BOOT.md was merged in PR #3733 before the feature was ready — the
built-in hook spawned a bare AIAgent() with no model/runtime kwargs,
which immediately 401s on any provider with a custom endpoint. Three
separate community PRs (#5240, #12514, #14992) tried to paper over it.
Remove the BOOT.md hook entirely and its user-facing docs/tips. Keep
the gateway/builtin_hooks/ package and the HookRegistry._register_builtin_hooks()
hook-point intact as the extension surface for future always-on
gateway hooks.
Closes#5239.
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
* perf(startup): lazy-import OpenAI, Anthropic, Firecrawl, account_usage
Four heavy SDK/module imports are now deferred off the hot startup path.
Net savings on cold module imports:
cli 1200 → 958 ms (-242)
run_agent 1220 → 901 ms (-319)
tools.web_tools 711 → 423 ms (-288)
agent.anthropic_adapter 230 → 15 ms (-215)
agent.auxiliary_client 253 → 68 ms (-185)
Four independent changes in one PR since they all use the same pattern
and share the same risk profile (heavy SDK import → lazy proxy or
function-local import):
1. tools/web_tools.py:
'from firecrawl import Firecrawl' moved into _get_firecrawl_client(),
which is only called when backend='firecrawl'. Users on Exa/Tavily/
Parallel pay zero firecrawl cost.
2. cli.py + gateway/run.py:
'from agent.account_usage import ...' moved into the /limits handlers.
account_usage transitively pulls the OpenAI SDK chain; only needed
when the user runs /limits.
3. agent/anthropic_adapter.py:
'try: import anthropic as _anthropic_sdk' replaced with a cached
'_get_anthropic_sdk()' accessor. The three usage sites
(build_anthropic_client, build_anthropic_bedrock_client,
read_claude_code_credentials_from_keychain) now resolve via the
accessor. All pre-existing test patches of
'agent.anthropic_adapter._anthropic_sdk' keep working because the
accessor respects any value already in module globals.
4. agent/auxiliary_client.py AND run_agent.py:
'from openai import OpenAI' replaced with an '_OpenAIProxy()' module-
level object that looks like the OpenAI class but imports the SDK on
first call/isinstance check. This preserves:
- 15+ in-module OpenAI(...) construction sites in auxiliary_client
and the single site in run_agent's _create_openai_client (Python's
function-scope name lookup finds the proxy, forwards the call);
- 'patch("agent.auxiliary_client.OpenAI", ...)' and
'patch("run_agent.OpenAI", ...)' test patterns used by 28+ test
files (patch replaces the module attribute as usual).
Tried two alternatives first:
- 'from openai._client import OpenAI' — doesn't skip openai/__init__.py
(the audit's hypothesis here was wrong).
- Module-level __getattr__ — works for external access but Python
function-scope name resolution skips __getattr__, so in-module
OpenAI(...) calls NameError.
Note: 'openai' still loads on 'import cli' because
cli.py -> neuter_async_httpx_del() -> openai._base_client, and
run_agent.py -> code_execution_tool.py (module-level
build_execute_code_schema) -> _load_config() -> 'from cli import
CLI_CONFIG'. Deferring those is a separate, larger change — out of scope
for this PR. The savings above all come from avoiding the openai/*,
anthropic/*, and firecrawl/* top-level type-tree imports on paths that
don't need them.
Verified:
- 302/302 tests in tests/agent/{test_anthropic_adapter,
test_bedrock_1m_context, test_minimax_provider, test_anthropic_keychain}
pass. Two pre-existing failures on main unchanged.
- 106/106 tests/agent/test_auxiliary_client.py pass (1 pre-existing fail).
- 97/97 tests/run_agent/test_create_openai_client_kwargs_isolation.py,
test_plugin_context_engine_init.py, test_invalid_context_length_warning.py,
test_api_max_retries_config.py,
tests/hermes_cli/test_gemini_provider.py, test_ollama_cloud_provider.py
pass (1 pre-existing fail).
- Live hermes chat smoke: 2 turns + /model switch + tool calls, zero
errors in the 57-line agent.log window.
- Module-level import of run_agent + auxiliary_client + anthropic_adapter
no longer pulls 'anthropic' or 'firecrawl' at all.
* fix(gateway): restore top-level account_usage import for test-patch surface
CI caught two failures in tests/gateway/test_usage_command.py that I
missed locally:
AttributeError: 'module' object at gateway.run has no attribute 'fetch_account_usage'
The test uses monkeypatch.setattr('gateway.run.fetch_account_usage', ...)
to inject a fake account-fetch call. Moving the import inside the
handler deleted that module-level attribute, breaking the patch surface.
Restoring the top-level import in gateway/run.py gives up the ~230 ms
gateway-boot savings from that one lazy, but:
1. the gateway is a long-running daemon — boot cost is paid once per
install, not per turn;
2. the other four lazy-imports (firecrawl, openai, anthropic, cli's
account_usage) remain in place and still account for the bulk of
the savings reported in the PR body;
3. preserving the patch surface keeps the established
'gateway.run.fetch_account_usage' monkeypatch pattern working
without touching tests.
Verified: tests/gateway/test_usage_command.py — 8 passed, 0 failed.
Full targeted sweep (2336 tests across agent/gateway/hermes_cli/run_agent):
2332 passed, 4 failed — all 4 pre-existing on main.
---------
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
load_config() and read_raw_config() now cache their result keyed on
the config file's (mtime_ns, size). On cache hit they return a deepcopy
of the cached value, skipping yaml.safe_load + deep-merge + normalize +
env-var expansion entirely. save_config() + migrate_config() write via
atomic_yaml_write which produces a fresh inode, so stat() sees a new
mtime_ns and the next load repopulates automatically — no explicit
invalidation hook needed.
