Drexuxux fb1b89b09e fix(prompt-caching): inject cache breakpoints after message normalization ... The conversation loop normalizes message text right before the API call so the request prefix is byte-identical across turns -- the stated reason is KV cache reuse on local inference servers and better cache hit rates on cloud providers. Cache breakpoints were injected *before* that pass, which defeats it. `_apply_cache_marker` rewrites a plain-string `content` into a `[{"type": "text", ...}]` block. The normalization pass is guarded on `isinstance(content, str)`, so every message that just got marked is silently skipped by it and keeps its raw leading/trailing whitespace. A message is only marked while it sits in the last-3 window, so: turn N in the window -> marked, content "file1\nfile2\n" turn N+1 rolled out -> plain, content "file1\nfile2" The same logical message is sent with different bytes on consecutive turns. The prefix stops matching at that position -- which is inside the span the breakpoints were placed to protect -- so the reusable prefix collapses back toward the system breakpoint on every turn. Tool results carry a trailing newline almost by default (any shell command output), so this is the common case, not an edge case. Move the injection below every message mutation. Besides fixing the whitespace divergence this stops breakpoints from being spent on messages that the orphan sweep or the thinking-only drop is about to remove or merge away -- a marker on a dropped message is a wasted breakpoint out of the four available. Nothing between the old and new call sites reads `cache_control`, and the mutators now see the plain-string shapes they were written against.		2026-07-24 16:01:38 -07:00
..
acp	feat(acp): list named custom providers in the ACP model selector	2026-07-24 15:57:30 -07:00
acp_adapter	feat(surfaces): route busy-input corrections through active-turn redirect	2026-07-22 12:10:58 -05:00
agent	fix(prompt-caching): inject cache breakpoints after message normalization	2026-07-24 16:01:38 -07:00
ci	fix(ci): report E2E evidence upload failures (#69901)	2026-07-23 05:45:17 +00:00
cli	Reapply "Merge pull request #30179 from NousResearch/feat/iron-proxy"	2026-07-24 09:49:00 -07:00
computer_use	Merge remote-tracking branch 'origin/main' into bb/computer-use-perf	2026-07-23 01:39:21 -05:00
cron	fix: update heartbeat test stubs to accept workdir kwarg	2026-07-24 15:55:39 -07:00
dashboard	fix(dashboard): use loopback host for in-container WebSocket client (#58993) [salvage #59682] (#60092)	2026-07-07 18:33:28 +10:00
docker	test(docker): cover tini -g legacy entrypoint boot path	2026-07-18 01:11:03 -07:00
e2e	fix(slack): handle leading-space text commands	2026-07-22 20:55:51 -07:00
fakes
fixtures/plugins/example-dashboard/dashboard
gateway	test: order compression-tip fixtures around the closed-parent write guard	2026-07-24 16:00:34 -07:00
hermes_cli	fix(checkpoints): bind an empty orphan preview to an empty deletion allowlist	2026-07-24 16:01:06 -07:00
hermes_state	fix(state): heal alternation at the ACP / CLI-resume / TUI-resume restore sites too	2026-07-17 06:53:38 -07:00
honcho_plugin	fix(honcho): default device-code poll interval to 5s when AS omits it	2026-07-24 07:53:12 -07:00
integration	fix: remove dead f-string prefixes via ruff F541 (216 sites) (#52336)	2026-07-05 13:42:46 -07:00
manual	docs(cron): scope in_channel to channels; document DM continuation knob	2026-07-01 03:16:13 -07:00
openviking_plugin	fix(openviking): cool down failed refreshes and publish conn identity atomically	2026-07-24 13:00:53 +05:30
plugins	fix(openviking): serialize client refresh state	2026-07-24 13:00:53 +05:30
providers	feat(nous): send top-level session_id for provider sticky routing (#69253)	2026-07-22 04:39:20 -07:00
run_agent	fix(agent): cache static system prompt prefixes	2026-07-24 16:01:38 -07:00
