Third review pass (Hermes subagent) declared convergence: no BLOCKING, the
round-2 generation-aware publish / context-engine staging / CLI reload / ACP
routing all verified correct by hand and by test.
- agent_init: capture _tool_snapshot_generation immediately before the tool
snapshot (was ~425 lines earlier); removes a harmless skew window so the
recorded generation always matches the snapshot it describes.
- gateway/run.py _execute_mcp_reload: keep preserving each cached agent's
build-time enabled_toolsets EXACTLY (do NOT merge newly-connected servers like
CLI/TUI do) and document WHY — gateway sessions can be deliberately locked
down, and test_reload_mcp_preserves_per_agent_toolset_overrides asserts this.
A reviewer suggested "parity" here; it would have violated that contract.
Second review pass (Codex + Hermes subagent). Codex reproduced a real race with
a two-thread harness; both converged on the remaining issues.
- Generation-aware publish (fixes a lost-update race): two refresh callers (the
late-refresh daemon and the between-turns prologue around turn 1) could each
compute a snapshot outside the lock; a SLOWER caller holding an OLDER registry
generation could acquire the publish lock after a newer caller and clobber it,
deleting just-landed tools. refresh_agent_mcp_tools now captures
registry._generation before computing and refuses to publish a stale set;
agent._tool_snapshot_generation tracks the published generation.
- Context-engine routing names (_context_engine_tool_names) are now staged on a
local and published atomically with the snapshot, and only claimed when this
rebuild actually appended the schema — matching agent_init's dedup so a
registry/plugin tool of the same name keeps its own dispatch. (Previously
mutated live, before the publish lock, and on no-change refreshes.)
- CLI /reload-mcp: self.enabled_toolsets is resolved once at startup, so a
server newly ENABLED in config mid-session wasn't picked up (TUI already
re-resolved). Merge now-connected MCP server names into the override (unless
the user pinned all/*), mirroring startup, and keep self.enabled_toolsets in
sync. Closes the CLI/TUI parity hole.
- ACP (acp_adapter/server.py) routed through the shared helper — it was a 5th
sibling rebuild that re-injected memory tools but NOT context-engine tools and
bypassed the atomic/name-diff path (inert today, fragile).
- mcp_startup._resolve_discovery_timeout pulls its default from DEFAULT_CONFIG
(single source of truth) instead of a stale hardcoded 5.0 literal.
- Tests: stale-generation-no-clobber, _skip_mcp_refresh honored, timeout
fallback uses DEFAULT_CONFIG.
Consolidated findings from three independent reviewers (Codex, Claude Code, a
Hermes subagent w/ the hermes-agent-dev skill):
- BLOCKING: refresh_agent_mcp_tools rebuilt only the registry subset, silently
dropping post-build-injected memory-provider (mem0/honcho/…) and context-
engine (lcm_*) tools on every refresh. Now additive-preserving: re-applies
the same injectors agent_init uses, staged on locals and published atomically.
- Re-injection now honors the #5544 enabled_toolsets gate for context-engine
tools, so a restricted-toolset platform can't get lcm_* leaked back in.
- Atomic read-diff-publish under one lock: the returned `added` set and the
(tools, valid_tool_names) pair are consistent even under concurrent callers
(no half-swap, no TOCTOU).
- background_review fork opts out (_skip_mcp_refresh) so its byte-identical
tools[] cache parity with the parent is preserved.
- CLI /reload-mcp routed through the shared helper (was a 4th divergent copy
with the same clobber bug + missing disabled_toolsets).
- Explicit reloads (TUI RPC + CLI) pass enabled_override so a server the user
just enabled in config this session is picked up; automatic paths reuse the
agent's build-time selection.
- mcp_discovery_timeout default 5.0 -> 1.5s: correctness now comes from the
between-turns refresh, so the startup wait is only a small turn-1 UX bump
rather than a heavy dead-server latency penalty.
- has_registered_mcp_tools checks registered TOOLS (not connected servers) so a
zero-tool/prompt-only server doesn't make the per-turn hook fire forever.
- Tests: rewrote the thread-safety test to actually exercise the write path
(alternating tool sets), added the #5544-gate regression, the memory/context
preservation regression, and a "callable next turn via valid_tool_names"
contract; removed a dead monkeypatch line.
A slow MCP server (HTTP/OAuth, 2-6s cold connect) that finishes connecting
after the agent's one-time tool snapshot was uncallable for the rest of the
session. The merged pre-first-turn late-refresh only helps during the dead air
before the user's first keystroke; once a turn starts it bails to protect the
prompt cache, so a user who types before the server connects never gets the
tools without a manual /reload-mcp.
Refresh the snapshot in the per-turn prologue (build_turn_context), before this
turn's first API call assembles tools=. This is cache-safe by construction: the
refresh only ever extends a fresh request prefix at a turn boundary, never
mutates the cached prefix of an in-flight turn. So late tools become callable on
the user's NEXT turn automatically, with no /reload-mcp and no cache cost.
