The _call_llm() and direct OpenAI fallback paths in flush_memories() both
hardcoded timeout=30.0, ignoring the user-configurable value at
auxiliary.flush_memories.timeout in config.yaml.
Remove the explicit timeout from the auxiliary _call_llm() call so that
_get_task_timeout('flush_memories') reads from config. For the direct
OpenAI fallback, import and use _get_task_timeout() instead of the
hardcoded value.
Add two regression tests verifying both code paths respect the config.
Fixes#6154
Fixes#4647 — Signal replies duplicated when gateway streaming is enabled.
Root cause: stream_consumer.py did not handle the case where send() returns
success=True but no message_id (Signal behavior). Every stream delta produced
a separate send() call (7+ messages instead of 2), plus the gateway sent
another full duplicate since already_sent was never set.
Changes:
- stream_consumer.py: Add elif branch for success-without-message_id — enters
fallback mode (sets already_sent, disables editing, sends only continuation)
- signal.py send(): Extract timestamp from signal-cli RPC result as message_id
so stream consumer follows normal edit→fallback path
- signal.py: Add public stop_typing() delegating to _stop_typing_indicator()
so base adapter's _keep_typing finally block can clean up typing tasks
- gateway/run.py: Per-platform tool_progress_overrides (#6164) — lets users
set e.g. signal: off while keeping telegram: all
- hermes_cli/config.py: Add tool_progress_overrides to DEFAULT_CONFIG
Refs: #4647, #6164
- Docker env tests: verify _build_init_env_args() instead of per-execute
Popen flags (env forwarding is now init-time only)
- Docker: preserve explicit forward_env bypass of blocklist from main
- Daytona tests: adapt to SDK-native timeout, _ThreadedProcessHandle,
base.py interrupt handling, HERMES_STDIN_ heredoc prefix
- Modal tests: fix _load_module to include _ThreadedProcessHandle stub,
check ensurepip in _resolve_modal_image instead of __init__
- SSH tests: mock time.sleep on base module instead of removed ssh import
- Add missing BaseEnvironment attributes to __new__()-based test fixtures
Add configurable reply-reference behavior for Discord, matching the
existing Telegram (TELEGRAM_REPLY_TO_MODE) and Mattermost
(MATTERMOST_REPLY_MODE) implementations.
Modes:
- 'off': never reply-reference the original message
- 'first': reply-reference on first chunk only (default, current behavior)
- 'all': reply-reference on every chunk
Set DISCORD_REPLY_TO_MODE=off in .env to disable reply-to messages.
Changes:
- gateway/config.py: parse DISCORD_REPLY_TO_MODE env var
- gateway/platforms/discord.py: read reply_to_mode from config, respect
it in send() — skip fetch_message entirely when 'off'
- hermes_cli/config.py: add to OPTIONAL_ENV_VARS for hermes setup
- 23 tests covering config, send behavior, env var override
- docs: discord.md env var table + environment-variables.md reference
Closes community request from Stuart on Discord.
Fixes 9 test failures on current main, incorporating ideas from PR stack
#6219-#6222 by xinbenlv with corrections:
- model_metadata: sync HF context length key casing
(minimaxai/minimax-m2.5 → MiniMaxAI/MiniMax-M2.5)
- cli.py: route quick command error output through self.console
instead of creating a new ChatConsole() instance
- docker.py: explicit docker_forward_env entries now bypass the
Hermes secret blocklist (intentional opt-in wins over generic filter)
- auxiliary_client: revert _read_main_provider() to simple
provider.strip().lower() — the _normalize_aux_provider() call
introduced in 5c03f2e7 stripped the custom: prefix, breaking
named custom provider resolution
- auxiliary_client: flip vision auto-detection order to
active provider → OpenRouter → Nous → stop (was OR → Nous → active)
- test: update vision priority test to match new order
Based on PR #6219-#6222 by xinbenlv.
mistralai v2.x is a namespace package — `Mistral` class lives at
`mistralai.client`, not at the top-level `mistralai` module. The
previous `from mistralai import Mistral` raises ImportError at runtime.
