tools/approval.py no longer re-exports sibling names (approval_context/prompt/floors/detection/
human_wait/smart/gateway_wait); it imports only what it uses. Siblings reference sibling-defined
names directly (module-attribute reads on tools.approval_context so patching the defining module
still works); only facade-owned state (_lock, _gateway_queues, _permanent_approved, _denied,
_denial_breaker_addendum, _gateway_notify_cb) is still read back through tools.approval.
approval_detection calls its own _command_detection_variants instead of late-binding through the facade.
tools/terminal_tool.py: drop 30 pure re-export names (lifecycle/config/backends/
sudo/guards/result/interrupt/utils/_DockerEnvironment/is_managed_tool_gateway_ready)
and the noqa-F401 comments on the 25 names the facade itself uses. Sibling modules
(terminal_tool_backends/_result/_sudo/_lifecycle, environments/base, process_registry)
that read removed names through the facade now import from the defining module.
tools/environments/base.py: drop 11 re-exports (base_output/base_session_env/
path_utils) and the BaseEnvironment.stop() compat alias (no in-tree caller; the
lifecycle hasattr(env, 'stop') fallback stays for third-party envs).
tools/environments/docker.py: drop 1 re-export + the re-export comment.
Callers/tests repointed to tools.terminal_tool_{lifecycle,backends,sudo,config,
guards,result}, tools.interrupt, tools.environments.{base_output,base_session_env,
path_utils}.
run_agent.py: delete the `# noqa: F401` re-export block (agent.process_bootstrap
OpenAI/_SafeWriter/_get_proxy_*, model_tools get_tool_definitions/
handle_function_call/check_toolset_requirements, FailoverReason,
_qwen_portal_headers/_routermint_headers, session_persistence names,
estimate_request_tokens_rough, ContextCompressor + friends, jittered_backoff,
prompt_builder names, message_sanitization names, tool_dispatch_helpers
names) — 41 names run_agent never used itself — and the `_STREAM_DIAG_HEADERS`
back-compat class alias (no in-tree reader). run_agent now imports only what
it uses (get_toolset_for_tool, is_local_endpoint, coalesce/uniquify tool-call
ids, cleanup_vm/get_active_env from terminal_tool_lifecycle).
agent/*: `_ra().X` late-binds that only reached a re-export now import the
defining module directly (agent_runtime_helpers -> process_bootstrap.OpenAI,
model_tools.handle_function_call, session_persistence._safe_session_filename_component;
agent_init -> model_tools.get_tool_definitions/check_toolset_requirements,
_lazy_headers("agent.client_lifecycle", ...) for qwen/routermint;
system_prompt -> agent.prompt_builder / model_tools directly, dropping its
own _ra() shim and the `_r` parameter threading). `_ra()` stays for
run_agent-resident names (logger, AIAgent, _hermes_home, _set_interrupt, ...).
toolsets.py: remove resolve_multiple_toolsets (shim-only, restored by
34abf954bd); tests/test_toolsets.py pins the same union behavior via
resolve_toolset over each name.
providers/__init__.py: drop the OMIT_TEMPERATURE re-export (no callers via the
package); ProviderProfile stays because __init__ uses it for annotations —
2 tests repointed to providers.base.
agent/iteration_budget.py: drop the "run_agent re-exports the class"
docstring pointer; 4 tests import IterationBudget from its home.
model_tools.py (arg_coercion names), agent/tool_executor.py, and
hermes_cli/cli_session_mixin.py repoints landed via a sibling commit on this
shared worktree.
Callers repointed: gateway/run.py, hermes_cli/cli_chat_turn_mixin.py,
hermes_cli/cli_tui_mixin.py, tui_gateway/session_workdir.py,
agent/transports/codex.py (one-line imports) + comment pointers in
tools/file_state.py, tools/schema_sanitizer.py, scripts/tool_search_livetest.py.
Tests: patch("run_agent.X") / monkeypatch.setattr(run_agent, "X") /
`from run_agent import X` -> defining module across 99 test files.
