Cybernetics-Based Autonomous AI Software-Engineering Convergence Runtime
PLD (Pi-Loop-Dev) is a development runtime that upgrades "multi-agent collaboration" into a "self-enhancing closed loop": starting from a DESIGN.md, it iterates continuously through a Builder → Tester → Analyzer cybernetic loop, stably converging any OpenAI-compatible model (no Claude / GPT quota needed) to an engineering artifact of "all tests pass + spec aligned." It treats the LLM as an uncontrollable actuator and wraps it with a reliable control system via feedback loops — the core methodology Xianma has crystallized in AI engineering.
PLD does not pursue a smarter LLM, but uses an engineered control loop to make LLM output verifiable, convergent, traceable, and rollbackable.
No top-tier model or quota needed. Any OpenAI-compatible interface runs; what truly decides the result is the constraint system and feedback loop around the actuator.
Goal (DESIGN.md) → controller → actuator (Builder / LLM) → controlled object (code) → sensor (Tester + Analyzer) feedback to controller, continuously driving convergence.
Reliable feedback, constrainable actuator, stable system, observable, controllable — oscillation detection + circuit breaker + degradation rollback + dual-convergence judgment + Failure Fingerprint.
Auto-scan repeated work patterns, crystallize into batchable, parallelizable Loops, compounding R&D experience rather than consuming it once.
Between "looks right" and "truly usable," AI code-writing spans seven chasms; PLD gives an engineering answer to each.
LLM generates "looks right" but hides bugs, and self-assessment almost always says "fine." PLD trusts only test-pass-rate (ground truth) + spec-alignment dual verification.
AI tools either loop forever, fix A and break B, or fake-converge. PLD gives convergence guarantee via 6-mode state machine + breaker + dual judgment.
AI-generated artifacts become "dark matter" in the codebase, untraceable. PLD's Provenance protocol + event stream make every artifact auditable, verifiable.
Every endpoint / data model reinvents the wheel. PLD's Loops module auto-discovers repeated patterns and batch-parallelizes.
Tools bind a single model; switching often rewrites the integration layer. PLD configures each agent independently, one-line backend switch, Advisor cross-validation.
Syntax errors surface only when pytest starts, wasting 10-30s per round-trip. PLD's TTSR + LSP intercept during / right after generation.
Hardcode return values, mock out logic, tweak tests to pass — 100% tests but unusable code. PLD counters systematically with four defense layers.
A cybernetic runtime that turns "AI writes code" from a probability game into an engineering system
6-mode RepairMode state machine (INITIAL / TEST_FIX / SPEC_COMPLETION / OSCILLATION_BREAK / REGRESSION_RECOVERY / FINAL_VERIFICATION), auto-switched by test_pass_rate; Hysteresis debounce + Circuit Breaker.
Auto-reject bare except / return expected / @pytest.mark.skip / mock in prod code / test-file deletion — blocking "shortcut" patches at the source.
TTSR intercepts in the token stream + LSP Sensor pre-test diagnosis (1-2s) + incremental test (full calibration every 3 rounds), compressing feedback from 10-30s to <2s.
Integrates the Proofpress provenance protocol, generating an immutable capsule per artifact (model / iteration / pass_rate / convergence); 20 event types persisted to EventStore.
opencode (default lightweight) / omp (Rust runtime, LSP/TTSR/Advisor/DAP) one-line switch; each agent independently configured; Advisor second model cross-validates.
pld scan discovers patterns → spec generates → loop-run batch executes → run-dag parallel schedules, turning repeated engineering tasks into reusable, parallelizable automation assets.
Not one-shot generation, but an autonomous Builder → Tester → Analyzer iteration loop until dual convergence.
Crystallize "AI writes code" capability into a measurable, reusable runtime asset.
The difficulty is not single-point algorithms, but engineering "multi-agent collaboration" stably and reusably into a self-enhancing loop.
Treat the LLM as actuator not decision-maker, driving stable convergence via negative-feedback loops — any OpenAI-compatible interface runs, no top-tier model or quota bound.
Test-pass-rate + spec-alignment dual judgment, with FINAL_VERIFICATION against fake convergence, making "done" an engineering guarantee not a claim.
Formal Guards formal rejection + TTSR generation-time intercept + Advisor second-model watch + Analyzer spec review, cross-validating to sharply cut missed detections.
Auto-mine repeated patterns from history and crystallize into batchable Loops, compounding R&D experience rather than losing it at project end.
Convert technical capability into quantifiable, reusable business value.
Product content has been published based on internal materials. The following areas are planned for further development:
Explore Xianma AI solutions in other domains