…d_id format (NousResearch#2455)

Parse thread_id from explicit deliver target (e.g. telegram:-1003724596514:17)
and forward it to _send_to_platform and mirror_to_session.

Previously _resolve_delivery_target() always set thread_id=None when
parsing the platform:chat_id format, breaking cron job delivery to
specific Telegram topics.

Added tests:
- test_explicit_telegram_topic_target_with_thread_id
- test_explicit_telegram_chat_id_without_thread_id

Also updated CRONJOB_SCHEMA deliver description to document the
platform:chat_id:thread_id format.

Co-authored-by: Alex Ferrari <alex@thealexferrari.com>

…rtup check, tests (NousResearch#2456)

fix(api-server): harden jobs API — input limits, field whitelist, startup check, tests

Remove the hardcoded Alibaba branch from resolve_runtime_provider()
that forced api_mode='anthropic_messages' regardless of the base URL.

Alibaba now goes through the generic API-key provider path, which
auto-detects the protocol from the URL:
- /apps/anthropic → anthropic_messages (via endswith check)
- /v1 → chat_completions (default)

This fixes Alibaba setup with OpenAI-compatible DashScope endpoints
(e.g. coding-intl.dashscope.aliyuncs.com/v1) that were broken because
runtime always forced Anthropic mode even when setup saved a /v1 URL.

Based on PR NousResearch#2024 by @kshitijk4poor.

Co-authored-by: kshitijk4poor <kshitijk4poor@users.noreply.github.com>

Cherry-picked from PR NousResearch#2017 by @simpolism. Fixes NousResearch#2011.

Discord slash commands in threads were missing thread_id in the
SessionSource, causing them to route to the parent channel session.
Commands like /usage and /reset returned wrong data or affected the
wrong session.

Detects discord.Thread channels in _build_slash_event and sets
chat_type='thread' with thread_id. Two tests added.

…5d6932ba

fix(discord): properly route slash event handling in threads

…kill (NousResearch#2461)

* fix: respect DashScope v1 runtime mode for alibaba

Remove the hardcoded Alibaba branch from resolve_runtime_provider()
that forced api_mode='anthropic_messages' regardless of the base URL.

Alibaba now goes through the generic API-key provider path, which
auto-detects the protocol from the URL:
- /apps/anthropic → anthropic_messages (via endswith check)
- /v1 → chat_completions (default)

This fixes Alibaba setup with OpenAI-compatible DashScope endpoints
(e.g. coding-intl.dashscope.aliyuncs.com/v1) that were broken because
runtime always forced Anthropic mode even when setup saved a /v1 URL.

Based on PR NousResearch#2024 by @kshitijk4poor.

* docs(skill): add split, merge, search examples to ocr-and-documents skill

Adds pymupdf examples for PDF splitting, merging, and text search
to the existing ocr-and-documents skill. No new dependencies — pymupdf
already covers all three operations natively.

---------

Co-authored-by: kshitijk4poor <kshitijk4poor@users.noreply.github.com>

… (salvage NousResearch#1981) (NousResearch#2462)

* fix: respect DashScope v1 runtime mode for alibaba

Remove the hardcoded Alibaba branch from resolve_runtime_provider()
that forced api_mode='anthropic_messages' regardless of the base URL.

Alibaba now goes through the generic API-key provider path, which
auto-detects the protocol from the URL:
- /apps/anthropic → anthropic_messages (via endswith check)
- /v1 → chat_completions (default)

This fixes Alibaba setup with OpenAI-compatible DashScope endpoints
(e.g. coding-intl.dashscope.aliyuncs.com/v1) that were broken because
runtime always forced Anthropic mode even when setup saved a /v1 URL.

Based on PR NousResearch#2024 by @kshitijk4poor.

* docs(skill): add split, merge, search examples to ocr-and-documents skill

Adds pymupdf examples for PDF splitting, merging, and text search
to the existing ocr-and-documents skill. No new dependencies — pymupdf
already covers all three operations natively.