326 methods lifted by AST (bodies identical; ast.dump-verified) into
hermes_cli/cli_{tui,status_bar,voice,model_switch,session,stream,modal,
terminal,info,loops}_mixin.py. cli.py-internal symbols resolve via lazy
'from cli import ...' inside each method (no import cycle; patch('cli.X')
keeps working). The three 'global' writers (_skill_commands, _cli_wake_owner)
now write the cli module attribute explicitly so the origin's readers still
see them. Dropped imports left unused in cli.py; kept display_hermes_home /
build_welcome_banner as re-exports (mixins + tests resolve them via cli).
Repointed two AST change-detector tests to cli_tui_mixin.py; one test
fixture now keeps 'cli' in sys.modules across its patch.dict scope.
70 nested closures (every prompt_toolkit key handler and handler factory, the
clarify/sudo/secret/approval/model-picker/command-palette/stash display
renderers, hint/placeholder/spinner callables, process_loop, spinner_loop,
_signal_handler, wake-startup) become HermesCLI._tui_* methods; run() only
binds them (kb.add(...)(self._tui_x)). The run() locals they closed over are
published on self at their original binding sites (_tui_multiline_shortcuts,
the four paste list-cells; process_loop reads self._app). Then four zero-
back-ref prologue regions become _tui_print_startup, _tui_init_run_state,
_tui_build_key_bindings -> kb and _tui_build_layout(kb) -> (layout, style).
All moved bodies verified AST-identical modulo cli_ref->self and the free-var
rewrites; unresolved-free-name check on every new method is empty. Source-
inspection tests repointed: getsource(run) -> _tui_process_loop, AST lookup of
handle_enter -> _tui_handle_enter.
process_command resolves the canonical command (hermes_cli/commands.py registry)
to a handler via _slash_handler(): a 44-entry _SLASH_DISPATCH table for the
irregular cases (no-arg handlers, differently named methods, /exit and /update
return-value adapters) and the _handle_<name>_command(cmd) naming convention for
the other 47. Inline branch bodies became small _cmd_<name> methods; the
else-fallthrough (quick_commands -> plugins -> bundles -> skills -> prefix
expansion -> unknown) became _process_unregistered_slash. Pre-dispatch side
effects (pre_command hook, pending-resume disarm) and the False-exits-REPL
contract are unchanged. Also unifies the three random-tip blocks into
_print_random_tip and the repeated arg parsing into _slash_args; removes two
zero-reference helpers (_run_curses_picker, _try_launch_chrome_debug).
Parity guard: tests/cli/test_slash_dispatch_table.py asserts every command of
the old chain resolves and that no other registry command silently gained a
handler.
GatewayRunner.__init__ snapshotted _ephemeral_system_prompt once from the
launch profile's config and _get_system_prompt_for_channel returned that
string for every source, so under multiplex a routed profile's
display.personality / agent.system_prompt never injected (#89161), and
/personality from any chat rewrote the one process-global attribute for
everyone.
Drop the snapshot: _get_system_prompt_for_channel now calls
_load_ephemeral_system_prompt() (env var, then
resolve_ephemeral_system_prompt_from_config(_load_gateway_runtime_config()))
on each call. Its caller run_sync already runs inside
_profile_runtime_scope, so the routed profile's config.yaml is what gets
read; single-profile hot-edits of the personality also take effect on the
next turn instead of requiring a restart. /personality only persists via
persist_personality() (get_hermes_home()/config.yaml = the routed profile)
and no longer touches in-memory state.
Fixes#89161
Co-authored-by: worlldz <101180447+worlldz@users.noreply.github.com>
Adds two bounded fast modes on top of the static /fast toggle, default OFF:
- `auto`: every user turn opens a `agent.fast_auto_seconds` (default 60s)
window; requests inside it carry the provider fast param, later tool-loop
requests fall back to standard pricing.