Update both production code and test fixture to use the correct path.
Based on #6079 by @tunamitom with critical fixes and comprehensive tests.
Changes from #6079:
- Fix: sanitization overwrite bug — Qwen message prep now runs AFTER codex
field sanitization, not before (was silently discarding Qwen transforms)
- Fix: missing try/except AuthError in runtime_provider.py — stale Qwen
credentials now fall through to next provider on auto-detect
- Fix: 'qwen' alias conflict — bare 'qwen' stays mapped to 'alibaba'
(DashScope); use 'qwen-portal' or 'qwen-cli' for the OAuth provider
- Fix: hardcoded ['coder-model'] replaced with live API fetch + curated
fallback list (qwen3-coder-plus, qwen3-coder)
- Fix: extract _is_qwen_portal() helper + _qwen_portal_headers() to replace
5 inline 'portal.qwen.ai' string checks and share headers between init
and credential swap
- Fix: add Qwen branch to _apply_client_headers_for_base_url for mid-session
credential swaps
- Fix: remove suspicious TypeError catch blocks around _prompt_provider_choice
- Fix: handle bare string items in content lists (were silently dropped)
- Fix: remove redundant dict() copies after deepcopy in message prep
- Revert: unrelated ai-gateway test mock removal and model_switch.py comment deletion
New tests (30 test functions):
- _qwen_cli_auth_path, _read_qwen_cli_tokens (success + 3 error paths)
- _save_qwen_cli_tokens (roundtrip, parent creation, permissions)
- _qwen_access_token_is_expiring (5 edge cases: fresh, expired, within skew,
None, non-numeric)
- _refresh_qwen_cli_tokens (success, preserve old refresh, 4 error paths,
default expires_in, disk persistence)
- resolve_qwen_runtime_credentials (fresh, auto-refresh, force-refresh,
missing token, env override)
- get_qwen_auth_status (logged in, not logged in)
- Runtime provider resolution (direct, pool entry, alias)
- _build_api_kwargs (metadata, vl_high_resolution_images, message formatting,
max_tokens suppression)
* fix(tools): skip camofox auto-cleanup when managed persistence is enabled
When managed_persistence is enabled, cleanup_browser() was calling
camofox_close() which destroys the server-side browser context via
DELETE /sessions/{userId}, killing login sessions across cron runs.
Add camofox_soft_cleanup() — a public wrapper that drops only the
in-memory session entry when managed persistence is on, returning True.
When persistence is off it returns False so the caller falls back to
the full camofox_close(). The inactivity reaper still handles idle
resource cleanup.
Also surface a logger.warning() when _managed_persistence_enabled()
fails to load config, replacing a silent except-and-return-False.
Salvaged from #6182 by el-analista (Eduardo Perea Fernandez).
Added public API wrapper to avoid cross-module private imports,
and test coverage for both persistence paths.
Co-authored-by: Eduardo Perea Fernandez <el-analista@users.noreply.github.com>
* fix(doctor): only check the active memory provider, not all providers unconditionally
hermes doctor had hardcoded Honcho Memory and Mem0 Memory sections that
always ran regardless of the user's memory.provider config setting. After
the swappable memory provider update (#4623), users with leftover Honcho
config but no active provider saw false 'broken' errors.
Replaced both sections with a single Memory Provider section that reads
memory.provider from config.yaml and only checks the configured provider.
Users with no external provider see a green 'Built-in memory active' check.
Reported by community user michaelruiz001, confirmed by Eri (Honcho).
