The hardcoded User-Agent 'KimiCLI/1.3' is outdated — Kimi CLI is now at
v1.30.0. The stale version string causes intermittent 403 errors from
Kimi's coding endpoint ('only available for Coding Agents').
Update all 8 occurrences across run_agent.py, auxiliary_client.py, and
doctor.py to 'KimiCLI/1.30.0' to match the current official Kimi CLI.
The gateway /usage handler only looked in _running_agents for the agent
object, which is only populated while the agent is actively processing a
message. Between turns (when users actually type /usage), the dict is
empty and the handler fell through to a rough message-count estimate.
The agent object actually lives in _agent_cache between turns (kept for
prompt caching). This fix checks both dicts, with _running_agents taking
priority (mid-turn) and _agent_cache as the between-turns fallback.
Also brings the gateway output to parity with the CLI /usage:
- Model name
- Detailed token breakdown (input, output, cache read, cache write)
- Cost estimation (estimated amount or 'included' for subscriptions)
- Cache token lines hidden when zero (cleaner output)
This fixes Nous Portal rate limit headers not showing up for gateway
users — the data was being captured correctly but the handler could
never see it.
Extends the /fast command to support Anthropic's Fast Mode beta in addition
to OpenAI Priority Processing. When enabled on Claude Opus 4.6, adds
speed:"fast" and the fast-mode-2026-02-01 beta header to API requests for
~2.5x faster output token throughput.
Changes:
- hermes_cli/models.py: Add _ANTHROPIC_FAST_MODE_MODELS registry,
model_supports_fast_mode() now recognizes Claude Opus 4.6,
resolve_fast_mode_overrides() returns {speed: fast} for Anthropic
vs {service_tier: priority} for OpenAI
- agent/anthropic_adapter.py: Add _FAST_MODE_BETA constant,
build_anthropic_kwargs() accepts fast_mode=True which injects
speed:fast + beta header via extra_headers (skipped for third-party
Anthropic-compatible endpoints like MiniMax)
- run_agent.py: Pass fast_mode to build_anthropic_kwargs in the
anthropic_messages path of _build_api_kwargs()
- cli.py: Update _handle_fast_command with provider-aware messaging
(shows 'Anthropic Fast Mode' vs 'Priority Processing')
- hermes_cli/commands.py: Update /fast description to mention both
providers
- tests: 13 new tests covering Anthropic model detection, override
resolution, CLI availability, routing, adapter kwargs, and
third-party endpoint safety
When `hermes update` stashes local changes and the restore hits merge
conflicts, the old code prompted the user to reset or keep conflict
markers. If the user declined the reset, git conflict markers
(<<<<<<< Updated upstream) were left in source files, making hermes
completely unrunnable with a SyntaxError on the next invocation.
Additionally, the interactive path called sys.exit(1), which killed
the entire update process before pip dependency install, skill sync,
and gateway restart could finish — even though the code pull itself
had succeeded.
Changes:
- Always auto-reset to clean state when stash restore conflicts
- Remove the "Reset working tree?" prompt (footgun)
- Remove sys.exit(1) — return False so cmd_update continues normally
- User's changes remain safely in the stash for manual recovery
Also fixes a secondary bug where the conflict handling prompt used
bare input() instead of the input_fn parameter, which would hang
in gateway mode.
Tests updated: replaced prompt/sys.exit assertions with auto-reset
behavior checks; removed the "user declines reset" test (path no
longer exists).
After mid-loop compression (triggered by 413, context_overflow, or Anthropic
long-context tier errors), _compress_context() creates a new session in SQLite
and resets _last_flushed_db_idx=0. However, conversation_history was not cleared,
so _flush_messages_to_session_db() computed:
flush_from = max(len(conversation_history=200), _last_flushed_db_idx=0) = 200
messages[200:] → empty (compressed messages < 200)
This resulted in zero messages being written to the new session's SQLite store.
On resume, the user would see 'Session found but has no messages.'
The preflight compression path (line 7311) already had the fix:
conversation_history = None
This commit adds the same clearing to the three mid-loop compression sites:
- Anthropic long-context tier overflow
- HTTP 413 payload too large
- Generic context_overflow error
Reported by Aaryan (Nous community).
The text batching feature routes TEXT messages through
asyncio.create_task() + asyncio.sleep(delay). Even with delay=0,
the task fires asynchronously and won't complete before synchronous
test assertions. This broke 33 tests across Discord, Matrix, and
WeCom adapters.
When _text_batch_delay_seconds is 0 (the test fixture setting),
dispatch directly to handle_message() instead of going through
the async batching path. This preserves the pre-batching behavior
for tests while keeping batching active in production (default
delay 0.6s).