Measured per-call cost:
load_config() cold: 13.3 ms
load_config() cached: 0.23 ms (57x faster)
read_raw_config() cached: 0.13 ms
A single gateway turn hits the config 5-15 times (session context,
auxiliary client resolution, memory config, plugin hooks, approval
lookups, per-tool settings). That's 65-200 ms/turn of pure YAML
re-parsing on main. After this change: 1-3 ms/turn.
Also migrates gateway/run.py's 6 direct yaml.safe_load(config.yaml)
call sites through _load_gateway_config, which now shares the
read_raw_config cache when _hermes_home agrees with the canonical
config path. The direct-read fallback is retained for tests that
monkeypatch gateway_run._hermes_home without touching HERMES_HOME.
Safety:
- load_config() returns a deepcopy on every call; the 67+ call sites
that mutate the result (cfg["model"]["default"] = ..., etc.) can't
corrupt the cache.
- save_config() / atomic_yaml_write bump mtime, naturally invalidating
the cache for the next reader.
- Cache is keyed on str(config_path), so HERMES_HOME profile switches
don't collide.
Verified:
- 112 config tests pass (test_config, test_config_env_expansion,
test_config_env_refs, test_config_drift, test_config_validation,
test_aux_config).
- 87 gateway tests pass (test_verbose_command, test_session_info,
test_compress_focus, test_runtime_footer, test_resume_command,
test_reasoning_command, test_approve_deny_commands,
test_run_progress_interrupt).
- Live hermes chat smoke — 2 turns + /model switch + tool calls,
zero errors in agent.log.
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
Discord's per-app command-management bucket is ~5 writes / 20 s. A
mass-prune-plus-upsert reconcile (77 orphans + 30 desired = 107 writes
in the reported case) can't finish under the old flat 30 s budget, and
the subsequent reconnect retries inside the rate-limit cooldown also
time out — leaving slash commands broken for ~60 min until the bucket
fully recovers.
Bump the timeout to 600 s so realistic bursts drain, update the warning
message to point at the saturated bucket instead of a hardcoded 30 s.
The 600 s cap still guards against a true hang.
Credit to @Tranquil-Flow for PR #16739 and @davidbordenwi for reporting
#16713 with the bucket-math diagnosis.
Closes#16713.
Co-authored-by: Teknium <teknium@nousresearch.com>
Append a compact 'model · 68% · ~/projects/hermes' footer to the FINAL
message of each turn, disabled by default (display.runtime_footer.enabled).
Answers the Telegram-side parity ask: runtime context that the CLI status
bar already shows is now available in messaging replies when enabled.
Wiring:
- gateway/runtime_footer.py: resolve_footer_config + format_runtime_footer +
build_footer_line. Pure-function renderer; per-platform overrides under
display.platforms.<platform>.runtime_footer.
- gateway/run.py: appends footer to response right after reasoning prepend
so it lands only on the final message (never tool progress or streaming
chunks). When streaming already delivered the body (already_sent), the
footer is sent as a small trailing message instead.
- agent_result now exposes context_length alongside last_prompt_tokens so
the footer can compute the pct; both gateway return paths updated.
- /footer [on|off|status] slash command, wired in CLI (cli.py) and gateway
(gateway/run.py both running-agent bypass and main dispatch). Global
toggle only; per-platform overrides via config.yaml.
Graceful degradation:
- Missing context_length (unknown model) → pct field silently dropped
(no '?%' artifact).
- Empty final_response → no footer appended.
- Unknown field names in config → silently ignored.
Tests: 25-case unit suite (tests/gateway/test_runtime_footer.py) plus E2E
harness covering streaming vs non-streaming branches, per-platform override,
and the exact argument contract gateway/run.py uses.
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
Mechanical cleanup across 43 files — removes 46 unused imports
(F401) and 14 unused local variables (F841) detected by
`ruff check --select F401,F841`. Net: -49 lines.
Also fixes a latent NameError in rl_cli.py where `get_hermes_home()`
was called at module line 32 before its import at line 65 — the
module never imported successfully on main. The ruff audit surfaced
this because it correctly saw the symbol as imported-but-unused
(the call happened before the import ran); the fix moves the import
to the top of the file alongside other stdlib imports.
One `# noqa: F401` kept in hermes_cli/status.py for `subprocess`:
tests monkeypatch `hermes_cli.status.subprocess` as a regression
guard that systemctl isn't called on Termux, so the name must
exist at module scope even though the module body doesn't reference
it. Docstring explains the reason.
Also fixes an invalid `# noqa:` directive in
gateway/platforms/discord.py:308 that lacked a rule code.
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
The gateway caches one AIAgent per session to preserve prompt-cache hits,
keyed by _agent_config_signature(). The signature previously only
fingerprinted model/credentials/toolsets/ephemeral-prompt — NOT the
compression or context_length config. As a result, users who edited
model.context_length or compression.threshold in config.yaml on a
long-lived gateway saw no effect until they triggered an unrelated
cache eviction (/model switch, /reset, gateway restart).
Add a new cache_keys parameter to _agent_config_signature and a
_CACHE_BUSTING_CONFIG_KEYS registry listing config values the agent
bakes in at construction time. Call sites read the current config and
pass it through — next gateway message with an edited config
rebuilds the agent.
Keys registered:
- model.context_length
- compression.enabled
- compression.threshold
- compression.target_ratio
- compression.protect_last_n
Reported by @OP (Apr 26 feedback bundle).
