Commit Graph

15 Commits

Author SHA1 Message Date
Teknium a9838c2100 fix(multiplex): tool and memory-provider env reads stay inside the routed profile
Under gateway.multiplex_profiles, os.environ holds the DEFAULT profile's .env; a
secondary profile's values exist only in the per-turn secret scope. Every reader
below still read os.environ/os.getenv at call time, so a secondary profile's turn
silently used the default profile's value.

Credentials (F6): FIRECRAWL_API_KEY (read_file hosted OCR), OPENVIKING_API_KEY,
mem0-OSS OPENAI_API_KEY, MODAL_TOKEN_ID/SECRET and BROWSER_USE_API_KEY presence
gates, and the xAI video plugin's os.getenv("XAI_API_KEY") fallback AFTER the
scoped resolver had already missed — the exact fallback-after-miss shape
gateway/AGENTS.md forbids. Deleted, not re-scoped: the resolver is the scope.

Identity / tenant (F7): MEM0_USER_ID/AGENT_ID/HOST/MODE, SUPERMEMORY_CONTAINER_TAG,
RETAINDB_PROJECT, OPENVIKING_ACCOUNT/USER/AGENT (and the whole layered() env
read), HINDSIGHT_BANK_ID/MODE/retain shaping, HERMES_HONCHO_HOST. A raw read
put a secondary profile's memories into the default profile's account/bank/
project/tenant and recalled them back into the default's turns. Each now uses
get_secret with the provider's own per-profile default on a miss.

Endpoints (F8): OPENAI_BASE_URL (aux custom runtime + direct-alias expansion),
XAI_BASE_URL/HERMES_XAI_BASE_URL (aux OAuth), NOUS_INFERENCE_BASE_URL (#65941,
both the aux builder and hermes_cli.auth_nous._nous_inference_env_override),
GATEWAY_PROXY_URL (same UnscopedSecretError-only fallback shape as
GATEWAY_PROXY_KEY three lines below), FIRECRAWL_API_URL, BROWSERBASE_BASE_URL,
SUPERMEMORY/RETAINDB/HONCHO/HINDSIGHT URLs. The keys beside them were already
scoped, so a secondary's key was sent to the default profile's proxy or host.

Targets / display (F11): WEIXIN_HOME_CHANNEL (message posted into the default's
chat), HERMES_LANGUAGE, and agent/i18n's process-wide lru_cache of
display.language — now keyed by HERMES_HOME.

Outbound webhooks: hooks.outbound[].secret_env resolved from os.environ while
the gateway registers each profile's targets inside that profile's scope, so a
secondary's deliveries were signed with the default's secret or left unsigned.

Agent-cache eviction: _spawn_release_thread started a bare threading.Thread, so
commit_memory_session -> provider on_session_end ran with an EMPTY context. The
thread now runs copy_context() and, for the unscoped housekeeping sweep, enters
the owning profile's _profile_runtime_scope resolved from the session key
(agent:<profile>:...). The pressure batch does the same per key.

session_search (#82903): agent/inline_tool_executors.py::_session_search
forwarded every schema argument except `profile`, so a gateway agent could
never select a named profile's store. Forwarded; the ownership-scoping design
in #87779/#87847 is a separate design call and is not attempted here.

Live repro (/tmp/mux_audit/fix-tool-memory-reads/repro.py): 28 FAIL on
origin/main -> 0 FAIL with this change; 10 new invariant tests red on base.

Fixes #82903
Fixes #65941
Fixes #99121
Addresses #87779
Co-authored-by: webtecnica <75556242+webtecnica@users.noreply.github.com>
Co-authored-by: Michael Versluis (Berry) <michael@wve.nl>
2026-09-11 15:26:46 -07:00
Teknium 2776813df3 compat(plugins): temporary import-path shims for external plugins — ONE commit, revert on schedule
The Sep 2026 decomposition (PR #102117) makes internal import paths a non-API: names now live in
the focused modules that define them. This commit is the ONLY thing keeping the old paths alive,
so external plugins have time to update. It is deliberately a single, unsquashed commit:

    git revert <this sha>

removes every shim, stub and manifest at once on the announced date. Nothing in-tree may depend on
these pointers: scripts/check_compat_pointers.py (wired into lint.yml) fails CI if it does.

