From 6c17f2bf57f5c2c90b7783c14bf57f303bf63aea Mon Sep 17 00:00:00 2001 From: Don Garrett Date: Mon, 7 Sep 2026 16:01:18 +0000 Subject: [PATCH] Enable the live planning test against claude-haiku-4-5 The virtual key now reaches a Haiku-class route, which holds the tool-call contract llama3.2 could not: a real planning turn returns a well-formed submit_plan call with an explicit, low-inference plan. Wires NISSE_LIVE_PLANNER_MODEL through the CI workflow (add the matching Actions secret to run it there) and records the finding in .env.example. Co-Authored-By: Claude Opus 5 --- .env.example | 10 +++++----- .gitea/workflows/ci.yml | 1 + 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/.env.example b/.env.example index 7116471..e00075f 100644 --- a/.env.example +++ b/.env.example @@ -11,11 +11,11 @@ NISSE_ROLE_PLANNER=anthropic/claude-opus-5 NISSE_ROLE_DELEGATE=anthropic/claude-opus-5 NISSE_ROLE_CONSULTANT=anthropic/claude-opus-5 -# Opt-in for the live planning test: set to a frontier model the virtual key -# can reach. Planning escalates unconditionally (A12) and small local models -# do not hold the tool-call contract reliably, so this stays unset until a -# frontier route exists. -# NISSE_LIVE_PLANNER_MODEL=anthropic/claude-opus-5 +# Opt-in for the live planning test: a model the virtual key can reach that +# holds the tool-call contract. Planning escalates unconditionally (A12), and +# small local models do not hold the contract reliably — llama3.2 returns +# truncated tool arguments, Haiku-class and up are solid. +NISSE_LIVE_PLANNER_MODEL=claude-haiku-4-5 # --- Matrix transport (A1), used by nisse-dev's MatrixTransport --- NISSE_MATRIX_HOMESERVER=https://matrix.example diff --git a/.gitea/workflows/ci.yml b/.gitea/workflows/ci.yml index 4bc502a..d1e23c9 100644 --- a/.gitea/workflows/ci.yml +++ b/.gitea/workflows/ci.yml @@ -34,6 +34,7 @@ jobs: NISSE_LLM_BASE_URL: ${{ secrets.NISSE_LLM_BASE_URL }} NISSE_LLM_TOKEN: ${{ secrets.NISSE_LLM_TOKEN }} NISSE_ROLE_EXECUTOR: ${{ secrets.NISSE_ROLE_EXECUTOR }} + NISSE_LIVE_PLANNER_MODEL: ${{ secrets.NISSE_LIVE_PLANNER_MODEL }} NISSE_MATRIX_HOMESERVER: ${{ secrets.NISSE_MATRIX_HOMESERVER }} NISSE_MATRIX_USER_ID: ${{ secrets.NISSE_MATRIX_USER_ID }} NISSE_MATRIX_TOKEN: ${{ secrets.NISSE_MATRIX_TOKEN }}