Files
hermes-agent/agent
kshitijk4poor af0be164c1 refactor(compression): one trigger derivation for update_model and the switch-guard preview
`preview_threshold_tokens` restated the resolve -> floor -> compute -> cap chain that `update_model`
runs; two copies of the trigger math drift the next time a step is added — the exact bug class
#83450 fixes (the guard quoting a number the compressor will not install). `_derive_trigger` is the
single pure derivation; the auxiliary-summariser ceiling stays in `_apply_threshold_tokens_cap`
because it is per-runtime, not per-model.

The startup banner names the cap only when it set the trigger; on windows where the ratio already
sits below it "(capped at 256,000)" was noise. Comments no longer repeat the default literal.
2026-09-19 16:28:57 +05:30
..
…
…