Proof — reproducible continuity tests

Proof

Reproducible, not rhetorical.

Renitor's claim is that a coding task survives when one agent stops — and that you can see what carried over. That's testable. Below is a deterministic benchmark you can run yourself, exactly what it checks, and — honestly — what it does and doesn't prove.

10continuity scenarios
88/100average continuation readiness
0secrets exposed in any handoff
247automated checks (151 unit · 96 sim)
200turns deep — the first instruction still delivered

Measured locally on v1.73.7. Reproduce every number below with two commands — no account, no quota.

Reproducible technical test

The continuity benchmark

Ten "the agent stopped here" situations run through the same code path the product uses to build a handoff. For each, we measure how completely the task state was captured — and assert that no secret ever leaks into the handoff. Deterministic: same input, same result, every time.

ScenarioReadinessChanged files capturedSecrets exposed
Quota hit before any edit88/10000
Quota hit after one edit88/10010
Quota hit after a failing test93/1002 · test state captured0
Multi-file refactor interrupted95/1004 · decisions captured0
Stopped with uncommitted changes88/10020
Model's summary contradicts the diff88/1001 · observed file list wins0
Session trace unavailable69/1001 · goal flagged as missing0
.env contains secrets90/1001 · secret redacted0
Unrelated dirty files present88/10020
Destination has a smaller context window88/10030 · diff bounded to budget0

Every readiness score is evidence-linked: it counts what was actually captured — goal, branch, HEAD commit, changed files, failing commands, test state, decisions, redactions — and an inferred goal is always labelled inferred, never presented as stated fact.

npm ci npm run bench:continuity # 10 scenarios · asserts 0 secret exposures · exits non-zero on any leak

The benchmark ships inside the extension source (benchmarks/continuity/) and runs as part of the test suite. The public reproduction repository — with the recorded Claude → Codex → Claude run, the CI badge, and a clickable methodology file — opens when the extension is published. Until then, these are Renitor's own locally-measured results, reproducible the moment the source is in your hands.

Reproducible technical test

Context survives the conversation — not just the handoff.

The benchmark above proves a task transfers between agents. This one proves a task keeps its whole memory inside one chat: a constraint you state at turn 1 still reaches the model deep into a long conversation. It drives the same code path the chat uses to build every request over threads of 40, 60, 100 and 200 turns.

ConversationMessages sent to the modelOlder turns folded to a summaryTurn-1 constraint
40 turns · full window820kept
60 turns · full window1220kept
100 turns · full window2020kept
200 turns · full window4020kept
200 turns · tight window (forced overflow)106296 · folded to a durable summarykept

The whole conversation is sent, compacted only when it genuinely won't fit — and when older turns are folded they become a durable summary, never a silent drop. A fixed "last-N-messages" cap would have lost the turn-1 constraint on every row past ~20 turns.

npm ci npm run bench:context # 5 conversations up to 200 turns · exits non-zero if any early constraint is lost

Ships in the extension source (benchmarks/context-window/) and is guarded at the wire by a flight-simulator scenario that drives a real chat past 40 turns and checks the request each model actually receives.

Honest scope

What this proves — and what it doesn't.

What it proves

That the handoff captures the task state with high fidelity — goal, changed files, branch/commit, failures, decisions — across the failure modes that actually happen, and that secret redaction holds (0 exposures across every scenario). Deterministic and reproducible on your machine.

What it does not prove

It measures capture fidelity, not task success. It does not claim a destination model will always finish the job — that depends on the model. It's an honest readiness estimate, not a guarantee, and it doesn't bypass any provider's limits.

Why you can trust the number

The benchmark runs the real `renderHandoff` + record builder — not a mock. It's part of the test suite (247 automated checks), and it fails the build if a secret ever leaks. The methodology is open in docs/continuity-benchmark.md.

Product demonstration

The round-trip, on a real repo.

Beyond the benchmark, the flagship handoff is demonstrated end-to-end: a task starts on Claude, a limit hits, work detours through Codex, and Claude resumes — carrying the goal, diff, failures and decisions across. The full transcript, with the exact prompts to reproduce it, lives in the docs.

Verified on this repo: running the handoff against Renitor's own codebase produced a 88/100 continuation record that correctly counted 22 changed files, pinned the branch and HEAD commit, and flagged the recovered goal as inferred — confirm before continuing rather than asserting it as fact. That's the same record every handoff writes to .renitor/continuity/.

A public, fully-recorded end-to-end run — starting commit, prompts, generated record, resulting diff and test output — is being prepared as a standalone reproducible case. Until it's published here, the benchmark above is the systematic evidence, and the docs carry the step-by-step reproduction.

See the handoff Reproduction steps in the docs

Locally measured usage

Your machine keeps the receipt.

Separate from the benchmark: Renitor counts — locally, on your machine — every provider limit it survived and every token it ran on a free model, priced at paid rates. These are your measured numbers, not ours, and they never leave your machine. Treat them as a local estimate, not a marketing figure.

How the savings ledger works

Run it yourself.

The strongest proof is the one you reproduce. Get the free beta, generate a handoff, and read the readiness section it writes for your own repo.

Get the free beta — 2 minutes