What it adds (see COMPAT_MANIFEST.md, compat_manifest.json):
- 332 facade modules get one delimited `PLUGIN-COMPAT` block appended at the end of the file
- 1,172 moved names resolved lazily via a module `__getattr__` (PEP 562) — never a top-level import,
  so no import cycles; facades that already had `__getattr__` get a chained one
- 592 third-party/stdlib names the old modules used to expose, with their original import statements
- 266 public definitions that had been deleted as unused, restored byte-for-byte from the pre-decomposition
  tree (+40 private helpers and 16 imports pulled in only because a restored definition needs them)
- 3 deleted modules recreated as re-export stubs (gateway/startup_watchdog, hermes_cli/observability/
  relay_runtime, tools/environments/modal_utils)
- private names (`_x`) get no pointer: they were never API (3,792 skipped)

Verified: all 335 touched modules import under a fresh HERMES_HOME and every manifest name resolves;
the lint reports zero in-tree uses; ruff clean; targeted suites unchanged.
2026-09-03 17:13:22 -07:00
Teknium e83816a4d1 review-fix(comments): restore lost #NNNN rationale comments across non-test source (mechanical sweep, condensed, code unchanged)
For each issue anchor present in BASE 63279301bc non-test .py and absent on HEAD, the BASE comment/docstring block was re-attached at the HEAD location of the code it explained (matched by the distinctive code line / enclosing def). Sentences already covered by an existing HEAD comment were deduped; the issue number always survives. Insert-only: no code lines changed.
2026-09-03 09:44:26 -07:00
Teknium 575b54d457 refactor(agent): iron_proxy/monitoring/outbound_webhooks pass-2 structural cut (helpers unified, single-use helpers inlined, packed literals) 2026-09-02 22:44:07 -07:00
Teknium af0ddcb2ec refactor(agent): iron_proxy signal guard ctx manager + yaml loader helper; table/kwargs compaction across group 2026-09-02 18:58:26 -07:00
Teknium eea8e8060e refactor(agent): compact module docstrings (outbound_webhooks, otlp_exporter, emitter, gateway_health_export) 2026-09-02 18:53:00 -07:00
Teknium 79c704f34f refactor(agent): monitoring/iron_proxy third pass — gateway.status dispatch helper, SDK symbol table by module, compact comments and inner blanks 2026-09-02 18:48:19 -07:00
Teknium 1a1716ee64 refactor(agent): compact outbound_webhooks — fold list-check into iter_configured_targets, tighten delivery logging 2026-09-02 18:24:14 -07:00
Teknium 4bfc55fbf0 refactor(agent/runtime): hooks/guardrails/dispatch — unify shell-hook and webhook plumbing, table-driven guardrail thresholds
- shell_hooks is the shared home: _ToolMatcherMixin (matcher compile + matches_tool),
  _payload_fields, _forget_home_registrations, _home_key, _utc_now_iso now serve
  outbound_webhooks too (copies deleted; every log string byte-identical).
- shell_hooks: response parsing is a per-event dispatch table; _spawn diagnostic
  dict + _evaluate_result shared by the live callback and run_once;
  _locked_update_approvals POSIX/non-POSIX bodies merged via ExitStack.
- tool_guardrails: ToolCallGuardrailConfig thresholds from a _THRESHOLD_SOURCES
  table (nested-wins-over-flat preserved); _int_at_least replaces
  _positive_int/_non_negative_int; observe_identical_call (0 refs) folded into
  observe_call; _halt helper for hard-stop decisions.
- tool_dispatch_helpers: _plan_tool_batch_segments split into _batch_admission +
  close/extend helpers with the post-hoc normalization merged in.
- Comment/docstring compaction keeping every stated rule.
2026-09-02 13:29:48 -07:00
Teknium 98c27aa25c feat(webhooks): stamp the emitting profile on outbound webhook payloads
Under a multiplexed gateway every profile's outbound webhooks share one
delivery worker, so receivers could not tell which profile fired an
event. Add a top-level `profile` field to the payload, resolved at fire
time from the bound Hermes home via get_active_profile_name() ("default"
outside profiles). Documents the field in the wire-format section.