- `cold`: the same window, but only on the first turn of a session (no prior
user/assistant/tool history).
agent/fast_mode.py holds the whole policy: `begin_turn()` at the
run_conversation ingress arms `agent._fast_until`; `effective_request_overrides()`
is consumed in the ONE place request_overrides feed the transports
(build_api_kwargs), so the fast param is a per-request kwarg only. System
prompt, tools and messages are untouched — the prompt cache is preserved.
resolve_fast_mode_overrides() is now the single gate for static and bounded
modes and accepts provider/base_url: OpenRouter, Nous, Copilot, Azure,
Bedrock and custom base_urls never receive service_tier/speed (#34308's
route gating). Both existing callers (CLI turn route, gateway turn route)
and the TUI config.set path pass the route.
Surfaces: config `agent.service_tier: auto|cold` + `agent.fast_auto_seconds`,
`/fast auto|cold` in CLI, gateway (picker gains both entries), TUI/desktop
config.set; status shows the mode; web dashboard select lists the real
values. Docs: configuration.md Fast Mode section with mode table + cost note,
slash-commands, cli-config.yaml.example, locale strings for the two picker
entries.
Salvages #89991 (bounded fast modes) and #34308 (route gating).
Fixes#64785, #74730.
Co-authored-by: Eva <239388517+100yenadmin@users.noreply.github.com>
Co-authored-by: kbaicai <kbaicai@qq.com>
The speed=fast allowlist still gates on Opus 4.6, but the fast-mode
matrix has changed twice since it was written (verified against the
live docs, platform.claude.com/docs/en/build-with-claude/fast-mode):
- Opus 4.8 and Opus 5 SUPPORT fast mode (research preview, Claude API
only — not Bedrock/Vertex/Foundry).
- Opus 4.6 LOST fast mode on 2026-06-29. The parameter does not error:
requests silently run at standard speed and bill standard rates
(usage.speed: 'standard'). Today's allowlist therefore shows 4.6
users a fast toggle that does nothing, while denying it to the two
models that actually support it.
- Opus 4.7 never had it and hard-400s (unchanged).
- Dedicated '…-fast' model ids (OpenRouter's claude-opus-4.8-fast)
select fast inference via the model field and are explicitly
excluded from the param gate.
Both gates move in lock-step as before: the adapter param gate
(agent.anthropic_adapter._supports_fast_mode) and the CLI toggle gate
(hermes_cli.models._is_anthropic_fast_model). Docstrings now record
the history in both directions so the next matrix change has context.
## How to test
scripts/run_tests.sh tests/agent/test_anthropic_adapter.py tests/cli/test_fast_command.py -- -q
113 tests pass. The updated predicate/matrix tests fail against the
previous allowlist (verified by stashing the source changes). Tested
on Linux (aarch64).
Desktop's cold resume (defer_history + omit_messages, transcript paged over
REST) only ever holds the live tip segment in memory, but session.resume
bounded it against the FULL compression lineage (sessions.max_resume_messages,
default 20000). A Bot Chat with 85 compaction segments / ~29k lineage rows
behind a ~700-row tip was refused at 20001, sent zero model prompts, and sat on
"Waking up default…" forever — the healthiest possible session shape, rejected
by a guard sized for in-memory materialization.
- hermes_state: one `_resume_lineage_ids` definition shared by the resume
readers (get_resume_conversations, get_ancestor_display_prefix) and the
guard (assert_resume_safe / get_resume_message_count). Guard grows
`tip_only=` and names the scope it counted; the branch-aware lineage the
readers already used is now what the guard counts too (a /branch copy was
being counted against its parent's rows).
- tui_gateway session.resume: deferred, omit_messages and lazy resumes are
bounded by the tip; only the full in-memory lineage resume keeps the
lineage-wide bound. Deferred hydration falls back to tip-only history when
the lineage exceeds the limit instead of loading the rows the guard refused.
- CLI mid-setup tip-only path routes through the same guard instead of
borrowing assert_export_safe.
- docs: sessions.max_resume_messages / max_export_messages documented with the
per-surface scope.
