openclaw#64796)

Merged via squash.

Prepared head SHA: 59ca82e
Co-authored-by: hclsys <7755017+hclsys@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras

Port from openclaw/openclaw#64796: Per MSC3952 / Matrix v1.7, the
m.mentions.user_ids field is the authoritative mention signal.  Non-
OpenClaw Matrix clients (Element, matrix-bot-sdk bots, etc.) commonly
send messages with proper m.mentions.user_ids metadata but without
duplicating the @bot text in the message body.

Before this change, _is_bot_mentioned() relied entirely on text-based
detection (body string matching and HTML pill detection), causing
messages from these clients to be silently dropped when
MATRIX_REQUIRE_MENTION=true.

Now, if the bot's user_id appears in m.mentions.user_ids, that alone
is sufficient to register a mention — matching the Matrix spec.
Text-based fallback remains for backwards compatibility with older
clients that don't populate m.mentions.

Port from openclaw/openclaw#64796: Per MSC3952 / Matrix v1.7, the
m.mentions.user_ids field is the authoritative mention signal. Clients
that populate m.mentions but don't duplicate @bot in the body text
were being silently dropped when MATRIX_REQUIRE_MENTION=true.

Cherry-picked from PR #8673.

Port from openclaw/openclaw#64796: Per MSC3952 / Matrix v1.7, the
m.mentions.user_ids field is the authoritative mention signal. Clients
that populate m.mentions but don't duplicate @bot in the body text
were being silently dropped when MATRIX_REQUIRE_MENTION=true.

Cherry-picked from PR #8673.

openclaw#64796)

Merged via squash.

Prepared head SHA: 59ca82e
Co-authored-by: hclsys <7755017+hclsys@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras

* refactor(terminal): remove check_interval parameter (#8001)

The check_interval parameter on terminal_tool sent periodic output
updates to the gateway chat, but these were display-only — the agent
couldn't see or act on them. This added schema bloat and introduced
a bug where notify_on_complete=True was silently dropped when
check_interval was also set (the not-check_interval guard skipped
fast-watcher registration, and the check_interval watcher dict
was missing the notify_on_complete key).

Removing check_interval entirely:
- Eliminates the notify_on_complete interaction bug
- Reduces tool schema size (one fewer parameter for the model)
- Simplifies the watcher registration path
- notify_on_complete (agent wake-on-completion) still works
- watch_patterns (output alerting) still works
- process(action='poll') covers manual status checking

Closes #7947 (root cause eliminated rather than patched).

* feat: per-platform display verbosity configuration (#8006)

Add display.platforms section to config.yaml for per-platform overrides of
display settings (tool_progress, show_reasoning, streaming, tool_preview_length).

Each platform gets sensible built-in defaults based on capability tier:
- High (telegram, discord): tool_progress=all, streaming follows global
- Medium (slack, mattermost, matrix, feishu): tool_progress=new
- Low (signal, whatsapp, bluebubbles, wecom, etc.): tool_progress=off, streaming=false
- Minimal (email, sms, webhook, homeassistant): tool_progress=off, streaming=false

Example config:
  display:
    platforms:
      telegram:
        tool_progress: all
        show_reasoning: true
      slack:
        tool_progress: off

Resolution order: platform override > global setting > built-in platform default.

Changes:
- New gateway/display_config.py: resolver module with tier-based platform defaults
- gateway/run.py: tool_progress, tool_preview_length, streaming, show_reasoning
  all resolve per-platform via the new resolver
- /verbose command: now cycles tool_progress per-platform (saves to
  display.platforms.<platform>.tool_progress instead of global)
- /reasoning show|hide: now saves show_reasoning per-platform
- Config version 15 -> 16: migrates tool_progress_overrides into display.platforms
- Backward compat: legacy tool_progress_overrides still read as fallback
- 27 new tests for resolver, normalization, migration, backward compat
- Updated verbose command tests for per-platform behavior

Addresses community request for per-channel verbosity control (Guillaume Meyer,
Nathan Danielsen) — high verbosity on backchannel Telegram, low on customer-facing
Slack, none on email.

* feat: component-separated logging with session context and filtering (#7991)

* feat: component-separated logging with session context and filtering

Phase 1 — Gateway log isolation:
- gateway.log now only receives records from gateway.* loggers
  (platform adapters, session management, slash commands, delivery)
- agent.log remains the catch-all (all components)
- errors.log remains WARNING+ catch-all
- Moved gateway.log handler creation from gateway/run.py into
  hermes_logging.setup_logging(mode='gateway') with _ComponentFilter

Phase 2 — Session ID injection:
- Added set_session_context(session_id) / clear_session_context() API
  using threading.local() for per-thread session tracking
- _SessionFilter enriches every log record with session_tag attribute
- Log format: '2026-04-11 10:23:45 INFO [session_id] logger.name: msg'
- Session context set at start of run_conversation() in run_agent.py
- Thread-isolated: gateway conversations on different threads don't leak

Phase 3 — Component filtering in hermes logs:
- Added --component flag: hermes logs --component gateway|agent|tools|cli|cron
- COMPONENT_PREFIXES maps component names to logger name prefixes
- Works with all existing filters (--level, --session, --since, -f)
- Logger name extraction handles both old and new log formats

Files changed:
- hermes_logging.py: _SessionFilter, _ComponentFilter, COMPONENT_PREFIXES,
  set/clear_session_context(), gateway.log creation in setup_logging()
- gateway/run.py: removed redundant gateway.log handler (now in hermes_logging)
- run_agent.py: set_session_context() at start of run_conversation()
- hermes_cli/logs.py: --component filter, logger name extraction
- hermes_cli/main.py: --component argument on logs subparser

Addresses community request for component-separated, filterable logging.
Zero changes to existing logger names — __name__ already provides hierarchy.

* fix: use LogRecord factory instead of per-handler _SessionFilter

The _SessionFilter approach required attaching a filter to every handler
we create. Any handler created outside our _add_rotating_handler (like
the gateway stderr handler, or third-party handlers) would crash with
KeyError: 'session_tag' if it used our format string.

Replace with logging.setLogRecordFactory() which injects session_tag
into every LogRecord at creation time — process-global, zero per-handler
wiring needed. The factory is installed at import time (before
setup_logging) so session_tag is available from the moment hermes_logging
is imported.

- Idempotent: marker attribute prevents double-wrapping on module reload
- Chains with existing factory: won't break third-party record factories
- Removes _SessionFilter from _add_rotating_handler and setup_verbose_logging
- Adds tests: record factory injection, idempotency, arbitrary handler compat

* perf(ssh,modal): bulk file sync via tar pipe and tar/base64 archive (#8014)

* perf(ssh,modal): bulk file sync via tar pipe and tar/base64 archive

SSH: symlink-staging + tar -ch piped over SSH in a single TCP stream.
Eliminates per-file scp round-trips. Handles timeout (kills both
processes), SSH Popen failure (kills tar), and tar create failure.

Modal: in-memory gzipped tar archive, base64-encoded, decoded+extracted
in one exec call. Checks exit code and raises on failure.

Both backends use shared helpers extracted into file_sync.py:
- quoted_mkdir_command() — mirrors existing quoted_rm_command()
- unique_parent_dirs() — deduplicates parent dirs from file pairs

Migrates _ensure_remote_dirs to use the new helpers.

28 new tests (21 SSH + 7 Modal), all passing.

Closes #7465
Closes #7467

* fix(modal): pipe stdin to avoid ARG_MAX, clean up review findings

- Modal bulk upload: stream base64 payload through proc.stdin in 1MB
  chunks instead of embedding in command string (Modal SDK enforces
  64KB ARG_MAX_BYTES — typical payloads are ~4.3MB)
- Modal single-file upload: same stdin fix, add exit code checking
- Remove what-narrating comments in ssh.py and modal.py (keep WHY
  comments: symlink staging rationale, SIGPIPE, deadlock avoidance)
- Remove unnecessary `sandbox = self._sandbox` alias in modal bulk
- Daytona: use shared helpers (unique_parent_dirs, quoted_mkdir_command)
  instead of inlined duplicates

---------

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

* fix(matrix): replace pickle crypto store with SQLite, fix E2EE decryption (#7981)

Fixes #7952 — Matrix E2EE completely broken after mautrix migration.