---------
Co-authored-by: Eduardo Perea Fernandez <el-analista@users.noreply.github.com>
Problem: hermes -w sessions accumulated 37+ worktrees and 1200+ orphaned
branches because:
- _cleanup_worktree bailed on any dirty working tree, but agent sessions
almost always leave untracked files/artifacts behind
- _prune_stale_worktrees had the same dirty-check, so stale worktrees
survived indefinitely
- pr-* and hermes/* branches from PR review had zero cleanup mechanism
Changes:
- _cleanup_worktree: check for unpushed commits instead of dirty state.
Agent work lives in pushed commits/PRs — dirty working tree without
unpushed commits is just artifacts, safe to remove.
- _prune_stale_worktrees: three-tier age system:
- Under 24h: skip (session may be active)
- 24h-72h: remove if no unpushed commits
- Over 72h: force remove regardless
- New _prune_orphaned_branches: on each -w startup, deletes local
hermes/hermes-* and pr-* branches with no corresponding worktree.
Protects main, checked-out branch, and active worktree branches.
Tests: 42 pass (6 new covering unpushed-commit logic, force-prune
tier, and orphaned branch cleanup).
- Fire on_session_finalize and on_session_reset in gateway _handle_reset_command()
- Fire on_session_finalize during gateway stop() for each active agent
- Move CLI test from tests/ root to tests/cli/ (matches recent restructure)
- Add 5 gateway tests covering reset hooks, ordering, shutdown, and error handling
- Place on_session_reset after new session is guaranteed to exist (covers
the get_or_create_session fallback path)
Plugins can now subscribe to session boundary events via
ctx.register_hook('on_session_finalize', ...) and
ctx.register_hook('on_session_reset', ...).
on_session_finalize — fires during CLI exit (/quit, Ctrl-C) and
before /new or /reset, giving plugins a chance to flush or clean up.
on_session_reset — fires after a new session is created via
/new or /reset, so plugins can initialize per-session state.
Closes#5592
Anthropic signs thinking blocks against the full turn content. Any
upstream mutation (context compression, session truncation, orphan
stripping, message merging) invalidates the signature, causing HTTP 400
'Invalid signature in thinking block' — especially in long-lived
gateway sessions.
Strategy (following clawdbot/OpenClaw pattern):
1. Strip thinking/redacted_thinking from all assistant messages EXCEPT
the last one — preserves reasoning continuity on the current
tool-use chain while avoiding stale signature errors on older turns.
2. Downgrade unsigned thinking blocks to plain text — Anthropic can't
validate them, but the reasoning content is preserved.
3. Strip cache_control from thinking/redacted_thinking blocks to
prevent cache markers from interfering with signature validation.
4. Drop thinking blocks from the second message when merging
consecutive assistant messages (role alternation enforcement).
5. Error recovery: on HTTP 400 mentioning 'signature' and 'thinking',
strip all reasoning_details from the conversation and retry once.
This is the safety net for edge cases the proactive stripping
misses.
Addresses the issue reported in PR #6086 by @mingginwan while
preserving reasoning continuity (their PR stripped ALL thinking
blocks unconditionally).
Files changed:
- agent/anthropic_adapter.py: thinking block management in
convert_messages_to_anthropic (strip old turns, downgrade unsigned,
strip cache_control, merge-time strip)
- run_agent.py: one-shot signature error recovery in retry loop
- tests/test_anthropic_adapter.py: 10 new tests covering all cases
Gateway and cron had inconsistent reasoning_effort resolution:
- CLI: config.yaml only (correct)
- Gateway: config.yaml first, env var fallback
- Cron: env var first, config.yaml fallback
All three now read exclusively from agent.reasoning_effort in config.yaml.
Removed HERMES_REASONING_EFFORT env var support entirely — .env is for
secrets only, not behavioral config.
Previously crash recovery recreated detached sessions as if they were
fully managed, so polls and kills could lie about liveness and the
checkpoint could forget recovered jobs after the next restart.
This commit refreshes recovered host-backed sessions from real PID
state, keeps checkpoint data durable, and preserves notify watcher
metadata while treating sandbox-only PIDs as non-recoverable.
