- Added support for true-color ANSI escape codes in the HermesCLI to enhance the visual appearance of streamed content.
- Introduced a fallback mechanism for text color in case of errors while retrieving the color from the active skin.
- Updated the output formatting to include the new text color in both line emissions and buffer flushing.
These changes improve the user experience by ensuring consistent and visually appealing text output in the command-line interface.
Remove the memory and skill nudges that were appended directly to user
messages, causing backward-looking system instructions to compete with
forward-looking user tasks. Found in 43% of user messages across 15
sessions, with confirmed cases of the agent spending tool calls on
nudge responses before starting the user's actual request.
Replace with a background review agent that runs AFTER the main agent
finishes responding:
- Spawns a background thread with a snapshot of the conversation
- Uses the main model (not auxiliary) for high-precision memory/skill work
- Only has memory + skill_manage tools (5 iteration budget)
- Shares the memory store for direct writes
- Never modifies the main conversation history
- Never competes with the user's task for model attention
- Zero latency impact (runs after response is delivered)
- Same token cost (processes the same context, just on a separate track)
The trigger conditions are unchanged (every 10 user turns for memory,
after 10+ tool iterations for skills). Only the execution path changes:
from inline injection to background fork.
Closes#2227.
Co-authored-by: Test <test@test.com>
- Changed the ANSI escape code for gold color in cli.py and banner.py to use true-color format (#FFD700) for better visual consistency.
- Enhanced the _on_tool_progress method in HermesCLI to update the TUI spinner with tool execution status, improving user feedback during operations.
These changes improve the visual representation and user experience in the command-line interface.
Co-authored-by: Test <test@test.com>
Remove the [Files already read — do NOT re-read these] user message
that was injected into the conversation after context compression.
This message used role='user' for system-generated content, creating
a fake user turn that confused models about conversation state and
could contribute to task-redo behavior.
The file_tools.py read tracker (warn on 3rd consecutive read, block
on 4th+) already handles re-read prevention inline without injecting
synthetic messages.
Closes#2224.
Co-authored-by: Test <test@test.com>
In Docker/systemd/piped environments, the KawaiiSpinner animation
generates ~500 log lines per tool call. Now checks isatty() and
falls back to clean [tool]/[done] log lines in non-TTY contexts.
Interactive CLI behavior unchanged.
Based on work by 42-evey in PR #2203.
The official international DashScope endpoint uses dashscope-intl.aliyuncs.com
(per Alibaba docs), which the substring match on dashscope.aliyuncs.com misses
because of the hyphenated prefix.
Replace asyncio.run() with thread-local persistent event loops for
worker threads (e.g., delegate_task's ThreadPoolExecutor). asyncio.run()
creates and closes a fresh loop on every call, leaving cached
httpx/AsyncOpenAI clients bound to a dead loop — causing 'Event loop is
closed' errors during GC when parallel subagents clean up connections.
The fix mirrors the main thread's _get_tool_loop() pattern but uses
threading.local() so each worker thread gets its own long-lived loop,
avoiding both cross-thread contention and the create-destroy lifecycle.
Added 4 regression tests covering worker loop persistence, reuse,
per-thread isolation, and separation from the main thread's loop.
If a tool_calls list contains a None entry (from malformed API response,
compression artifact, or corrupt session replay), convert_messages_to_anthropic
crashes with AttributeError: 'NoneType' object has no attribute 'get'.
Skip None and non-dict entries in the tool_calls iteration. Found via
chaos/fuzz testing with mixed valid/invalid tool_call entries.
Custom endpoint users (DashScope/Alibaba, Z.AI, Kimi, DeepSeek, etc.)
get wrong context lengths because their provider resolves as "openrouter"
or "custom", skipping the models.dev lookup entirely. For example,
qwen3.5-plus on DashScope falls to the generic "qwen" hardcoded default
(131K) instead of the correct 1M.
Add _infer_provider_from_url() that maps known API hostnames to their
models.dev provider IDs. When the explicit provider is generic
(openrouter/custom/empty), infer from the base URL before the models.dev
lookup. This resolves context lengths correctly for DashScope, Z.AI,
Kimi, MiniMax, DeepSeek, and Nous endpoints without requiring users to
manually set context_length in config.
Also refactors _is_known_provider_base_url() to use the same URL mapping,
removing the duplicated hostname list.
When the model returns multiple tool calls, run_agent.py executes them
concurrently in a ThreadPoolExecutor. Each thread called _run_async()
which used a shared persistent event loop (_get_tool_loop()). If two
async tools (like web_extract) ran in parallel, the second thread would
hit 'This event loop is already running' on the shared loop.
Fix: detect worker threads (not main thread) and use asyncio.run() with
a per-thread fresh loop instead of the shared persistent one. The shared
loop is still used for the main thread (CLI sequential path) to keep
cached async clients (httpx/AsyncOpenAI) alive.