* fix: replace all production print() calls with logger in rl_training_tool

Replace all bare print() calls in production code paths with proper logger calls.

- Add `import logging` and module-level `logger = logging.getLogger(__name__)`
- Replace print() in _start_training_run() with logger.info()
- Replace print() in _stop_training_run() with logger.info()
- Replace print(Warning/Note) calls with logger.warning() and logger.info()

Using the logging framework allows log level filtering, proper formatting,
and log routing instead of always printing to stdout.

---------

Co-authored-by: kshitijk4poor <kshitijk4poor@users.noreply.github.com>
Co-authored-by: memosr.eth <96793918+memosr@users.noreply.github.com>

Two fixes:

1. CLI /stop command crashed with 'cannot import name get_registry' —
   the code imported a non-existent function. Fixed to use the actual
   process_registry singleton and list_sessions() method.
   (Reported in NousResearch#2458 by haiyuzhong1980)

2. Streaming media delivery used undefined 'adapter' variable —
   our PR NousResearch#2382 called _deliver_media_from_response(adapter=adapter)
   but 'adapter' wasn't guaranteed to be defined in that scope.
   Fixed to resolve via self.adapters.get(source.platform).
   (Reported in NousResearch#2424 by 42-evey)

…ery (NousResearch#2463)

fix: /stop command crash + UnboundLocalError in streaming media delivery

…summary model

Closes NousResearch#2453

The DEFAULT_CONFIG was hardcoding google/gemini-3-flash-preview as the
summary_model for context compression. This caused unexpected OpenRouter
charges for users who configured a different provider/model, because the
compression task would silently fall back to gemini via OpenRouter even
when the user's main model was on a different provider.

Fix: change summary_model default to empty string. When empty,
call_llm() resolves the model through the standard auto-detection chain
(auxiliary.compression config -> env vars -> main provider), which
correctly uses the user's configured provider and model.

Users who want a dedicated cheap model for compression can still
explicitly set compression.summary_model in their config.yaml.

…summary model (NousResearch#2464)

fix(compression): remove hardcoded gemini-3-flash-preview as default summary model

When sounddevice is installed but libportaudio2 is not present on the
system, the OSError was caught together with ImportError and showed a
generic 'pip install sounddevice' message that sent users down the wrong
path.

Split the except clause to give a clear, actionable message for the
OSError case, including the correct apt/brew commands to install the
system library.

…sResearch#2428)

When subagents run in ThreadPoolExecutor threads, the shared stdout handle
can close between thread teardown and KawaiiSpinner cleanup. Python raises
ValueError (not OSError) for I/O operations on closed files:
  ValueError: I/O operation on closed file

The _SafeWriter class was only catching OSError, missing this case.

Changes:
- Add ValueError to exception handling in write(), flush(), and isatty()
- Update docstring to document the ThreadPoolExecutor teardown scenario

Fixes NousResearch#2428

imap.uid('search') can return data=[] when the mailbox is empty or
has no matching messages. Accessing data[0] without checking len first
raises IndexError: list index out of range.

Fixed at both call sites in gateway/platforms/email.py:
- Line 233 (connect): ALL search on startup
- Line 298 (fetch): UNSEEN search in the polling loop

Closes NousResearch#2137

…unt()

Both methods accessed self._conn without self._lock, breaking the
thread-safety contract documented on SessionDB (line 111). All 22 other
DB methods use with self._lock — these two were the only exceptions.

In the gateway's multi-threaded environment (multiple platform reader
threads + single writer) this could cause cursor interleaving,
sqlite3.ProgrammingError, or inconsistent COUNT results.