## Changes
- gateway/run.py: new _CACHE_BUSTING_CONFIG_KEYS tuple,
_extract_cache_busting_config classmethod, cache_keys kwarg on
_agent_config_signature, call site passes the extracted dict
- tests/gateway/test_agent_cache.py: 11 new tests
(5 on _agent_config_signature behavior, 6 on _extract_cache_busting_config)
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
Network errors through proxies (e.g. sing-box) can leave httpx
connections in a half-closed state occupying pool slots. After enough
reconnect cycles the 256-connection default fills up entirely, causing
Pool timeout: All connections in the connection pool are occupied.
Fix: cycle only the getUpdates request object (_request[0]) via
shut-down + re-initialize before restarting polling. This drains stale
connections without touching the general request (_request[1]) that
concurrent send_message / edit_message calls rely on.
The drain is applied to both _handle_polling_network_error and
_handle_polling_conflict reconnect paths via a shared
_drain_polling_connections() helper. Failures in the drain are
swallowed so reconnect always proceeds.
Based on #16466 by @Mirac1eSky.
The gateway session-hygiene pre-compression safety valve had a hardcoded
400-message threshold. On long-lived sessions with short turns this was
either too high (users with aggressive compression preferences) or too
low (users with very large context models who want to keep more history
in-flight).
Add compression.hygiene_hard_message_limit (default 400) so it can be
tuned without forking the gateway.
Reported by @OP (Apr 26 feedback bundle).
## Changes
- hermes_cli/config.py: new DEFAULT_CONFIG key with 400 default
- gateway/run.py: read compression.hygiene_hard_message_limit at
hygiene-time, fall back to 400 if missing/invalid
- tests/gateway/test_session_hygiene.py: two tests — override fires at
the configured limit, default does not fire below 400
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
The rate-limit branch added by the original PR did sleep+continue with
no attempt to record the last error, so persistent iLink -2 responses
exhausted the retry loop and hit 'assert last_error is not None',
raising AssertionError instead of a descriptive RuntimeError.
Record last_error = RuntimeError(...) before continuing, and break out
of the loop on the final attempt instead of sleeping uselessly.
- Change MAX_MESSAGE_LENGTH from 4000 to 2000 to match Weixin iLink API limit
- Add RATE_LIMIT_ERRCODE = -2 handling with 3x backoff retry
- Increase default send_chunk_delay_seconds from 0.35 to 1.5 to avoid rate limits
- Increase default send_chunk_retries from 2 to 4 for better reliability
- Use _split_text() in send() to chunk long messages before delivery
Fixes#16411
Follow-up to PR #16802 (BeliefanX). The original fix read
`agent_history[-1].get("timestamp")` for the tool-tail freshness gate,
but `gateway/run.py` strips the `timestamp` field off all tool/tool_call
rows when building `agent_history` from the raw transcript (see
`clean_msg = {k: v for k, v in msg.items() if k != "timestamp"}`). At
runtime the tool-tail branch always saw `None` and silently took the
legacy-fresh path — the stale-guard never fired for the tool-tail case
it was supposed to cover.
Changes:
- Read the freshness signal from the RAW `history` list (via new
`_last_transcript_timestamp()` helper) BEFORE the strip. Both the
resume_pending branch and the tool-tail branch use this single signal,
replacing the two divergent ones.
- Default window bumped 15 min → 1 hour via new
`_AUTO_CONTINUE_FRESHNESS_SECS_DEFAULT`. The 15-minute default was
shorter than the default `gateway_timeout` of 30 min, so a legitimate
long-running turn interrupted near its timeout boundary and resumed
shortly after would have been misclassified as stale.
- Configurable via `config.yaml` `agent.gateway_auto_continue_freshness`
(bridged to `HERMES_AUTO_CONTINUE_FRESHNESS` at gateway startup — same
pattern as `gateway_timeout`). Set to 0 to disable the gate.
- `_coerce_gateway_timestamp` now explicitly rejects bool (which is a
subclass of int and would otherwise coerce to 0.0/1.0).
- Tests rewritten to exercise the real production data shape: raw
`history` → `_build_agent_history` strip → freshness decision. A
regression guard (`test_stale_tool_tail_with_production_data_shape`)
asserts `agent_history` tool rows carry NO timestamp, protecting
against someone "fixing" the original bug by re-adding the stripped
field (which would break the OpenAI tool-result message contract).
Add BeliefanX to scripts/release.py AUTHOR_MAP.
E2E verified: config.yaml → env var bridge → helper returns configured
value; default 1h window; malformed/empty env var falls back to default;
ISO-Z timestamps parse; ms-epoch coerced; bool rejected.
Extract the islink/realpath guard from the 16743 fix into a single
atomic_replace() helper in utils.py, then migrate every os.replace()
call site in the codebase to use it.
The original PR #16777 correctly identified and fixed the bug, but
only patched 9 of ~24 call sites. The same bug class (managed
deployments that symlink state files silently losing the link on
every write) still existed at auth.json, sessions file, gateway
config, env_loader, webhook subscriptions, debug store, model
catalog, pairing, google OAuth, nous rate guard, and more.
Rather than add another 10+ copies of the same three-line guard,
consolidate into atomic_replace(tmp, target) which:
- resolves symlinks via os.path.realpath before os.replace
- returns the resolved real path so callers can re-apply permissions
- is a drop-in replacement for os.replace at the use sites
Changes:
- utils.py: new atomic_replace() helper + atomic_json_write /
atomic_yaml_write now call it instead of inlining the guard
- 16 files: all os.replace() call sites migrated to atomic_replace()
- agent/{google_oauth, nous_rate_guard, shell_hooks}.py
- cron/jobs.py
- gateway/{pairing, session, platforms/telegram}.py
- hermes_cli/{auth, config, debug, env_loader, model_catalog, webhook}.py
- tools/{memory_tool, skill_manager_tool, skills_sync}.py
Tests: tests/test_atomic_replace_symlinks.py pins the invariant for
atomic_replace + atomic_json_write + atomic_yaml_write, covers plain
files, first-time creates, broken symlinks, and permission preservation.