- Replace MemoryCryptoStore + pickle/HMAC persistence with mautrix's
  PgCryptoStore backed by SQLite via aiosqlite. Crypto state now
  persists reliably across restarts without fragile serialization.

- Add handle_sync() call on initial sync response so to-device events
  (queued Megolm key shares) are dispatched to OlmMachine instead of
  being silently dropped.

- Add _verify_device_keys_on_server() after loading crypto state.
  Detects missing keys (re-uploads), stale keys from migration
  (attempts re-upload), and corrupted state (refuses E2EE).

- Add _CryptoStateStore adapter wrapping MemoryStateStore to satisfy
  mautrix crypto's StateStore interface (is_encrypted,
  get_encryption_info, find_shared_rooms).

- Remove redundant share_keys() call from sync loop — OlmMachine
  already handles this via DEVICE_OTK_COUNT event handler.

- Fix datetime vs float TypeError in session.py suspend_recently_active()
  that crashed gateway startup.

- Add aiosqlite and asyncpg to [matrix] extra in pyproject.toml.

- Update test mocks for PgCryptoStore/Database and add query_keys mock
  for key verification. 174 tests pass.

- Add E2EE upgrade/migration docs to Matrix user guide.

* feat: add hermes backup and hermes import commands (#7997)

* feat: add `hermes backup` and `hermes import` commands

hermes backup — creates a zip of ~/.hermes/ (config, skills, sessions,
profiles, memories, skins, cron jobs, etc.) excluding the hermes-agent
codebase, __pycache__, and runtime PID files. Defaults to
~/hermes-backup-<timestamp>.zip, customizable with -o.

hermes import <zipfile> — restores from a backup zip, validating it
looks like a hermes backup before extracting. Handles .hermes/ prefix
stripping, path traversal protection, and confirmation prompts (skip
with --force).

29 tests covering exclusion rules, backup creation, import validation,
prefix detection, path traversal blocking, confirmation flow, and a
full round-trip test.

* test: improve backup/import coverage to 97%

Add 17 additional tests covering:
- _format_size helper (bytes through terabytes)
- Nonexistent hermes home error exit
- Output path is a directory (auto-names inside it)
- Output without .zip suffix (auto-appends)
- Empty hermes home (all files excluded)
- Permission errors during backup and import
- Output zip inside hermes root (skips itself)
- Not-a-zip file rejection
- EOFError and KeyboardInterrupt during confirmation
- 500+ file progress display
- Directory-only zip prefix detection

Remove dead code branch in _detect_prefix (unreachable guard).

* feat: auto-restore profile wrapper scripts on import

After extracting backup files, hermes import now scans profiles/ for
subdirectories with config.yaml or .env and recreates the ~/.local/bin
wrapper scripts so profile aliases (e.g. 'coder chat') work immediately.

Also prints guidance for re-installing gateway services per profile.

Handles edge cases:
- Skips profile dirs without config (not real profiles)
- Skips aliases that collide with existing commands
- Gracefully degrades if hermes_cli.profiles isn't available (fresh install)
- Shows PATH hint if ~/.local/bin isn't in PATH

3 new profile restoration tests (49 total).

* fix(discord): decouple readiness from slash sync

* feat: /compress <focus> — guided compression with focus topic (#8017)

Adds an optional focus topic to /compress: `/compress database schema`
guides the summariser to preserve information related to the focus topic
(60-70% of summary budget) while compressing everything else more aggressively.
Inspired by Claude Code's /compact <focus>.

Changes:
- context_compressor.py: focus_topic parameter on _generate_summary() and
  compress(); appends FOCUS TOPIC guidance block to the LLM prompt
- run_agent.py: focus_topic parameter on _compress_context(), passed through
  to the compressor
- cli.py: _manual_compress() extracts focus topic from command string,
  preserves existing manual_compression_feedback integration (no regression)
- gateway/run.py: _handle_compress_command() extracts focus from event args
  and passes through — full gateway parity
- commands.py: args_hint="[focus topic]" on /compress CommandDef

Salvaged from PR #7459 (CLI /compress focus only — /context command deferred).
15 new tests across CLI, compressor, and gateway.

* fix(gateway): add missing RedactingFormatter import

The gateway startup path references RedactingFormatter without
importing it, causing a NameError crash when launched with a
verbosity flag (e.g. via launchd --replace).

Fixes #8044

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: improve context compaction to prevent model answering stale questions (#8107)

After compression, models (especially Kimi 2.5) would sometimes respond
to questions from the summary instead of the latest user message. This
happened ~30% of the time on Telegram.

Root cause: the summary's 'Next Steps' section read as active instructions,
and the SUMMARY_PREFIX didn't explicitly tell the model to ignore questions
in the summary. When the summary merged into the first tail message, there
was no clear separator between historical context and the actual user message.

Changes inspired by competitor analysis (Claude Code, OpenCode, Codex):

1. SUMMARY_PREFIX rewritten with explicit 'Do NOT answer questions from
   this summary — respond ONLY to the latest user message AFTER it'

2. Summarizer preamble (shared by both prompts) adds:
   - 'Do NOT respond to any questions' (from OpenCode's approach)
   - 'Different assistant' framing (from Codex) to create psychological
     distance between summary content and active conversation

3. New summary sections:
   - '## Resolved Questions' — tracks already-answered questions with
     their answers, preventing re-answering (from Claude Code's
     'Pending user asks' pattern)
   - '## Pending User Asks' — explicitly marks unanswered questions
   - '## Remaining Work' replaces '## Next Steps' — passive framing
     avoids reading as active instructions

4. merge-summary-into-tail path now inserts a clear separator:
   '--- END OF CONTEXT SUMMARY — respond to the message below ---'

5. Iterative update prompt now instructs: 'Move answered questions to
   Resolved Questions' to maintain the resolved/pending distinction
   across multiple compactions.

* feat: add network.force_ipv4 config to fix IPv6 timeout issues (#8196)

On servers with broken or unreachable IPv6, Python's socket.getaddrinfo
returns AAAA records first. urllib/httpx/requests all try IPv6 connections
first and hang for the full TCP timeout before falling back to IPv4. This
affects web_extract, web_search, the OpenAI SDK, and all HTTP tools.

Adds network.force_ipv4 config option (default: false) that monkey-patches
socket.getaddrinfo to resolve as AF_INET when the caller didn't specify a
family. Falls back to full resolution if no A record exists, so pure-IPv6
hosts still work.

Applied early at all three entry points (CLI, gateway, cron scheduler)
before any HTTP clients are created.

Reported by user @29n — Chinese Ubuntu server with unreachable IPv6 causing
timeouts on lobste.rs and other IPv6-enabled sites while Google/GitHub
worked fine (IPv4-only resolution).

* fix(cron): steer model away from explicit deliver targets that lose topic context (#8187)

Rewrite the cronjob tool's 'deliver' parameter description to strongly
guide models toward omitting the parameter (which auto-detects origin
including thread/topic). The previous description listed all platform
names equally, inviting models to construct explicit targets like
'telegram:<chat_id>' which silently drops the thread_id.

New description:
- Leads with 'Omit this parameter' as the recommended path
- Explicitly warns that platform:chat_id without :thread_id loses topics
- Removes the long flat list of platform names that invited construction

Also adds diagnostic logging at two key points:
- _origin_from_env(): logs when thread_id is captured during job creation
- _deliver_result(): warns when origin has thread_id but delivery target
  lost it; logs at debug when delivering to a specific thread

Helps diagnose user-reported issue where cron responses from Telegram
topics are delivered to the main chat instead of the originating topic.

* fix(cli): restore stacked tool progress scrollback in TUI (#8201)

The TUI transition (4970705, f83e86d) replaced stacked per-tool history
lines with a single live-updating spinner widget. While the spinner
provides a nice live timer, it removed the scrollback history that
users relied on to see what the agent did during a session.

This restores stacked tool progress lines in 'all' and 'new' modes by
printing persistent scrollback lines via _cprint() when tools complete,
in addition to the existing live spinner display.