scripts	feat(linter): detect subprocess text=True without explicit encoding=	2026-07-24 11:45:57 -07:00
secret_sources	feat(secrets): orchestrator-level preserve_existing + profile aliasing (#69058)	2026-07-22 03:20:45 -07:00
skills	fix(skills): keep xurl SKILL self-contained; move x_search routing to gated surfaces	2026-07-23 21:06:47 -07:00
state	fix(compression): recover rotated session lineage	2026-07-24 16:00:34 -07:00
stress	fix: remove dead f-string prefixes via ruff F541 (216 sites) (#52336)	2026-07-05 13:42:46 -07:00
tools	fix(checkpoints): bind orphan confirmation to previewed identities	2026-07-24 16:01:06 -07:00
tui_gateway	fix(tui_gateway): recover custom provider identity from the session's model name	2026-07-24 10:47:32 -07:00
website
__init__.py
conftest.py	feat(slack): bridge slack.ignored_channels through the YAML→env config path	2026-07-23 12:01:24 -07:00
run_interrupt_test.py
test_account_usage.py
test_atomic_replace_symlinks.py	fix(config): preserve owner on atomic writes (#56644)	2026-07-03 14:27:34 +10:00
test_background_review_list_shapes.py	fix(background-review): guard summarize against list-shaped tool responses (#59437)	2026-07-06 03:28:30 -07:00
test_background_review_session_isolation.py	test(review): add integration guards for the two isolation wirings (review)	2026-07-01 16:21:39 +05:30
test_base_url_hostname.py
test_batch_runner_checkpoint.py
test_bitwarden_secrets.py	fix(secrets): unify encrypted-cache fallback with the merged stale-cache path	2026-07-22 04:40:07 -07:00
test_cli_file_drop.py
test_cli_manual_compress.py	test(cli): prove /compress type-ahead queue-drain; map contributor email	2026-07-23 07:24:46 -07:00
test_cli_skin_integration.py
test_code_skew.py
test_command_secret_source.py	feat(secrets): rework command source as a registered SecretSource — no provider selector	2026-07-22 04:39:28 -07:00
test_copilot_initiator.py	fix(copilot): set x-initiator per turn so user prompts bill as premium requests (salvage #4097) (#58544)	2026-07-05 00:44:15 -07:00
test_credential_file_permissions.py	harden(slack): CDN-allowlist inbound file URLs, DNS-pin token downloads, widen token-file perms warning	2026-07-23 11:44:43 -07:00
test_ctx_halving_fix.py	chore: restore test_ctx_halving_fix.py to main	2026-07-14 03:58:54 +05:30
test_delegate_cascade_49148.py
test_dispatch_session_id.py
test_empty_model_fallback.py	feat(models): catalog-labeled silent default — GLM-5.2 marked "default": true in the model catalog	2026-07-15 00:10:31 -07:00
test_empty_session_hygiene.py
test_env_loader_applied_homes.py	fix(secrets): mark _APPLIED_HOMES only after a real fetch attempt (#40597) (#69056)	2026-07-22 03:20:25 -07:00
test_env_loader_op_bootstrap.py	fix(secrets): make 1Password bootstrap token reliable outside systemd	2026-07-06 04:58:07 -07:00
test_env_loader_secret_sources.py	test(secrets): match real ApplyReport shape in isolation test	2026-07-22 04:39:17 -07:00
test_evidence_store.py
test_fast_safe_load.py	perf(startup): parse config + plugin manifests with libyaml CSafeLoader (#54486)	2026-06-28 15:38:39 -07:00
test_fts_cjk_bigram.py	test(state): cover pure-Latin embedded-in-CJK recovery via the cjk index	2026-07-22 10:35:04 -07:00
test_gateway_streaming_nested_config.py	fix(gateway): normalize YAML boolean streaming mode and keep enabled a mode-only alias	2026-07-20 05:39:09 -07:00
test_get_tool_definitions_cache_isolation.py
test_hermes_bootstrap.py	fix(windows): platform._syscmd_ver stub in bootstrap + PYTHONUTF8 in desktop backend env	2026-07-24 15:47:12 -07:00
test_hermes_constants.py	fix(dashboard): keep custom themes visible after embedded chat starts (#60601)	2026-07-18 00:34:54 -04:00
test_hermes_home_profile_warning.py
test_hermes_logging.py	fix(logging): drive rotating file handlers through an async QueueListener	2026-07-05 11:44:53 +05:30
test_hermes_state.py	fix(compression): recover rotated session lineage	2026-07-24 16:00:34 -07:00