Live repro (real SessionDB fixture, 85 segments / 29,226 lineage rows / 666 tip
rows, real tui_gateway.server.handle_request): before — deferred resume ->
4130; after — ok, hydrated history=666 prefix=0; the non-deferred full resume
still returns 4130 on the same fixture.
hermes chat -q wired the interactive prompt_toolkit clarify callback
unconditionally, but a -q turn never builds the prompt_toolkit
application — the modal can never be painted or answered, so the turn
polls its response queue until agent.clarify_timeout expires (default
3600 s, 0 = unlimited). The gateway, cron jobs, the kanban dispatcher
and inter-agent wakeups all deliver work as -q turns. Route the
single-query case to a headless callback at the agent-construction site
that already knows _single_query_mode, mirroring _oneshot_clarify_callback
on the -z path (#94943; third member of the family after #86909 and
#88013).
Follow-up to the salvaged #88097: the same normalization covers the
Shift+letter class reported in #92343 (xterm modifyOtherKeys and both
kitty CSI-u codepoint forms), plus a guard that plain ASCII typing
never triggers the ESC-prefix predicate.
Two growth leaks closed:
1. Pushed-branch tier (the dominant survivor class — 24 of 33 preserved
trees, ~18GB on the reporting box): managed installs fetch with a
single-branch refspec, so pushed PR branches never get refs/remotes/*
entries and read as 'unpushed' forever. When a clean tree's branch head
EXACTLY matches origin (one lazy git ls-remote per sweep), the checkout
is redundant: reap the TREE, keep the BRANCH ref (shielded from the
orphaned-branch pass). Anything diverged/unverifiable stays preserved.
Applied to both the startup pruner and hermes worktree prune/list.
2. Cron-tick maintenance: the pruner only ran on hermes -w launches, so
gateway-driven boxes accumulated trees for days. The scheduler tick now
dispatches the same conservative pruner on a daemon thread, throttled
to once per 6h, against the install checkout + job-workdir repos that
have a .worktrees/ dir.
Follow-up to the cherry-picked #41909/#92696 + #39760 + #97970 cluster:
- single field-key namespace (display.status_bar.fields) instead of the
second tui_statusbar_fields list; cache_hit/latency/tps/stash/battery/
title join the existing key set
- cache-hit % prefers the baseline-delta regime (resets on model switch
and compression) and hides on zero cache reads instead of alarming 0%
- latency/tps segments added to the styled fragment renderer too
- docs updated in website/docs/user-guide/configuration.md
- 7 new tests: rolling latency/t/s, NaN/negative guard, field filtering,
baseline resets, title badge gating
Add a ◎ XX% indicator to the CLI status bar showing the prompt cache
hit rate (cache_read / prompt_tokens). This helps users monitor how
effectively their provider's prompt caching is working.
Features:
- Color-coded: green (≥70%), yellow (40-70%), red (<40%)
- Adaptive precision: integer on narrow terminals, one decimal on wide
- Only shown when cache data is available (provider supports it)
- Compatible with OpenAI, Anthropic, DeepSeek, xiaomi, and other
providers that return prompt_tokens_details.cached_tokens
Tests: 6 new test cases, 43/43 passing
Allow users to control which fields appear in the interactive CLI status
bar via display.status_bar.fields in config.yaml.
Available fields: model, context_pct, context_detail, compressions,
bg_tasks, bg_processes, duration, prompt_elapsed, yolo, total_tokens.
When the list is empty (default), all fields are shown as before.
The field order is fixed (model always first); the config controls
visibility only. Narrow terminals (<76 cols) automatically drop
context_detail regardless of config.
total_tokens is opt-in only (not shown by default) to avoid width
overflow in the prompt_toolkit fragment renderer.
Closes#41909
Live-reproduced on main: /handoff poll-waited a flat 60s for a TERMINAL
state, but the gateway's dispatch is a full synthetic agent turn (whole
transcript replay + delivery) that routinely exceeds 60s on long sessions.