Co-authored-by: Test <test@test.com>
- Convert ~~text~~ to ~text~ (MarkdownV2 strikethrough)
- Protect ||text|| from pipe escaping (MarkdownV2 spoiler)
- Preserve > at line start as blockquote instead of escaping it
- Update _strip_mdv2() to strip ~strikethrough~ and ||spoiler|| markers
- Add tests covering new formatting paths and edge cases
- Updated _stream_delta method in HermesCLI to handle None values, flushing the stream and resetting state for clean tool execution.
- Enhanced quiet mode handling in AIAgent to ensure proper display closure before tool execution, preventing display issues with intermediate streamed content.
These changes improve the robustness of the streaming functionality and ensure a smoother user experience during tool interactions.
Cherry-picked from PR #2146 by @crazywriter1. Fixes#2104.
asyncio.run() creates and closes a fresh event loop each call. Cached
httpx/AsyncOpenAI clients bound to the dead loop crash on GC with
'Event loop is closed'. This hit vision_analyze on first use in CLI.
Two-layer fix:
- model_tools._run_async(): replace asyncio.run() with persistent
loop via _get_tool_loop() + run_until_complete()
- auxiliary_client._get_cached_client(): track which loop created
each async client, discard stale entries if loop is closed
6 regression tests covering loop lifecycle, reuse, and full vision
dispatch chain.
Co-authored-by: Test <test@test.com>
Adds /queue <prompt> (alias /q) that queues a message for the next
turn while the agent is busy, without interrupting the current run.
- CLI: /queue <prompt> puts it in _pending_input for the next turn
- Gateway: /queue <prompt> creates a pending MessageEvent on the
adapter, picked up after the current agent run finishes
- Enter still interrupts as usual (no behavior change)
- /queue with no prompt shows usage
- /queue when agent is idle tells user to just type normally
Co-authored-by: Test <test@test.com>
Salvaged from PR #2162 by @Zindar. Reply prefix changes excluded (already
on main via #1756 configurable prefix).
Bridge improvements (bridge.js):
- Download incoming images to ~/.hermes/image_cache/ via downloadMediaMessage
so the agent can actually see user-sent photos
- Add getMessage callback required for Baileys 7.x E2EE session
re-establishment (without it, some messages arrive as null)
- Build LID→phone reverse map for allowlist resolution (WhatsApp LID format)
- Add placeholder body for media without caption: [image received]
- Bind express to 127.0.0.1 instead of 0.0.0.0 for security
- Use 127.0.0.1 consistently throughout (more reliable than localhost)
Adapter improvements (whatsapp.py):
- Detect and reuse already-running bridge (only if status=connected)
- Handle local file paths from bridge-cached images in _build_message_event
- Don't kill external bridges on disconnect
- Use 127.0.0.1 throughout for consistency with bridge binding
Fix vs original PR: bridge reuse now checks status=connected, not just
HTTP 200. A disconnected bridge gets restarted instead of reused.
Co-authored-by: Zindar <zindar@users.noreply.github.com>
Cherry-picked from PR #2169 by @0xbyt4.
1. _strip_provider_prefix: skip Ollama model:tag names (qwen:0.5b)
2. Fuzzy match: remove reverse direction that made claude-sonnet-4
resolve to 1M instead of 200K
3. _has_content_after_think_block: reuse _strip_think_blocks() to
handle all tag variants (thinking, reasoning, REASONING_SCRATCHPAD)
4. models.dev lookup: elif→if so nous provider also queries models.dev
5. Disk cache fallback: use 5-min TTL instead of full hour so network
is retried soon
6. Delegate build: wrap child construction in try/finally so
_last_resolved_tool_names is always restored on exception
Matrix, Mattermost, Home Assistant, and DingTalk were missing from the
platform_map in both cron/scheduler.py and tools/send_message_tool.py,
causing delivery to those platforms to silently fail.
Also updates the cronjob tool schema description to list all available
delivery targets so the model knows its options.
Two fixes for Telegram/gateway-specific bugs:
1. Anthropic adapter: strip orphaned tool_result blocks (mirror of
existing tool_use stripping). Context compression or session
truncation can remove an assistant message containing a tool_use
while leaving the subsequent tool_result intact. Anthropic rejects
these with a 400: 'unexpected tool_use_id found in tool_result
blocks'. The adapter now collects all tool_use IDs and filters out
any tool_result blocks referencing IDs not in that set.
2. Gateway: /reset and /new now bypass the running-agent guard (like
/status already does). Previously, sending /reset while an agent
was running caused the raw text to be queued and later fed back as
a user message with the same broken history — replaying the
corrupted session instead of resetting it. Now the running agent is
interrupted, pending messages are cleared, and the reset command
dispatches immediately.
