arcodange-org/factory
1
0
Fork 0
Code Issues 4 Pull Requests Actions Packages Projects Releases Wiki Activity

docs(prd): harness portability — Claude as escalation tier, not hard dependency

Browse Source 
Operator direction 2026-07-15: the orchestration layer itself (builder
sessions, cold verifiers) must run on Mistral or hermes+Ornith/MLX too.
The protocol already carries everything in files+issues; new model-fleet
section defines the evidence-gated ladder — verifier roles migrate
first (cross-family refutation is stronger verification), scoped
builders benched on unchanged acceptance gates, Claude default until
the bench says otherwise. D2 row records the direction; spike = erp#63.

Co-Authored-By: Claude Fable 5 <[email protected]>
This commit is contained in:
arcodange
2026-07-15 18:49:05 +02:00
co-authored by Claude Fable 5
parent 72cca8a3b0
commit 5aea83749d
2 changed files with 13 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
vibe/PRD/ai-back-office/model-fleet.md
+12
View File
@@ -44,6 +44,18 @@ The format guarantee never rests on the model:
…and regardless of tier, every payload passes the same deterministic validators downstream ([agent architecture](agent-architecture.md#atom-contract)). Constrained decoding guarantees *shape*; validators guarantee *truth conditions* (arithmetic, checksums, plausibility).
## Harness portability
The **atoms** above are multi-model by construction. The **harness** — the orchestration layer that executes backlog issues (builder sessions), verifies them (cold readers, locate-tests) and files PRs — ran its first full loop on Claude (erp#38 → PR erp#62, 2026-07-15). **Operator direction (2026-07-15): that layer must not have Anthropic as a hard dependency either — the same loop should run on Mistral, or on hermes + Ornith / MLX-served local models.**
The protocol was built for this: everything an executing agent needs lives in **files and issues** — AGENTS.md orientation, per-issue Execution footers (first command, done-means), acceptance tests defined in the issue itself, deterministic validators around every output. Nothing load-bearing lives in a vendor's context window. Any runtime that can read the forge and run a shell can attempt an issue; the acceptance gates don't care who built the thing.
Migration ladder (evidence-gated like everything else — erp#63):
1. **Verifier roles first** — locate-tests, cold-reader audits, refutation passes: bounded, read-only, cheap. Re-run the already-passed erp#38 locate-test on **Ornith** (hermes, `127.0.0.1:18080`) and on an **MLX-served candidate** (Qwen3 14B/30B-A3B, Mistral Small 3.x class); require verdict parity with the Claude run. Once parity holds, **prefer cross-family verification**: a different model family refuting the builder is stronger evidence than the builder's family agreeing with itself.
2. **Scoped builders benched** — one small, tightly-footered issue (a #56-class fix) attempted end-to-end by a Mistral-driven runtime against the unchanged acceptance gates; measure completion rate and intervention count.
3. **Claude stays the default** for multi-file builders, ambiguity and fiscal reasoning **until the bench says otherwise** — a routing-policy fact (complexity ceiling above), not an allegiance.
## Degraded modes
| Outage | Keeps working | Queues | Lost until recovery |