Add streaming timeout documentation to three pages:
- guides/local-llm-on-mac.md: New 'Timeouts' section with table of all
three timeouts, their defaults, local auto-adjustments, and env var
overrides
- reference/faq.md: Tip box in the local models FAQ section
- user-guide/configuration.md: 'Streaming Timeouts' subsection under
the agent config section
Follow-up to #6967.
Set _text_batch_delay_seconds = 0 on test adapter fixtures so messages
dispatch immediately (bypassing async batching). This preserves the
existing synchronous assertion patterns while the batching logic is
tested separately in test_text_batching.py.
22 tests covering:
- Single message dispatch after delay
- Split message aggregation (2-way and 3-way)
- Different chats/rooms not merged
- Adaptive delay for near-limit chunks
- State cleanup after flush
- Split continuation merging
All 5 platform adapters tested.
Feishu already had text batching with a static 0.6s delay. This adds
adaptive delay: waits 2.0s when a chunk is near the ~4096-char split
point since a continuation is almost certain.
Tracks _last_chunk_len on each queued event to determine the delay.
Configurable via HERMES_FEISHU_TEXT_BATCH_SPLIT_DELAY_SECONDS (default 2.0).
Ref #6892
Ports the adaptive batching pattern from the Telegram adapter.
WeCom clients split messages around 4000 chars. Adaptive delay waits
2.0s when a chunk is near the limit, 0.6s otherwise. Only text messages
are batched; commands/media dispatch immediately.
Ref #6892
Ports the adaptive batching pattern from the Telegram adapter.
Matrix clients split messages around 4000 chars. Adaptive delay waits
2.0s when a chunk is near the limit, 0.6s otherwise. Only text messages
are batched; commands dispatch immediately.
Ref #6892
Cherry-picked from PR #6894 by SHL0MS with fixes:
- Only batch TEXT messages; commands/media dispatch immediately
- Use build_session_key() for proper session-scoped batch keys
- Consistent naming (_text_batch_delay_seconds)
- Proper Dict[str, MessageEvent] typing
Discord splits at 2000 chars (lowest of all platforms). Adaptive delay
waits 2.0s when a chunk is near the limit, 0.6s otherwise.
Cherry-picked from PR #6891 by SHL0MS.
When a chunk is near the 4096-char split point, wait 2.0s instead of 0.6s
since a continuation is almost certain.
Raise the default httpx stream read timeout from 60s to 120s for all
providers. Additionally, auto-detect local LLM endpoints (Ollama,
llama.cpp, vLLM) and raise the read timeout to HERMES_API_TIMEOUT
(1800s) since local models can take minutes for prefill on large
contexts before producing the first token.
The stale stream timeout already had this local auto-detection pattern;
the httpx read timeout was missing it — causing a hard 60s wall that
users couldn't find (HERMES_STREAM_READ_TIMEOUT was undocumented).
Changes:
- Default HERMES_STREAM_READ_TIMEOUT: 60s -> 120s
- Auto-detect local endpoints -> raise to 1800s (user override respected)
- Document HERMES_STREAM_READ_TIMEOUT and HERMES_STREAM_STALE_TIMEOUT
- Add 10 parametrized tests
Reported-by: Pavan Srinivas (@pavanandums)
When the model mentions <think> as literal text in its response (e.g.
"(/think not producing <think> tags)"), the streaming display treated it
as a reasoning block opener and suppressed everything after it. The
response box would close with truncated content and no error — the API
response was complete but the display ate it.
Root cause: _stream_delta() matched <think> anywhere in the text stream
regardless of position. Real reasoning blocks always start at the
beginning of a line; mentions in prose appear mid-sentence.
Fix: track line position across streaming deltas with a
_stream_last_was_newline flag. Only enter reasoning suppression when
the tag appears at a block boundary (start of stream, after a newline,
or after only whitespace on the current line). Add a _flush_stream()
safety net that recovers buffered content if no closing tag is found
by end-of-stream.
Also fixes three related issues discovered during investigation:
- anthropic_adapter: _get_anthropic_max_output() now normalizes dots to
hyphens so 'claude-opus-4.6' matches the 'claude-opus-4-6' table key
(was returning 32K instead of 128K)
- run_agent: send explicit max_tokens for Claude models on Nous Portal,
same as OpenRouter — both proxy to Anthropic's API which requires it.
Without it the backend defaults to a low limit that truncates responses.
- run_agent: reset truncated_tool_call_retries after successful tool
execution so a single truncation doesn't poison the entire conversation.