- tools/mcp_tool.py: has_registered_mcp_tools() — cheap guard so sessions with
no MCP servers (the common case) skip the rebuild entirely.
- agent/turn_context.py: call the shared refresh_agent_mcp_tools() helper at the
top of the prologue when MCP servers are registered.
- tests: 3 contract tests through the real build_turn_context (adds late tool;
skipped when no servers; no snapshot churn when unchanged).
.hermes/plans/: SPEC + PLAN documenting the root cause, the cache-safety
constraint, and why the existing fixes (#48403/#41630/#42802) don't close it.
MCP servers that connect after the agent's one-time tool snapshot were
invisible for the whole session. Two root causes, fixed together:
1. The startup discovery wait was a flat 0.75s. HTTP/OAuth servers
commonly take 2-6s on a cold connect, so they missed the window and
their tools never entered the agent's snapshot. `thread.join(timeout)`
already returns the instant discovery completes, so raising the bound
costs ~0s for the common case (no MCP / fast servers) and only ever
blocks for a genuinely-pending server, capped so a dead server can't
freeze startup. The bound is now configurable via
`mcp_discovery_timeout` (config.yaml, default 5.0s).
2. Three call sites duplicated the agent tool-snapshot rebuild (the TUI
`reload.mcp` RPC, the gateway reload, and the TUI late-binding refresh
thread), and the late-refresh detected changes by tool COUNT — missing
an equal-size add/remove swap. Consolidated into one shared
`tools.mcp_tool.refresh_agent_mcp_tools(agent)` helper that diffs by
tool NAME, mutates the agent under a lock (thread-safe), and respects
the agent's own enabled/disabled toolsets.
The late-binding refresh keeps its pre-first-turn cache-safety guard:
it never rebuilds the tool list once a turn has started, so the cached
prompt prefix is never invalidated mid-conversation.
Tests: new tests/tools/test_refresh_agent_mcp_tools.py covers the
name-based diff, in-place mutation, agent-scoped filtering, thread
safety, and the config-driven discovery bound (incl. instant-return
when nothing is pending). 75 passed across the touched areas.
Wires support for the MCP `elicitation/create` request (Python SDK 1.11+)
so MCP servers can ask the user to confirm sensitive operations
mid-tool-call (payment authorization, OAuth confirmation, etc.) instead
of failing closed or requiring out-of-band biometrics.
Behavior:
- `tools/mcp_tool.py` adds `ElicitationHandler`, attached per server task
and passed to `ClientSession` as `elicitation_callback`. Form-mode
requests route through the existing approval system; URL-mode requests
decline cleanly (out of scope for this pass).
- `tools/approval.py` adds `request_elicitation_consent()`, which dispatches
to whichever surface owns the active session — `_await_gateway_decision`
for Telegram / Slack / etc. (so the approval prompt lands on the right
platform), `prompt_dangerous_approval` for CLI / TUI. Fails closed on
timeout, missing notify_cb, or exception.
- The MCP tool wrapper snapshots `contextvars.copy_context()` into
`MCPServerTask._pending_call_context` before each `session.call_tool`
and clears it after. The recv-loop task that dispatches incoming
`elicitation/create` requests does not inherit the agent task's
contextvars (HERMES_SESSION_PLATFORM and friends), so without the
bridge `_is_gateway_approval_context()` returns False on every
gateway session and the elicitation falls through to a CLI prompt
that has no TTY → fail-closed decline. The handler now reads the
snapshot via its `owner` back-reference and replays it through
`Context.copy().run(...)` so attribution survives the task hop.
Tests (`tests/tools/test_mcp_elicitation.py`):
- form-mode accept / decline / cancel
- URL-mode declined without prompting
- exception in approval system → decline
- timeout in approval → cancel
- context-bridge regression tests (replay observed in consent call,
missing-context fallback, multiple-replay safety, owner with
cleared `_pending_call_context`)
Verified end-to-end against pay's MCP server on macOS: agent message
arrives via Telegram, agent calls `mcp_pay_curl` against a paid endpoint,
pay returns 402, ElicitationHandler routes the approval prompt back to
the originating Telegram chat, user replies in TG, the curl tool signs
and completes.
Platforms tested: macOS 14 (darwin/arm64). No Unix-only syscalls
introduced; Windows footgun checker passes on the touched files.
Sets the Telegram bot's short description (the line under its name) to
"Online" on gateway connect and "Offline" on clean disconnect, gated
behind extra.status_indicator (off by default).
Telegram bots have no presence/online dot — that's a user-account
feature the Bot API doesn't expose for bots. The short description is
the closest available surface, so this gives users a way to tell whether
the gateway is up from the bot's profile.
- New extra.status_indicator flag (+ status_online/status_offline text
overrides), read in __init__ via config.extra — no config-schema change.