Reported by @vszgdcn8cj-ctrl.

Fixes #92674
2026-09-02 07:00:13 -07:00
chelsealong 600b9c7e7e fix(gateway): scope force-reload hook re-registration to its own home
re_register_config_hooks() cleared the entire process-global idempotence
set on every force-reload, so a profile-local plugin force-reload dropped
another live profile's ledger key without touching its still-registered
callback — the next registration call for that profile then appended a
duplicate. Scope the clear to the reloading profile's own home, and give
outbound webhooks the same force-reload restoration shell hooks already
had, since unload() wipes both from the shared _hooks dict.
2026-09-02 07:00:13 -07:00
chelsealong 29640e3b5a fix(gateway): register secondary profiles' shell hooks and outbound webhooks
Multiplex gateway startup only ever calls agent.shell_hooks/
outbound_webhooks register_from_config() once, against the
root/default profile's config, before any profile scope exists.
_start_one_profile_adapters() discovers Python plugins per profile
but never registered that profile's own declarative `hooks:` block,
so a secondary profile's shell hooks (e.g. a deny-writes gate) and
outbound webhooks silently never fire.

Load and register each profile's own config inside its
_profile_runtime_scope, and key the module-level idempotence sets in
shell_hooks.py/outbound_webhooks.py by resolved Hermes home so two
profiles configuring an identical hook/webhook both register on
their own plugin manager instead of the second being dropped as a
duplicate of the first.

Fixes #92672
2026-09-02 07:00:13 -07:00
Teknium 5b4d20b524 fix(hooks): flush outbound queue at interpreter exit
The delivery worker is a daemon thread, so a short-lived process
(hermes chat -q, a cron session) could exit right after firing
on_session_end — silently dropping the headline event. Register a
bounded atexit flush (5s) when the worker starts: a dead endpoint can
delay exit slightly, never hang it.

Live-verified: hermes chat -q now delivers on_session_start,
post_tool_call, and on_session_end to a real receiver; regression test
runs a subprocess that exits without flushing (sabotage-verified).
2026-08-02 15:01:11 -07:00
Teknium 86fd6da1dc fix(hooks): single delivery_id across header+body, never follow redirects
- delivery_id is now generated once per firing and used for both the
  X-Hermes-Delivery header and the signed body's delivery_id field —
  previously they were two different uuid4s, breaking receiver-side
  dedupe as documented.
- 3xx responses are no longer followed: urllib's default redirect
  handler converts a redirected POST into a body-less GET, silently
  dropping the signed payload. Redirects now log a misconfiguration
  warning and count as delivery failure (no retry).
- Docs: receiver-side replay-protection guidance (dedupe on
  delivery_id, timestamp freshness window) + redirect semantics.
- Tests: 5xx retry count, redirect-not-followed (sabotage-verified),
  header/body delivery_id equality.
2026-08-02 15:01:11 -07:00
Teknium 3829e34e23 feat(hooks): outbound webhooks — push signed lifecycle events to external HTTP endpoints
The inverse of the inbound webhook platform: hooks.outbound in
config.yaml lists HTTP targets + the plugin-hook events they subscribe
to (on_session_end, subagent_stop, post_tool_call, ...). Each firing
POSTs a JSON payload (same top-level shape as shell hooks' stdin wire)
signed GitHub-style with HMAC-SHA256 (X-Hermes-Signature-256).

Rides the existing hook bus — notify-only callbacks registered on the
plugin manager at the same CLI/gateway/main entry points as shell
hooks. Delivery is fire-and-forget via a bounded queue + single daemon
worker thread, so a dead endpoint can never stall a tool call. Bounded
retries (5xx/conn errors once; 4xx never). secret_env preferred over
inline secret. HERMES_SAFE_MODE skips registration. hermes hooks list
shows outbound targets with signed/UNSIGNED status.

Zero new model tools, zero new subsystems.
2026-08-02 15:01:11 -07:00