Files
hermes-agent/agent
Teknium cb71d5f1b1 fix(agent_init): clamp compressor window to Ollama num_ctx resolved after construction
model.ollama_num_ctx is resolved AFTER the context compressor is
constructed, so a config that sets only ollama_num_ctx (without
model.context_length) ran every request at the smaller served num_ctx
while the compressor still targeted the probed GGUF window (e.g. 256K
Gemma metadata). The compaction trigger then sat several times above the
window the server actually serves and never fired — reproducing the
original #57275 'blows past the limit' symptom on current main.

Live repro (real imports, temp HERMES_HOME, config = {model:
{ollama_num_ctx: 65536}}, probed window 262144):
  before: _ollama_num_ctx=65536, compressor.context_length=262144,
          threshold_tokens=196608 (300% of the served window)
  after:  compressor.context_length=65536, threshold below the window

The clamp is one-directional (a num_ctx larger than the resolved window
never inflates the compressor) and reuses update_model() so every
threshold-derived budget recalibrates. Overlaps #60103 (silent-clamp
dead zone) — this is the init-order half.

Reported by @Artemonim in #57275 (residual claim 3).
2026-08-31 12:22:17 -07:00
..