test_hermes_state_compression_locks.py	fix(compression): prefer psutil.pid_exists for lease liveness probe; add same-pid self-reclaim guard	2026-07-23 16:21:19 -07:00
test_hermes_state_wal_fallback.py	test(state): cover SQLite WAL-reset version gate and doctor probe	2026-07-23 17:32:38 +05:30
test_honcho_client_concurrency.py
test_honcho_client_config.py	feat(honcho): make latency-adding paths configurable	2026-07-16 12:48:48 -07:00
test_honcho_session_context.py
test_honcho_startup_fail_open.py	fix(ci): make tests, workflows, and attribution reliable under load (#66373)	2026-07-17 20:55:24 +00:00
test_install_autostash_conflict_recovery.py	test: add happy-path + no-markers coverage for autostash recovery	2026-07-18 19:18:03 +05:30
test_install_diverged_update.py	test(installer): cover diverged managed-clone recovery in install scripts	2026-06-30 20:11:01 +07:00
test_install_lockfile_churn.py	fix(install): discard managed lockfile churn before stashing	2026-06-25 23:49:11 -07:00
test_install_no_initial_commit.py
test_install_ps1_ascii_only.py	fix(install): keep install.ps1 pure ASCII so Windows PowerShell 5.1 doesn't misparse it	2026-07-18 18:40:59 -04:00
test_install_ps1_native_stderr_eap.py
test_install_ps1_node_path_for_npm.py	test(installer): guard Ensure-NodeExeOnPath wiring in install.ps1	2026-07-07 21:17:34 +07:00
test_install_ps1_python_fallback_venv.py
test_install_ps1_uv_powershell_host.py
test_install_ps1_web_server_syntax_probe.py	fix(install): guard Windows desktop installs against broken web_server	2026-07-05 19:35:30 -07:00
test_install_sh_browser_install.py	test(install): track run_with_timeout extraction after #39219 refactor (#54185)	2026-06-28 03:58:01 -07:00
test_install_sh_install_method_stamp.py
test_install_sh_node_global_prefix.py	fix(hermes): heal broken managed Node tree instead of PATH fallback	2026-06-26 20:10:20 +05:30
test_install_sh_pythonpath_sanitization.py
test_install_sh_root_fhs_uv_python_path.py
test_install_sh_setup_wizard_tty_probe.py
test_install_sh_symlink_stomp.py
test_install_sh_termux_network_prereqs.py
test_install_unmerged_index.py	fix(install): discard managed lockfile churn before stashing	2026-06-25 23:49:11 -07:00
test_ipv4_preference.py
test_iron_proxy.py	Reapply "Merge pull request #30179 from NousResearch/feat/iron-proxy"	2026-07-24 09:49:00 -07:00
test_iron_proxy_cli.py	Reapply "Merge pull request #30179 from NousResearch/feat/iron-proxy"	2026-07-24 09:49:00 -07:00
test_iron_proxy_e2e.py	Reapply "Merge pull request #30179 from NousResearch/feat/iron-proxy"	2026-07-24 09:49:00 -07:00
test_lazy_session_regressions.py
test_lint_config.py
test_live_system_guard_self_test.py	fix(tests): make the live-system-guard canary fail closed	2026-07-21 12:15:46 +05:30
test_mcp_serve.py	refactor: consolidate gateway session metadata into state.db (#58899)	2026-07-05 14:01:03 -07:00
test_mini_swe_runner.py
test_minimax_model_validation.py
test_minimax_oauth.py
test_minisweagent_path.py
test_model_forces_max_completion_tokens.py
test_model_picker_scroll.py
test_model_tools.py	fix(toolsets): preserve core tools when a posture toolset is in disabled_toolsets (#57315)	2026-07-05 14:51:49 -07:00
test_model_tools_async_bridge.py
test_ollama_num_ctx.py	test(vision): cover Ollama /api/show vision capability routing (#54511)	2026-06-28 22:52:59 -07:00
test_onepassword_secrets.py	fix(secrets): pass OP_LOAD_DESKTOP_APP_SETTINGS through to the op child env	2026-07-22 03:19:32 -07:00
test_output_cap_parsing.py	fix(context): parse vLLM's token-based output-cap error format	2026-07-01 03:17:48 -07:00
test_packaging_build_guard.py	rip out brew + pip/PyPI wheel support (#68217)	2026-07-22 16:51:01 -04:00
test_packaging_metadata.py	rip out brew + pip/PyPI wheel support (#68217)	2026-07-22 16:51:01 -04:00
test_plugin_skills.py
test_plugin_utils.py
test_process_loop_event_loop_warning.py
