Teknium 4f24db4258 fix(compression): enforce 64k floor on aux model + auto-correct threshold (#12898) ... Context compression silently failed when the auxiliary compression model's context window was smaller than the main model's compression threshold (e.g. GLM-4.5-air at 131k paired with a 150k threshold). The feasibility check warned but the session kept running and compression attempts errored out mid-conversation. Two changes in _check_compression_model_feasibility(): 1. Hard floor: if detected aux context < MINIMUM_CONTEXT_LENGTH (64k), raise ValueError so the session refuses to start. Mirrors the existing main-model rejection at AIAgent.__init__ line 1600. A compression model below 64k cannot summarise a full threshold-sized window. 2. Auto-correct: when aux context is >= 64k but below the computed threshold, lower the live compressor's threshold_tokens to aux_context (and update threshold_percent to match so later update_model() calls stay in sync). Warning reworded to say what was done and how to persist the fix in config.yaml. Only ValueError re-raises; other exceptions in the check remain swallowed as non-fatal.		2026-04-20 00:56:04 -07:00
..
acp	fix(acp): silence 'Background task failed' noise on liveness-probe requests (#12855)	2026-04-20 00:10:27 -07:00
agent	fix(aux): add session_search extra_body and concurrency controls	2026-04-20 00:47:39 -07:00
cli
cron	fix(ci): stub resolve_runtime_provider in cron wake-gate tests + shield update-check timeout test from thread race	2026-04-19 19:18:19 -07:00
e2e
environments/benchmarks
fakes
gateway	fix(signal): normalize direct recipients to UUIDs	2026-04-20 00:35:55 -07:00
hermes_cli	fix(config): add stale timeout settings	2026-04-20 00:52:50 -07:00
honcho_plugin
integration
plugins
run_agent	fix(compression): enforce 64k floor on aux model + auto-correct threshold (#12898)	2026-04-20 00:56:04 -07:00
skills
tools	fix(aux): add session_search extra_body and concurrency controls	2026-04-20 00:47:39 -07:00
tui_gateway
__init__.py
conftest.py
run_interrupt_test.py
test_batch_runner_checkpoint.py
test_cli_file_drop.py
test_cli_skin_integration.py
test_ctx_halving_fix.py
test_empty_model_fallback.py
test_evidence_store.py
test_hermes_constants.py
test_hermes_logging.py
test_hermes_state.py
test_honcho_client_config.py
test_ipv4_preference.py
test_mcp_serve.py
test_mini_swe_runner.py	fix: propagate kimi base-url temperature overrides	2026-04-19 18:54:35 -07:00
test_minimax_model_validation.py	fix(models): validate MiniMax models against static catalog (#12611, #12460, #12399, #12547)	2026-04-19 22:44:47 -07:00
test_minisweagent_path.py
test_model_picker_scroll.py
test_model_tools_async_bridge.py
test_model_tools.py
test_ollama_num_ctx.py
test_packaging_metadata.py
test_plugin_skills.py
test_project_metadata.py
test_retry_utils.py
test_sql_injection.py
test_subprocess_home_isolation.py
test_timezone.py
test_toolset_distributions.py
test_toolsets.py	fix(ci): unblock test suite + cut ~2s of dead Z.AI probes from every AIAgent	2026-04-19 19:18:19 -07:00
test_trajectory_compressor_async.py	test(kimi): cover api.moonshot.cn direct-call regressions\n\n- add run_agent coverage for the Moonshot China endpoint\n- add sync/async trajectory compressor coverage for api.moonshot.cn	2026-04-20 00:32:06 -07:00
test_trajectory_compressor.py	test(kimi): cover api.moonshot.cn direct-call regressions\n\n- add run_agent coverage for the Moonshot China endpoint\n- add sync/async trajectory compressor coverage for api.moonshot.cn	2026-04-20 00:32:06 -07:00
test_tui_gateway_server.py
test_utils_truthy_values.py