Behavior per mode:
- off: no scrollback lines, no spinner (unchanged)
- new: scrollback line on completion, skipping consecutive same-tool repeats
- all: scrollback line on every tool completion
- verbose: no scrollback (run_agent.py handles verbose output directly)

Implementation:
- Store function_args from tool.started events in _pending_tool_info
- On tool.completed, pop stored args and format via get_cute_tool_message()
- FIFO queue per function_name handles concurrent tool execution
- 'new' mode tracks _last_scrollback_tool for dedup
- State cleared at end of agent run

Reported by community user Mr.D — the stacked history provides
transparency into what the agent is doing, which builds trust.

Addresses user report from Discord about lost tool call visibility.

* fix: make gateway interrupt detection resilient to monitor task failures

The interrupt mechanism for regular text messages (non-commands) during
active agent runs relied on a single async polling task
(monitor_for_interrupt) with no error handling. If this task died
silently due to an unhandled exception, stale adapter reference after
reconnect, or any other failure, user messages sent during agent
execution would be queued but never trigger an actual interrupt — the
agent would continue running until it finished naturally, then process
the queued message.

Three improvements:

1. Error handling in monitor_for_interrupt(): wrap the polling body in
   try/except so transient errors are logged and retried instead of
   silently killing the task.

2. Fresh adapter reference on each poll iteration: re-resolve
   self.adapters.get(source.platform) every 200ms instead of capturing
   the adapter once at task creation time. This prevents stale
   references after adapter reconnects.

3. Backup interrupt check in the inactivity poll loop: both the
   unlimited and timeout-enabled paths now check for pending interrupts
   every 5 seconds (the existing poll interval). Uses a shared
   _interrupt_detected asyncio.Event to avoid double-firing when the
   primary monitor already handled the interrupt. Logs at INFO level
   with monitor task state for debugging.

* fix: openai-codex and anthropic not appearing in /model picker for external credentials (#8224)

Users whose credentials exist only in external files — OpenAI Codex
OAuth tokens in ~/.codex/auth.json or Anthropic Claude Code credentials
in ~/.claude/.credentials.json — would not see those providers in the
/model picker, even though hermes auth and hermes model detected them.

Root cause: list_authenticated_providers() only checked the raw Hermes
auth store and env vars. External credential file fallbacks (Codex CLI
import, Claude Code file discovery) were never triggered.

Fix (three parts):
1. _seed_from_singletons() in credential_pool.py: openai-codex now
   imports from ~/.codex/auth.json when the Hermes auth store is empty,
   mirroring resolve_codex_runtime_credentials().
2. list_authenticated_providers() in model_switch.py: auth store + pool
   checks now run for ALL providers (not just OAuth auth_type), catching
   providers like anthropic that support both API key and OAuth.
3. list_authenticated_providers(): direct check for anthropic external
   credential files (Claude Code, Hermes PKCE). The credential pool
   intentionally gates anthropic behind is_provider_explicitly_configured()
   to prevent auxiliary tasks from silently consuming tokens. The /model
   picker bypasses this gate since it is discovery-oriented.

* feat: rebrand OpenClaw references to Hermes during migration

- Add rebrand_text() that replaces OpenClaw, Open Claw, Open-Claw,
  ClawdBot, and MoltBot with Hermes (case-insensitive, word-boundary)
- Apply rebranding to memory entries (MEMORY.md, USER.md, daily memory)
- Apply rebranding to SOUL.md and workspace instructions via new
  transform parameter on copy_file()
- Fix moldbot -> moltbot typo across codebase (claw.py, migration
  script, docs, tests)
- Add unit tests for rebrand_text and integration tests for memory
  and soul migration rebranding

* fix(migration): don't auto-archive OpenClaw source directory

Remove auto-archival from hermes claw migrate — not its
responsibility (hermes claw cleanup is still there for that).

Skip MESSAGING_CWD when it points inside the OpenClaw source
directory, which was the actual root cause of agent confusion
after migration. Use Path.is_relative_to() for robust path
containment check.

Salvaged from PR #8192 by opriz.
Co-authored-by: opriz <opriz@users.noreply.github.com>

* feat(cli): show random tip on new session start (#8225)

Add a 'tip of the day' feature that displays a random one-liner about
Hermes Agent features on every new session — CLI startup, /clear, /new,
and gateway /new across all messaging platforms.

- New hermes_cli/tips.py module with 210 curated tips covering slash
  commands, keybindings, CLI flags, config options, tools, gateway
  platforms, profiles, sessions, memory, skills, cron, voice, security,
  and more
- CLI: tips display in skin-aware dim gold color after the welcome line
- Gateway: tips append to the /new and /reset response on all platforms
- Fully wrapped in try/except — tips are non-critical and never break
  startup or reset

Display format (CLI):
  ✦ Tip: /btw <question> asks a quick side question without tools or history.

Display format (gateway):
  ✨ Session reset! Starting fresh.
  ✦ Tip: hermes -c resumes your most recent CLI session.

* fix: suppress duplicate completion notifications when agent already consumed output via wait/poll/log (#8228)

When the agent calls process(action='wait') or process(action='poll')
and gets the exited status, the completion_queue notification is
redundant — the agent already has the output from the tool return.
Previously, the drain loops in CLI and gateway would still inject
the [SYSTEM: Background process completed] message, causing the
agent to receive the same information twice.

Fix: track session IDs in _completion_consumed set when wait/poll/log
returns an exited process. Drain loops in cli.py and gateway watcher
skip completion events for consumed sessions. Watch pattern events
are never suppressed (they have independent semantics).

Adds 4 tests covering wait/poll/log marking and running-process
negative case.

* fix(weixin): split chatty short replies into separate bubbles, keep structured content together

Add content-aware splitting to compact mode: short chat-like exchanges
(2-6 short lines without headings/lists/quotes) get separate message
bubbles for a natural chat feel, while structured content (tables,
headings with body, numbered lists) stays in a single message.

Cherry-picked from PR #7587 by bravohenry, adapted to the compact/legacy
split_per_line architecture from #7903.

* fix(docker): run as non-root user, use virtualenv (salvage #5811)

- Add gosu for runtime privilege dropping from root to hermes user
- Support HERMES_UID/HERMES_GID env vars for host mount permission matching
- Switch to debian:13.4-slim base image
- Use uv venv instead of pip install --break-system-packages
- Pin uv and gosu multi-stage images with SHA256 digests
- Set PLAYWRIGHT_BROWSERS_PATH to /opt/hermes/.playwright so build-time
  chromium install survives the /opt/data volume mount
- Keep procps for container debugging

Based on work by m0n5t3r in PR #5811. Stripped to hardening-only
changes (non-root, virtualenv, slim base); matrix deps, fonts, xvfb,
and entrypoint playwright download deferred to follow-up.

* revert: keep debian:13.4 full image instead of slim

The slim image drops packages that may be needed at runtime.
Keep the full Debian base for compatibility.

* feat(tips): add 69 deeper hidden-gem tips (279 total) (#8237)

Add lesser-known power-user tips covering:
- BOOT.md gateway startup automation
- Cron script attachment for data collection pipelines
- Prefill messages for few-shot priming
- Focus topic compression (/compress <topic>)
- Terminal exit code annotations and auto-retry
- Automatic sudo password piping
- execute_code built-in helpers (json_parse, shell_quote, retry)
- File loop detection and staleness warnings
- MCP sampling and dynamic tool discovery
- Delegation heartbeat and ACP child agents (Claude Code)
- 402 auto-fallback in auxiliary client
- Container mode, HERMES_HOME_MODE, subprocess HOME isolation
- Ctrl+C 5-tier priority system
- Browser CDP URL override and stealth mode
- Skills quarantine, audit log, and well-known protocol
- Per-platform display overrides, human delay mode
- And many more deep-cut features

* fix: list all available toolsets in delegate_task schema description (#8231)

* fix: list all available toolsets in delegate_task schema description

The delegate_task tool's toolsets parameter description only mentioned
'terminal', 'file', and 'web' as examples. Models (especially smaller
ones like Gemma) would substitute 'web' for 'browser' because they
didn't know 'browser' was a valid option.