Tests updated: existing tests now include proper tool_use→tool_result
pairs; two new tests cover orphaned tool_result stripping.
Co-authored-by: Test <test@test.com>
- quickstart.md: mention context length prompt for custom endpoints,
link to configuration docs, add Ollama to provider table
- faq.md: rewrite local models section with hermes model flow and
context length prompt example, add Ollama num_ctx tip, expand
context-length-exceeded troubleshooting with detection override
options and config.yaml examples
Co-authored-by: Test <test@test.com>
* feat: context pressure warnings for CLI and gateway
User-facing notifications as context approaches the compaction threshold.
Warnings fire at 60% and 85% of the way to compaction — relative to
the configured compression threshold, not the raw context window.
CLI: Formatted line with a progress bar showing distance to compaction.
Cyan at 60% (approaching), bold yellow at 85% (imminent).
◐ context ▰▰▰▰▰▰▰▰▰▰▰▰▱▱▱▱▱▱▱▱ 60% to compaction 100k threshold (50%) · approaching compaction
⚠ context ▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▰▱▱▱ 85% to compaction 100k threshold (50%) · compaction imminent
Gateway: Plain-text notification sent to the user's chat via the new
status_callback mechanism (asyncio.run_coroutine_threadsafe bridge,
same pattern as step_callback).
Does NOT inject into the message stream. The LLM never sees these
warnings. Flags reset after each compaction cycle.
Files changed:
- agent/display.py — format_context_pressure(), format_context_pressure_gateway()
- run_agent.py — status_callback param, _context_50/70_warned flags,
_emit_context_pressure(), flag reset in _compress_context()
- gateway/run.py — _status_callback_sync bridge, wired to AIAgent
- tests/test_context_pressure.py — 23 tests
* Merge remote-tracking branch 'origin/main' into hermes/hermes-7ea545bf
---------
Co-authored-by: Test <test@test.com>
Matrix is a supported gateway platform but was missing from the
cron scheduler's delivery platform_map, causing cron job results
to silently fail delivery when targeting Matrix rooms.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace the fragile hardcoded context length system with a multi-source
resolution chain that correctly identifies context windows per provider.
Key changes:
- New agent/models_dev.py: Fetches and caches the models.dev registry
(3800+ models across 100+ providers with per-provider context windows).
In-memory cache (1hr TTL) + disk cache for cold starts.
- Rewritten get_model_context_length() resolution chain:
0. Config override (model.context_length)
1. Custom providers per-model context_length
2. Persistent disk cache
3. Endpoint /models (local servers)
4. Anthropic /v1/models API (max_input_tokens, API-key only)
5. OpenRouter live API (existing, unchanged)
6. Nous suffix-match via OpenRouter (dot/dash normalization)
7. models.dev registry lookup (provider-aware)
8. Thin hardcoded defaults (broad family patterns)
9. 128K fallback (was 2M)
- Provider-aware context: same model now correctly resolves to different
context windows per provider (e.g. claude-opus-4.6: 1M on Anthropic,
128K on GitHub Copilot). Provider name flows through ContextCompressor.
- DEFAULT_CONTEXT_LENGTHS shrunk from 80+ entries to ~16 broad patterns.
models.dev replaces the per-model hardcoding.
- CONTEXT_PROBE_TIERS changed from [2M, 1M, 512K, 200K, 128K, 64K, 32K]
to [128K, 64K, 32K, 16K, 8K]. Unknown models no longer start at 2M.
- hermes model: prompts for context_length when configuring custom
endpoints. Supports shorthand (32k, 128K). Saved to custom_providers
per-model config.
- custom_providers schema extended with optional models dict for
per-model context_length (backward compatible).
- Nous Portal: suffix-matches bare IDs (claude-opus-4-6) against
OpenRouter's prefixed IDs (anthropic/claude-opus-4.6) with dot/dash
normalization. Handles all 15 current Nous models.
- Anthropic direct: queries /v1/models for max_input_tokens. Only works
with regular API keys (sk-ant-api*), not OAuth tokens. Falls through
to models.dev for OAuth users.
Tests: 5574 passed (18 new tests for models_dev + updated probe tiers)
Docs: Updated configuration.md context length section, AGENTS.md
Co-authored-by: Test <test@test.com>
Cron jobs run unattended with no user present. Previously the agent had
send_message and clarify tools available, which makes no sense — the
final response is auto-delivered, and there's nobody to ask questions to.
Changes:
- Disable messaging and clarify toolsets for cron agent sessions
- Update cron platform hint to emphasize autonomous execution: no user
present, cannot ask questions, must execute fully and make decisions
- Update cronjob tool schema description to match (remove stale
send_message guidance)
When streaming was enabled, two visual feedback mechanisms were
completely suppressed:
1. The thinking spinner (TUI toolbar) was skipped because the entire
spinner block was gated on 'not self._has_stream_consumers()'.
