Skip to main content
convergence is a pure graph form. It folds recorded form events into state and returns the next command. The form has one generator, one done check, one repair node, and one or more review seats. A review seat is an independent reviewer node.

​
Run the example

From an Obversa checkout, run:
The example records two valid passes from separate providers and model families. It prints this JSON report:
The clean-consumer check compiles and runs the same source from the packed package with TypeScript 6 and TypeScript 7. Its source is examples/packages/review-loop.ts.

​
Define a review loop

The next fragment is from examples/packages/review-loop.ts.

​
Recorded behaviour

  • Node records: The form accepts dispatch, completion, failure, pause, and resume records for each node attempt.
  • Review records: A seat pass includes its confidence, input hashes, and workspace fingerprint. Evaluator evidence also names one proof artifact digest. Every seat dispatch receives that digest, and every seat result must echo it. A missing or changed digest makes that result invalid and dispatches the seat again while its retry limit permits. Findings from that result cannot enter repair inputs or finding counts. The seat’s lane declares the provider and model family. evidencePaths names the input hashes that can invalidate that seat; omitting it makes every input hash relevant. The form checks whether a pairwise-distinct provider and model-family subset meets the quorum.
  • Repair records: Findings can send the form to its repair node. A later cycle keeps valid seat passes and reruns invalid seats.
  • Policy records: New evaluator evidence invalidates each seat whose named input hash changed. A producer can also invalidate an in-flight seat or record a limit pause.
The form consumes the graph executor’s upper-case failure codes. ABORTED pauses the run. ENGINE_UNAVAILABLE skips a declared skippable seat and pauses for a required seat. Other node failures use the declared retry cap before the required seat pauses as unresolved.

​
Stored plans and evaluator failures

The convergence graph type uses version 2. A stored plan for version 1 is refused by createGraphExecutor with STORED_GRAPH_MISMATCH before a node starts. The executor does not convert the stored plan. Start a new run with a plan compiled from version 2 to use this evidence contract. When the evaluator completes without valid review evidence, the form returns fail with code CONVERGENCE_REVIEW_EVIDENCE_INVALID. It dispatches no review seat. Reopening the run preserves that failure. Correct the evaluator and start a new run.

​
Limits and output

maxIterations, maxReviewRestarts, and retryCapPerNode bound the described dispatch count. seatConcurrency sets the review batch size. The complete output states the cycle count, repair count, result for each review seat, and any blocking findings returned by seats outside the accepted quorum.