Previously /fast only supported gpt-5.4 and forced a provider switch to
openai-codex. Now supports all 13 models from OpenAI's Priority Processing
pricing table (gpt-5.4, gpt-5.4-mini, gpt-5.2, gpt-5.1, gpt-5, gpt-5-mini,
gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, gpt-4o, gpt-4o-mini, o3, o4-mini).
Key changes:
- Replaced _FAST_MODE_BACKEND_CONFIG with _PRIORITY_PROCESSING_MODELS frozenset
- Removed provider-forcing logic — service_tier is now injected into whatever
API path the user is already on (Codex Responses, Chat Completions, or
OpenRouter passthrough)
- Added request_overrides support to chat_completions path in run_agent.py
- Updated messaging from 'Codex inference tier' to 'Priority Processing'
- Expanded test coverage for all supported models
Add /fast slash command to toggle OpenAI Codex service_tier between
normal and priority ('fast') inference. Only exposed for models
registered in _FAST_MODE_BACKEND_CONFIG (currently gpt-5.4).
- Registry-based backend config for extensibility
- Dynamic command visibility (hidden from help/autocomplete for
non-supported models) via command_filter on SlashCommandCompleter
- service_tier flows through request_overrides from route resolution
- Omit max_output_tokens for Codex backend (rejects it)
- Persists to config.yaml under agent.service_tier
Salvage cleanup: removed simple_term_menu/input() menu (banned),
bare /fast now shows status like /reasoning. Removed redundant
override resolution in _build_api_kwargs — single source of truth
via request_overrides from route.
Co-authored-by: Hermes Agent <hermes@nousresearch.com>
The Codex retry block and valid-token short-circuit in _refresh_entry()
both return early, bypassing the auth.json sync at the end of the method.
This adds _sync_device_code_entry_to_auth_store() calls on both paths
so refreshed/synced tokens are written back to auth.json regardless of
which code path succeeds.
When OpenRouter returns 'No endpoints found that support tool use'
(HTTP 404), display a hint explaining that provider routing restrictions
may be filtering out tool-capable providers. Links the user directly
to the model's OpenRouter page to check which providers support tools.
The hint fires in the error display block that runs regardless of whether
fallback succeeds — so the user always understands WHY the model failed,
not just that it fell back.
Reported via Discord: GLM-5.1 on OpenRouter with US-based provider
restrictions eliminated all 4 tool-supporting endpoints (DeepInfra,
Z.AI, Friendli, Venice), leaving only 7 non-tool providers.
MiniMax's Anthropic-compatible endpoints reject requests that include
the fine-grained-tool-streaming beta header — every tool-use message
triggers a connection error (~18s timeout). Regular chat works fine.
Add _common_betas_for_base_url() that filters out the tool-streaming
beta for Bearer-auth (MiniMax) endpoints while keeping all other betas.
All four client-construction branches now use the filtered list.
Based on #6528 by @HiddenPuppy.
Original cherry-picked from PR #6688 by kshitijk4poor.
Fixes#6510, fixes#6555.
* feat: API server model name derived from profile name
For multi-user setups (e.g. OpenWebUI), each profile's API server now
advertises a distinct model name on /v1/models:
- Profile 'lucas' -> model ID 'lucas'
- Profile 'admin' -> model ID 'admin'
- Default profile -> 'hermes-agent' (unchanged)
Explicit override via API_SERVER_MODEL_NAME env var or
platforms.api_server.model_name config for custom names.
Resolves friction where OpenWebUI couldn't distinguish multiple
hermes-agent connections all advertising the same model name.
* docs: multi-user setup with profiles for API server + Open WebUI
- api-server.md: added Multi-User Setup section, API_SERVER_MODEL_NAME
to config table, updated /v1/models description
- open-webui.md: added Multi-User Setup with Profiles section with
step-by-step guide, updated model name references
- environment-variables.md: added API_SERVER_MODEL_NAME entry
When a streaming response is cut mid-tool-call (connection drop, timeout),
the accumulated function.arguments is invalid JSON. The mock response
builder defaulted finish_reason to 'stop', so the agent loop treated it
as a valid completed turn and tried to execute tools with broken args.
Fix: validate tool call arguments with json.loads() during mock response
reconstruction. If any are invalid JSON, override finish_reason to
'length'. In the main loop's length handler, if tool calls are present,
refuse to execute and return partial=True with a clear error instead of
silently failing or wasting retries.
Also fixes _thinking_exhausted to not short-circuit when tool calls are
present — truncated tool calls are not thinking exhaustion.
Original cherry-picked from PR #6776 by AIandI0x1.