Refs #16743
Builds on #16777 by @vominh1919.
The mention_user_id injection from #38a6bada9 unconditionally attached an
@user:server mention pill + MSC3952 m.mentions.user_ids payload to every
outbound reply and every tool-progress status update. The stated intent
was push notifications in muted rooms, but shipped as always-on in every
room, DM or group, muted or not — so every reply pinged the user.
- gateway/platforms/base.py: stop injecting mention_user_id into send
metadata on every reply; restore the original _thread_metadata passthrough.
- gateway/run.py: drop mention_user_id from status-thread metadata.
- gateway/platforms/matrix.py: drop the mention-pill append block in
_send_text that consumed the metadata. Keep the reaction-based exec
approval half of #38a6bada9 and the inbound/outbound m.mentions
handling (unrelated to the per-reply ping).
Reported by Elkim [NOUS] on Discord.
Co-authored-by: teknium1 <teknium@users.noreply.github.com>
Narrow plaintext shortcut that rewrites a tiny set of admin phrases
("restart gateway", "restart the gateway", "restart hermes") into the
/restart slash command, but only in DMs. Scope is intentionally tight:
- DM text messages only — group chats keep natural-language semantics
- Exact restart-style phrases only
- Skips anything already starting with "/"
Without this, the LLM can receive "restart gateway" as a user turn and
try to satisfy it via the terminal tool (systemctl restart ...). That
kills the gateway while the originating agent is still running, which
leaves systemd in "draining" state waiting on a process it's about to
kill. Routing the phrase to the slash-command dispatcher bypasses the
agent loop and uses the existing restart machinery (request_restart).
Called once, at the adapter level in BasePlatformAdapter.handle_message,
so every platform gets it for free and pending-message reinjection is
covered by the same call site.
Adds 2 Telegram-parametrized e2e tests: DM routes to request_restart,
group chats fall through to the normal agent path.
model_tools.py ran discover_mcp_tools() as a module-level side effect.
discover_mcp_tools() uses a blocking 120s wait internally (via
_run_on_mcp_loop -> future.result(timeout=120)).
The gateway lazy-imports run_agent -> model_tools on the first user
message, which happens inside the asyncio event loop thread. A slow or
unreachable MCP server therefore froze Discord shard heartbeats and
Telegram polling for up to 120s on the first message after gateway
start.
Fix: remove the module-level call. Every entry point now runs
discovery explicitly at its own startup, using the context-appropriate
blocking/non-blocking pattern:
- gateway/run.py: loop.run_in_executor(None, discover_mcp_tools)
before platforms start accepting traffic
- hermes_cli/main.py: inline (no event loop at CLI startup)
- tui_gateway/entry.py: inline (sync stdin loop, no event loop)
- acp_adapter/entry.py: inline before asyncio.run()
Closes#16856.
_handle_set_home_command wrote FEISHU_HOME_CHANNEL / DISCORD_HOME_CHANNEL /
etc. as top-level keys into config.yaml, but load_gateway_config() only
reads home channels from env vars. After every gateway restart the home
channel was lost — on every platform, not just Feishu.
Fix: switch /sethome to save_env_value(), which atomically writes to
~/.hermes/.env and updates the current process env in one shot. The
handler builds the env key from platform_name.upper(), so one line
change repairs /sethome for every platform that has a HOME_CHANNEL
env var.
Also widen _EXTRA_ENV_KEYS in hermes_cli/config.py so HOME_CHANNEL and
HOME_CHANNEL_NAME for every platform are treated as managed env vars:
SIGNAL, SLACK, SMS, DINGTALK, BLUEBUBBLES, FEISHU, WECOM, YUANBAO, plus
the missing *_NAME variants for DISCORD/TELEGRAM/MATTERMOST.
Closes#16806
Co-authored-by: teknium1 <screenmachine@gmail.com>
Without this, every Matrix bot started under hermes-agent shows the
"Encrypted by a device not verified by its owner" badge in Element
indefinitely, because the cross-signing chain (master → SSK → device)
was never published. Operators currently have to write their own
bootstrap script and remember to run it once per bot — and it's easy
to get wrong (the obvious base64.b64encode().decode() produces padded
keyids that matrix-rust-sdk silently rejects in /keys/query, so even
correctly-signed keys fail to load identity in Element).
mautrix already has the right primitive: generate_recovery_key() does
the full flow — generate seeds, upload privates to SSSS, publish
publics to the homeserver, sign the current device with the new SSK,
and return the human-readable recovery key. We invoke it once on
startup if the bot has no existing cross-signing identity, and log
the recovery key with a clear instruction to save it for future
restarts via MATRIX_RECOVERY_KEY (which the existing recovery-key
path already consumes).
Skipped when MATRIX_RECOVERY_KEY is set (existing path takes over)
or when the bot already has cross-signing keys on the homeserver
(get_own_cross_signing_public_keys returns non-None).
Bootstrap failure is non-fatal — logged with hint about UIA; the bot
continues without cross-signing and Element will show the warning
that prompted this PR. That matches the existing soft-fail pattern
for verify_with_recovery_key.
Tested against Continuwuity 0.5.7 (no UIA required). Synapse with
UIA enabled will need a follow-up PR to thread MATRIX_PASSWORD
through to /keys/device_signing/upload.