- Persist `pid_scope` in `tools/process_registry.py` and skip
recovering sandbox-backed entries without a host-visible PID handle
- Refresh detached sessions on access so `get`/`poll`/`wait` and active
session queries observe exited processes instead of hanging forever
- Allow recovered host PIDs to be terminated honestly and requeue
`notify_on_complete` watchers during checkpoint recovery
- Add regression tests for durable checkpoints, detached exit/kill
behavior, sandbox skip logic, and recovered notify watchers
- DEFAULT_RESULT_SIZE_CHARS: 50K -> 100K (match current _LARGE_RESULT_CHARS)
- DEFAULT_PREVIEW_SIZE_CHARS: 2K -> 1.5K (match current _LARGE_RESULT_PREVIEW_CHARS)
- Per-tool overrides all set to 100K (terminal, execute_code, search_files)
- Remove pre-read byte guard (no behavioral regression vs current main)
- Revert limit signature change to int=500 (match current default)
- Restore original read_file schema description
- Update test assertions to match 100K thresholds
Simplify the vision auto-detection chain from 5 backends (openrouter,
nous, codex, anthropic, custom) down to 3:
1. OpenRouter (known vision-capable default model)
2. Nous Portal (known vision-capable default model)
3. Active provider + model (whatever the user is running)
4. Stop
This is simpler and more predictable. The active provider step uses
resolve_provider_client() which handles all provider types including
named custom providers (from #5978).
Removed the complex preferred-provider promotion logic and API-level
fallback — the chain is short enough that it doesn't need them.
Based on PR #5376 by Mibay. Closes#5366.
_deliver_result() now returns Optional[str] — None on success, error
message on failure. All failure paths (unknown platform, platform
disabled, config load error, send failure, unresolvable target)
return descriptive error strings.
mark_job_run() gains delivery_error param, tracked as
last_delivery_error on the job — separate from agent execution errors.
A job where the agent succeeded but delivery failed shows
last_status='ok' + last_delivery_error='...'.
The cronjob list tool now surfaces last_delivery_error so agents and
users can see when cron outputs aren't arriving.
Inspired by PR #5863 (oxngon) — reimplemented with proper wiring.
Tests: 3 new mark_job_run tests + 6 new _deliver_result return tests.
Add button-based exec approval to the Feishu adapter, matching the
existing Discord, Telegram, and Slack implementations.
When the agent encounters a dangerous command, Feishu users now see
an interactive card with four buttons instead of text instructions:
- Allow Once (primary)
- Allow Session
- Always Allow
- Deny (danger)
Implementation:
- send_exec_approval() sends an interactive card via the Feishu
message API with buttons carrying hermes_action in their value dict
- _handle_card_action_event() intercepts approval button clicks
before routing them as synthetic commands, directly calling
resolve_gateway_approval() to unblock the agent thread
- _update_approval_card() replaces the orange approval card with a
green (approved) or red (denied) status card showing who acted
- _approval_state dict tracks pending approval_id → session_key
mappings; cleaned up on resolution
The gateway's existing routing in _approval_notify_sync already checks
getattr(type(adapter), 'send_exec_approval', None) and will
automatically use the button-based flow for Feishu.
Tests: 16 new tests covering send, callback resolution, state
management, card updates, and non-interference with existing card
actions.
Salvaged fixes from community PRs:
- fix(model_switch): _read_auth_store → _load_auth_store + fix auth store
key lookup (was checking top-level dict instead of store['providers']).
OAuth providers now correctly detected in /model picker.
Cherry-picked from PR #5911 by Xule Lin (linxule).
- fix(ollama): pass num_ctx to override 2048 default context window.
Ollama defaults to 2048 context regardless of model capabilities. Now
auto-detects from /api/show metadata and injects num_ctx into every
request. Config override via model.ollama_num_ctx. Fixes#2708.
Cherry-picked from PR #5929 by kshitij (kshitijk4poor).