Now dynamically builds the toolset list from the TOOLSETS dict at import
time, excluding blocked, composite, and platform-specific toolsets.
Auto-updates when new toolsets are added.

Reported by jeffutter on Discord.

* chore: exclude moa and rl from delegate_task toolset list

* fix(agent): route compression aux through live session runtime

* fix: three provider-related bugs (#8161, #8181, #8147) (#8243)

- Add openai/openai-codex -> openai mapping to PROVIDER_TO_MODELS_DEV
  so context-length lookups use models.dev data instead of 128k fallback.
  Fixes #8161.

- Set api_mode from custom_providers entry when switching via hermes model,
  and clear stale api_mode when the entry has none. Also extract api_mode
  in _named_custom_provider_map(). Fixes #8181.

- Convert OpenAI image_url content blocks to Anthropic image blocks when
  the endpoint is Anthropic-compatible (MiniMax, MiniMax-CN, or any URL
  containing /anthropic). Fixes #8147.

* fix: make skill loading instructions more aggressive in system prompt (#8209)

The previous wording ('If one clearly matches') set too high a threshold,
and 'If none match, proceed normally' was an easy escape hatch for lazy
models. Now:

- Lowered threshold: 'matches or is even partially relevant'
- Added MUST directive and 'err on the side of loading' guidance
- Replaced permissive closer with 'only proceed without if genuinely none
  are relevant'

This should reduce cases where the agent skips loading relevant skills
unless explicitly forced.

* fix(setup): validate base URL input in hermes model flow (#8264)

Reject non-URL values (e.g. shell commands typed by mistake) in the
base URL prompt during provider setup. Previously any string was saved
as-is to .env, breaking connectivity when the garbage value was used
as the API endpoint.

Adds http:// / https:// prefix check with a clear error message.
The custom-endpoint flow already had this validation (line 1620);
this brings the generic API-key provider flow to parity.

Triggered by a user support case where 'nano ~/.hermes/.env' was
accidentally entered as GLM_BASE_URL during Z.AI setup.

* fix(gateway): peek at pending message during interrupt instead of consuming it

The monitor_for_interrupt() and backup interrupt checks were calling
get_pending_message() which pops the message from the adapter's queue.
This created a race condition: if the agent finished naturally before
checking _interrupt_requested, the pending message was permanently lost.

Timeline of the race:
1. Agent near completion, user sends message
2. Level 1 guard stores message in adapter._pending_messages, sets event
3. monitor_for_interrupt() detects event, POPS message, calls agent.interrupt()
4. Agent's run_conversation() was already returning (interrupted=False)
5. Post-run dequeue finds nothing (monitor already consumed it)
6. result.get('interrupted') is False so interrupt_message fallback doesn't fire
7. User message permanently lost — agent finishes without processing it

Fix: change all three interrupt detection sites (primary monitor + two
backup checks) from get_pending_message() (pop) to
_pending_messages.get() (peek). The message stays in the adapter's queue
until _dequeue_pending_event() consumes it in the post-run handler,
which runs regardless of whether the agent was interrupted or finished
naturally.

Reported by @_SushantSays — intermittent message loss during long
terminal command execution, persisting after the previous fix (73f970fa)
which addressed monitor task death but not this consumption race.

* fix(gateway): evict cached agent on /model switch + add diagnostic logging (#8276)

After /model switches the model (both picker and text paths), the cached
agent's config signature becomes stale — the agent was updated in-place
via switch_model() but the cache tuple's signature was never refreshed.
The next turn *should* detect the signature mismatch and create a fresh
agent, but this relies on the new model's signature differing from the
old one in _agent_config_signature().

Evicting the cached agent explicitly after storing the session override
is more defensive — the next turn is guaranteed to create a fresh agent
from the override without depending on signature mismatch detection.

Also adds debug logging at three key decision points so we can trace
exactly what happens when /model + /retry interact:
- _resolve_session_agent_runtime: which override path is taken (fast
  with api_key vs fallback), or why no override was found
- _run_agent.run_sync: final resolved model/provider before agent
  creation

Reported: /model switch to xiaomi/mimo-v2-pro followed by /retry still
used the old model (glm-5.1).

* fix: write refreshed Codex tokens back to ~/.codex/auth.json (#8277)

OpenAI OAuth refresh tokens are single-use and rotate on every refresh.
When Hermes refreshes a Codex token, it consumed the old refresh_token
but never wrote the new pair back to ~/.codex/auth.json. This caused
Codex CLI and VS Code to fail with 'refresh_token_reused' on their
next refresh attempt.

This mirrors the existing Anthropic write-back pattern where refreshed
tokens are written to ~/.claude/.credentials.json via
_write_claude_code_credentials().

Changes:
- Add _write_codex_cli_tokens() in hermes_cli/auth.py (parallel to
  _write_claude_code_credentials in anthropic_adapter.py)
- Call it from _refresh_codex_auth_tokens() (non-pool refresh path)
- Call it from credential_pool._refresh_entry() (pool happy path + retry)
- Add tests for the new write-back behavior
- Update existing test docstring to clarify _save_codex_tokens vs
  _write_codex_cli_tokens separation

Fixes refresh token conflict reported by @ec12edfae2cb221

* chore: simplify Docker image tags

- Main branch push: only push :latest (remove SHA tag)
- Release push: only push release tag name (remove :latest and SHA tag)

* fix(matrix): restore verify_with_recovery_key after device key rotation

After the PgCryptoStore migration in v0.8.0, the verify_with_recovery_key
call that previously ran after share_keys() was dropped. On any rotation
that uploads fresh device keys (fresh crypto.db, server had stale keys
from a prior install, etc.), the new device keys carry no valid self-
signing signature because the bot has no access to the self-signing
private key.

Peers like Element then refuse to share Megolm sessions with the
rotated device, so the bot silently stops decrypting incoming messages.

This restores the recovery-key bootstrap: on startup, if
MATRIX_RECOVERY_KEY is set, import the cross-signing private keys from
SSSS and sign_own_device(), producing a valid signature server-side.

Idempotent and gated on MATRIX_RECOVERY_KEY — no behavior change for
users who don't configure a recovery key.

Verified end-to-end by deleting crypto.db and restarting: the bot
rotates device identity keys, re-uploads, self-signs via recovery key,
and decrypts+replies to fresh messages from a paired Element client.

* fix: register MATRIX_RECOVERY_KEY env var + document migration path

Follow-up for cherry-picked PR #8272:
- Add MATRIX_RECOVERY_KEY to module docstring header in matrix.py
- Register in OPTIONAL_ENV_VARS (config.py) with password=True, advanced=True
- Add to _NON_SETUP_ENV_VARS set
- Document cross-signing verification in matrix.md E2EE section
- Update migration guide with recovery key step (step 3)
- Add to environment-variables.md reference

* feat: add WSL environment hint to system prompt (#8285)

When running inside WSL (Windows Subsystem for Linux), inject a hint into
the system prompt explaining that the Windows host filesystem is mounted
at /mnt/c/, /mnt/d/, etc. This lets the agent naturally translate Windows
paths (Desktop, Documents) to their /mnt/ equivalents without the user
needing to configure anything.

Uses the existing is_wsl() detection from hermes_constants (cached,
checks /proc/version for 'microsoft'). Adds build_environment_hints()
in prompt_builder.py — extensible for Termux, Docker, etc. later.

Closes the UX gap where WSL users had to manually explain path
translation to the agent every session.

* fix: write update exit code before gateway restart (cgroup kill race) (#8288)

When /update runs via Telegram, hermes update --gateway is spawned inside
the gateway's systemd cgroup.  The update process itself calls
systemctl restart hermes-gateway, which tears down the cgroup with
KillMode=mixed — SIGKILL to all remaining processes.  The wrapping bash
shell is killed before it can execute the exit-code epilogue, so
.update_exit_code is never created.  The new gateway's update watcher
then polls for 30 minutes and sends a spurious timeout message.