Five ``except Exception as exc:`` blocks in the Matrix adapter logged
only ``str(exc)`` without ``exc_info=True``:
- _reverify_keys_after_upload → post-upload key verification failure
- _upload_keys_if_needed → initial device-key query failure
- _upload_keys_if_needed → re-upload device keys failure
- _upload_keys_if_needed → initial device key upload failure
- connect → whoami / access-token validation failure
The E2EE key paths here are security-critical: a silent traceback-
less failure during device-key verification or upload makes it
hard for operators to tell whether their Matrix bot is failing
because of a stale token, a federation timeout, or an olm state
mismatch — all three fail with different tracebacks, which
``str(exc)`` alone flattens.
The contributing guide asks for ``exc_info=True`` on error logs.
Append it to each of the five call sites. Pure logging enrichment.
- Wrap _sync_loop sync() call with asyncio.wait_for(timeout=45s) to guard
against TCP-level hangs that the Matrix long-poll timeout cannot catch
- Add logger.debug at the top of _on_room_message so LOG_LEVEL=DEBUG
confirms whether callbacks fire at all (diagnoses #5819, #7914, #12614)
- Add logger.debug when MATRIX_REQUIRE_MENTION silently drops a message,
pointing users to the env var to disable the filter
Adapted for current mautrix-python adapter (PR was written against the
legacy matrix-nio adapter).
Closes#5819
A misconfigured auxiliary.compression.model is a user-fixable problem that silent recovery would hide. The previous retry-on-main logic transparently swallowed aux-model failures whenever the fallback succeeded, leaving the user's broken config in place and racking up future failures.
Track the aux-model failure on the compressor alongside the existing fallback-placeholder fields:
- _last_aux_model_failure_model: str | None
- _last_aux_model_failure_error: str | None
Both are set at the moment the aux model errors (captured before summary_model is cleared for retry), regardless of whether the retry succeeds. Cleared at compress() start and on on_session_reset() so a clean run doesn't leak stale warnings.
Surface at three places:
- gateway hygiene auto-compress: ℹ note to the platform adapter (thread_id preserved)
- gateway /compress command: ℹ line appended to the reply
- CLI via _emit_warning: deduped on (model, error) so repeat compactions don't spam
Distinct from the existing ⚠️ dropped-turns warning — different severity, different emoji, explicit 'context is intact' reassurance.
Address review feedback on PR #16333:
1. The hygiene-path warning send was missing metadata=_hyg_meta. On
Telegram topics / Slack threads / Discord threads the warning would
land in the main channel instead of the originating thread. Now
reuses the same _hyg_meta dict already computed for the hygiene
compaction itself.
2. New gateway-level test
test_session_hygiene_warns_user_when_summary_generation_fails
verifies end-to-end:
- When the compressor's _last_summary_fallback_used flag is True,
the gateway invokes adapter.send() exactly once.
- The warning message includes the dropped count and the underlying
error string.
- metadata={'thread_id': ...} is propagated so the warning lands
in the originating topic/thread.
Tests: 20 gateway hygiene + 54 context_compressor — all pass.
When auxiliary compression's summary LLM call fails (e.g. model 404,
auxiliary model misconfigured), the compressor still drops the selected
turns and inserts a static fallback placeholder — the dropped context
is unrecoverable.
Previously the only signal of this was a WARNING in agent.log. Gateway
users (Telegram/Discord/etc.) had no way to know context was lost
because the existing _emit_warning path requires a status_callback,
and the gateway hygiene path uses a temporary _hyg_agent with
quiet_mode=True and no callback wired up.
Changes:
- ContextCompressor: track _last_summary_fallback_used and
_last_summary_dropped_count on each compress() call. Cleared at the
start of compress() and on session reset.
- gateway/run.py hygiene: after auto-compress, inspect the temp
agent's compressor; if fallback was used, send a visible ⚠️ warning
to the user via the platform adapter (TG/Discord/etc.) including
dropped count and the underlying error.
- gateway/run.py /compress: append the same warning to the manual
compress reply so users running /compress see the failure too.
Acceptance:
- Summary success: no user-visible warning (unchanged).
- Summary failure on gateway hygiene: user receives a TG/Discord
message with dropped count + error + remediation hint.
- Summary failure on /compress: warning appended to the command reply.
- CLI status_callback / _emit_warning path is untouched.
- Test coverage: two new tests verify the tracking fields are set on
failure and cleared on subsequent success.
The typing-indicator refresh loop in BasePlatformAdapter._keep_typing
awaited each send_typing call unconditionally. Each call is an HTTP
round-trip to the platform API (Telegram/Discord), normally ~100ms. When
the same network instability that causes upstream provider timeouts
(e.g. Anthropic capacity blips slowing first-token latency past the
120s stream-read timeout) also slows the platform typing API to
multi-second response times, the refresh loop stalls inside the await.
Platform-side typing expires at ~5s, so the bubble dies and stays dead
until the stuck send_typing call returns — right when the user most
needs the 'still working' signal and instead sees a bot that looks
dead, then asks 'wtf are you doing' which itself interrupts the
eventually-recovering turn.
Bound each send_typing with asyncio.wait_for (1.5s cap, derived from
interval so it's always below the 2s cadence). Slow calls get abandoned
so the next scheduled tick fires a fresh send_typing on schedule. As
long as any one of them reaches the platform within its ~5s
typing-expiry window, the bubble stays visible across the stall.
Also catches non-timeout send_typing exceptions (transient HTTP errors)
so one bad tick doesn't terminate the whole loop.
Tests: 4 new in tests/gateway/test_keep_typing_timeout.py covering
slow-send non-blocking, fast-send still-awaited, exception resilience,
and paused-chat regression guard.