Closes NousResearch#2130

…to prevent prefill rejection

fix: batch of 5 small contributor fixes — PortAudio, SafeWriter, IMAP, thread lock, prefill

* docs: add Gemini OAuth provider implementation plan

Planning doc for a standard-route Gemini provider using Google OAuth
(Authorization Code + PKCE) with the OpenAI-compatible endpoint at
generativelanguage.googleapis.com. Covers OAuth flow, token lifecycle,
file list, and estimated scope (~700 lines).

Replaces the Node.js bridge approach from PR NousResearch#2042.

* chore: update OpenRouter model list

- Add xiaomi/mimo-v2-pro
- Add nvidia/nemotron-3-super-120b-a12b (paid, higher rate limits)
- Remove openrouter/hunter-alpha and openrouter/healer-alpha (discontinued)

Based on PR NousResearch#2427 by @oxngon (core feature extracted, reformatting
and unrelated changes dropped).

Discord's TYPING_START gateway event is unreliable for bot DMs. This
adds a background typing loop that hits POST /channels/{id}/typing
every 8 seconds (indicator lasts ~10s) until the response is sent.

- send_typing() starts a per-channel background loop (idempotent)
- stop_typing() cancels it (called after _run_agent returns)
- Base adapter gets stop_typing() as a no-op default
- Per-channel tracking via _typing_tasks dict prevents duplicates

Add hermes mcp add/remove/list/test/configure CLI for managing MCP
server connections interactively. Discovery-first 'add' flow connects,
discovers tools, and lets users select which to enable via curses checklist.

Add OAuth 2.1 PKCE authentication for MCP HTTP servers (RFC 7636).
Supports browser-based and manual (headless) authorization, token
caching with 0600 permissions, automatic refresh. Zero external deps.

Add ${ENV_VAR} interpolation in MCP server config values, resolved
from os.environ + ~/.hermes/.env at load time.

Core OAuth module from PR NousResearch#2021 by @imnotdev25. CLI and mcp_tool
wiring rewritten against current main. Closes NousResearch#497, NousResearch#690.

…5d6932ba

feat(discord): persistent typing indicator for DMs

Reverts the sanitizer addition from PR NousResearch#2466 (originally NousResearch#2129).
We already have _empty_content_retries handling for reasoning-only
responses. The trailing strip risks silently eating valid messages
and is redundant with existing empty-content handling.

…ch#2471)

revert: remove trailing empty assistant message stripping

…sResearch#2472)

The /v1/responses endpoint used an in-memory OrderedDict that lost
all conversation state on gateway restart. Replace with SQLite-backed
storage at ~/.hermes/response_store.db.

- Responses and conversation name mappings survive restarts
- Same LRU eviction behavior (configurable max_size)
- WAL mode for concurrent read performance
- Falls back to in-memory SQLite if disk path unavailable
- Conversation name→response_id mapping moved into the store

…esearch#2469)

* fix: respect DashScope v1 runtime mode for alibaba

Remove the hardcoded Alibaba branch from resolve_runtime_provider()
that forced api_mode='anthropic_messages' regardless of the base URL.

Alibaba now goes through the generic API-key provider path, which
auto-detects the protocol from the URL:
- /apps/anthropic → anthropic_messages (via endswith check)
- /v1 → chat_completions (default)

This fixes Alibaba setup with OpenAI-compatible DashScope endpoints
(e.g. coding-intl.dashscope.aliyuncs.com/v1) that were broken because
runtime always forced Anthropic mode even when setup saved a /v1 URL.

Based on PR NousResearch#2024 by @kshitijk4poor.

* docs(skill): add split, merge, search examples to ocr-and-documents skill

Adds pymupdf examples for PDF splitting, merging, and text search
to the existing ocr-and-documents skill. No new dependencies — pymupdf
already covers all three operations natively.

* fix: replace all production print() calls with logger in rl_training_tool

Replace all bare print() calls in production code paths with proper logger calls.

- Add `import logging` and module-level `logger = logging.getLogger(__name__)`
- Replace print() in _start_training_run() with logger.info()
- Replace print() in _stop_training_run() with logger.info()
- Replace print(Warning/Note) calls with logger.warning() and logger.info()

Using the logging framework allows log level filtering, proper formatting,
and log routing instead of always printing to stdout.