- _set_status_indicator() helper: best-effort, swallows API errors so it
never blocks connect/disconnect; truncates to Telegram's 120-char cap.
- Wired Online after _mark_connected(), Offline at top of disconnect()
while the bot HTTP client is still alive.
- 9 unit tests + Telegram docs section.
Requested by @ilTrumpista, cc @Teknium.
The image-too-large reactive shrink (try_shrink_image_parts_in_messages)
conflated two independent constraints: it always rejected a resize whose
re-encoded bytes were >= the original, even when the shrink was driven by a
PIXEL-DIMENSION cap (Anthropic many-image 2000px) rather than the byte budget.
Downscaled screenshot PNGs routinely re-encode LARGER in bytes, so the
dimension-correct result was discarded and the image left oversized -> the
provider re-rejected on retry and the session wedged forever.
Fix: track which constraint triggered the shrink (bytes vs dimension) and gate
the accept on the SAME axis.
* dimension path: accept the result as long as it is now within max_dimension,
regardless of byte size (verify via Pillow; fall back to the byte gate only
when the re-encode can't be decoded).
* bytes path: still require bytes to shrink, but ALSO re-check the per-side cap
when it's active — _resize_image_for_vision returns a best-effort, possibly
over-cap blob when it exhausts its halving budget on a very-high-aspect
image, so a byte-shrink alone can leave it over the dimension cap and
re-brick on retry.
Extend the unshrinkable-oversized guard to the pixel axis so a partial shrink
doesn't burn the one-shot retry.
Single shared agent path -> fixes CLI, TUI, and gateway alike.
Adds a real-Pillow runnable proof (repro_48013_image_shrink_brick.py) that
reproduces the issue's per-image table (bricks 3/5 before, passes 5/5 after)
plus unit invariants for the dimension and bytes accept/reject paths,
partial-progress accounting, and the bytes-path still-over-cap regression
surfaced by adversarial review.
Closes#48013
The web dashboard only showed a read-only "Reasoning" capability badge
with no way to set the effort level — unlike the desktop app, which has
an effort radio in its composer model menu. This adds a picker so the two
surfaces reach parity.
- ReasoningPicker: a Select rendered in the chat sidebar, gated on the
effective model's supports_reasoning capability (from /api/model/info).
Reads/writes agent.reasoning_effort via the existing config REST
endpoints (read-modify-write, the dashboard's single-key save pattern),
so the value lands in the config the agent boots a fresh chat from.
Options mirror the desktop: Off/Minimal/Low/Medium/High/Max.
- ChatSidebar: capture supports_reasoning from the model-info fetch and
render the picker; on change, show the same 'apply on /new or reload'
notice the model switch uses.
- reasoning-effort.ts: DOM-free helpers (normalizeEffort + options) so the
node-env vitest harness can cover the resolution logic, plus tests.
The classic CLI status bar could appear twice after a horizontal terminal
resize — two bars at two widths with two different elapsed readings.
Root cause: prompt_toolkit's Application._on_resize() calls renderer.erase(),
which does cursor_up(_cursor_pos.y) + erase_down() using the _cursor_pos.y
cached from the LAST render at the OLD width (renderer.py:745). On a column
shrink the terminal reflows the already-painted full-width chrome into extra
physical rows, so the cached y undershoots: cursor_up doesn't climb past the
reflowed rows and erase_down leaves the old bar stranded ABOVE the live
origin. The next paint stacks a fresh bar below it. The existing post-resize
suppression hides the NEW bar for ~0.35s but never erases the already-reflowed
OLD one, so the ghost survives the whole window. Ctrl+L / /redraw clears it,
confirming a viewport wipe is the fix.
Fix: on a WIDTH change, _recover_after_resize now routes through the same
recovery as Ctrl+L — _clear_prompt_toolkit_screen(rebuild_scrollback=False)
(CSI 2J, visible viewport only) + _replay_output_history() — BEFORE delegating
to prompt_toolkit's resize. Banner-safe: 2J never touches scrollback history
(that's CSI 3J, which we don't send here), so the startup banner is preserved.
Rows-only resizes skip the clear (no reflow → no ghost) to avoid an extra
repaint. Tracks _last_resize_width to distinguish the two.
Tests: replace the now-obsolete 'never clears on resize' assertion with two
tests — rows-only resize delegates without clearing; width change clears the
viewport + replays and never wipes scrollback.
Resolves the 2 npm audit advisories (1 high, 1 moderate), both from
transitive undici:
- undici 6.26.0 -> 6.27.0 (high: TLS bypass / header injection /
response queue poisoning class, via node-gyp + ui-tui)
- jsdom's undici 7.27.2 -> 7.28.0 (moderate, via jsdom test dep)
Both are in-range bumps (no --force). Lockfile also reconciled two
pre-existing manifest drifts during the install: dompurify 3.4.10 ->
3.4.11 (in-range patch) and the web workspace's already-declared
vitest ^4.1.5 devDep. No package.json changes. npm audit reports 0
vulnerabilities in root, ui-tui, and apps/desktop after.