Reviewer pushback on the original boundary-hardening commits — three
overreach points pulled plugin-specific policy into shared core paths:
1. gateway/run.py hardcoded a '## Honcho Context' literal split for
vision-LLM output. Plugin-format heading in framework code; could
truncate legitimate output naturally containing that header.
Drop the literal split; keep generic sanitize_context (the wrapper
strip is plugin-agnostic). Plugin-specific cleanup belongs at the
provider boundary, not the shared gateway path.
2. run_agent.run_conversation scrubbed user_message and
persist_user_message before the conversation loop. User text is
sacred — if a user types a literal <memory-context> tag we must
not silently delete it. The producer (build_memory_context_block)
is the only legitimate emitter; user input should never need the
reverse op.
3. _build_assistant_message scrubbed model output before persistence.
Same hazard: would silently mutate legitimate documentation/code
the model emits containing the literal markers. The streaming
scrubber catches real leaks delta-by-delta before content is
concatenated; persist-time scrub was redundant belt-and-suspenders.
4. _fire_stream_delta stripped leading newlines from every delta unless
a paragraph break flag was set. Mid-stream '\n' is legitimate
markdown — lists, code fences, paragraph breaks — and chunk
boundaries are arbitrary. Narrow lstrip to the very first delta
of the stream only (so stale provider preamble still gets cleaned
on turn start, but mid-stream formatting survives).
Plus: build_memory_context_block now logs a warning when its defensive
sanitize_context strips something — surfaces buggy providers returning
pre-wrapped text instead of silently double-fencing.
Net architectural change: scrub surface collapses from 8 sites to 3
(StreamingContextScrubber on output deltas, plugin→backend send,
build_memory_context_block input-validation). Plugin-specific strings
stay out of shared runtime paths. User input and persisted assistant
output are no longer mutated.
Tests: rescoped TestMemoryContextSanitization (helper-correctness only,
no source-inspection of removed call sites), updated vision tests to
drop '## Honcho Context' literal-split assertions, updated
_build_assistant_message persistence test to assert preservation.
Added: cross-turn scrubber reset, build_memory_context_block warn-on-
violation, mid-stream newline preservation (plain + code fence).
fixes#5719
The auxiliary vision LLM called by gateway._enrich_message_with_vision
can echo its injected Honcho system prompt back into the image
description. That description gets embedded verbatim into the enriched
user message, so recalled memory (personal facts, dialectic output)
surfaces into a user-visible bubble.
Strips both forms of leak before embedding:
- <memory-context>...</memory-context> fenced blocks (sanitize_context)
- trailing '## Honcho Context' sections (header + everything after)
Plus regression tests:
- tests/agent/test_streaming_context_scrubber.py — 13 tests on the
stateful scrubber (whole block, split tags, false-positive partial
tags, unterminated span, reset, case-insensitivity)
- tests/run_agent/test_run_agent_codex_responses.py — 2 new tests on
_fire_stream_delta covering the realistic 7-chunk leak scenario and
the cross-turn scrubber reset
- tests/gateway/test_vision_memory_leak.py — 4 tests covering the
vision auto-analysis boundary (clean pass-through, '## Honcho Context'
header, fenced block, both patterns together)
Handle queued-title ValueError cleanup during session init, harden Discord message source building for test stubs, and fix the Dockerfile contract test syntax error. Also refresh the TUI lockfile and Nix build flags so nix ubuntu-latest no longer fails on npm lock/peer resolution drift.
* fix: clean gateway auxiliary client caches on teardown
* fix(gateway): recover from stale pid files and close cron agents
Two issues were keeping the gateway from surviving long runs:
1. `_cleanup_invalid_pid_path` delegated to `remove_pid_file`, which
refuses to unlink when the file's pid differs from our own. That
safety check exists for the --replace atexit handoff, but it also
applied to stale-record cleanup, so after a crashy exit the pid
file was orphaned: `write_pid_file()`'s O_EXCL create then failed
with `FileExistsError`, and systemd looped on "PID file race lost
to another gateway instance". Unlink unconditionally from this
helper since the caller has already verified the record is dead.
2. The cron scheduler never closed the ephemeral `AIAgent` it creates
per tick, and never swept the process-global auxiliary-client
cache. Over days of 10-minute ticks this leaked subprocesses and
async httpx transports until the gateway hit EMFILE. Release the
agent and call `cleanup_stale_async_clients()` in `run_job`'s
outer `finally`, matching the gateway's own per-turn cleanup.
* chore(release): map bloodcarter@gmail.com -> bloodcarter
---------
Co-authored-by: bloodcarter <bloodcarter@gmail.com>
``_cleanup_agent_resources`` previously invoked
``agent.shutdown_memory_provider()`` with no arguments, so every memory
provider's ``on_session_end`` hook received an empty list. Providers
with an early-return guard on empty input (Holographic, Hindsight) never
extracted facts from the conversation, and users hit
"抱歉，找不到相關的對話記錄" on the first turn after any gateway
restart, session reset, or idle expiry.
Forward ``agent._session_messages`` — the transcript the agent itself
maintains and refreshes every turn via ``_persist_session`` — so
providers see the actual conversation. Falls back to the legacy no-arg
call whenever the attribute is absent or not a list (test stubs built
via ``object.__new__`` or ``MagicMock``) to preserve backward
compatibility with existing suites. ``AIAgent.shutdown_memory_provider``
already accepts ``messages: list = None`` (run_agent.py:4126), so this
is a pure caller-side fix.
Paths that use ``skip_memory=True`` temporary agents (memory flush,
hygiene auto-compress, ``/compress``) are no-ops inside
``shutdown_memory_provider`` because ``self._memory_manager`` is None —
no behaviour change for them.
Covers Part A of the bug report. Part B (adding ``on_session_end`` to
the Hindsight plugin) is a separate concern that would benefit from
this fix landing first.