* fix(gateway): process /queue'd messages after agent completion

/queue stored messages in adapter._pending_messages but never consumed
them after normal (non-interrupted) completion. The consumption path
at line 5219 only checked pending messages when result.get('interrupted')
was True — since /queue deliberately doesn't interrupt, queued messages
were silently dropped.

Now checks adapter._pending_messages after both interrupted AND normal
completion. For queued messages (non-interrupt), the first response is
delivered before recursing to process the queued follow-up. Skips the
direct send when streaming already delivered the response.

Reported by GhostMode on Discord.

---------

Co-authored-by: kshitijk4poor <kshitijk4poor@users.noreply.github.com>
Co-authored-by: memosr.eth <96793918+memosr@users.noreply.github.com>

…31d7db3b

feat(cli): MCP server management CLI + OAuth 2.1 PKCE auth

Follow-up to 669c60a (cherry-pick of PR NousResearch#2187, fixes NousResearch#2177).

The original fix emits a "\n\n" delta immediately after every
_execute_tool_calls() invocation. When the model runs multiple
consecutive tool iterations before producing text (common with
search → read → analyze flows), each iteration appends its own
paragraph break, resulting in 4-6+ blank lines before the actual
response.

Replace the immediate delta with a deferred flag
(_stream_needs_break). _fire_stream_delta() checks the flag and
prepends a single "\n\n" only when the first real text delta
arrives, so multiple back-to-back tool iterations still produce
exactly one paragraph break.

…ng (NousResearch#2473)

fix: defer streaming iteration linebreak to prevent blank line stacking

* fix: respect DashScope v1 runtime mode for alibaba

Remove the hardcoded Alibaba branch from resolve_runtime_provider()
that forced api_mode='anthropic_messages' regardless of the base URL.

Alibaba now goes through the generic API-key provider path, which
auto-detects the protocol from the URL:
- /apps/anthropic → anthropic_messages (via endswith check)
- /v1 → chat_completions (default)

This fixes Alibaba setup with OpenAI-compatible DashScope endpoints
(e.g. coding-intl.dashscope.aliyuncs.com/v1) that were broken because
runtime always forced Anthropic mode even when setup saved a /v1 URL.

Based on PR NousResearch#2024 by @kshitijk4poor.

* docs(skill): add split, merge, search examples to ocr-and-documents skill

Adds pymupdf examples for PDF splitting, merging, and text search
to the existing ocr-and-documents skill. No new dependencies — pymupdf
already covers all three operations natively.

* fix: replace all production print() calls with logger in rl_training_tool

Replace all bare print() calls in production code paths with proper logger calls.

- Add `import logging` and module-level `logger = logging.getLogger(__name__)`
- Replace print() in _start_training_run() with logger.info()
- Replace print() in _stop_training_run() with logger.info()
- Replace print(Warning/Note) calls with logger.warning() and logger.info()

Using the logging framework allows log level filtering, proper formatting,
and log routing instead of always printing to stdout.

* fix(gateway): process /queue'd messages after agent completion

/queue stored messages in adapter._pending_messages but never consumed
them after normal (non-interrupted) completion. The consumption path
at line 5219 only checked pending messages when result.get('interrupted')
was True — since /queue deliberately doesn't interrupt, queued messages
were silently dropped.

Now checks adapter._pending_messages after both interrupted AND normal
completion. For queued messages (non-interrupt), the first response is
delivered before recursing to process the queued follow-up. Skips the
direct send when streaming already delivered the response.

Reported by GhostMode on Discord.