* fix(desktop): rename "Restart messaging" -> "Restart gateway"
The Command Center control restarts the whole messaging gateway, yet was
labelled "Restart messaging" while the status line above it reads "Messaging
gateway running/stopped". Rename the i18n key to match what it does, across
all 4 locales.
* feat(desktop): restart the gateway from Cmd+K, with statusbar spinner feedback
Add a shared runGatewayRestart() (store/system-actions.ts) and wire it to a
new Cmd+K "Restart gateway" action. While a restart is in flight the
statusbar "Gateway" item swaps its icon for the TUI glyph spinner and reads
"restarting…", returning to its real state on completion — driven by a
$gatewayRestarting atom, not a transient toast or the generic "Agents
running" counter. The helper owns its error handling so fire-and-forget
callers can't leak an unhandled rejection; only a failure toasts.
* fix(desktop): offer a Restart gateway action on messaging save/toggle toasts
The "setup saved" and "platform enabled/disabled" toasts told users their
change needs a gateway restart but left it a separate hunt. Attach a "Restart
gateway" action (the shared runGatewayRestart), and reword the copy to state
the pending consequence ("...takes effect after a gateway restart") now that
the button carries the verb. Updated all 4 locales.
* fix(desktop): make rendered logs selectable so they can be copied
The global body { user-select: none } left log surfaces unselectable. Opt them
back in via the existing data-selectable-text convention — at the shared
LogView primitive (boot-failure + bootstrap install overlays) plus Command
Center recent logs, toolset post-setup output, notification detail, and
subagent stream/file lines.
The global body { user-select: none } left log surfaces unselectable. Opt them
back in via the existing data-selectable-text convention — at the shared
LogView primitive (boot-failure + bootstrap install overlays) plus Command
Center recent logs, toolset post-setup output, notification detail, and
subagent stream/file lines.
The "setup saved" and "platform enabled/disabled" toasts told users their
change needs a gateway restart but left it a separate hunt. Attach a "Restart
gateway" action (the shared runGatewayRestart), and reword the copy to state
the pending consequence ("...takes effect after a gateway restart") now that
the button carries the verb. Updated all 4 locales.
Add a shared runGatewayRestart() (store/system-actions.ts) and wire it to a
new Cmd+K "Restart gateway" action. While a restart is in flight the
statusbar "Gateway" item swaps its icon for the TUI glyph spinner and reads
"restarting…", returning to its real state on completion — driven by a
$gatewayRestarting atom, not a transient toast or the generic "Agents
running" counter. The helper owns its error handling so fire-and-forget
callers can't leak an unhandled rejection; only a failure toasts.
The Command Center control restarts the whole messaging gateway, yet was
labelled "Restart messaging" while the status line above it reads "Messaging
gateway running/stopped". Rename the i18n key to match what it does, across
all 4 locales.
The Chat-tab session switcher rendered rows in the API's default
order="created" (original start time) while each row displays
last_active — so a session you just messaged in could sit below an
older one, and the list looked unsorted against its own timestamps.
Pass order="recent" from ChatSessionList so the switcher sorts by
latest activity across the compression chain (most-recently-used at
top, ChatGPT-style; long conversations that auto-compressed into a new
continuation id stay on the first page). Adds an optional, defaulted
`order` arg to api.getSessions; the paginated Sessions page keeps the
stable created order.
The classic CLI status bar could vanish for the rest of a session: any
terminal reflow (SIGWINCH from a tmux pane change, SSH window restore, font
zoom) set _status_bar_suppressed_after_resize=True, but the flag was ONLY
cleared on the next *submitted* user input. Resize then sit idle and the
bottom chrome rendered at height 0 on every repaint — even with the
refresh clock ticking — so the bar was gone until you typed and hit enter.
Fix: _recover_after_resize now schedules a debounced unsuppress timer that
clears the flag and repaints once the reflow settles (~0.35s), so the bar
returns on its own during idle. The next-submit clear stays as a fast path.
Fails open: any error in scheduling clears the flag immediately rather than
leaving the bar stuck hidden.
Satisfies the repo-wide subprocess-stdin guard
(tests/tools/test_subprocess_stdin_guard.py); the long-lived bridge
child should not inherit the gateway's stdin.
Adds a Raft platform adapter as a bundled plugin (plugins/platforms/raft/)
connecting Hermes to Raft as an external agent via a wake-channel bridge.
The adapter starts a loopback HTTP endpoint, spawns 'raft agent bridge' as a
child process, and injects content-free wake hints into the gateway session
pipeline. The agent reads/sends messages through the Raft CLI; the adapter
never touches message bodies or delivery cursors. Activity observer hooks
report tool/LLM/session lifecycle events via a bounded at-most-once queue.
Auto-enables when RAFT_PROFILE is set.
Cherry-picked from PR #47629. Authored by skyzh (@xxchan).