Regression test added at
``tests/gateway/test_shutdown_memory_provider_messages.py`` covering:
populated messages forwarded, empty list still forwarded, attribute
missing falls back, non-list (MagicMock) falls back, provider
exceptions don't block ``close()``, None agent no-op, and agent
without ``shutdown_memory_provider`` tolerated.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(image-input): native multimodal routing based on model vision capability
Attach user-sent images as OpenAI-style content parts on the user turn when
the active model supports native vision, so vision-capable models see real
pixels instead of a lossy text description from vision_analyze.
Routing decision (agent/image_routing.py::decide_image_input_mode):
agent.image_input_mode = auto | native | text (default: auto)
In auto mode:
- If auxiliary.vision.provider/model is explicitly configured, keep the
text pipeline (user paid for a dedicated vision backend).
- Else if models.dev reports supports_vision=True for the active
provider/model, attach natively.
- Else fall back to text (current behaviour).
Call sites updated: gateway/run.py (all messaging platforms), tui_gateway
(dashboard/Ink), cli.py (interactive /attach + drag-drop).
run_agent.py changes:
- _prepare_anthropic_messages_for_api now passes image parts through
unchanged when the model supports vision — the Anthropic adapter
translates them to native image blocks. Previous behaviour
(vision_analyze → text) only runs for non-vision Anthropic models.
- New _prepare_messages_for_non_vision_model mirrors the same contract
for chat.completions and codex_responses paths, so non-vision models
on any provider get text-fallback instead of failing at the provider.
- New _model_supports_vision() helper reads models.dev caps.
vision_analyze description rewritten: positions it as a tool for images
NOT already visible in the conversation (URLs, tool output, deeper
inspection). Prevents the model from redundantly calling it on images
already attached natively.
Config default: agent.image_input_mode = auto.
Tests: 35 new (test_image_routing.py + test_vision_aware_preprocessing.py),
all existing tests that reference _prepare_anthropic_messages_for_api
still pass (198 targeted + new tests green).
* feat(image-input): size-cap + resize oversized images, charge image tokens in compressor
Two follow-ups that make the native image routing safer for long / heavy
sessions:
1) Oversize handling in build_native_content_parts:
- 20 MB ceiling per image (matches vision_tools._MAX_BASE64_BYTES,
the most restrictive provider — Gemini inline data).
- Delegates to vision_tools._resize_image_for_vision (Pillow-based,
already battle-tested) to downscale to 5 MB first-try.
- If Pillow is missing or resize still overshoots, the image is
dropped and reported back in skipped[]; caller falls back to text
enrichment for that image.
2) Image-token accounting in context_compressor:
- New _IMAGE_TOKEN_ESTIMATE = 1600 (matches Claude Code's constant;
within the realistic range for Anthropic/GPT-4o/Gemini billing).
- _content_length_for_budget() helper: sums text-part lengths and
charges _IMAGE_CHAR_EQUIVALENT (1600 * 4 chars) per image/image_url/
input_image part. Base64 payload inside image_url is NOT counted
as chars — dimensions don't matter, only image-presence.
- Both tail-cut sites (_prune_old_tool_results L527 and
_find_tail_cut_by_tokens L1126) now call the helper so multi-image
conversations don't slip past compression budget.
Tests: 9 new in test_image_routing.py (oversize triggers resize,
resize-fails-returns-None, oversize-skipped-reported), 11 new in
test_compressor_image_tokens.py (flat charge per image, multiple images,
Responses-API / Anthropic-native / OpenAI-chat shapes, no-inflation on
raw base64, bounds-check on the constant, integration test that an
image-heavy tail actually gets trimmed).
* fix(image-input): replace blanket 20MB ceiling with empirically-verified per-provider limits
The previous commit imposed a hardcoded 20 MB base64 ceiling on all
providers, triggering auto-resize on anything larger. This was wrong in
both directions:
* Too loose for Anthropic — actual limit is 5 MB (returns HTTP 400
'image exceeds 5 MB maximum' above that).
* Too strict for OpenAI / Codex / OpenRouter — accept 49 MB+ without
complaint (empirically verified April 2026 with progressive PNG
sizes).
New behaviour:
* _PROVIDER_BASE64_CEILING table: only anthropic and bedrock have a
ceiling (5 MB, since bedrock-on-Claude shares Anthropic's decoder).
* Providers NOT in the table get no ceiling — images attach at native
size and we trust the provider to return its own error if it
disagrees. A provider-specific 400 message is clearer than us
guessing wrong and silently degrading image quality.
* build_native_content_parts() gains a keyword-only provider arg;
gateway/CLI/TUI pass the active provider so Anthropic users get
auto-resize protection while OpenAI users don't pay it.
* Resize target dropped from 5 MB to 4 MB to slide safely under
Anthropic's boundary with header overhead.
Empirical measurements (direct API, no Hermes in the loop):
image b64 anthropic openrouter/gpt5.5 codex-oauth/gpt5.5
0.19 MB ✓ ✓ ✓
12.37 MB ✗ 400 5MB ✓ ✓
23.85 MB ✗ 400 5MB ✓ ✓
49.46 MB ✗ 413 ✓ ✓
Tests: rewrote TestOversizeHandling (5 tests): no-ceiling pass-through,
Anthropic resize fires, Anthropic skip on resize-fail, build_native_parts
routes ceiling by provider, unknown provider gets no ceiling. All 52
targeted tests pass.
* refactor(image-input): attempt native, shrink-and-retry on provider reject
Replace proactive per-provider size ceilings with a reactive shrink path
on the provider's actual rejection. All providers now attempt native
full-size attachment first; if the provider returns an image-too-large
error, the agent silently shrinks and retries once.