Fix: write .update_exit_code from Python inside cmd_update() immediately
after the git pull + pip install succeed ("Update complete!"), before
attempting the gateway restart.  The shell epilogue still writes it too
(idempotent overwrite), but now the marker exists even when the process
is killed mid-restart.

* fix: prevent unwanted session auto-reset after graceful gateway restarts (#8299)

When the gateway shuts down gracefully (hermes update, gateway restart,
/restart), it now writes a .clean_shutdown marker file. On the next
startup, if this marker exists, suspend_recently_active() is skipped
and the marker is cleaned up.

Previously, suspend_recently_active() fired on EVERY startup —
including planned restarts from hermes update or hermes gateway restart.
This caused users to lose their conversation history unexpectedly: the
session would be marked as suspended, and the next message would
trigger an auto-reset with a notification the user never asked for.

The original purpose of suspend_recently_active() is crash recovery —
preventing stuck sessions that were mid-processing when the gateway
died unexpectedly. Graceful shutdowns already drain active agents via
_drain_active_agents(), so there is no stuck-session risk. After a
crash (no marker written), suspension still fires as before.

Fixes the scenario where a user asks the agent to run hermes update,
the gateway restarts, and the user's next message gets an unwanted
'Session automatically reset' notification with their history cleared.

* fix: make skill loading instructions more aggressive in system prompt (#8286)

The previous wording ('If one clearly matches') set too high a threshold,
and 'If none match, proceed normally' was an easy escape hatch for lazy
models. Now:

- Lowered threshold: 'matches or is even partially relevant'
- Added MUST directive and 'err on the side of loading' guidance
- Replaced permissive closer with 'only proceed without if genuinely none
  are relevant'

This should reduce cases where the agent skips loading relevant skills
unless explicitly forced.

* fix: fall back to provider's default model when model config is empty (#8303)

When a user configures a provider (e.g. `hermes auth add openai-codex`)
but never selects a model via `hermes model`, the gateway and CLI would
pass an empty model string to the API, causing:
  'Codex Responses request model must be a non-empty string'

Now both gateway (_resolve_session_agent_runtime) and CLI
(_ensure_runtime_credentials) detect an empty model and fill it from
the provider's first catalog entry in _PROVIDER_MODELS. This covers
all providers that have a static model list (openai-codex, anthropic,
gemini, copilot, etc.).

The fix is conservative: it only triggers when model is truly empty
and a known provider was resolved. Explicit model choices are never
overridden.

* fix: title_generator no longer logs as 'compression' task

Changed task='compression' to task='title_generation' so auto-title
calls don't pollute logs with false compression alarms.

* fix: prevent duplicate update prompt spam in gateway watcher (#8343)

The _watch_update_progress() poll loop never deleted .update_prompt.json
after forwarding the prompt to the user, causing the same prompt to be
re-sent every poll cycle (2s). Two fixes:

1. Delete .update_prompt.json after forwarding — the update process only
   polls for .update_response, it doesn't need the prompt file to persist.
2. Guard re-sends with _update_prompt_pending check — belt-and-suspenders
   to prevent duplicates even under race conditions.

Add regression test asserting the prompt is sent exactly once.

* fix: improve profile creation UX — seed SOUL.md + credential warning (#8553)

Fresh profiles (created without --clone) now:
- Auto-seed a default SOUL.md immediately, so users have a file to
  customize right away instead of discovering it only after first use
- Print a clear warning that the profile has no API keys and will
  inherit from the shell environment unless configured separately
- Show the SOUL.md path for personality customization

Previously, fresh profiles started with no SOUL.md (only seeded on
first use via ensure_hermes_home), no mention of credential isolation,
and no guidance about customizing personality. Users reported confusion
about profiles using the wrong model/plan tokens and SOUL.md not
being read — both traced to operational gaps in the creation UX.

Closes #8093 (investigated: code correctly loads SOUL.md from profile
HERMES_HOME; issue was operational, not a code bug).

* fix: handle broken stdin in prompt_toolkit startup (#6393) (#8560)

On macOS with uv-managed Python, stdin (fd 0) can be invalid or
unregisterable with the asyncio selector, causing:

  KeyError: '0 is not registered'

during prompt_toolkit's app.run() → asyncio.run() → _add_reader(0).

Three-layer fix:
1. Pre-flight fstat(0) check before app.run() — detects broken stdin
   early and prints actionable guidance instead of a raw traceback.
2. Catch KeyError/OSError around app.run() as fallback for edge cases
   that slip past the fstat guard.
3. Extend asyncio exception handler to suppress selector registration
   KeyErrors in async callbacks.

Fixes #6393

* fix: make agent_thread daemon to prevent orphan CLI processes on tab close (#8557)

When a user closes a terminal tab, SIGHUP exits the main thread but
the non-daemon agent_thread kept the entire Python process alive —
stuck in the API call loop with no interrupt signal. Over many
conversations, these orphan processes accumulate and cause massive
swap usage (reported: 77GB on a 32GB M1 Pro).

Changes:
- Make agent_thread daemon=True so the process exits when the main
  thread finishes its cleanup. Under normal operation this changes
  nothing — the main thread already waits on agent_thread.is_alive().
- Interrupt the agent in the finally/exit path so the daemon thread
  stops making API calls promptly rather than being killed mid-flight.

* fix: strip <thought> tags from Gemma 4 responses in _strip_think_blocks

Gemma 4 (26B/31B) uses <thought>...</thought> to wrap its reasoning
output. This tag was not included in the existing list of reasoning tag
variants stripped by _strip_think_blocks(), causing raw thinking blocks
to leak into the visible response.

Added a new re.sub() line for <thought> and extended the cleanup regex
to include 'thought' alongside the existing variants.

Fixes #6148

* fix: also strip <thought> tags during streaming in cli.py

* fix: add <thought> stripping to auxiliary_client + tests

auxiliary_client.py had its own regex mirroring _strip_think_blocks
but was missing the <thought> variant. Also adds test coverage for
<thought> paired and orphaned tags.

* fix: contextual error diagnostics for invalid API responses (#8565)

Previously, all invalid API responses (choices=None) were diagnosed
as 'fast response often indicates rate limiting' regardless of actual
response time or error code. A 738s Cloudflare 524 timeout was labeled
as 'fast response' and 'possible rate limit'.

Now extracts the error code from response.error and classifies:
- 524: upstream provider timed out (Cloudflare)
- 504: upstream gateway timeout
- 429: rate limited by upstream provider
- 500/502: upstream server error
- 503/529: upstream provider overloaded
- Other codes: shown with code number
- No code + <10s: likely rate limited (timing heuristic)
- No code + >60s: likely upstream timeout
- No code + 10-60s: neutral response time

All downstream messages (retry status, final error, interrupt message)
now use the classified hint instead of generic rate-limit language.

Reported by community member Lumen Radley (MiMo provider timeouts).

* feat(feishu): add scan-to-create onboarding for Feishu / Lark

Add a QR-based onboarding flow to `hermes gateway setup` for Feishu / Lark.
Users scan a QR code with their phone and the platform creates a fully
configured bot application automatically — matching the existing WeChat
QR login experience.

Setup flow:
- Choose between QR scan-to-create (new app) or manual credential input (existing app)
- Connection mode selection (WebSocket / Webhook)
- DM security policy (pairing / open / allowlist / disabled)
- Group chat policy (open with @mention / disabled)

Implementation:
- Onboard functions (init/begin/poll/QR/probe) in gateway/platforms/feishu.py
- _setup_feishu() in hermes_cli/gateway.py with manual fallback
- probe_bot uses lark_oapi SDK when available, raw HTTP fallback otherwise
- qr_register() catches expected errors (network/protocol), propagates bugs
- Poll handles HTTP 4xx JSON responses and feishu/lark domain auto-detection

Tests:
- 25 tests for onboard module (registration, QR, probe, contract, negative paths)
- 16 tests for setup flow (credentials, connection mode, DM policy, group policy,
  adapter integration verifying env vars produce valid FeishuAdapterSettings)

Change-Id: I720591ee84755f32dda95fbac4b26dc82cbcf823

* fix: salvage follow-ups for Feishu QR onboarding (#7706)

- Remove duplicate _setup_feishu() definition (old 3-line version left
  behind by cherry-pick — Python picked the new one but dead code
  remained)
- Remove misleading 'Disable direct messages' DM option — the Feishu
  adapter has no DM policy mechanism, so 'disable' produced identical
  env vars to 'pairing'. Users who chose 'disable' would still see
  pairing prompts. Reduced to 3 options: pairing, allow-all, allowlist.
- Fix test_probe_returns_bot_info_on_success and
  test_probe_returns_none_on_failure: patch FEISHU_AVAILABLE=True so
  probe_bot() takes the SDK path when lark_oapi is not installed

* feat: make gateway 'still working' notification interval configurable (#8572)

Add agent.gateway_notify_interval config option (default 600s).
Set to 0 to disable periodic 'still working' notifications.
Bridged to HERMES_AGENT_NOTIFY_INTERVAL env var (same pattern as
gateway_timeout and gateway_timeout_warning).