Now the thinking_callback fires in streaming mode too — the
raw KawaiiSpinner is still skipped (would conflict with streamed
tokens) but the TUI toolbar widget works fine alongside streaming.
2. Tool progress lines (the ┊ feed) were invisible because _vprint
was blanket-suppressed when stream consumers existed. But during
tool execution, no tokens are actively streaming, so printing is
safe. Added an _executing_tools flag that _vprint respects to
allow output during tool execution even with stream consumers
registered.
Based on PR #1859 by @magi-morph (too stale to cherry-pick, reimplemented).
GPT-5.x models reject tool calls + reasoning_effort on
/v1/chat/completions with a 400 error directing to /v1/responses.
This auto-detects api.openai.com in the base URL and switches to
codex_responses mode in three places:
- AIAgent.__init__: upgrades chat_completions → codex_responses
- _try_activate_fallback(): same routing for fallback model
- runtime_provider.py: _detect_api_mode_for_url() for both custom
provider and openrouter runtime resolution paths
Also extracts _is_direct_openai_url() helper to replace the inline
check in _max_tokens_param().
Support Signal 'Note to Self' messages in single-number setups where
signal-cli is linked as a secondary device on the user's own account.
syncMessage.sentMessage envelopes addressed to the bot's own account
are now promoted to dataMessage for normal processing, while other
sync events (read receipts, typing, etc.) are still filtered.
Echo-back prevention mirrors the WhatsApp bridge pattern:
- Track timestamps of recently sent messages (bounded set of 50)
- When a Note to Self sync arrives, check if its timestamp matches
a recent outbound — skip if so (agent echo-back)
- Only process sync messages that are genuinely user-initiated
Based on PR #2115 by @Stonelinks with added echo-back protection.
* fix: preserve Ollama model:tag colons in context length detection
The colon-split logic in get_model_context_length() and
_query_local_context_length() assumed any colon meant provider:model
format (e.g. "local:my-model"). But Ollama uses model:tag format
(e.g. "qwen3.5:27b"), so the split turned "qwen3.5:27b" into just
"27b" — which matches nothing, causing a fallback to the 2M token
probe tier.
Now only recognised provider prefixes (local, openrouter, anthropic,
etc.) are stripped. Ollama model:tag names pass through intact.
* fix: update claude-opus-4-6 and claude-sonnet-4-6 context length from 200K to 1M
Both models support 1,000,000 token context windows. The hardcoded defaults
were set before Anthropic expanded the context for the 4.6 generation.
Verified via models.dev and OpenRouter API data.
---------
Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com>
Co-authored-by: Test <test@test.com>
Cherry-picked from PR #2120 by @unclebumpy.
- from_env() now reads HONCHO_BASE_URL and enables Honcho when base_url
is set, even without an API key
- from_global_config() reads baseUrl from config root with
HONCHO_BASE_URL env var as fallback
- get_honcho_client() guard relaxed to allow base_url without api_key
for no-auth local instances
- Added HONCHO_BASE_URL to OPTIONAL_ENV_VARS registry
Result: Setting HONCHO_BASE_URL=http://localhost:8000 in ~/.hermes/.env
now correctly routes the Honcho client to a local instance.
When the user is on a custom provider (provider=custom, localhost, or
127.0.0.1 endpoint), /model <name> no longer tries to auto-detect a
provider switch. The model name changes on the current endpoint as-is.
To switch away from a custom endpoint, users must use explicit
provider:model syntax (e.g. /model openai-codex:gpt-5.2-codex).
A helpful tip is printed when changing models on a custom endpoint.
This prevents the confusing case where someone on LM Studio types
/model gpt-5.2-codex, the auto-detection tries to switch providers,
fails or partially succeeds, and requests still go to the old endpoint.
Also fixes the missing prompt_toolkit.auto_suggest mock stub in
test_cli_init.py (same issue already fixed in test_cli_new_session.py).
Follow-up to PR #2101 (InB4DevOps). Adds three missing context compressor
resets in reset_session_state():
- compression_count (displayed in status bar)
- last_total_tokens
- _context_probed (stale context-error flag)
Also fixes the test_cli_new_session.py prompt_toolkit mock (missing
auto_suggest stub) and adds a regression test for #2099 that verifies
all token counters and compressor state are zeroed on /new.
The colon-split logic in get_model_context_length() and
_query_local_context_length() assumed any colon meant provider:model
format (e.g. "local:my-model"). But Ollama uses model:tag format
(e.g. "qwen3.5:27b"), so the split turned "qwen3.5:27b" into just
"27b" — which matches nothing, causing a fallback to the 2M token
probe tier.
Now only recognised provider prefixes (local, openrouter, anthropic,
etc.) are stripped. Ollama model:tag names pass through intact.
Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com>