The CLI then printed "Timed out waiting for the gateway. Is `hermes
gateway` running?" (false diagnosis), called fail_handoff() on the RUNNING
row (stomping the gateway's claim), and promised "Your CLI session is
intact" after switch_session had already re-pointed the session. The
watcher later overwrote failed -> completed: split-brain.
- hermes_state.fail_handoff gains only_states CAS; waiters can only fail
rows still pending. Owner (gateway watcher) keeps the unconditional form.
- CLI wait loop is two-phase: 60s for the CLAIM (pending) — a timeout
there really does mean no gateway — then up to 15 min for the claimed
dispatch with 30s heartbeats; a running row is never failed by the CLI.
- Desktop handoff.fail RPC now CAS-fails pending rows only; a running row
returns {failed: false, state: running} instead of stomping the claim.
Repro (real _handoff_watcher, real state.db, CLI as separate process,
75s dispatch): before — CLI timeout @60s + false message + row stomped;
after — pending->running@5s->completed@80s, clean CLI exit.
74a95a3ddf promoted /bg and /btw to independent canonical commands and
retired /background entirely (hermes_cli/commands.py's COMMAND_REGISTRY
has no "background" command or alias). Three places still taught the
old name:
- skills/autonomous-ai-agents/hermes-agent/references/slash-commands.md:
the bundled hermes-agent skill's own slash-command reference — the
skill's SKILL.md explicitly routes the model here for in-session
command questions, so a model following it would emit the dead
`/background <prompt>` and never learn /btw exists.
- ui-tui/README.md: listed /btw as an alias of /background, which is
simply wrong post-split (both are independent, alias-free commands).
- tests/cli/test_cli_background_status_indicator.py: docstring/comments
described the ▶ indicator by the retired command name.
No behavior change; corrects documentation only.
/bg (formerly /background, which is retired) keeps the existing semantics:
spawn a fresh, independent agent session in the background.
/btw is now its own command matching the convention other harnesses use:
ask a quick side question ABOUT the current conversation without
interrupting it. A one-shot auxiliary LLM call (main model by default,
overridable via auxiliary.side_question.* in config.yaml) answers from a
read-only transcript snapshot — the live session's history, role
alternation, and prompt cache are untouched, and the current turn keeps
running.
Surfaces wired: CLI (inline mid-run dispatch), gateway (all messengers,
busy-dispatch table + idle dispatch, i18n across all 17 locales), TUI
(prompt.btw RPC + btw.complete event), Discord native slash, relay
command manifest, desktop exec routing, docs (EN + zh-Hans).
Reuse kitty Unicode placeholders plus after_render write_raw so
prompt_toolkit's screen-diff can host the same crisp sprite as the TUI.
Re-queue the transmit after Ctrl+L / resize so the image comes back.
Co-authored-by: Sam Foreman <saforem2@gmail.com>
The protected agent-instruction gate grants one operation and persists
nothing, but only the TUI/desktop and Runs transports were taught that.
The prompt_toolkit panel, the input() fallback, and the ACP editor menu
still rendered "Allow for session", so a user editing SOUL.md tapped it,
got re-prompted on the next write, and read the gate as broken.
Thread allow_session through prompt_dangerous_approval so a caller that
re-asks every time collapses every surface to once/deny, and cover the
producer-to-transport contract end to end.
text.splitlines() returns [] for empty strings. Accessing msg_lines[0]
then raises IndexError, making session resume crash when the session
contains a message with empty or whitespace-only text (e.g. reasoning-only
turns, tool-only assistant messages).
Guard with `or [""]` in all three branches (user, assistant_last,
regular assistant) so an empty message renders as a blank line.
Fixes#59265
Co-authored-by: AlexFucuson9 <AlexFucuson9@users.noreply.github.com>
tests/tools/test_website_policy.py and tests/cli/test_surrogate_sanitization.py
repeatedly failed under the parallel CI runner (process-teardown timeouts /
async-timeout flakes) across multiple unrelated PRs this cycle, while passing
locally. Removed per maintainer direction to stop the flake taxing every PR.