Manual verification surfaced a second bypass class beyond the standalone
config loaders: several code paths bridge config.yaml values into os.environ
(HERMES_TIMEZONE, HERMES_REDACT_SECRETS, HERMES_MAX_ITERATIONS, TERMINAL_*,
network.force_ipv4, ...) by reading the raw user YAML, so the env the whole
process reads carried the USER's value even when an administrator pinned it —
e.g. a managed timezone was overridden because gateway/run.py wrote the user's
timezone into HERMES_TIMEZONE, and _resolve_timezone_name() checks the env var
first.
Wired the shared apply_managed_overlay() into every config→env bridge:
- gateway/run.py module-level startup bridge (timezone, redact_secrets,
max_turns, terminal, display, gateway.strict, ...)
- gateway/run.py _reload_runtime_env_preserving_config_authority (the per-turn
re-bridge that keeps config authoritative over reloaded .env — must keep
MANAGED authoritative on every turn, not just startup)
- hermes_cli/main.py early security.redact_secrets / network.force_ipv4 bridge
(runs before load_config is usable, at import time)
- hermes_cli/send_cmd.py top-level scalar config→env bridge
Verified end-to-end against a writable managed dir (12/12 checks incl. timezone,
logging, model, skin, gateway settings, write-guard) and in a clean process the
gateway per-turn bridge writes HERMES_TIMEZONE=<managed>. Adds an
order-independent regression test for the bridge overlay.
The skin bug was one instance of a class: several subsystems build their
config dict directly from config.yaml instead of routing through
hermes_cli.config.load_config (which carries the managed merge), so they
silently ignored administrator-pinned values. Audited every config.yaml
reader and fixed the behavioral-read bypasses:
- gateway/config.py load_gateway_config (messaging gateway: session_reset,
quick_commands, stt, model, ...)
- gateway/run.py _load_gateway_config (its read_raw_config fast path also
skipped the merge — read_raw_config returns raw user YAML)
- tui_gateway/server.py _load_cfg (new TUI + desktop backend: skin,
reasoning_effort, service_tier, provider_routing)
- cron/scheduler.py (scheduled-job model/reasoning/toolsets/provider_routing)
- hermes_logging.py (logging.level/max_size_mb/backup_count)
- hermes_time.py (timezone)
- hermes_cli/doctor.py (memory-provider diagnostic reads effective config)
All route through a new shared managed_scope.apply_managed_overlay() helper
that mirrors _load_config_impl (env-only expansion so a user ${VAR} can't
shadow a managed literal, root-model-string normalization, leaf-merge) and is
fail-open. cli.py's earlier inline fix is refactored onto the same helper.
Write-back paths (slash_commands, telegram/yuanbao dm_topics, profile
distribution) are deliberately left reading raw user YAML — overlaying managed
values there would persist them into the user file. The dashboard
(web_server.py) already routes through load_config and needed no change.
TUI loader caches the RAW config so _save_cfg never writes managed values to
disk. Adds test_managed_scope_overlay.py (helper) and
test_managed_scope_loaders.py (per-surface integration); mutation-checked.
cli.py's load_cli_config() builds CLI_CONFIG independently of
hermes_cli.config._load_config_impl (it reads config.yaml directly and merges
into hardcoded defaults), so the Phase 2 managed merge never reached the
interactive CLI/TUI surface. Symptom: a managed display.skin (and any other
display/CLI pref read from CLI_CONFIG) was silently ignored by the TUI while
`hermes config`/`doctor`/write-guards — which go through load_config — correctly
honored it. Found via manual testing: the skin engine kept using 'default'.
Fix: overlay the managed config last in load_cli_config(), mirroring
_load_config_impl — expand against the process env only (so a user ${VAR} can't
shadow a managed literal), normalize the root model key so a managed
`model: x/y` string can't clobber the dict shape callers expect, then
leaf-merge. Fail-open so managed scope can never block CLI startup.
Adds tests/hermes_cli/test_managed_scope_cli_config.py locking that CLI_CONFIG
honors managed values, preserves user siblings, and is inert with no scope.
- show_config prints an administrator header naming the managed source and
lists the pinned config/env keys when a scope is active (silent otherwise).
- hermes doctor gains a managed_scope_check under Configuration Files that
reports the resolved managed dir + pinned key counts, and flags a
HERMES_MANAGED_DIR redirect (the documented foot-gun).
- set_config_value hard-rejects a managed config key (D2) and names the
source, exiting non-zero.
- save_env_value / remove_env_value refuse a managed env key.
- save_config strips managed leaves from a bulk write (mechanical safety net)
with a warning, so the unmanaged remainder still persists.
New _strip_dotted_keys helper drives the bulk-save pruning. All guards are
distinct from and layered after the existing is_managed() package-manager
write-lock.
load_hermes_dotenv now loads the managed-scope .env after user/project .env
and external secret sources, with override=True, so managed env values beat
the user .env and any pre-existing shell export. Reuses the existing dotenv
fallback + credential-sanitization path. Fail-open: no managed dir/.env is a
no-op and any error is swallowed so managed scope never blocks startup.
