Sanjays2402 570f8bab8f fix(compression): exclude completion tokens from compression trigger (#12026) ... Cherry-picked from PR #12481 by @Sanjays2402. Reasoning models (GLM-5.1, QwQ, DeepSeek R1) inflate completion_tokens with internal thinking tokens. The compression trigger summed prompt_tokens + completion_tokens, causing premature compression at ~42% actual context usage instead of the configured 50% threshold. Now uses only prompt_tokens — completion tokens don't consume context window space for the next API call. - 3 new regression tests - Added AUTHOR_MAP entry for @Sanjays2402 Closes #12026		2026-04-20 05:12:10 -07:00
..
acp	fix(acp): silence 'Background task failed' noise on liveness-probe requests (#12855)	2026-04-20 00:10:27 -07:00
agent	test(error_classifier): broaden non-string message type coverage	2026-04-20 02:40:20 -07:00
cli	feat(cli): add editor workflow for drafts	2026-04-20 02:53:40 -07:00
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(telegram): cache inbound videos and accept mp4 uploads	2026-04-20 05:10:23 -07:00
hermes_cli	fix: enable plugins in config.yaml for lazy-discovery tests	2026-04-20 05:11:39 -07:00
honcho_plugin
integration
plugins	feat(plugins): make all plugins opt-in by default	2026-04-20 04:46:45 -07:00
run_agent	fix(compression): exclude completion tokens from compression trigger (#12026)	2026-04-20 05:12:10 -07:00
skills
tools	feat(plugins): add transform_tool_result hook for generic tool-result rewriting (#12972)	2026-04-20 03:48:08 -07:00
tui_gateway
__init__.py
conftest.py	feat(plugins): make all plugins opt-in by default	2026-04-20 04:46:45 -07:00
run_interrupt_test.py
test_batch_runner_checkpoint.py	fix(batch_runner): mark discarded no-reasoning prompts as completed (#9950)	2026-04-20 04:56:06 -07:00
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	fix(session_search): restore same-session context when message ids are interleaved	2026-04-20 05:10:03 -07:00
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.py	feat(plugins): add transform_tool_result hook for generic tool-result rewriting (#12972)	2026-04-20 03:48:08 -07:00
test_model_tools_async_bridge.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.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_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_transform_tool_result_hook.py	feat(plugins): add transform_tool_result hook for generic tool-result rewriting (#12972)	2026-04-20 03:48:08 -07:00
test_tui_gateway_server.py	fix(tui): /model picker surfaces curated list, matching classic CLI (#12671)	2026-04-19 16:15:22 -07:00
test_utils_truthy_values.py