Builds on @fattchris resolve_turn_limit salvage (#67696): flips the default
from a numeric cap to unlimited across all construction paths (CLI, agent_init,
run_agent subagents), adds inf/infinity/null to the unlimited spellings, and
sets DEFAULT_CONFIG agent.max_turns to null. The turn cap caused more problems
than it solved (silent mid-task truncation).
Two gaps behind the recurring 'hermes -w timed out after 30 seconds':
1. Rebase-merge leak: git cherry only catches patch-identical commits.
Salvage flows routinely change the diff (conflict resolution, follow-up
commits), so 12 of 22 'unpushed' trees on the incident box had MERGED
PRs and were preserved forever. The pruner now falls back to
'gh pr list --head <branch> --state merged' — authoritative, memoized
on (branch, head_sha) with True-only caching, fail-safe to preserve.
2. Creation timeout 30s -> 120s: the ~10k-file checkout measured 113s at
near-zero CPU under multi-agent disk contention vs 1.2s idle. 30s
killed legitimate creates and threw away completed work.
Follow-up to the salvaged #89676 + #90291 lock-bit fixes: extract a shared _lock_variants() helper and cover the sites both PRs missed - install_shift_enter_alias / install_ctrl_enter_alias / install_cmd_backspace_alias CSI-u spellings, legacy CSI-letter and CSI-tilde navigation twins derived from the existing table for ALL modifiers 1-16 (not just plain/shift), plain F1-F4 SS3 fallback, unmodified CSI-u keys (Tab/Enter/Space/Backspace), and kitty PUA functional keys (keypad, F13-F24, Ignore range) under lock bits. 8 new tests.
kitty and ghostty OR the CapsLock (64) / NumLock (128) state into the
CSI-u modifier parameter. With NumLock on, Ctrl+C arrives as
ESC[99;133u (5 + 128) instead of ESC[99;5u; the alias table had no
entry for it, so every key combo leaked as literal text like
[127;133u (#89651). Install every CSI-u alias with the lock-bit
variants (+64/+128/+192); the xterm modifyOtherKeys encoding never
carries lock bits, so the ESC[27;N;CP~ form is left untouched. The
Esc-key registration now covers modifier 1 as well (1+128=129 is a
lone Esc with NumLock on).
Widen the cli.py Ghostty exception to the sibling sites the review found: the Ink TUI pushes CSI >1u at raw-mode entry (App.tsx), on alt-screen exit, and on the extended-keys re-assert path (ink.tsx) for every EXTENDED_KEYS_TERMINALS entry including ghostty - same Alt-stripping bug. New skipKittyKeyboardProtocol() helper in terminal.ts gates the ENABLE push at all 3 sites; the DISABLE (pop) stays unconditional since popping an empty stack is a spec no-op. Also fix the cli.py comment citing the modifyOtherKeys encoding where the kitty CSI-u form (ESC[127;3u) is what the broken path expected, dedupe the quadruplicated Ghostty comment, and update the stale 'mirroring the Ink TUI' docstring. 7 new vitest cases.
Ghostty's Kitty disambiguate-mode implementation strips the Alt modifier
from the Backspace key — Option+Backspace arrives as bare \x7f instead of
the expected \x1b[27;3;127~, breaking backward-kill-word. This was a
regression introduced when PR #87630 re-added the CSI >1u Kitty protocol
push for all allowlisted terminals including Ghostty.
Under modifyOtherKeys mode (CSI >4;2m), Ghostty correctly sends
\x1b[27;3;127~ for Option+Backspace, which the alias table in
pt_input_extras already maps to (Escape, ControlH) = backward-kill-word.
Fix: for Ghostty only, push just modifyOtherKeys and skip the Kitty
protocol push. All other terminals (iTerm2, WezTerm, kitty, tmux, VS Code)
still get the full dual-protocol push.
Ghostty upstream tracking: discussion #9560, issue #9895 (cmd+backspace
variant of the same root cause).
Teknium