_load_config_impl now deep-merges the managed config.yaml on top of the
expanded user config so managed leaves win while sibling keys stay
user-controlled (leaf-level merge, D3). Managed values are expanded against
the process env only, never user-defined ${VAR}, so a user can't shadow a
managed literal. The managed file's (mtime,size) is folded into the load
cache key so editing it invalidates the cache. This inverts the usual
env-over-config precedence for pinned keys by design (see design doc §4.1).
New hermes_cli/managed_scope.py resolves a system-level managed directory
(HERMES_MANAGED_DIR override > /etc/hermes), parses managed config.yaml/.env
with fail-open semantics, and exposes is_key_managed/is_env_managed helpers.
The system default is ignored under pytest and HERMES_MANAGED_DIR is added to
the conftest env scrub so a real managed scope can't leak into the suite.
Not wired into the load paths yet (Phases 2-3).
_terminate_reclaimed_worker early-returned on ProcessLookupError with
terminated=False. The new reclaim-defer guard reads that as 'worker
survived the kill' and defers the reclaim forever, so a stale task whose
worker is already dead never lands in result.stale. ProcessLookupError
means the process is gone — that IS a successful termination. Split it
from the generic OSError branch and set terminated=True.
release_stale_claims and detect_stale_running call _terminate_reclaimed_worker
and then release the task claim unconditionally, even when the termination did
not actually kill the worker. _terminate_reclaimed_worker already reports this
via its "terminated" flag, but the callers ignore it.
When a worker is parked in uninterruptible (D) state — for example throttled by
a cgroup memory.high limit — a pending SIGTERM/SIGKILL cannot be delivered until
the throttle lifts, so the kill is a no-op. The dispatcher then frees the claim
and spawns a fresh worker beside the still-alive one. Repeated every dispatch
tick this accumulates duplicate workers without bound, deepening the memory
pressure that caused the throttle in the first place — a self-reinforcing
runaway.
Fix: gate both automatic reclaim paths on _worker_survived_termination(). When
we attempted to kill our own host-local worker and it is still alive, defer the
reclaim (_defer_reclaim_for_live_worker extends the claim a short grace and
emits a reclaim_deferred event) instead of releasing. This guarantees at most
one live worker per task and is self-correcting: not spawning a duplicate is
what relieves the pressure so the pending signal lands and the worker dies, and
the next tick reclaims cleanly. Non-host-local claims and the operator-driven
reclaim_task() path keep their existing force-release behaviour.
Related: #41448 (concurrent dispatchers amplify this by doubling reclaim
frequency); #42858 (kill the worker rather than orphan it on archive).
Tests: defer-when-worker-survives, reclaim-when-killed,
release-when-not-host-local, and the detect_stale_running path.
The lazy_deps pin (memory.hindsight -> hindsight-client==0.6.1) was newer
than the plugin's stated floor (>=0.4.22). Align _MIN_CLIENT_VERSION,
the setup wizard dep string, plugin.yaml, and the README to 0.6.1 so the
floor check, auto-upgrade target, and runtime lazy-install all agree.
Also drops the redundant local _MIN_CLIENT_VERSION redefinition in
post_setup.
Five targeted enhancements to the upstream simplify-code skill:
1. Risk-tiered application (SAFE/CAREFUL/RISKY) — safe changes auto-applied,
careful changes verified per-file, risky changes flagged for human review.
Prevents auto-applying N+1 restructures and public API renames.
2. Chesterton's Fence — before flagging anything for removal, reviewers run
'git blame' to understand why it exists. Low-confidence findings are
escalated rather than guessed.
3. AI slop detection — Quality reviewer now catches: extra comments restating
obvious code, unnecessary defensive null-checks on validated inputs, 'as any'
casts, and patterns inconsistent with the rest of the file.
4. Silent failure detection — Efficiency reviewer now catches: empty catch
blocks, ignored error returns, except:pass, .catch(()=>{}) with no handling,
and error propagation gaps.
5. Structured reviewer output with confidence+risk tags — reviewers report in
'file:line → problem → fix | confidence: H/M/L | risk: SAFE/CAREFUL/RISKY'
format, enabling the orchestrator to tier the application.
Plus 3 new pitfalls: over-trusting dead code tools, public contract awareness,
and preserving intentional error handling.
Total: +45/-8 lines. Keeps the 212-line compact spirit.
Ref: #379
ruff (unspecified-encoding) and the Windows-footgun checker both flag
open() in text mode without encoture=. Keep text mode (the Windows lock
path in _try_acquire_file_lock writes a str newline) and pass
encoding='utf-8'.
