michael/AI-Profile-Router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Harden and demote experimental Hermes compressor

Browse Source
This commit is contained in:
Mikei386
2026-08-26 01:40:38 +02:00
parent 99285fe81a
commit aaadc57c07
7 changed files with 52 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files
platform/hermes/config.yaml
+1 -11
View File
@@ -86,7 +86,7 @@ compression:
threshold: 0.82
target_ratio: 0.35
tail_mode: "lean"
protect_last_n: 12
protect_last_n: 20
protect_first_n: 0
proactive_prune_tokens: 50000
proactive_prune_min_result_chars: 4000
@@ -99,16 +99,6 @@ auxiliary:
# actual chat, so keep the original timestamp/session id instead.
title_generation:
enabled: false
compression:
provider: "openai-api"
model: "qwen-compression"
base_url: "http://192.168.1.212:8099/v1"
api_key: "local"
reasoning_effort: "none"
extra_body:
chat_template_kwargs:
enable_thinking: false
timeout: 600
# The full hermes-cli preset injects several large, overlapping schemas on
# every turn. Athena already exposes browsing, orchestration and host services
platform/hermes/install-profiles.sh
+6 -9
View File
@@ -33,16 +33,13 @@ create_profile() {
docker exec "$HERMES_CONTAINER" hermes -p "$name" config unset compression.threshold_tokens || true
docker exec "$HERMES_CONTAINER" hermes -p "$name" config set compression.threshold 0.82
docker exec "$HERMES_CONTAINER" hermes -p "$name" config set compression.target_ratio 0.35
docker exec "$HERMES_CONTAINER" hermes -p "$name" config set compression.protect_last_n 12
docker exec "$HERMES_CONTAINER" hermes -p "$name" config set compression.protect_last_n 20
docker exec "$HERMES_CONTAINER" hermes -p "$name" config set compression.protect_first_n 0
docker exec "$HERMES_CONTAINER" hermes -p "$name" config set auxiliary.compression.provider openai-api
docker exec "$HERMES_CONTAINER" hermes -p "$name" config set auxiliary.compression.model qwen-compression
docker exec "$HERMES_CONTAINER" hermes -p "$name" config set auxiliary.compression.base_url http://192.168.1.212:8099/v1
docker exec "$HERMES_CONTAINER" hermes -p "$name" config set auxiliary.compression.api_key local
docker exec "$HERMES_CONTAINER" hermes -p "$name" config set auxiliary.compression.reasoning_effort none
docker exec "$HERMES_CONTAINER" hermes -p "$name" config set auxiliary.compression.extra_body \
'{"chat_template_kwargs":{"enable_thinking":false}}'
docker exec "$HERMES_CONTAINER" hermes -p "$name" config set auxiliary.compression.timeout 600
# The small compressor remains an opt-in benchmark endpoint. It is not safe
# as a global technical-session compressor: end-to-end tests showed that it
# can omit older exact KEY=value state. Remove stale opt-in settings so the
# selected 27B profile performs production compaction.
docker exec "$HERMES_CONTAINER" hermes -p "$name" config unset auxiliary.compression || true
docker exec "$HERMES_CONTAINER" hermes -p "$name" config set platform_toolsets.cli \
'["web","terminal","file","skills","todo","memory","vision","tts"]'
[[ $(docker exec "$HERMES_CONTAINER" hermes -p "$name" config get model.default) == "$model" ]] || \