* chore: add minimax/minimax-m2.7 to OpenRouter and MiniMax model catalogs

---------

Co-authored-by: kshitijk4poor <kshitijk4poor@users.noreply.github.com>
Co-authored-by: memosr.eth <96793918+memosr@users.noreply.github.com>

NousResearch#3405)

Two independent bugs caused the reasoning box to appear three times when
the model produced reasoning + tool_calls:

Bug A: _build_assistant_message() re-fired reasoning_callback with the full
reasoning text even when streaming had already displayed it. The original
guard only checked structured reasoning_content deltas, but reasoning also
arrives via content tag extraction (<REASONING_SCRATCHPAD>/<think> tags
in delta.content), which went through _fire_stream_delta not
_fire_reasoning_delta. Fix: skip the callback entirely when streaming is
active — both paths display reasoning during the stream. Any reasoning not
shown during streaming is caught by the CLI post-response fallback.

Bug B: The post-response reasoning display checked _reasoning_stream_started,
but that flag was reset by _reset_stream_state() during intermediate turn
boundaries (when stream_delta_callback(None) fires between tool calls).
Introduced _reasoning_shown_this_turn flag that persists across the tool
loop and is only reset at the start of each user turn.

Live-tested in PTY: reasoning now shows exactly once per API call, no
duplicates across tool-calling loops.

…ess (NousResearch#3274)

* refactor: suffix runtimeDeps PATH so apt-installed tools take priority

Changes makeWrapper from --prefix to --suffix. In container mode,
tools installed via apt in /usr/bin now win over read-only nix store
copies. Nix store versions become dead-letter fallbacks. Native NixOS
mode unaffected — tools in /run/current-system/sw/bin already precede
the suffix.

* feat(container): first-boot apt provisioning for agent tools

Installs nodejs, npm, curl via apt and uv via curl on first container
boot. Uses sentinel file so subsequent boots skip. Container recreation
triggers fresh install. Combined with --suffix PATH change, agents get
mutable tools that support npm i -g and uv without hitting read-only
nix store paths.

* docs: update nixosModules header for tool provisioning

* feat(container): consolidate first-boot provisioning + Python 3.11 venv

Merge sudo and tool apt installs into a single apt-get update call.
Move uv install outside the sentinel so transient failures retry on
next boot. Bootstrap a Python 3.11 venv via uv (--seed for pip) and
prepend ~/.venv/bin to PATH so agents get writable python/pip/node
out of the box.

---------

Co-authored-by: Hermes Agent <hermes@nousresearch.com>

NousResearch#3366) (NousResearch#3421)

Two-layer caching for build_skills_system_prompt():
  1. In-process LRU (OrderedDict, max 8) — same-process: 546ms → <1ms
  2. Disk snapshot (.skills_prompt_snapshot.json) — cold start: 297ms → 103ms

Key improvements over original PR NousResearch#3366:
- Extract shared logic into agent/skill_utils.py (parse_frontmatter,
  skill_matches_platform, get_disabled_skill_names, extract_skill_conditions,
  extract_skill_description, iter_skill_index_files)
- tools/skills_tool.py delegates to shared module — zero code duplication
- Proper LRU eviction via OrderedDict.move_to_end + popitem(last=False)
- Cache invalidation on all skill mutation paths:
  - skill_manage tool (in-conversation writes)
  - hermes skills install (CLI hub)
  - hermes skills uninstall (CLI hub)
  - Automatic via mtime/size manifest on cold start

prompt_builder.py no longer imports tools.skills_tool (avoids pulling
in the entire tool registry chain at prompt build time).

6301 tests pass, 0 failures.

Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com>

…nect (salvage NousResearch#3399) (NousResearch#3427)

Salvage of NousResearch#3399 by @binhnt92 with true agent interruption added on top.

When a streaming /v1/chat/completions client disconnects mid-stream, the agent is now interrupted via agent.interrupt() so it stops making LLM API calls, and the asyncio task wrapper is cancelled.

Closes NousResearch#3399.

…rch#3419)

Salvage of PR NousResearch#1747 (original PR NousResearch#1171 by @davanstrien) onto current main.