Closes#6638.
The test was mocking _vprint entirely, bypassing the suppress guard.
Switch to capturing _print_fn output so the real _vprint runs and
the guard suppresses retry noise as intended.
Replace 6 identical copies of the Termux detection function across
cli.py, browser_tool.py, voice_mode.py, status.py, doctor.py, and
gateway.py with a single shared implementation in hermes_constants.py.
Each call site imports with its original local name to preserve all
existing callers (internal references and test monkeypatches).
_classify_by_message had no handling for _USAGE_LIMIT_PATTERNS, so
messages like 'usage limit exceeded, try again in 5 minutes' arriving
without an HTTP status code fell through to FailoverReason.unknown
instead of rate_limit.
Apply the same billing/rate-limit disambiguation that _classify_402
already uses: USAGE_LIMIT_PATTERNS + transient signal → rate_limit,
USAGE_LIMIT_PATTERNS alone → billing.
Add 4 tests covering the no-status-code usage-limit path.
* feat(nix): shared-state permission model for interactive CLI users
Enable interactive CLI users in the hermes group to share full
read-write state (sessions, memories, logs, cron) with the gateway
service via a setgid + group-writable permission model.
Changes:
nix/nixosModules.nix:
- Directories use setgid 2770 (was 0750) so new files inherit the
hermes group. home/ stays 0750 (no interactive write needed).
- Activation script creates HERMES_HOME subdirs (cron, sessions, logs,
memories) — previously Python created them but managed mode now skips
mkdir.
- Activation migrates existing runtime files to group-writable (chmod
g+rw). Nix-managed files (config.yaml, .env, .managed) stay 0640/0644.
- Gateway systemd unit gets UMask=0007 so files it creates are 0660.
hermes_cli/config.py:
- ensure_hermes_home() splits into managed/unmanaged paths. Managed mode
verifies dirs exist (raises RuntimeError if not) instead of creating
them. Scoped umask(0o007) ensures SOUL.md is created as 0660.
hermes_logging.py:
- _ManagedRotatingFileHandler subclass applies chmod 0660 after log
rotation in managed mode. RotatingFileHandler.doRollover() creates new
files via open() which uses the process umask (0022 → 0644), not the
scoped umask from ensure_hermes_home().
Verified with a 13-subtest NixOS VM integration test covering setgid,
interactive writes, file ownership, migration, and gateway coexistence.
Refs: #6044
* Fix managed log file mode on initial open
Co-authored-by: Siddharth Balyan <alt-glitch@users.noreply.github.com>
* refactor: simplify managed file handler and merge activation loops
- Cache is_managed() result in handler __init__ instead of lazy-importing
on every _open()/_chmod_if_managed() call. Avoids repeated stat+env
checks on log rotation.
- Merge two for-loops over the same subdir list in activation script
into a single loop (mkdir + chown + chmod + find in one pass).
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Siddharth Balyan <alt-glitch@users.noreply.github.com>
The overflow split loop required _message_id to be set, but on the
first streamed message (or after a segment break) _message_id is None.
Oversized text fell through to _send_or_edit → adapter.send(), which
split internally — but subsequent edits hit Telegram's 'message too
long' and were silently truncated with '…', cutting off the response.
Add a new code path for the _message_id is None case that uses
truncate_message() (same as the non-streaming path) to split with
proper word/code-fence boundaries and chunk indicators. Each chunk
is sent as a new message via _send_new_chunk().
Properly handles got_done (returns immediately after sending chunks
instead of continuing into an infinite loop) and got_segment_break.
Original cherry-picked from PR #6816 by dangelo352.
Fixes silent message truncation on Telegram for long streamed responses.
Chrome auto-launch now passes --user-data-dir, --no-first-run, and
--no-default-browser-check so the debug instance doesn't conflict with
an already-running Chrome using the default profile. The profile dir
lives at {hermes_home}/chrome-debug/.
Also updates the fallback manual instructions to include the same flags
and removes the stale 'close existing Chrome windows' hint.
When managed_persistence is enabled, cleanup_all now only clears local
tracking state without sending DELETE requests to the Camofox server.
This prevents persistent browser profiles (cookies, logins, localStorage)
from being destroyed during process-wide cleanup.
Ephemeral sessions still get full server-side deletion as before.
Chrome auto-launch now passes --user-data-dir, --no-first-run, and
--no-default-browser-check so the debug instance doesn't conflict with
an already-running Chrome using the default profile. The profile dir
lives at {hermes_home}/chrome-debug/.
Also updates the fallback manual instructions to include the same flags
and removes the stale 'close existing Chrome windows' hint.