The inactivity warning (gateway_timeout_warning) was already
configurable; this makes the wall-clock ping configurable too.

* fix: empty response recovery for reasoning models (mimo, qwen, GLM) (#8609)

Three fixes for the (empty) response bug affecting open reasoning models:

1. Allow retries after prefill exhaustion — models like mimo-v2-pro always
   populate reasoning fields via OpenRouter, so the old 'not _has_structured'
   guard on the retry path blocked retries for EVERY reasoning model after
   the 2 prefill attempts.  Now: 2 prefills + 3 retries = 6 total attempts
   before (empty).

2. Reset prefill/retry counters on tool-call recovery — the counters
   accumulated across the entire conversation, never resetting during
   tool-calling turns.  A model cycling empty→prefill→tools→empty burned
   both prefill attempts and the third empty got zero recovery.  Now
   counters reset when prefill succeeds with tool calls.

3. Strip think blocks before _truly_empty check — inline <think> content
   made the string non-empty, skipping both retry paths.

Reported by users on Telegram with xiaomi/mimo-v2-pro and qwen3.5 models.
Reproduced: qwen3.5-9b emits tool calls as XML in reasoning field instead
of proper function calls, causing content=None + tool_calls=None + reasoning
with embedded <tool_call> XML.  Prefill recovery works but counter
accumulation caused permanent (empty) in long sessions.

* fix(backup): correct marker filenames in _validate_backup_zip

The backup validation checked for 'hermes_state.db' and 'memory_store.db'
as telltale markers of a valid Hermes backup zip. Neither name exists in a
real Hermes installation — the actual database file is 'state.db'
(hermes_state.py: DEFAULT_DB_PATH = get_hermes_home() / 'state.db').

A fresh Hermes installation produces:
  ~/.hermes/state.db        (actual name)
  ~/.hermes/config.yaml
  ~/.hermes/.env

Because the marker set never matched 'state.db', a backup zip containing
only 'state.db' plus 'config.yaml' would fail validation with:
  'zip does not appear to be a Hermes backup'
and the import would exit with sys.exit(1), silently rejecting a valid backup.

Fix: replace the wrong marker names with the correct filename.

Adds TestValidateBackupZip with three cases:
- state.db is accepted as a valid marker
- old wrong names (hermes_state.db, memory_store.db) alone are rejected
- config.yaml continues to pass (existing behaviour preserved)

* fix(gateway): harden Docker/container gateway pathway

Centralize container detection in hermes_constants.is_container() with
process-lifetime caching, matching existing is_wsl()/is_termux() patterns.
Dedup _is_inside_container() in config.py to delegate to the new function.

Add _run_systemctl() wrapper that converts FileNotFoundError to RuntimeError
for defense-in-depth — all 10 bare subprocess.run(_systemctl_cmd(...)) call
sites now route through it.

Make supports_systemd_services() return False in containers and when
systemctl binary is absent (shutil.which check).

Add Docker-specific guidance in gateway_command() for install/uninstall/start
subcommands — exit 0 with helpful instructions instead of crashing.

Make 'hermes status' show 'Manager: docker (foreground)' and 'hermes dump'
show 'running (docker, pid N)' inside containers.

Fix setup_gateway() to use supports_systemd instead of _is_linux for all
systemd-related branches, and show Docker restart policy instructions in
containers.

Replace inline /.dockerenv check in voice_mode.py with is_container().

Fixes #7420

Co-authored-by: teknium1 <teknium1@users.noreply.github.com>

* chore: sync uv.lock with matrix extra deps (aiosqlite, asyncpg) (#8661)

These were already declared in pyproject.toml but missing from the lockfile.

* fix(skills): cache GitHub repo trees to avoid rate-limit exhaustion on install

Skills.sh installs hit the GitHub API 45 times per install because the
same repo tree was fetched 6 times redundantly. Combined with search
(23 API calls), this totals 68 — exceeding the unauthenticated rate
limit of 60 req/hr, causing 'Could not fetch' errors for users without
a GITHUB_TOKEN.

Changes:
- Add _get_repo_tree() cache to GitHubSource — repo info + recursive
  tree fetched once per repo per source instance, eliminating 10
  redundant API calls (6 tree + 4 candidate 404s)
- _download_directory_via_tree returns {} (not None) when cached tree
  shows path doesn't exist, skipping unnecessary Contents API fallback
- _check_rate_limit_response() detects exhausted quota and sets
  is_rate_limited flag
- do_install() shows actionable hint when rate limited: set
  GITHUB_TOKEN or install gh CLI

Before: 45 API calls per install (68 total with search)
After:  31 API calls per install (54 total with search — under 60/hr)

Reported by community user from Vietnam (no GitHub auth configured).

* feat(skills): centralized skills index — eliminate GitHub API calls for search/install

Add a CI-built skills index served from the docs site. The index is
crawled daily by GitHub Actions, resolves all GitHub paths upfront, and
is cached locally by the client. When the index is available:

- Search uses the cached index (0 GitHub API calls, was 23+)
- Install uses resolved paths from index (6 API calls for file
  downloads only, was 31-45 for discovery + downloads)

Total: 68 → 6 GitHub API calls for a typical search + install flow.
Unauthenticated users (60 req/hr) can now search and install without
hitting rate limits.

Components:
- scripts/build_skills_index.py: Crawl all sources (skills.sh, GitHub
  taps, official, clawhub, lobehub), batch-resolve GitHub paths via
  tree API, output JSON index
- tools/skills_hub.py: HermesIndexSource class — search/fetch/inspect
  backed by the index, with lazy GitHubSource for file downloads
- parallel_search_sources() skips external API sources when index is
  available (0 GitHub calls for search)
- .github/workflows/skills-index.yml: twice-daily CI build + deploy
- .github/workflows/deploy-site.yml: also builds index during docs deploy

Graceful degradation: when the index is unavailable (first run, network
down, stale), all methods return empty/None and downstream sources
handle the request via direct API as before.

* fix(claw): warn if OpenClaw is running before migration

Add _is_openclaw_running() and _warn_if_openclaw_running() to detect
OpenClaw processes (via pgrep/tasklist) before hermes claw migrate.
Warns the user that messaging platforms only allow one active session
per bot token, and lets them cancel or continue.

Fixes #7907

* fix(claw): address Copilot review on Windows detection and non-interactive prompt

- Use PowerShell to inspect node.exe command lines on Windows,
  since tasklist output does not include them.
- Also check for dedicated openclaw.exe/clawd.exe processes.
- Skip the interactive prompt in non-interactive sessions so the
  preview-only behavior is preserved.
- Update tests accordingly.

Relates to #7907

* fix(claw): warn and prompt if OpenClaw is still running before archival (fixes #8502)

* fix: unify OpenClaw detection, add isatty guard, fix print_warning import

Combines detection from both PRs into _detect_openclaw_processes():
- Cross-platform process scan (pgrep/tasklist/PowerShell) from PR #8102
- systemd service check from PR #8555
- Returns list[str] with details about what's found

Fixes in cleanup warning (from PR #8555):
- print_warning -> print_error/print_info (print_warning not in import chain)
- Added isatty() guard for non-interactive sessions
- Removed duplicate _check_openclaw_running() in favor of shared function

Updated all tests to match new API.