Registers Hugging Face Inference Providers (router.huggingface.co/v1) as a named provider:
- hermes chat --provider huggingface (or --provider hf)
- 18 curated open models via hermes model picker
- HF_TOKEN in ~/.hermes/.env
- OpenAI-compatible endpoint with automatic failover (Groq, Together, SambaNova, etc.)

Files: auth.py, models.py, main.py, setup.py, config.py, model_metadata.py, .env.example, 5 docs pages, 17 new tests.

Co-authored-by: Daniel van Strien <davanstrien@gmail.com>

…g models (NousResearch#3431)

Models like GLM-5/5.1 can think for 15+ minutes. The previous 900s
(15 min) default for HERMES_API_TIMEOUT killed legitimate requests.

Raised to 1800s (30 min) in both places that read the env var:
- _build_api_kwargs() timeout (non-streaming total timeout)
- _call_chat_completions() write timeout (streaming connection)

The streaming per-chunk read timeout (60s) and stale stream detector
(180-300s) are unchanged — those are appropriate for inter-chunk timing.

…6K (NousResearch#3426)

The Anthropic adapter defaulted to max_tokens=16384 when no explicit value
was configured.  This severely limits thinking-enabled models where thinking
tokens count toward max_tokens:

- Claude Opus 4.6 supports 128K output but was capped at 16K
- Claude Sonnet 4.6 supports 64K output but was capped at 16K

With extended thinking (adaptive or budget-based), the model could exhaust
the entire 16K on reasoning, leaving zero tokens for the actual response.
This caused two user-visible errors:
- 'Response truncated (finish_reason=length)' — thinking consumed most tokens
- 'Response only contains think block with no content' — thinking consumed all

Fix: add _ANTHROPIC_OUTPUT_LIMITS lookup table (sourced from Anthropic docs
and Cline's model catalog) and use the model's actual output limit as the
default.  Unknown future models default to 128K (the current maximum).

Also adds context_length clamping: if the user configured a smaller context
window (e.g. custom endpoint), max_tokens is clamped to context_length - 1
to avoid exceeding the window.

Closes NousResearch#2706

…ousResearch#3428)

Previously, tirith exit code 1 (block) immediately rejected the command
with no approval prompt — users saw 'BLOCKED: Command blocked by
security scan' and the agent moved on.  This prevented gateway/CLI users
from approving pipe-to-shell installs like 'curl ... | sh' even when
they understood the risk.

Changes:
- Tirith 'block' and 'warn' now both go through the approval flow.
  Users see the full tirith findings (severity, title, description,
  safer alternatives) and can choose to approve or deny.
- New _format_tirith_description() builds rich descriptions from tirith
  findings JSON so the approval prompt is informative.
- CLI startup now warns when tirith is enabled but not available, so
  users know command scanning is degraded to pattern matching only.

The default approval choice is still deny, so the security posture is
unchanged for unattended/timeout scenarios.

Reported via Discord by pistrie — 'curl -fsSL https://mandex.dev/install.sh | sh'
was hard-blocked with no way to approve.

…3440)

Show only agentic models that map to OpenRouter defaults:

  Qwen/Qwen3.5-397B-A17B          ↔ qwen/qwen3.5-plus
  Qwen/Qwen3.5-35B-A3B            ↔ qwen/qwen3.5-35b-a3b
  deepseek-ai/DeepSeek-V3.2       ↔ deepseek/deepseek-chat
  moonshotai/Kimi-K2.5             ↔ moonshotai/kimi-k2.5
  MiniMaxAI/MiniMax-M2.5           ↔ minimax/minimax-m2.5
  zai-org/GLM-5                    ↔ z-ai/glm-5
  XiaomiMiMo/MiMo-V2-Flash         ↔ xiaomi/mimo-v2-pro
  moonshotai/Kimi-K2-Thinking      ↔ moonshotai/kimi-k2-thinking

Users can still pick any HF model via Enter custom model name.

