceptions, approvals, tenant boundaries, and evidence traceable without giving the coding agent authority to redefine success.
• Connected agents: use the CLI, FactoryLine IDE surfaces, MCP, WebMCP, or A2A handoffs to follow the same bounded process and report the next action to a human.

Specialist modules join the same review when needed: Deep Defect Mesh consumes analyzer evidence, SaaS checks examine customer journeys, and AppForge organizes mobile build, design, privacy, signing, and store-submission evidence. AppForge does not replace the other audit lanes or promise store approval.

Choose your review path

pip install factoryline-code-factory
factory guide

factory guide is a read-only orientation: it shows the smallest suitable path without running tests or agents. When you are ready to produce evidence, follow the engineering review workflow. Its result shows what was checked, what failed, why it matters, what evidence supports the finding, and what must happen next. Code Factory does not promise perfect software. It makes the basis for approval visible and keeps the final decision human-owned.

From a plausible change to an inspectable engineering decision

• Build what was actually requested. SpecLine clarifies requirements; sealed intent and Oracle Firewall checks flag scope drift and weakened gates.
• Review behavior beyond a green unit test. Six audit lanes coordinate stateful invariants, authorization and tenant isolation, failure/concurrency recovery, API compatibility, database migration, and performance/resource regressions. Each lane needs the appropriate runner and real evidence.
• Turn findings into repair work. Deep Defect Mesh checks supplied analyzer evidence; linked traces and repair comparisons keep consequences, stale results, and the next validation visible.
• Keep the handoff coherent. ForgeLine orchestration and FactoryLine receipts connect work across modules. Mission Control and Graph Ops show humans and connected agents the same scope, blockers, evidence, and next step.
• Activate specialist checks when needed. SaaS journey checks and AppForge mobile-release evidence fit into the same review path. AppForge is an optional module, not the whole product.

The payoff: a reviewer can see what was audited, what passed, what remains unknown, and what must happen next. A receipt supports that decision; it is not a guarantee of defect-free code, enterprise certification, or store approval. People retain authority over policy, exceptions, and release.

Install the CLI, then follow the engineering review workflow for a full review:

pip install factoryline-code-factory

Want a small demonstration first? factory first-proof --root . challenges whether a test can actually reject its declared failure in a disposable sandbox. It writes a receipt and a privacy-safe Proof Card; it does not assess or change your project. First Proof is one entry point—not the scope of the full audit.

LLM-friendly product context: Canonical Product Card states the supported capabilities, boundaries, audiences, integration terms, and exact vocabulary that documentation assistants and agent tools may safely reuse. It is intentionally claim-bounded: local evidence is not a release, provider approval, remote execution, or a guarantee of correctness.

Pick the path that matches your work

Beyond hollow tests: Deep Defect Mesh evaluates signed analyzer-report contracts, flags missing negative controls, traces findings into Graph Ops, and compares repair outcomes. It coordinates supplied evidence; it does not execute the analyzers or guarantee that a clean report means safe code.

Choose your review path below. The current factory guide command still lists the existing onboarding paths, including the solo First Proof demo; it is not the full engineering-review workflow linked above.

• Individual developer or vibe coder: What did my change miss? Use the engineering review workflow to inspect intent, behavior, and evidence. Try factory first-proof --root . for a contained demonstration first.
• Engineering team: Did the agent build what we asked for? Start with factory oracle status --root .. Bind the original intent, observe the exact file delta, challenge the tests independently, and keep approval human-owned.
• Enterprise evaluator: Can we govern agent work without trusting the agent's story? Start with factory graph ops --root . --json. Inspect the source-to-decision chain, blockers, unknowns, and authority boundaries in a controlled pilot.

Choose the relevant audit scope. Specialized SaaS, mobile, multi-repository, and enterprise controls remain available in the advanced workflow guide only when their trigger applies. AppForge is an optional mobile-delivery capability; it surfaces avoidable gaps but cannot guarantee store approval.

For a release-bound service change, use the six-lane runtime assurance workflow. It coordinates stateful invariants, tenant isolation, fault recovery, consumer compatibility, database migration, and equivalent-load performance/resource checks under one signed plan. Every failed lane returns the consequence, evidence digest, exact replay, and next repair. A six-lane pass means ready for human review—not approved for release.

