Enable the live planning test against claude-haiku-4-5
CI / checks (push) Successful in 13s
CI / checks (pull_request) Successful in 12s

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 <noreply@anthropic.com>
This commit is contained in:
dongarandClaude Opus 5 committed 2026-09-07 16:01:18 +00:00
1 parent cf85648719
commit 6c17f2bf57
2 files changed
+6 -5

No files matched your search

+5 -5
View File
@@ -11,11 +11,11 @@ NISSE_ROLE_PLANNER=anthropic/claude-opus-5
NISSE_ROLE_DELEGATE=anthropic/claude-opus-5 NISSE_ROLE_DELEGATE=anthropic/claude-opus-5
NISSE_ROLE_CONSULTANT=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 # Opt-in for the live planning test: a model the virtual key can reach that
# can reach. Planning escalates unconditionally (A12) and small local models # holds the tool-call contract. Planning escalates unconditionally (A12), and
# do not hold the tool-call contract reliably, so this stays unset until a # small local models do not hold the contract reliably — llama3.2 returns
# frontier route exists. # truncated tool arguments, Haiku-class and up are solid.
# NISSE_LIVE_PLANNER_MODEL=anthropic/claude-opus-5 NISSE_LIVE_PLANNER_MODEL=claude-haiku-4-5
# --- Matrix transport (A1), used by nisse-dev's MatrixTransport --- # --- Matrix transport (A1), used by nisse-dev's MatrixTransport ---
NISSE_MATRIX_HOMESERVER=https://matrix.example NISSE_MATRIX_HOMESERVER=https://matrix.example
+1
View File
@@ -34,6 +34,7 @@ jobs:
NISSE_LLM_BASE_URL: ${{ secrets.NISSE_LLM_BASE_URL }} NISSE_LLM_BASE_URL: ${{ secrets.NISSE_LLM_BASE_URL }}
NISSE_LLM_TOKEN: ${{ secrets.NISSE_LLM_TOKEN }} NISSE_LLM_TOKEN: ${{ secrets.NISSE_LLM_TOKEN }}
NISSE_ROLE_EXECUTOR: ${{ secrets.NISSE_ROLE_EXECUTOR }} 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_HOMESERVER: ${{ secrets.NISSE_MATRIX_HOMESERVER }}
NISSE_MATRIX_USER_ID: ${{ secrets.NISSE_MATRIX_USER_ID }} NISSE_MATRIX_USER_ID: ${{ secrets.NISSE_MATRIX_USER_ID }}
NISSE_MATRIX_TOKEN: ${{ secrets.NISSE_MATRIX_TOKEN }} NISSE_MATRIX_TOKEN: ${{ secrets.NISSE_MATRIX_TOKEN }}