* fix(weixin): streaming cursor, media uploads, markdown links, blank messages (#8665)

Four fixes for the Weixin/WeChat adapter, synthesized from the best
aspects of community PRs #8407, #8521, #8360, #7695, #8308, #8525,
#7531, #8144, #8251.

1. Streaming cursor (▉) stuck permanently — WeChat doesn't support
   message editing, so the cursor appended during streaming can never
   be removed.  Add SUPPORTS_MESSAGE_EDITING = False to WeixinAdapter
   and check it in gateway/run.py to use an empty cursor for non-edit
   platforms.  (Fixes #8307, #8326)

2. Media upload failures — two bugs in _send_file():
   a) upload_full_url path used PUT (404 on WeChat CDN); now uses POST.
   b) aes_key was base64(raw_bytes) but the iLink API expects
      base64(hex_string); images showed as grey boxes.  (Fixes #8352, #7529)
   Also: unified both upload paths into _upload_ciphertext(), preferring
   upload_full_url.  Added send_video/send_voice methods and voice_item
   media builder for audio/.silk files.  Added video_md5 field.

3. Markdown links stripped — WeChat can't render [text](url), so
   format_message() now converts them to 'text (url)' plaintext.
   Code blocks are preserved.  (Fixes #7617)

4. Blank message prevention — three guards:
   a) _split_text_for_weixin_delivery('') returns [] not ['']
   b) send() filters empty/whitespace chunks before _send_text_chunk
   c) _send_message() raises ValueError for empty text as safety net

Community credit: joei4cm (#8407), lyonDan (#8521), SKFDJKLDG (#8360),
tomqiaozc (#7695), joshleeeeee (#8308), luoxiao6645(#8525),
longsizhuo (#7531), Astral-Yang (#8144), QingWei-Li (#8251).

* fix: make mimo-v2-pro the default model for Nous portal users

Users who set up Nous auth without explicitly selecting a model via
`hermes model` were silently falling back to anthropic/claude-opus-4.6
(the first entry in _PROVIDER_MODELS['nous']), causing unexpected
charges on their Nous plan. Move xiaomi/mimo-v2-pro to the first
position so unconfigured users default to a free model instead.

* feat(tts): add speed support for Edge TTS and OpenAI TTS

Read tts.speed (global) or tts.<provider>.speed (provider-specific) from
config. Provider-specific takes precedence over global.

- Edge TTS: converts speed float to SSML prosody rate string
- OpenAI TTS: passes speed param clamped to 0.25-4.0
- MiniMax: wired into global tts.speed fallback for consistency

Co-authored-by: 0xbyt4 <0xbyt4@users.noreply.github.com>

* test(tts): add speed config tests for Edge, OpenAI, and MiniMax

12 tests covering:
- Provider-specific speed overrides global speed
- Global speed used as fallback
- Default (no speed) preserves existing behavior
- Edge SSML rate string conversion (positive/negative)
- OpenAI speed clamping to 0.25-4.0 range

* fix(compression): pass configured context_length to feasibility check

_check_compression_model_feasibility() called get_model_context_length()
without passing config_context_length, so custom endpoints that do not
support /models API queries always fell through to the 128K default,
ignoring auxiliary.compression.context_length in config.yaml.

Fix: read auxiliary.compression.context_length from config and pass it
as config_context_length (highest-priority hint) so the user-configured
value is always respected regardless of API availability.

Fixes #8499

* test: add tests for compression config_context_length passthrough

- Test that auxiliary.compression.context_length from config is forwarded
  to get_model_context_length (positive case)
- Test that invalid/non-integer config values are silently ignored
- Fix _make_agent() to set config=None (cherry-picked code reads self.config)

* fix(weixin,wecom,matrix): respect system proxy via aiohttp trust_env

aiohttp.ClientSession defaults to trust_env=False, ignoring HTTP_PROXY/
HTTPS_PROXY env vars. This causes QR login and all API calls to fail for
users behind a proxy (e.g. Clash in fake-ip mode), which is common in
China where Weixin and WeCom are primarily used.

Added trust_env=True to all aiohttp.ClientSession instantiations that
connect to external hosts (weixin: 3 places, wecom: 1, matrix: 1).
WhatsApp sessions are excluded as they only connect to localhost.

httpx-based adapters (dingtalk, signal, wecom_callback) are unaffected
as httpx defaults to trust_env=True.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* docs: add HermesClaw to community ecosystem

Adds a one-line entry for HermesClaw (community WeChat bridge) to the Community section. It lets users run Hermes Agent and OpenClaw on the same WeChat account.

* fix(api_server): normalize array-based content parts in chat completions

Some OpenAI-compatible clients (Open WebUI, LobeChat, etc.) send
message content as an array of typed parts instead of a plain string:

    [{"type": "text", "text": "hello"}]

The agent pipeline expects strings, so these array payloads caused
silent failures or empty messages.

Add _normalize_chat_content() with defensive limits (recursion depth,
list size, output length) and apply it to both the Chat Completions
and Responses API endpoints. The Responses path had inline
normalization that only handled input_text/output_text — the shared
function also handles the standard 'text' type.

Salvaged from PR #7980 (ikelvingo) — only the content normalization;
the SSE and Weixin changes in that PR were regressions and are not
included.

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

* feat: add `hermes debug share` — upload debug report to pastebin (#8681)

* feat: add `hermes debug share` — upload debug report to pastebin

Adds a new `hermes debug share` command that collects system info
(via hermes dump), recent logs (agent.log, errors.log, gateway.log),
and uploads the combined report to a paste service (paste.rs primary,
dpaste.com fallback). Returns a shareable URL for support.

Options:
  --lines N    Number of log lines per file (default: 200)
  --expire N   Paste expiry in days (default: 7, dpaste.com only)
  --local      Print report locally without uploading

Files:
  hermes_cli/debug.py           - New module: paste upload + report collection
  hermes_cli/main.py            - Wire cmd_debug + argparse subparser
  tests/hermes_cli/test_debug.py - 19 tests covering upload, collection, CLI

* feat: upload full agent.log and gateway.log as separate pastes

hermes debug share now uploads up to 3 pastes:
  1. Summary report (system info + log tails) — always
  2. Full agent.log (last ~500KB) — if file exists
  3. Full gateway.log (last ~500KB) — if file exists

Each paste uploads independently; log upload failures are noted
but don't block the main report. Output shows all links aligned:

  Report     https://paste.rs/abc
  agent.log  https://paste.rs/def
  gateway.log https://paste.rs/ghi

Also adds _read_full_log() with size-capped tail reading to stay
within paste service limits (~512KB per file).

* feat: prepend hermes dump to each log paste for self-contained context

Each paste (agent.log, gateway.log) now starts with the hermes dump
output so clicking any single link gives full system context without
needing to cross-reference the summary report.

Refactored dump capture into _capture_dump() — called once and
reused across the summary report and each log paste.

* fix: fall back to .1 rotated log when primary log is missing or empty

When gateway.log (or agent.log) doesn't exist or is empty, the debug
share now checks for the .1 rotation file. This is common — the
gateway rotates logs and the primary file may not exist yet.

Extracted _resolve_log_path() to centralize the fallback logic for
both _read_log_tail() and _read_full_log().

* chore: remove unused display_hermes_home import

* fix(matrix): trust m.mentions.user_ids as authoritative mention signal

Port from openclaw/openclaw#64796: Per MSC3952 / Matrix v1.7, the
m.mentions.user_ids field is the authoritative mention signal. Clients
that populate m.mentions but don't duplicate @bot in the body text
were being silently dropped when MATRIX_REQUIRE_MENTION=true.

Cherry-picked from PR #8673.

* fix(gateway): reject known-weak placeholder credentials at startup

Port from openclaw/openclaw#64586: users who copy .env.example without
changing placeholder values now get a clear error at startup instead of
a confusing auth failure from the platform API. Also rejects placeholder
API_SERVER_KEY when binding to a network-accessible address.

Cherry-picked from PR #8677.

* feat: add /debug slash command for all platforms

Adds /debug as a slash command available in CLI, Telegram, Discord,
Slack, and all other gateway platforms. Uploads debug report + full
logs to paste services and returns shareable URLs.