Senior engineering controls in 0.46.3

When a team needs stronger evidence than a self-reported green build, use the senior-engineering integration:

• verify an independently collected, candidate-bound execution attestation;
• measure a reviewed buggy/fixed defect corpus with case-level recall and precision; and
• route a dependency DAG through RUN, REUSE, SKIP, or BLOCK, then compare the incremental plan with a full baseline;
• reproduce a failure in a fresh, contract-bound process workspace, compare the original failure with a repair and negative controls, explain every reuse decision across policy/dependency/toolchain/environment fingerprints, and hand a reviewer a runnable, evidence-linked failure briefing.

These adapters are provider-neutral and review-only. Replay and repair execute only when the operator supplies --execute; they use a fresh temporary process workspace with a secret-free environment, not a kernel/container sandbox. They never publish a package or approve a release. Missing independent evidence remains an evidence gap.

Do not take the word verified on faith. The Capability Evidence Map separates the locally verified core, controlled-pilot workflows, reference enterprise controls, and candidate-bound mobile preflight—and links each claim to the tests you can inspect and run yourself. For one agent-neutral human review path, use factory proof-review to seal intent, audit trajectory evidence, route the change, learn confirmed regressions, inspect the team inbox, and export a tamper-evident Proof Card. To create a contained starter later, run factory mvp "Build an approval tracker" --root .. That starter is never called production-ready until the relevant proof exists.

AppForge: make the review queue the last surprise, not the first

You have a build, a launch date, and a review queue that can take days to come back around. The costly failure is often not a crash—it is discovering after submission that the selected build has no exercised restore path, an iPad dead end, unrepresentative screenshots, an accessibility gap, or reviewer access that does not match the app.

AppForge turns that uncertainty into a local, candidate-bound worklist. Start with the user’s design direction, keep a story-led storyboard, then bind real iPhone/iPad media, App Review checks, quality evidence, SaaS journey evidence, and a final Markdown/PDF dossier to the same build. In JetBrains, AppForge Mission Control makes the missing lane visible before a human decides to enter the queue.

For iOS and Android delivery, factory revenue appforge-mobile-evidence normalizes supplied, hash-bound Xcode/XCTest, Android Gradle/ADB, Fastlane, device-cloud, and production-monitoring exports into one local receipt. It requires visual, privacy-to-listing, release-chain, design-system, production-signal, and Android-parity evidence to be explicit; it does not run those tools, access a store, submit a build, or guarantee approval.

That can prevent avoidable rework and repeat review cycles; it does not submit to Apple, access credentials, replace TestFlight, provide legal advice, or guarantee approval. Start with the AppForge Evidence Kit, then use the credential-free EAS handoff preflight before a separately authorized build or submission.

Support posture

The open-source core is free. Community support runs through public GitHub issues and has no guaranteed response time. For teams that need an operating commitment, the repository includes a transparent proposed Support SLA with P1/P2/P3 response targets, availability, recovery, exclusions, and an activation checklist.

Those targets are planning terms, not a current contract: the SLA remains proposed and non-effective until Code Factory has a named support owner, monitored escalation, production telemetry, dependency and recovery evidence, legal/security terms, and a signed enterprise order. This keeps the GitHub page useful to evaluators without implying that a free repository already carries a managed-service guarantee.

See actual Factory Studio and the current FactoryLine visual set or open the live Hugging Face Space.