test_profile_isolation_runtime.py	test(profile): two-profile regression suite + preserve skills_hub monkeypatch seam	2026-06-30 15:30:06 -07:00
test_project_metadata.py	rip out brew + pip/PyPI wheel support (#68217)	2026-07-22 16:51:01 -04:00
test_pty_keepalive_ws.py	fix(dashboard): scope chat attach tokens by session (#60745)	2026-07-16 19:48:47 -04:00
test_pty_session.py	feat(pty): periodic reaper wired into dashboard lifespan	2026-07-07 15:15:37 -07:00
test_retry_utils.py	refactor(retry): single-source Z.AI overload short-attempts + drop change-detector assert	2026-07-07 11:57:01 +05:30
test_run_tests_parallel.py	fix(ci): make tests, workflows, and attribution reliable under load (#66373)	2026-07-17 20:55:24 +00:00
test_sanitize_tool_error.py
test_search_slow_query_log.py	feat(state): messages_fts_cjk — CJK-bigram index on the v23 external-content layout	2026-07-22 07:56:47 -07:00
test_session_workspace_binding.py	feat(sessions): workspace_key grouping helper + tests	2026-07-12 05:07:52 -04:00
test_slack_thread_require_mention.py	Add Slack thread mention gating	2026-07-22 21:14:44 -07:00
test_slash_worker_watchdog.py	test(tui): keep watchdog checks behavior-focused	2026-07-18 04:15:13 -07:00
test_sql_injection.py
test_sqlite_wal_reset_gate.py	test(runtime): cover managed SQLite cutover (E-949)	2026-07-24 16:00:03 -07:00
test_stale_utils_module_import.py
test_state_db_malformed_repair.py	perf(state): external-content FTS + tool-row-free trigram index (schema v23) (#65798)	2026-07-22 04:42:50 -07:00
test_subprocess_home_isolation.py
test_telegram_polling_progress_ptb.py	test(telegram): gate slots premise assert on runtimes without instance __dict__	2026-07-14 21:25:44 -07:00
test_termux_all_extra_compat.py
test_timezone.py
test_tini_shim.py	test(docker): cover tini -g legacy entrypoint boot path	2026-07-18 01:11:03 -07:00
test_toolset_distributions.py
test_toolsets.py	docs(xai): clarify x_search vs xurl routing without schema cross-refs	2026-07-23 21:06:47 -07:00
test_trajectory_compressor.py	fix(compaction): skip compression when it can't reduce tokens	2026-07-23 16:21:03 -07:00
test_trajectory_compressor_async.py
test_transform_llm_output_hook.py
test_transform_tool_result_hook.py
test_tui_entry_mcp_owner.py	fix(tui): gate the shared-owner MCP discovery wait on the stdio TUI flag	2026-07-21 12:43:27 -07:00
test_tui_gateway_loop_noise.py	fix(tui_gateway): suppress WS peer-hangup teardown error flood (#50005) (#54126)	2026-06-28 02:35:01 -07:00
test_tui_gateway_queue_on_busy.py	fix(desktop): preserve active correction on warm resume (#69725)	2026-07-22 21:53:56 -04:00
test_tui_gateway_server.py	fix: serialize on-demand slash-worker spawn per session	2026-07-24 15:58:32 -07:00
test_tui_gateway_ws.py	fix(tui_gateway): preserve websocket batch order (#69684)	2026-07-23 05:02:45 +00:00
test_tui_mcp_late_refresh.py
test_utils_truthy_values.py
test_wal_checkpoint_strategy.py	fix(state): use PASSIVE checkpoint for periodic WAL flush to prevent B-tree corruption	2026-07-15 04:55:46 -07:00
test_web_server.py	feat(serve): add secure Desktop SSH bootstrap contract	2026-07-16 14:43:14 +02:00
test_web_server_sessiondb_eventloop.py	Merge pull request #65893 from NousResearch/bb/salvage-63082-sessiondb-offload	2026-07-16 15:23:32 -04:00
test_windows_subprocess_no_window_flags.py	fix(cron): respect the platform-conditional decode design in _run_job_script + taskkill kwarg snapshot	2026-07-24 11:45:57 -07:00
test_yaml_indent_consistency_31999.py	fix(utils): unify YAML list indent across all config writers (#31999)	2026-06-25 23:27:44 +05:30
test_yuanbao_integration.py
test_yuanbao_markdown.py
test_yuanbao_pipeline.py	perf(yuanbao): bounded-concurrency inbound media resolve	2026-07-08 08:05:45 -07:00
test_yuanbao_proto.py
test_yuanbao_reconnect_set_active.py	fix(yuanbao): restore active singleton after WS reconnect	2026-07-05 00:41:34 -07:00
test_yuanbao_shutdown.py