Two robustness gaps from community review (#44919):
1. Windows dead-path: replaced bespoke fcntl.flock with gateway.status
_try_acquire_file_lock / _release_file_lock — already cross-platform
(msvcrt on Windows, fcntl on POSIX). Added _release_singleton_lock
helper.
2. Lock fd never released: stored handle is now released explicitly in
both exit paths — CancelledError handler and normal while-loop exit.
Allows in-process stop/restart (tests, embedded use).
Also tightened docstrings — 'corrupt the SQLite DBs' is now specific
(wal_autocheckpoint=0 + concurrent manual WAL checkpoints can corrupt
index pages), matching the module's own concurrency claims.
The gateway's embedded dispatcher has no guard against more than one dispatcher
running concurrently. dispatch_in_gateway defaults to true, so a second gateway
for the same profile (a restart race where the old process is slow to exit) — or
any deployment that runs multiple profile gateways with the default — starts a
second dispatcher loop. As #41448 describes, concurrent dispatchers each run
release_stale_claims() against the same boards, double reclaim frequency, and
re-dispatch slow workers before they finish. In practice they also corrupt the
shared kanban SQLite DBs under concurrent write load.
Add _acquire_singleton_lock(): an exclusive, non-blocking fcntl.flock at the
machine-global kanban root (kanban_home()/kanban/.dispatcher.lock — the board is
shared across profiles by design, so this serialises every gateway, not just one
profile). The first gateway to start its dispatcher holds the lock for its
process lifetime; any other gateway finds it contended, logs, and skips
dispatching while still running for messaging. Falls back to config-only control
on non-POSIX or filesystems without flock.
This is more robust than a per-profile guard because the documented model is
"one dispatcher sweeps all boards" — the contention is across profiles, not just
within one. Closes#41448.
Test: lock is exclusive (held, then contended while held, then held again after
release).
Two small, focused fixes for the cron scheduler and checkpoint manager.
1. _summarize_cron_failure_for_delivery (cron/scheduler.py):
Replaces the raw error dump in _process_job with a compact
pattern-matched summary. Provider rate limits, timeouts, and
authentication errors now produce a short human-readable message
instead of dumping multi-KB provider JSON into the delivery channel.
2. _repair_bare_repo_dirs (tools/checkpoint_manager.py):
Recreates refs/heads/ and branches/ directories after git gc
--prune=now, which can remove empty dirs from bare repos and cause
subsequent git add -A to fail with 'fatal: not a git repository'.
Called after all four git gc call sites.
Both fixes use only standard library imports and plug into existing
call sites with no architectural changes.
PR #49056 set the default to 0, which reverts the #45592 idle-clock fix:
without a periodic invalidate, prompt_toolkit stops repainting the bottom
chrome during idle and the status bar goes stale/disappears after a turn.
Restore 1.0 as the default for everyone. The config knob stays — users on
emulators where the per-second redraw fights auto-scroll (#48309) can set
display.cli_refresh_interval: 0 to opt out.
Extend the 'Running Many Gateways at Once' user-guide page with a
'one gateway for all profiles (multiplexing)' section, kept to a single page:
- How to opt in (gateway.multiplex_profiles on the default profile) and when to
prefer it vs one-process-per-profile.
- Every contract change a user sees when the flag is on:
1. secondary-profile 'gateway start' is a hard error (--force escape hatch),
2. HTTP-inbound reached via /p/<profile>/ prefix; secondary profiles must NOT
enable a port-binding platform (webhook/api_server/msgraph_webhook/feishu/
wecom_callback/bluebubbles/sms) — config error at startup,
3. per-credential platforms still need their own token per profile,
4. session keys namespaced agent:<profile>: (default stays agent:main:),
5. single PID/lock + aggregated hermes status, per-profile runtime_status.json.
- What does NOT change: per-profile .env credential isolation (stricter, incl.
MCP/Kanban subprocess env), Kanban, profile-scoped skills/memory/SOUL, routing.
All inert when the flag is off.
- _guard_named_profile_under_multiplexer: when the default gateway is running
with gateway.multiplex_profiles=on, a named-profile 'hermes gateway run' hard
-errors (pointing at the multiplexer) instead of double-binding that
profile's platforms. Inert unless all hold: this invocation is a named
profile, a default-profile gateway is alive, and its config has multiplexing
on. --force overrides. Wired into run_gateway's guard chain.
- write_runtime_status gains served_profiles: the secondary-adapter startup
records [active] + multiplexed profiles into runtime_status.json so
'hermes status' can show per-profile coverage without a second probe. Absent
for single-profile gateways.
Tests: served_profiles round-trips and is absent by default; guard is inert for
the default profile / under --force / when no default gateway is running.
Bring up adapters for every profile the gateway serves, not just the active
one. Keeps self.adapters as the default/active profile's map (the ~93 existing
self.adapters[...] sites are untouched) and adds secondary profiles under
self._profile_adapters[profile][platform].