…retry (salvage NousResearch#3389) (NousResearch#3449)

Salvage of NousResearch#3389 by @binhnt92 with reasoning fallback and retry logic added on top.

All 7 auxiliary LLM call sites now use extract_content_or_reasoning() which mirrors the main agent loop's behavior: extract content, strip think blocks, fall back to structured reasoning fields, retry on empty.

Closes NousResearch#3389.

…less retries (NousResearch#3444)

When finish_reason='length' and the response contains only reasoning
(think blocks or empty content), the model exhausted its output token
budget on thinking with nothing left for the actual response.

Previously, this fell into either:
- chat_completions: 3 useless continuation retries (model hits same limit)
- anthropic/codex: generic 'Response truncated' error with rollback

Now: detect the think-only + length condition early and return immediately
with a targeted error message: 'Model used all output tokens on reasoning
with none left for the response. Try lowering reasoning effort or
increasing max_tokens.'

This saves 2 wasted API calls on the chat_completions path and gives
users actionable guidance instead of a cryptic error.

The existing think-only retry logic (finish_reason='stop') is unchanged —
that's a genuine model glitch where retrying can help.

…ousResearch#3457)

hermes tools and _get_platform_tools() call get_plugin_toolsets() /
_get_plugin_toolset_keys() without first ensuring plugins have been
discovered. discover_plugins() only runs as a side effect of importing
model_tools.py, which hermes tools never does. This means:

- hermes tools TUI never shows plugin toolsets (invisible to users)
- _get_platform_tools() in standalone processes misses plugin toolsets

Fix: call discover_plugins() (idempotent) in both
_get_plugin_toolset_keys() and _get_effective_configurable_toolsets()
before accessing plugin state. In the gateway/CLI where model_tools.py
is already imported, the call is a no-op (discover_and_load checks
_discovered flag).

…rch#3469)

_expand_git_reference() and _rg_files() called subprocess.run()
without a timeout. On a large repository, @diff, @StaGeD, or
@git:N references could hang the agent indefinitely while git
or ripgrep processes slow output.

- Add timeout=30 to git subprocess in _expand_git_reference()
  with a user-friendly error message on TimeoutExpired
- Add timeout=10 to rg subprocess in _rg_files() returning
  None on timeout (falls back to os.walk folder listing)

Co-authored-by: memosr.eth <96793918+memosr@users.noreply.github.com>

…#3473)

Matrix platform was missing from the PLATFORMS config, causing a
KeyError in _get_platform_tools() when handling Matrix messages.
Every other platform (telegram, discord, slack, etc.) was present
but matrix was overlooked.

Co-authored-by: williamtwomey <williamtwomey@users.noreply.github.com>

…NousResearch#3413) (NousResearch#3478)

* Fix NousResearch#3409: Add fallback to session_search to prevent false negatives on summarization failure

Fixes NousResearch#3409. When the auxiliary summarizer fails or returns None, the tool now returns a raw fallback preview of the matched session instead of silently dropping it and returning an empty list

* fix: clean up fallback logic — separate exception handling from preview

Restructure the loop: handle exceptions first (log + nullify), build
entry dict once, then branch on result truthiness. Removes duplicated
field assignments and makes the control flow linear.

---------

Co-authored-by: devorun <130918800+devorun@users.noreply.github.com>

…#3480)

* fix: cap context pressure percentage at 100% in display

The forward-looking token estimate can overshoot the compaction threshold
(e.g. a large tool result pushes it from 70% to 109% in one step). The
progress bar was already capped via min(), but pct_int was not — causing
the user to see '109% to compaction' which is confusing.

Cap pct_int at 100 in both CLI and gateway display functions.

Reported by @JoshExile82.

