Commit Graph

1682 Commits

Author SHA1 Message Date
Teknium 11310068c6 feat(plugins): pre_command observer hook + capability-gated ctx.call_mcp (#64204)
Part A — pre_command observer hook (observer-first per #64182 ground rule 3):
- New VALID_HOOKS event `pre_command`: fires when a recognized slash command
  is about to be dispatched, BEFORE the handler runs, on both surfaces:
  - CLI: cli.py process_command (right after alias resolution)
  - Gateway: gateway/run.py _handle_message cold-path canonical dispatch
- Payload: surface ('cli'|'gateway'), command (canonical), alias_used,
  args_raw, session_key, platform. Return values IGNORED in v1; a plugin
  returning a directive-shaped dict gets a debug log so future
  block/rewrite adopters are discoverable (#64231 taxonomy).
- Deliberately NOT fired on the gateway running-agent intercept path
  (/stop, /approve, busy_policy dispatch during an active run): those are
  control-plane escape hatches on an in-flight run and must stay outside
  plugin observation/veto reach.
- fire_pre_command_hook() helper never raises, so broken plugin infra can
  never break command dispatch.

Part B — ctx.call_mcp (capability-gated, default-off, ground rule 4):
- PluginContext.call_mcp(server, tool, arguments, timeout=30): synchronous,
  callable from plugin hooks/tools, routes through the EXISTING native MCP
  client machinery (tools.mcp_tool._make_tool_handler: background loop,
  trust-tier gates, circuit breaker, reconnect) — never a parallel client.
- Gate: plugins.entries.<id>.mcp_allowlist (list of server names).
  Absent key / unreadable config / non-list value => default-deny.
  Unlisted server raises PermissionError naming the exact config key.
  TODO seam left for the #64228 declared-capability model.
- Bounded: timeout clamped to 1-600s and forwarded to the MCP loop call;
  results capped at 64KB with truncation marker; stable
  {ok, result|error, structuredContent?, truncated?} envelope.

Tests (transport mocked, no live MCP servers):
- tests/hermes_cli/test_pre_command_hook.py: both surfaces fire, canonical
  alias reporting (/exit->quit, /q->queue), hook-before-handler ordering,
  control-plane exclusion, hook failure non-fatal, observer-only directive
  handling.
- tests/hermes_cli/test_plugin_call_mcp.py: default-deny (absent entry,
  unreadable config, non-list, '*'), allowlist enforced per-server,
  denied calls never touch transport, timeout forwarding/clamping,
  result truncation, error/structuredContent envelopes.

Docs: hooks.md shipped-catalog row for pre_command; plugins.md
"Calling MCP servers from plugins" section with the security note.

Closes #64204
2026-08-12 19:16:59 -07:00
Hans 52eb8eb533 feat(plugins): add pre_transcription hook and STT prompt threading
Adds a pre_transcription transform hook (prompt/language/model mutable,
file_path read-only, last-writer-wins per the transform_* convention)
fired before any STT backend, threads prompt to faster-whisper
(initial_prompt) and OpenAI/Groq/Mistral/DeepInfra (prompt), adds an
optional stt.prompt config key on the same plumbing, and keeps the
no-hook dispatch path byte-identical. Fixes #64168.

Documents the new surface for users: a "Transcription prompt
(vocabulary hints)" subsection in the configuration guide (composition
order, per-provider support matrix, length contract, privacy warning),
a pre_transcription entry in the hooks reference, and the mirrored row
in the plugins hook table.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AG6LyYMvHC2o6HbVUozmVR
2026-08-12 19:01:30 -07:00
Teknium 2e0183169c feat(plugins): community plugin index + hermes plugins search (#64181)
Static machine-readable community plugin index with fuzzy search and
index-resolved installs, mirroring the Skills Hub catalog pattern
(fetch → HERMES_HOME/cache with 24h TTL → bundled seed fallback).

- hermes_cli/plugin_index.py: index fetch/cache/seed chain, fuzzy
  search (name/description/tags/author + typo tolerance), capability
  filter, bare-name resolution. Canonical URL overridable via
  plugins.index_url config key.
- hermes_cli/data/plugin_index.json: bundled seed (offline fallback +
  format reference) with 5 real ecosystem plugins, each pinned to an
  exact commit SHA.
- hermes plugins search [term] [--json] [--capability] [--refresh]:
  Rich table or JSON output, offline-safe, with an explicit
  'indexed ≠ audited' footer.
- hermes plugins install <name>: bare names (no slash, no URL scheme)
  resolve through the index to owner/repo[/subdir] @ pinned ref and
  hand off to the existing install path (ref wired through the #82029
  exact-ref support). Ambiguous names list candidates and exit;
  explicit owner/repo and Git URL installs are untouched, and an
  explicit --ref always beats the index pin.
- Docs: discovery section in user-guide plugins.md (format, submission
  workflow via PR to hermes-plugin-index, security framing) and
  reference/cli-commands.md rows.
- Tests: tests/hermes_cli/test_plugin_index_search.py (38 tests, no
  live network) covering parsing, search, remote→cache→seed fallback,
  TTL, install resolution/ambiguity/passthrough, and --json output.
2026-08-12 18:52:08 -07:00
Teknium bd6dcd4bd5 feat(plugins): manifest v2 — schema version, api_version, inter-plugin deps, pip-dependency declaration seam, config schema (#64165)
Additive plugin.yaml v2 fields (all optional; v1 manifests unchanged forever):

