From 83162e7a64e8e07ec9141135e10aea4f30fe7492 Mon Sep 17 00:00:00 2001 From: Gahow Wang Date: Fri, 19 Jun 2026 11:27:47 +0800 Subject: [PATCH] Ablation: pin gpt-5.5 @ ai.gahow.org (chat.completions); re-read token per arm - Pin endpoint.model=gpt-5.5, base_url=https://ai.gahow.org/v1, wire_api=chat.completions in both ablation specs so both arms uniformly use the current ~/.codex model (the prior runs used the stale ai.prism.uno/gpt-5.4 that config.toml has since moved off). - run_ablation_pair_d1.sh re-reads the codex token from auth.json right before each arm instead of capturing it once at launch (the stale-at-use capture 401'd naive 2/3). Co-Authored-By: Claude Opus 4.8 --- configs/examples/dash0_qwen27b_ablation_harness_on.json | 4 +++- configs/examples/dash0_qwen27b_ablation_naive_off.json | 4 +++- scripts/run_ablation_pair_d1.sh | 6 +++++- 3 files changed, 11 insertions(+), 3 deletions(-) diff --git a/configs/examples/dash0_qwen27b_ablation_harness_on.json b/configs/examples/dash0_qwen27b_ablation_harness_on.json index 8fa7d5b..1aed154 100644 --- a/configs/examples/dash0_qwen27b_ablation_harness_on.json +++ b/configs/examples/dash0_qwen27b_ablation_harness_on.json @@ -168,7 +168,9 @@ "max_history_trials": 8, "endpoint": { "provider": "codex", - "model": "gpt-5.4", + "model": "gpt-5.5", + "base_url": "https://ai.gahow.org/v1", + "wire_api": "chat.completions", "stream": true, "api_key_env": "OPENAI_API_KEY", "timeout_s": 180 diff --git a/configs/examples/dash0_qwen27b_ablation_naive_off.json b/configs/examples/dash0_qwen27b_ablation_naive_off.json index 4acbf68..73a77f6 100644 --- a/configs/examples/dash0_qwen27b_ablation_naive_off.json +++ b/configs/examples/dash0_qwen27b_ablation_naive_off.json @@ -168,7 +168,9 @@ "max_history_trials": 8, "endpoint": { "provider": "codex", - "model": "gpt-5.4", + "model": "gpt-5.5", + "base_url": "https://ai.gahow.org/v1", + "wire_api": "chat.completions", "stream": true, "api_key_env": "OPENAI_API_KEY", "timeout_s": 180 diff --git a/scripts/run_ablation_pair_d1.sh b/scripts/run_ablation_pair_d1.sh index 3821898..57abcfe 100644 --- a/scripts/run_ablation_pair_d1.sh +++ b/scripts/run_ablation_pair_d1.sh @@ -5,19 +5,23 @@ # window), per-probe Stop-A-consistent drain deadline. Harness stops early; naive # runs the full budget. Run from the repo root on dash1. set -u -export OPENAI_API_KEY=$(python3 -c 'import json,pathlib;print(json.load(open(pathlib.Path.home()/".codex/auth.json"))["OPENAI_API_KEY"])') +# Re-read the codex token from auth.json right before each arm (capturing it once at +# launch goes stale during a long run -- that is what 401'd naive runs 2/3). +read_key() { export OPENAI_API_KEY=$(python3 -c 'import json,pathlib;print(json.load(open(pathlib.Path.home()/".codex/auth.json"))["OPENAI_API_KEY"])'); } # codex config.toml points at a dash0-local proxy (127.0.0.1:11235); on dash1 the # LLM endpoint is reachable directly, so force a direct connection. export http_proxy= https_proxy= all_proxy= HTTP_PROXY= HTTPS_PROXY= ALL_PROXY= no_proxy='*' mkdir -p .aituner rm -rf .aituner/abl12-harness .aituner/abl12-naive .aituner/ABLATION12_DONE +read_key echo "=== harness ON (12-iter) start $(date -Is) ===" PYTHONPATH=src python3 -m aituner.cli study tune \ --spec configs/examples/dash0_qwen27b_ablation_harness_on.json \ --store-root .aituner/abl12-harness --max-trials 12 --skip-baseline > .aituner/abl12-harness.log 2>&1 echo "=== harness ON (12-iter) done $(date -Is) ===" +read_key echo "=== naive OFF (12-iter) start $(date -Is) ===" PYTHONPATH=src python3 -m aituner.cli study tune \ --spec configs/examples/dash0_qwen27b_ablation_naive_off.json \