- commands.py: CommandDef in Info category (no cli_only/gateway_only)
- gateway/run.py: async handler with run_in_executor for blocking I/O
- cli.py: dispatch in process_command to run_debug_share

* fix(telegram): use UTF-16 code units for message length splitting (#8725)

Port from nearai/ironclaw#2304: Telegram's 4096 character limit is
measured in UTF-16 code units, not Unicode codepoints. Characters
outside the Basic Multilingual Plane (emoji like 😀, CJK Extension B,
musical symbols) are surrogate pairs: 1 Python char but 2 UTF-16 units.

Previously, truncate_message() used Python's len() which counts
codepoints. This could produce chunks exceeding Telegram's actual limit
when messages contain many astral-plane characters.

Changes:
- Add utf16_len() helper and _prefix_within_utf16_limit() for
  UTF-16-aware string measurement and truncation
- Add _custom_unit_to_cp() binary-search helper that maps a custom-unit
  budget to the largest safe codepoint slice position
- Update truncate_message() to accept optional len_fn parameter
- Telegram adapter now passes len_fn=utf16_len when splitting messages
- Fix fallback truncation in Telegram error handler to use
  _prefix_within_utf16_limit instead of codepoint slicing
- Update send_message_tool.py to use utf16_len for Telegram platform
- Add comprehensive tests: utf16_len, _prefix_within_utf16_limit,
  truncate_message with len_fn (emoji splitting, content preservation,
  code block handling)
- Update mock lambdas in reply_mode tests to accept **kw for len_fn

* fix: show full last assistant response when resuming a session (#8724)

When resuming a session with --resume or -c, the last assistant response
was truncated to 200 chars / 3 lines just like older messages in the recap.
This forced users to waste tokens re-asking for the response.

Now the last assistant message in the recap is shown in full with non-dim
styling, so users can see exactly where they left off. Earlier messages
remain truncated for compact display.

Changes:
- Track un-truncated text for the last assistant entry during collection
- Replace last entry with full text after history trimming
- Render last assistant entry with bold (non-dim) styling
- Update existing truncation tests to use multi-message histories
- Add new tests for full last response display (char + multiline)

* fix: improve WhatsApp UX — chunking, formatting, streaming (#8723)

Three changes that address the poor WhatsApp experience reported by users:

1. Reclassify WhatsApp from TIER_LOW to TIER_MEDIUM in display_config.py
   — enables streaming and tool progress via the existing Baileys /edit
   bridge endpoint. Users now see progressive responses instead of
   minutes of silence followed by a wall of text.

2. Lower MAX_MESSAGE_LENGTH from 65536 to 4096 and add proper chunking
   — send() now calls format_message() and truncate_message() before
   sending, then loops through chunks with a small delay between them.
   The base class truncate_message() already handles code block boundary
   detection (closes/reopens fences at chunk boundaries). reply_to is
   only set on the first chunk.

3. Override format_message() with WhatsApp-specific markdown conversion
   — converts **bold** to *bold*, ~~strike~~ to ~strike~, headers to
   bold text, and [links](url) to text (url). Code blocks and inline
   code are protected from conversion via placeholder substitution.

Together these fix the two user complaints:
- 'sends the whole code all the time' → now chunked at 4K with proper
  formatting
- 'terminal gets interrupted and gets cooked' → streaming + tool progress
  give visual feedback so users don't accidentally interrupt with
  follow-up messages

* fix: resolve npm audit vulnerabilities in browser tools and whatsapp bridge (#8745)

* fix(telegram): use UTF-16 code units for message length splitting

Port from nearai/ironclaw#2304: Telegram's 4096 character limit is
measured in UTF-16 code units, not Unicode codepoints. Characters
outside the Basic Multilingual Plane (emoji like 😀, CJK Extension B,
musical symbols) are surrogate pairs: 1 Python char but 2 UTF-16 units.

Previously, truncate_message() used Python's len() which counts
codepoints. This could produce chunks exceeding Telegram's actual limit
when messages contain many astral-plane characters.

Changes:
- Add utf16_len() helper and _prefix_within_utf16_limit() for
  UTF-16-aware string measurement and truncation
- Add _custom_unit_to_cp() binary-search helper that maps a custom-unit
  budget to the largest safe codepoint slice position
- Update truncate_message() to accept optional len_fn parameter
- Telegram adapter now passes len_fn=utf16_len when splitting messages
- Fix fallback truncation in Telegram error handler to use
  _prefix_within_utf16_limit instead of codepoint slicing
- Update send_message_tool.py to use utf16_len for Telegram platform
- Add comprehensive tests: utf16_len, _prefix_within_utf16_limit,
  truncate_message with len_fn (emoji splitting, content preservation,
  code block handling)
- Update mock lambdas in reply_mode tests to accept **kw for len_fn

* fix: resolve npm audit vulnerabilities in browser tools and whatsapp bridge

Browser tools (agent-browser):
- Override lodash to 4.18.1 (fixes prototype pollution CVEs in transitive
  dep via node-simctl → @appium/logger). Not reachable in Hermes's cod…

openclaw#64796)

Merged via squash.

Prepared head SHA: 59ca82e
Co-authored-by: hclsys <7755017+hclsys@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras

Port from openclaw/openclaw#64796: Per MSC3952 / Matrix v1.7, the
m.mentions.user_ids field is the authoritative mention signal. Clients
that populate m.mentions but don't duplicate @bot in the body text
were being silently dropped when MATRIX_REQUIRE_MENTION=true.

Cherry-picked from PR NousResearch#8673.

Port from openclaw/openclaw#64796: Per MSC3952 / Matrix v1.7, the
m.mentions.user_ids field is the authoritative mention signal. Clients
that populate m.mentions but don't duplicate @bot in the body text
were being silently dropped when MATRIX_REQUIRE_MENTION=true.

Cherry-picked from PR NousResearch#8673.

openclaw#64796)

Merged via squash.

Prepared head SHA: 59ca82e
Co-authored-by: hclsys <7755017+hclsys@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras

openclaw#64796)

Merged via squash.

Prepared head SHA: 59ca82e
Co-authored-by: hclsys <7755017+hclsys@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras

openclaw#64796)

Merged via squash.

Prepared head SHA: 59ca82e
Co-authored-by: hclsys <7755017+hclsys@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras

Port from openclaw/openclaw#64796: Per MSC3952 / Matrix v1.7, the
m.mentions.user_ids field is the authoritative mention signal. Clients
that populate m.mentions but don't duplicate @bot in the body text
were being silently dropped when MATRIX_REQUIRE_MENTION=true.

Cherry-picked from PR NousResearch#8673.

Port from openclaw/openclaw#64796: Per MSC3952 / Matrix v1.7, the
m.mentions.user_ids field is the authoritative mention signal. Clients
that populate m.mentions but don't duplicate @bot in the body text
were being silently dropped when MATRIX_REQUIRE_MENTION=true.

Cherry-picked from PR NousResearch#8673.

openclaw#64796)

Merged via squash.

Prepared head SHA: 59ca82e
Co-authored-by: hclsys <7755017+hclsys@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras

openclaw#64796)

Merged via squash.

Prepared head SHA: 59ca82e
Co-authored-by: hclsys <7755017+hclsys@users.noreply.github.com>
Co-authored-by: gumadeiras <5599352+gumadeiras@users.noreply.github.com>
Reviewed-by: @gumadeiras

Port from openclaw/openclaw#64796: Per MSC3952 / Matrix v1.7, the
m.mentions.user_ids field is the authoritative mention signal. Clients
that populate m.mentions but don't duplicate @bot in the body text
were being silently dropped when MATRIX_REQUIRE_MENTION=true.

Cherry-picked from PR #8673.

Port from openclaw/openclaw#64796: Per MSC3952 / Matrix v1.7, the
m.mentions.user_ids field is the authoritative mention signal. Clients
that populate m.mentions but don't duplicate @bot in the body text
were being silently dropped when MATRIX_REQUIRE_MENTION=true.

Cherry-picked from PR NousResearch#8673.