- fix(aux): normalize provider aliases for vision/auxiliary routing.
Adds _normalize_aux_provider() with 17 aliases (google→gemini,
claude→anthropic, glm→zai, etc). Fixes vision routing failure when
provider is set to 'google' instead of 'gemini'.
Cherry-picked from PR #5793 by e11i (Elizabeth1979).
- fix(aux): rewrite MiniMax /anthropic base URLs to /v1 for OpenAI SDK.
MiniMax's inference_base_url ends in /anthropic (Anthropic Messages API),
but auxiliary client uses OpenAI SDK which appends /chat/completions →
404 at /anthropic/chat/completions. Generic _to_openai_base_url() helper
rewrites terminal /anthropic to /v1 for OpenAI-compatible endpoint.
Inspired by PR #5786 by Lempkey.
Added debug logging to silent exception blocks across all fixes.
Co-authored-by: Hermes Agent <hermes@nousresearch.com>
Currently, MCP servers are included on all platforms by default. If a
platform's toolset list does not explicitly name any MCP servers, every
globally enabled MCP server is injected. There is no way to opt a
platform out of MCP servers entirely.
This matters for the API server platform when used as an execution
backend — each spawned agent session gets the full MCP tool schema
injected into its system prompt, dramatically inflating token usage
(e.g. 57K tokens vs 9K without MCP tools) and slowing response times.
Add a "no_mcp" sentinel value for platform_toolsets. When present in a
platform's toolset list, all MCP servers are excluded for that platform.
Other platforms are unaffected.
Usage in config.yaml:
platform_toolsets:
api_server:
- terminal
- file
- web
- no_mcp # exclude all MCP servers
The sentinel is filtered out of the final toolset — it does not appear
as an actual toolset name.
- The MCP SDK Pydantic model uses camelCase (structuredContent), not
snake_case (structured_content). The original getattr was a silent no-op.
- When structuredContent is present, return it AS the result instead of
alongside text — the structured payload is the machine-readable data.
- Move test file to tests/tools/ and fix fake class to use camelCase.
- Patch _run_on_mcp_loop in tests so the handler actually executes.
* fix(telegram): replace substring caption check with exact line-by-line match
Captions in photo bursts and media group albums were silently dropped when
a shorter caption happened to be a substring of an existing one (e.g.
"Meeting" lost inside "Meeting agenda"). Extract a shared _merge_caption
static helper that splits on "\n\n" and uses exact match with whitespace
normalisation, then use it in both _enqueue_photo_event and
_queue_media_group_event.
Adds 13 unit tests covering the fixed bug scenarios.
Cherry-picked from PR #2671 by Dilee.
* fix: extend caption substring fix to all platforms
Move _merge_caption helper from TelegramAdapter to BasePlatformAdapter
so all adapters inherit it. Fix the same substring-containment bug in:
- gateway/platforms/base.py (photo burst merging)
- gateway/run.py (priority photo follow-up merging)
- gateway/platforms/feishu.py (media batch merging)
The original fix only covered telegram.py. The same bug existed in base.py
and run.py (pure substring check) and feishu.py (list membership without
whitespace normalization).
* fix(auxiliary): resolve named custom providers and 'main' alias in auxiliary routing
Two bugs caused auxiliary tasks (vision, compression, etc.) to fail when
using named custom providers defined in config.yaml:
1. 'provider: main' was hardcoded to 'custom', which only checks legacy
OPENAI_BASE_URL env vars. Now reads _read_main_provider() to resolve
to the actual provider (e.g., 'custom:beans', 'openrouter', 'deepseek').
2. Named custom provider names (e.g., 'beans') fell through to
PROVIDER_REGISTRY which doesn't know about config.yaml entries.
Now checks _get_named_custom_provider() before the registry fallback.
Fixes both resolve_provider_client() and _normalize_vision_provider()
so the fix covers all auxiliary tasks (vision, compression, web_extract,
session_search, etc.).