- manifest_version: manifest FILE-FORMAT version (absent = 1). Deliberately
  split from api_version per the round-2 design correction. Newer-than-
  supported versions load with a warning, unknown fields ignored.
- api_version: runtime plugin API generation the plugin targets (integer).
- requires_plugins: advisory inter-plugin deps ({id, version_range?}).
  Missing dep = warn + still load (ctx.has_plugin() runtime probe added).
  Load ORDER is dependency-respecting: graphlib topological sort, stable
  alphabetical tiebreak; cycles warn and fall back to alphabetical.
- python_dependencies: declared pip requirements — VALIDATED AND SURFACED
  ONLY (loader warning + install-time printout + doctor checks with a pip
  install hint). Never auto-installed: the isolation design for the install
  seam (#15220) is an explicitly deferred follow-up per the round-2 review.
- config_schema: JSON-schema-ish description of plugins.entries.<id>.settings
  keys; validated at load, mismatches are actionable warnings naming the key
  and expected type — never load failures.
- Formalized metadata: license, homepage, tags.
- Unknown manifest fields warn-don't-fail (debug-level for v1 manifests).
- hermes plugins doctor gains v2 checks: future manifest_version, invalid
  api_version, dep declarations, unpinned/missing python_dependencies,
  unknown config_schema types.
- Docs: manifest v2 reference table in the developer-guide plugins index,
  including the explicit pip-seam isolation deferral and the note that
  #64166 packs build on these fields.
- Tests: tests/hermes_cli/test_plugin_manifest_v2.py (19 tests) covering v1
  regression, v2 parse, unknown-field warn, dep order, cycle fallback,
  config_schema warnings, and the surfaced-not-installed pip seam.
2026-08-12 18:39:22 -07:00
Dineth Hettiarachchi 00f4da01ec feat(plugins): add streaming output observer hooks
Salvage of PR #64317 (@deaneeth) onto current main, implementing #64161:
observer-only on_stream_start / on_stream_delta / on_stream_end /
on_interim_message plugin hooks dispatched through a host-owned bounded
queue (one worker per callback) so plugin callbacks never run inline on
the token path. Reasoning deltas are opt-in via
plugins.stream_reasoning_deltas.
2026-08-12 18:38:25 -07:00
GodsBoy e64fb2b614 fix(review): harden plugin gateway injection 2026-08-12 18:25:33 -07:00
GodsBoy f46c600a54 feat(gateway): allow plugins to inject session messages 2026-08-12 18:25:33 -07:00
Teknium b088535c78 feat(plugins): capability declarations + install/update consent flow (#64228)
Unify the scattered per-plugin trust gates into one declared, diffable
capability model with an install/update-time consent flow. Consent +
audit over host API surfaces — explicitly NOT a sandbox.

New module hermes_cli/plugin_capabilities.py:
- Canonical CAPABILITY_REGISTRY mapping each capability id 1:1 to an
  EXISTING enforcing gate (no capability minted without a surface):
    tools.override          -> allow_tool_override
    llm.provider_override   -> llm.allow_provider_override
    llm.model_override      -> llm.allow_model_override
    llm.agent_id_override   -> llm.allow_agent_id_override
    llm.profile_override    -> llm.allow_profile_override
    llm.task_override       -> llm.allow_task_override
- plugin_capability_granted(plugin_id, capability): canonical check —
  granted set OR deprecated legacy allow_* key; fail closed on unknown
  ids and any unreadable/corrupt consent state; emits checked_by audit
  log lines on every decision.
- record_consent() persists plugins.entries.<id>.granted_capabilities +
  capabilities_consent {hash, granted_at} and mirrors grants into the
  legacy keys so existing enforcement sites keep working unchanged.
- capability_set_hash / pending_capabilities / declared_set_changed
  power the update-time re-consent diff.