Why the previous design was wrong: hardcoding provider ceilings
(anthropic=5MB, others=unlimited) meant OpenAI users on a 10MB image
paid no tax, but Anthropic users lost quality on anything >5MB even
though the empirical behaviour at provider-reject time is the same
(shrink + retry). Baking the table into the routing layer also
requires updating Hermes every time a provider's limit changes.
Reactive design:
- image_routing.py: _file_to_data_url encodes native size, no ceiling.
build_native_content_parts drops its provider kwarg.
- error_classifier.py: new FailoverReason.image_too_large + pattern
match ("image exceeds", "image too large", etc.) checked BEFORE
context_overflow so Anthropic's 5MB rejection lands in the right
bucket.
- run_agent.py: new _try_shrink_image_parts_in_messages walks api
messages in-place, re-encodes oversized data: URL image parts
through vision_tools._resize_image_for_vision to fit under 4MB,
handles both chat.completions (dict image_url) and Responses
(string image_url) shapes, ignores http URLs (provider-fetched).
New image_shrink_retry_attempted flag in the retry loop fires the
shrink exactly once per turn after credential-pool recovery but
before auth retries.
E2E verified live against Anthropic claude-sonnet-4-6:
- 17.9MB PNG (23.9MB b64) attached at native size
- Anthropic returns 400 "image exceeds 5 MB maximum"
- Agent logs '📐 Image(s) exceeded provider size limit — shrank and
retrying...'
- Retry succeeds, correct response delivered in 6.8s total.
Tests: 12 new (8 shrink-helper shapes + 4 classifier signals),
replaces 5 proactive-ceiling tests with 3 simpler 'native attach works'
tests. 181 targeted tests pass. test_enum_members_exist in
test_error_classifier.py updated for the new enum value.
Previously 'hermes debug share' uploads only got DELETEd when the user
ran 'hermes debug share' again — opportunistic-sweep-on-invoke was the
only cleanup path. A user who uploaded once and never ran debug again
left pastes up until paste.rs's retention kicked in (which, empirically,
never actually expires them).
Hook _sweep_expired_pastes into the gateway cron ticker at the same
hourly cadence as the image/document cache cleanups. The opportunistic
sweep in 'hermes debug share' stays as a fallback for CLI-only users
who never start the gateway.
Telegram groups emit a single bot_command entity covering the whole
/cmd@botname span with no accompanying mention entity, so the existing
mention gate in _message_mentions_bot dropped slash commands sent via
the bot-menu autocomplete whenever require_mention is enabled.
Recognise bot_command entities whose @botname suffix matches the bot
username (case-insensitive) as a direct mention, and keep rejecting
commands addressed at other bots. Fixes#15415.
Harden the Matrix adapter's sender-drop guards so bot-self events and
appservice/bridge identities never reach the gateway's pairing flow or
the agent loop.
Two filters, applied as early as possible in _on_room_message (and
_on_reaction for the self-filter):
1. _is_self_sender(sender) — case-insensitive + whitespace-trimmed
equality with self._user_id. When self._user_id is still empty
(whoami has not resolved, or login failed), returns True
defensively: an unidentified bot dropping its own events is always
preferable to falling into an echo loop. The previous byte-for-byte
equality check let differently-cased copies of the bot's MXID slip
through, and an unresolved self-ID silently disabled the guard.
2. _is_system_or_bridge_sender(sender) — drops appservice namespace
puppets (conventional @_bridge_...:server form) and malformed
senders with an empty localpart. These identities used to fall
through to the gateway's unauthorized-user path, trigger a pairing
code, and — once an operator approved the bridge — every outbound
message the bridge relayed would loop back as an authorized user
message. This was the root of the 'hall of mirrors' symptom.
Fixes#15763
Test plan
---------
scripts/run_tests.sh tests/gateway/test_matrix.py
scripts/run_tests.sh tests/gateway/test_matrix_mention.py tests/gateway/test_matrix_voice.py
All 182 tests pass. 14 new regression tests cover exact / case-insensitive
/ whitespace / unresolved-self-id matches, bridge prefix detection, empty
sender, and the full _on_room_message drop path.
Closes#15775.
Title generation swallowed exceptions at debug level and returned None,
so a depleted auxiliary provider (e.g. OpenRouter 402) silently left
sessions with NULL titles. Reporter observed 45 untitled sessions
accumulated over 19 days with no user-visible indication.
- agent/title_generator.py: accept optional failure_callback, bump log
to WARNING, invoke callback on call_llm exception (swallowing callback
errors so nothing can crash the fire-and-forget worker thread).
- cli.py, gateway/run.py: pass agent._emit_auxiliary_failure as the
callback so failures route through the existing user-visible warning
channel.
- tests: cover callback fires / errors are swallowed / no-callback
legacy behavior / maybe_auto_title forwards kwarg to worker.
Follow-up on top of #16243. Two small tweaks:
- Compile the regex once as `_SAFE_IDENTIFIER_RE` and pin it to
`[A-Za-z0-9@.+\-]`. The previous `\w` accepts Unicode word chars
(full-width digits, accented letters) which aren't valid WhatsApp
identifiers and shouldn't reach the mapping-file lookup.
- Add a comment clarifying this is defense-in-depth, not a live
traversal. The hardcoded `lid-mapping-{current}{suffix}.json`
prefix already prevents escape via pathlib's component split —
with `current='../secrets'`, the first path component under
`session/` is the literal directory name `lid-mapping-..`,
which the attacker cannot create.
E2E verified: legit mapping chains still resolve, all probed attack
shapes (`../`, absolute paths, shell metacharacters, Unicode digit
tricks) are rejected before any file access.