Adds 13 unit tests. Reported by Laura via Discord.
---------
Co-authored-by: Dilee <uzmpsk.dilekakbas@gmail.com>
* fix(cli): route error messages through ChatConsole inside patch_stdout
Cherry-pick of PR #5798 by @icn5381.
Replace self.console.print() with ChatConsole().print() for 11 error/status
messages reachable during the interactive session. Inside patch_stdout,
self.console (plain Rich Console) writes raw ANSI escapes that StdoutProxy
mangles into garbled text. ChatConsole uses prompt_toolkit's native
print_formatted_text which renders correctly.
Same class of bug as #2262 — that fix covered agent output but missed
these error paths in _ensure_runtime_credentials, _init_agent, quick
commands, skill loading, and plan mode.
* fix(model-picker): add scrolling viewport to curses provider menu
Cherry-pick of PR #5790 by @Lempkey. Fixes#5755.
_curses_prompt_choice rendered items starting unconditionally from index 0
with no scroll offset. The 'More providers' submenu has 13 entries. On
terminals shorter than ~16 rows, items past the fold were never drawn.
When UP-arrow wrapped cursor from 0 to the last item (Cancel, index 12),
the highlight rendered off-screen — appearing as if only Cancel existed.
Adds scroll_offset tracking that adjusts each frame to keep the cursor
inside the visible window.
* feat(cli): skin-aware compact banner + git state in startup banner
Combined salvage of PR #5922 by @ASRagab and PR #5877 by @xinbenlv.
Compact banner changes (from #5922):
- Read active skin colors and branding instead of hardcoding gold/NOUS HERMES
- Default skin preserves backward-compatible legacy branding
- Non-default skins use their own agent_name and colors
Git state in banner (from #5877):
- New format_banner_version_label() shows upstream/local git hashes
- Full banner title now includes git state (upstream hash, carried commits)
- Compact banner line2 shows the version label with git state
- Widen compact banner max width from 64 to 88 to fit version info
Both the full Rich banner and compact fallback are now skin-aware
and show git state.
- Add 7 unit tests for _profile_arg: default home, named profile,
hash path, nested path, invalid name, systemd integration, launchd integration
- Add stt.local.language to config.yaml (empty = auto-detect)
- Both STT code paths now read config.yaml first, env var fallback,
then default (auto-detect for faster-whisper, 'en' for CLI command)
- HERMES_LOCAL_STT_LANGUAGE env var still works as backward-compat fallback
Follow-up to sroecker's PR #5918 — test mocks were using the old 3-arg
callback signature (name, preview, args) instead of the new
(event_type, name, preview, args, **kwargs).
The response validation stage unconditionally marked Codex Responses API
replies as invalid when response.output was empty, triggering unnecessary
retries and fallback chains. However, _normalize_codex_response can
recover from this state by synthesizing output from response.output_text.
Now the validation stage checks for output_text before marking the
response invalid, matching the normalization logic. Also fixes
logging.warning → logger.warning for consistency with the rest of the
file.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The webhook adapter stored per-request `deliver`/`deliver_extra` config in
`_delivery_info[chat_id]` during POST handling and consumed it via `.pop()`
inside `send()`. That worked for routes whose agent run produced exactly
one outbound message — the final response — but it broke whenever the
agent emitted any interim status message before the final response.
Status messages flow through the same `send(chat_id, ...)` path as the
final response (see `gateway/run.py::_status_callback_sync` →
`adapter.send(...)`). Common triggers include:
- "🔄 Primary model failed — switching to fallback: ..."
(run_agent.py::_emit_status when `fallback_providers` activates)
- context-pressure / compression notices
- any other lifecycle event routed through `status_callback`
When any of those fired, the first `send()` call popped the entry, so the
subsequent final-response `send()` saw an empty dict and silently
downgraded `deliver_type` from `"telegram"` (or `discord`/`slack`/etc.) to
the default `"log"`. The agent's response was logged to the gateway log
instead of being delivered to the configured cross-platform target — no
warning, no error, just a missing message.