- _start_secondary_profile_adapters loops profiles_to_serve(multiplex=True),
skips the active profile (handled by the primary startup loop), and for each
other profile loads its gateway config and creates+connects its enabled
adapters under that profile's _profile_runtime_scope (home + secret scope).
- Each secondary adapter gets _make_profile_message_handler(profile): stamps
source.profile (when unset) before delegating to the shared _handle_message,
so the agent turn and session key resolve to that profile.
- Same-platform credential-conflict detection: _adapter_credential_fingerprint
hashes the adapter's bot token (salted, truncated — never logs the token);
two profiles claiming the same (platform, token) refuse the duplicate with a
clear error naming both, since one token can't be polled twice.
- Port-binding hard-error: a SECONDARY profile that enables a port-binding
platform (webhook, api_server, msgraph_webhook, feishu, wecom_callback,
bluebubbles, sms) is a config error and aborts startup via MultiplexConfigError
— the default profile owns the single shared HTTP listener and serves every
profile through the /p/<profile>/ prefix, so a second bind can only collide.
Distinct from a transient connect failure (which logs + stays alive to retry):
a config error writes gateway_state=startup_failed and exits cleanly with an
actionable message (names the profile, the platform, and the fix). There is no
valid reason to bind a second port once you've opted into a multiplexer.
- Shutdown tears down secondary adapters alongside the primary ones.
- Defensive getattr guards keep partial-construction unit tests (stop(),
_run_agent on bare instances) working.
No-op when multiplex_profiles is off (self._profile_adapters stays empty).
Tests: fingerprint stability/log-safety/distinctness, profile message-handler
stamping (and not overriding an already-stamped source), port-binding hard-error
raises + names the profile/platform, non-binding platform is not rejected, and
the guard set covers every TCP-binding adapter.
Serve webhook inbound for multiple profiles off the one shared listener via a
URL prefix, with no second port bound.
- SessionSource gains a 'profile' field (round-trips through to_dict/from_dict;
omitted when unset so existing serialization is unchanged). It carries which
profile an inbound message was routed to.
- WebhookAdapter registers /p/{profile}/webhooks/{route_name} alongside the
existing /webhooks/{route_name}. _resolve_request_profile validates the
prefix against profiles_to_serve(): None when absent or multiplexing is off
(ignored, handled as default — no spurious 404), the profile name when valid,
_PROFILE_REJECTED (→ 404) when the profile isn't served. The resolved profile
is stamped onto the SessionSource.
- session-key namespacing and the per-turn home/credential scope now prefer
source.profile: SessionStore._resolve_profile_for_key(source),
_session_key_for_source fallback, and _resolve_profile_home_for_source all
honor it (→ the agent turn resolves that profile's config/skills/credentials
via the Phase 2 _profile_runtime_scope).
Constraint: routing inbound needs no per-profile platform credential, but the
agent still needs the routed profile's provider key — delivered by Phase 2's
secret scope. api_server (OpenAI-compatible surface) profile routing is a
focused follow-on; its source-construction path differs from webhook's.
Tests: SessionSource.profile round-trip + namespace drive; _resolve_request_
profile accept/reject/ignore matrix.
The credential gate. When multiplexing is active, a profile's secrets resolve
from a context-local scope, never the process-global os.environ (which in a
multiplexer may hold another profile's keys, and is inherited by every
subprocess spawned with env=dict(os.environ)).
- agent/secret_scope.py: get_secret() backed by a secret-scope contextvar.
FAIL-CLOSED: when multiplex is active and no scope is installed, an unscoped
read RAISES UnscopedSecretError instead of falling back to os.environ — a
missed/new call site crashes loudly at that line rather than leaking a
cross-profile value. Genuinely-global vars (HERMES_*, PATH, kanban paths,
…) keep reading os.environ via an allowlist. load_env_file/build_profile_
secret_scope parse a profile .env into an isolated dict WITHOUT mutating
os.environ. Off by default => transparent os.getenv behavior.
- hermes_cli/runtime_provider.py: all credential/provider/base-url reads go
through _getenv -> get_secret.
- agent/credential_pool.py: env fallbacks route through get_secret (the
~/.hermes/.env-first preference is preserved and already profile-correct via
the home override).
- tools/mcp_tool.py: MCP config interpolation resolves through
get_secret, so a server's picks up the routed profile's value.
- gateway/run.py: set_multiplex_active() at GatewayRunner init; per-turn .env
reload is a no-op for credentials in multiplex mode (secrets come from the
scope, not global env); _profile_runtime_scope context manager combines the
HERMES_HOME override + secret scope; _run_agent wraps _run_agent_inner in
that scope (resolved via _resolve_profile_home_for_source) when multiplexing.
Propagates into the agent worker thread for free via the existing
copy_context() in _run_in_executor_with_context.
Tests: 13 unit (fail-closed, scope isolation, global allowlist, .env parsing
without environ mutation) + 7 E2E (runtime_provider + MCP interpolation prove
two profiles isolated, unscoped read raises, globals still read environ).