* refactor: use real API token counts for compression decisions

Replace the rough chars/3 estimation with actual prompt_tokens +
completion_tokens from the API response. The estimation was needed to
predict whether tool results would push context past the threshold, but
the default 50% threshold leaves ample headroom — if tool results push
past it, the next API call reports real usage and triggers compression
then.

This removes all estimation from the compression and context pressure
paths, making both 100% data-driven from provider-reported token counts.

Also removes the dead _msg_count_before_tools variable.

)

- Change default inference_base_url from dashscope-intl Anthropic-compat
  endpoint to coding-intl OpenAI-compat /v1 endpoint. The old Anthropic
  endpoint 404'd when used with the OpenAI SDK (which appends
  /chat/completions to a /apps/anthropic base URL).

- Update curated model list: remove models unavailable on coding-intl
  (qwen3-max, qwen-plus-latest, qwen3.5-flash, qwen-vl-max), add
  third-party models available on the platform (glm-5, glm-4.7,
  kimi-k2.5, MiniMax-M2.5).

- URL-based api_mode auto-detection still works: overriding
  DASHSCOPE_BASE_URL to an /apps/anthropic endpoint automatically
  switches to anthropic_messages mode.

- Update provider description and env var descriptions to reflect the
  coding-intl multi-provider platform.

- Update tests to match new default URL and test the anthropic override
  path instead.

…ousResearch#3414) (NousResearch#3488)

* test(gateway): map fixture adapter by platform in progress threading tests

* fix(gateway): scope progress thread fallback to Slack only

---------

Co-authored-by: EmpireOperating <258363005+EmpireOperating@users.noreply.github.com>

…arch#3490)

EmailAdapter._seen_uids accumulates every IMAP UID ever seen but
never removes any. A long-running gateway processing a high-volume
inbox would leak memory indefinitely — thousands of integers per day.

IMAP UIDs are monotonically increasing integers, so old UIDs are safe
to drop: new messages always have higher UIDs, and the IMAP UNSEEN
flag already prevents re-delivery regardless of our local tracking.

Fix adds _trim_seen_uids() which keeps only the most recent 1000 UIDs
(half of the 2000-entry cap) when the set grows too large. Called
automatically during connect() and after each fetch cycle.

Co-authored-by: memosr.eth <96793918+memosr@users.noreply.github.com>

…, and gateway edge cases (salvage NousResearch#3489) (NousResearch#3492)

* fix: harden `hermes update` against diverged history, non-main branches, and gateway edge cases

The self-update command (`hermes update` / gateway `/update`) could fail
or silently corrupt state in several scenarios:

1. **Diverged history** — `git pull --ff-only` aborts with a cryptic
   subprocess error when upstream has force-pushed or rebased. Now falls
   back to `git reset --hard origin/main` since local changes are already
   stashed.

2. **User on a feature branch / detached HEAD** — the old code would
   either clobber the feature branch HEAD to point at origin/main, or
   silently pull against a non-existent remote branch. Now auto-checkouts
   main before pulling, with a clear warning.

3. **Fetch failures** — network or auth errors produced raw subprocess
   tracebacks. Now shows user-friendly messages ("Network error",
   "Authentication failed") with actionable hints.

4. **reset --hard failure** — if the fallback reset itself fails (disk
   full, permissions), the old code would still attempt stash restore on
   a broken working tree. Now skips restore and tells the user their
   changes are safe in stash.

5. **Gateway /update stash conflicts** — non-interactive mode (Telegram
   `/update`) called sys.exit(1) when stash restore had conflicts, making
   the entire update report as failed even though the code update itself
   succeeded. Now treats stash conflicts as non-fatal in non-interactive
   mode (returns False instead of exiting).

* fix: restore stash and branch on 'already up to date' early return

The PR moved stash creation before the commit-count check (needed for
the branch-switching feature), but the 'already up to date' early return
didn't restore the stash or switch back to the original branch — leaving
the user stranded on main with changes trapped in a stash.

Now the early-return path restores the stash and checks out the original
branch when applicable.

---------

Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com>