This was easy to hit in practice. Any user with `fallback_providers`
configured saw it the first time their primary provider hiccuped on a
webhook-triggered run. Routes that worked perfectly in dev (where the
primary stays healthy) silently dropped responses in prod.
Fix: read `_delivery_info` with `.get()` so multiple `send()` calls for
the same `chat_id` all see the same delivery config. To keep the dict
bounded without relying on per-send cleanup, add a parallel
`_delivery_info_created` timestamp dict and a `_prune_delivery_info()`
helper that drops entries older than `_idempotency_ttl` (1h, same window
already used by `_seen_deliveries`). Pruning runs on each POST, mirroring
the existing `_seen_deliveries` cleanup pattern.
Worst-case memory footprint is now `rate_limit * TTL = 30/min * 60min =
1800` entries, each ~1KB → under 2 MB. In practice it'll be far smaller
because most webhooks complete in seconds, not the full hour.
Test changes:
- `test_delivery_info_cleaned_after_send` is replaced with
`test_delivery_info_survives_multiple_sends`, which is now the
regression test for this bug — it asserts that two consecutive
`send()` calls both see the delivery config.
- A new `test_delivery_info_pruned_via_ttl` covers the TTL cleanup
behavior.
- The two integration tests that asserted `chat_id not in
adapter._delivery_info` after `send()` now assert the opposite, with
a comment explaining why.
All 40 tests in `tests/gateway/test_webhook_adapter.py` and
`tests/gateway/test_webhook_integration.py` pass. Verified end-to-end
locally against a dynamic `hermes webhook subscribe` route configured
with `--deliver telegram --deliver-chat-id <user>`: with `gpt-5.4` as
the primary (currently flaky) and `claude-opus-4.6` as the fallback,
the fallback notification fires, the agent finishes, and the final
response is delivered to Telegram as expected.
* refactor: re-architect tests to mirror the codebase
* Update tests.yml
* fix: add missing tool_error imports after registry refactor
* fix(tests): replace patch.dict with monkeypatch to prevent env var leaks under xdist
patch.dict(os.environ) can leak TERMINAL_ENV across xdist workers,
causing test_code_execution tests to hit the Modal remote path.
* fix(tests): fix update_check and telegram xdist failures
- test_update_check: replace patch("hermes_cli.banner.os.getenv") with
monkeypatch.setenv("HERMES_HOME") — banner.py no longer imports os
directly, it uses get_hermes_home() from hermes_constants.
- test_telegram_conflict/approval_buttons: provide real exception classes
for telegram.error mock (NetworkError, TimedOut, BadRequest) so the
except clause in connect() doesn't fail with "catching classes that do
not inherit from BaseException" when xdist pollutes sys.modules.
* fix(tests): accept unavailable_models kwarg in _prompt_model_selection mock
Previously, all/new tool progress modes always hard-truncated previews
to 40 chars, ignoring the display.tool_preview_length config. This made
it impossible for gateway users to see meaningful command/path info
without switching to verbose mode (which shows too much detail).
Now all/new modes read tool_preview_length from config:
- tool_preview_length: 0 (default/unset) → 40 chars (no regression)
- tool_preview_length: 120 → 120-char previews in all/new mode
- verbose mode: unchanged (already respected the config)
Users who want longer previews can set:
display:
tool_preview_length: 120
Reported by demontut_ on Discord.
Captions in photo bursts and media group albums were silently dropped when
a shorter caption happened to be a substring of an existing one (e.g.
"Meeting" lost inside "Meeting agenda"). Extract a shared _merge_caption
static helper that splits on "\n\n" and uses exact match with whitespace
normalisation, then use it in both _enqueue_photo_event and
_queue_media_group_event.
Adds 13 unit tests covering the fixed bug scenarios.
