fix(compressor): pass threshold_percent through update_model on model switch#18638
Open
liuhao1024 wants to merge 1 commit into
Open
fix(compressor): pass threshold_percent through update_model on model switch#18638liuhao1024 wants to merge 1 commit into
liuhao1024 wants to merge 1 commit into
Conversation
… switch When the model changes at runtime (via /model command, fallback activation, or primary restore), ContextCompressor.update_model() recalculates threshold_tokens from context_length × threshold_percent. But threshold_percent was never updated — it retained the old model's value. This commit: - Adds threshold_percent parameter to update_model() - Passes the current threshold_percent at all three model-switch call sites - Saves threshold_percent in _primary_runtime for restore - Uses the saved value when restoring primary runtime Closes NousResearch#18617
9 tasks
Cyrene963
pushed a commit
to Cyrene963/hermes-agent
that referenced
this pull request
May 3, 2026
Community PRs applied: - NousResearch#18596: Enable secret redaction by default (SECURITY) - NousResearch#18650: Sanitize malformed tool messages + auto-recover on API 400 - NousResearch#18607: Emergency compression before max_iterations exhaustion - NousResearch#18603: Compression fallback to main model on 413 rate limit - NousResearch#18638: Pass threshold_percent on model switch - NousResearch#18663: Strip extra_content from tool_calls for strict APIs - NousResearch#18618: Forward explicit_api_key to OpenRouter - NousResearch#18632: Show cache tokens in /insights breakdown - NousResearch#18614: Add idempotency guard for patch duplicate loops - NousResearch#18600: Raise ValueError when HERMES_HOME unset in profile mode - NousResearch#18616: Allow ZWJ emoji in context files - NousResearch#18582: Reload .env on /restart - NousResearch#18547: Stabilize system prompt prefix for KV cache reuse - NousResearch#18692: Strip FTS5 operators from session search truncation terms Fix: Add order_by_last_active=True to list_sessions_rich call (pre-existing commit 142b4bf code sync)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does this PR do?
When the model changes at runtime (via
/modelcommand, fallback activation, or primary restore),ContextCompressor.update_model()recalculatesthreshold_tokensfromcontext_length × threshold_percent. Butthreshold_percentwas never passed through — it retained the value from whichever model the compressor was initialized with.This means switching from a 200K model (threshold at 70% = 140K) to a 1M model would still use 70% → 700K threshold, even if a different percentage was configured or expected for the new model.
Related Issue
N/A
Type of Change
Changes Made
agent/context_compressor.py: Add optionalthreshold_percentparameter toupdate_model(). When provided, updatesself.threshold_percentbefore recalculatingthreshold_tokens.run_agent.py—switch_model(): Pass the compressor's currentthreshold_percentthroughupdate_model()so it's preserved across model switches.run_agent.py—_try_activate_fallback(): Same — passthreshold_percentso fallback doesn't lose the configured value.run_agent.py—_restore_primary_runtime(): Readcompressor_threshold_percentfrom the saved_primary_runtimedict and pass it toupdate_model(). Also savethreshold_percentin_primary_runtimeduringswitch_model().tests/agent/test_update_model_threshold_percent.py: 5 tests covering the new parameter, backward compatibility (no-op when not passed), threshold floor preservation, and token recalculation.How to Test
pytest tests/ -q— all tests should passChecklist
Code
fix(scope):,feat(scope):, etc.)pytest tests/ -qand all tests passDocumentation & Housekeeping
docs/, docstrings) — or N/Acli-config.yaml.exampleif I added/changed config keys — or N/ACONTRIBUTING.mdorAGENTS.mdif I changed architecture and workflows — or N/A