Advanced workflows

• Start a real project. Turn one outcome into a contained web, mobile, API, CLI, worker, MCP, or agent-UI starting state.
• Review what AI produced. Turn requirements, diffs, proofs, and blockers into receipts, Graph Ops, and one fact-derived next action.
• Refresh the evidence that matters. Watch a local Assembly while it runs, refresh the next-proof brief, and see privacy-bounded observed Git contribution context without pretending it is a verified directory or billing roster.
• Keep "done" honest. Challenge declared validators for hollow tests; a green-looking scaffold is never called production-ready by default.
• Stop vague work before it starts. Use Intake Grill to record framework, exact intent, observable acceptance evidence, and the external-effects boundary before a Product Mission begins.
• Make a behavior survive its declared failure cases. Use the supervised Gauntlet to turn human-written E2E sabotage cases into an offline-verifiable Survival Card. A hollow negative check stays visible; a card is never a production-readiness certificate.
• Let autonomy be earned, not assumed. Use factory license to derive an expiry-bound local tier from independently verified governed runs. A severe hollow-test, hollow-validator, or scope-escape result demotes the declared agent automatically; it never authenticates identity or grants execution.
• Compare agents with receipts, not vibes. Use factory combine to rank completed, sealed, independently verified runs on the same task. It never starts an agent or turns a local scoreboard into a vendor-quality claim.
• Make every agent session feed the evidence loop. Use factory wrap around Claude Code, Codex, DeepSeek, or another local CLI. It verifies a sealed admission before launch, observes the exact file delta, runs declared independent validators, and records the result for Agent License and Combine. It stores hashes and bounded facts—not prompts or raw output—and observes the process without pretending to sandbox it.
• Verify an explicit agent workflow without adopting its runtime. Use factory atomic import to bind a secret-free exported stage DAG, scoped handoffs, checkpoint facts, and immutable source preconditions to a current Oracle Contract. Graph Ops, MCP, and WebMCP show the receipt read-only; Code Factory never starts Atomic, resumes a checkpoint, or treats a declared workflow as release authority.
• Keep decisions from becoming tribal knowledge. Use factory judgment to track a human-promoted design decision with exact paths, a named owner, review date, and hash-bound proof obligations. A Change Safety Case routes one explicit diff to its owner; it never infers intent, promotes a decision, runs a test, or approves a release.
• Prove the whole journey—and audit the repairing agent. Use factory journey to compare declared and observed product journeys, preserve a hash-bound failure capsule, prove state flow and cleanup, and challenge a proposed healing with a negative mutation. Choose human-controlled or bounded supervised-auto mode; every autonomous attempt receives a separate FactoryLine audit and neither mode can self-approve.

What the latest upgrade resolves

Common AI-assisted delivery pain	FactoryLine response	What stays under human control
A test is green but could never catch the behavior it claims to cover	Reality Check and Gauntlet bind declared positive and negative cases, then keep hollow or blocked checks visible in a Survival Card	Which behaviors and commands to admit; whether evidence is sufficient
A vague PRD becomes the wrong scaffold or framework	Intake Grill records a named, byte-bound intent, framework decision, observable acceptance evidence, and external-effects posture before a mission begins	The answers, architecture choice, and decision to start work
An agent retries the same failed approach and burns review time	Proof-Delta requires a changed candidate plus fresh, hash-bound evidence for a retry; no-gain attempts halt	Any repair, retry admission, and final apply
Teams gradually trust an agent because it has been successful recently	Earned Autonomy derives an expiring local tier from governed evidence and demotes severe hollow-test or scope-escape results	Identity, permissions, execution, approval, and release authority
A hard-won design decision is forgotten, then a later diff silently breaks its assumptions	Engineering Judgment Capsules bind one named owner, explicit path scope, review date, and declared proof obligations; an optional human-declared Change Profile makes novel boundaries and required Senior Attention explicit before review	Proposal, independent promotion, decision reconsideration, proof execution, acceptance, merge, and release
A reviewer has suggestions but no shared evidence picture	Graph Ops, local receipts, and read-only MCP facts show current scope, proof debt, and the next fact-derived action	Merge, release, deployment, and provider access
A selector repair makes the test green but changes the user journey—or an autonomous agent silently edits outside scope	Journey Reality, Stateful Workflow Proof, and Proof-Gated Healing require preserved semantic identity and coverage, cleanup proof, an adversarial negative result, exact workspace deltas, and an independent Agent Work Audit	Agent/provider choice, repair admission, final approval, merge, and release
Agent work happens outside the evidence ledger, while writing real E2E manifests takes too long	Evidence Supply Line wraps any admitted local agent CLI; gauntlet draft proposes inert, structure-derived promise drafts and explicitly withholds commands it cannot derive	Agent identity, sandboxing, draft promotion, validator choice, Gauntlet admission, and release
A large/remote workspace feels opaque or sluggish	Workspace Advisor measures bounded local project shape and path-only WSL/remote signals without changing indexes, heap, caches, inspections, or remote settings	Every IDE performance change and environment setting

These are local evidence and supervision tools, not guarantees of performance, security, productivity, production readiness, or an automatic repair service.

FactoryLine by role