Cherry-picked from PR #2671 by Dilee.
Based on PR #5413 spec by MaheshtheDev (Mahesh Sanikommu).
Changes:
- Add search_mode config (hybrid/memories/documents) passed to SDK
- Add {identity} template support in container_tag for profile-scoped containers
- Add SUPERMEMORY_CONTAINER_TAG env var override (priority over config)
- Add multi-container mode: enable_custom_container_tags, custom_containers,
custom_container_instructions in supermemory.json
- Dynamic tool schemas when multi-container enabled (optional container_tag param)
- Whitelist validation for custom container tags in tool calls
- Simplify get_config_schema() to only prompt for API key during setup
- Defer container_tag sanitization to initialize() (after template resolution)
- Add custom_id support to documents.add calls
- Update README with multi-container docs, search_mode, identity template,
support links (Discord, email)
- Update memory-providers.md with new features and multi-container example
- Update memory-provider-plugin.md with minimal vs full schema guidance
- Add 12 new tests covering identity template, search_mode, multi-container,
config schema, and env var override
When the model produces structured reasoning (via API fields like .reasoning,
.reasoning_content, .reasoning_details) but no visible text content, append
the assistant message as prefill and continue the loop. The model sees its own
reasoning context on the next turn and produces the text portion.
Inspired by clawdbot's 'incomplete-text' recovery pattern. Up to 2 prefill
attempts before falling through to the existing '(empty)' terminal.
Key design decisions:
- Only triggers for structured reasoning (API fields), NOT inline <think> tags
- Prefill messages are popped on success to maintain strict role alternation
- _thinking_prefill marker stripped from all API message building paths
- Works across all providers: OpenAI (continuation), Anthropic (native prefill)
Verified with E2E tests: simulated thinking-only → real OpenRouter continuation
produces correct content. Also confirmed Qwen models consistently produce
structured-reasoning-only responses under token pressure.
Add win32 platform branch to clipboard.py so Ctrl+V image paste
works on native Windows (PowerShell / Windows Terminal), not just
WSL2.
Uses the same .NET System.Windows.Forms.Clipboard approach as the
WSL path but calls PowerShell directly instead of powershell.exe
(the WSL cross-call path). Tries 'powershell' first (Windows
PowerShell 5.1, always available), then 'pwsh' (PowerShell 7+).
PowerShell executable is discovered once and cached for the process
lifetime.
Includes 14 new tests covering:
- Platform dispatch (save_clipboard_image + has_clipboard_image)
- Image detection via PowerShell .NET check
- Base64 PNG extraction and decode
- Edge cases: no PowerShell, empty output, invalid base64, timeout
Adapted from PR #5679 (0xbyt4) to cover edge cases not in the integration tests:
video routing, unknown extension fallback to send_document, multi-file delivery,
and single-failure isolation.
The cron delivery path sent raw 'MEDIA:/path/to/file' text instead
of uploading the file as a native attachment. The standalone path
(via _send_to_platform) already extracted MEDIA tags and forwarded
them as media_files, but the live adapter path passed the unprocessed
delivery_content directly to adapter.send().
Two bugs fixed:
1. Live adapter path now sends cleaned text (MEDIA tags stripped)
instead of raw content — prevents 'MEDIA:/path' from appearing
as literal text in Discord/Telegram/etc.
2. Live adapter path now sends each extracted media file via the
adapter's native method (send_voice for audio, send_image_file
for images, send_video for video, send_document as fallback) —
files are uploaded as proper platform attachments.
The file-type routing mirrors BasePlatformAdapter._process_message_background
to ensure consistent behavior between normal gateway responses and
cron-delivered responses.
Adds 2 tests:
- test_live_adapter_sends_media_as_attachments: verifies Discord
adapter receives send_voice call for .mp3 file
- test_live_adapter_sends_cleaned_text_not_raw: verifies MEDIA tag
stripped from text sent via live adapter