Wiring:
- plugin.yaml manifest field `capabilities:` parsed into
  PluginManifest.capabilities (unknown ids dropped with a warning).
- hermes plugins install: consent screen (one Y/n) when the manifest
  declares capabilities; non-interactive installs proceed with
  capabilities ungranted (fail closed).
- hermes plugins update: when the new version declares capabilities the
  granted set lacks (hash diff), the additions are surfaced and require
  re-consent — an update can never silently widen access.
- hermes plugins enable: consent screen replaces the standalone
  tool-override prompt for capability-declaring plugins.
- hermes plugins capabilities [<id>]: declared vs granted per plugin,
  flags grants held via deprecated legacy keys.
- PluginContext.has_capability() probing API so plugins degrade
  gracefully; _tool_override_allowed migrated to the canonical
  plugin_capability_granted path (reference migration; legacy
  allow_tool_override still honored).

Tests: tests/hermes_cli/test_plugin_capabilities.py (38 tests) —
declaration parsing, consent grant/persist, update re-consent on added
capability, fail-closed on missing/corrupt state, legacy-gate backward
compat, consent CLI flow (grant / decline / non-interactive).

Docs: user-guide plugins.md consent section (with explicit not-a-sandbox
warning) + developer-guide plugin authoring capability note.

Salvages the intent of PR #37976 (@coygeek — require renewed review
before plugin updates), scoped to capability diffs.

Part of #64182.
2026-08-12 18:05:21 -07:00
Teknium 9994bc9ec9 fix(gateway): enforce post-auth normalized reaction observer
Builds on Paolo Antinori's #68431 salvage for #64176. Move plugin dispatch behind the profile-scoped runner authorization boundary, fail closed on malformed reaction identities, preserve observer registration across Telegram app rebuilds, and document the deliberately observer-only contract.

Co-authored-by: Paolo Antinori <pantinor@redhat.com>
2026-08-12 16:42:28 -07:00
khanhngoo f1c45f5727 feat(voice): add configurable TUI draft submission
Add voice.submit_mode=direct|draft without model-refine hooks or callbacks. Validate the config, preserve direct-submit compatibility, render editable drafts in the Ink composer, and document both locales.

Co-authored-by: BELIVIN MEDIA <212580280+KarateWilly@users.noreply.github.com>
2026-08-12 16:42:07 -07:00
SeoYeonKim 9acf0db889 feat(plugins): add cache-safe system prompt sections
Salvage the plugin-owned static prompt idea from PR #51589 into the constrained #64167 contract: stable IDs, deterministic placement, bounded fail-open rendering, and full-prompt resume recovery without new session columns.

Co-authored-by: Topher Ross <biz@topherross.com>
2026-08-12 16:34:58 -07:00
Teknium 6601330e0a feat(plugins): install exact commit refs 2026-08-12 16:27:30 -07:00
Teknium d409f67485 feat(platforms): add typed plugin send paths
Route plugin target parsing, validation, and host-driven delivery through PlatformEntry across CLI and cron while preserving the host-only send_message policy.
2026-08-12 16:27:19 -07:00
Teknium 7a5062fbcd feat(plugins): add runtime-backed plugin Doctor
Validate plugin manifests, imports, hook signatures, and runtime registrations through the real plugin loader in an isolated temporary home.
2026-08-12 16:27:07 -07:00
webdevtodayjason 2711e41c4f docs(plugins): fold unique guide content into the canonical author guide
Per review, docs/plugins.md was a parallel guide outside the published
navigation. Its genuinely unique material moves into
website/docs/developer-guide/plugins/index.md: the middleware
registration surface (all four VALID_MIDDLEWARE kinds with contracts and
chaining rules), the per-API-call request hooks, and the
allow_tool_override operator grant (which also fixes pre-existing text
implying override=True alone suffices for non-bundled plugins). Every
migrated claim was re-verified against current main; stale material
(deep-copy claim, approval-surface coverage, a hook that is not in
VALID_HOOKS on main) was corrected or dropped rather than copied.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PnMCvi2vXqfs996AjVeF2F
2026-08-12 16:27:07 -07:00
Teknium cd7c674d74 fix(plugins): harden approval transport boundaries 2026-08-12 16:26:55 -07:00
Teknium de56e49a7c feat(plugins): add approval transport interface 2026-08-12 16:26:55 -07:00
Teknium 5265409012 docs(plugins): document config and state ownership 2026-08-12 16:26:43 -07:00
Teknium 729b8a7169 test(plugins): enforce behavior compatibility contract 2026-08-12 16:25:29 -07:00
Magnus Hedemark 79c11aea7a fix(plugins): complete task-routed LLM integration 2026-08-12 16:25:20 -07:00
Teknium e0bb71cb73 fix: track secret source registration origin 2026-08-12 16:25:10 -07:00
Bartok9 2e29de2296 fix(plugins): delegate secret-source enablement to is_enabled contract (#64177)
Address teknium1 review on #64189:
- Re-pull gate now delegates to each source's is_enabled(cfg) via the
  registry contract, so a plugin source with custom activation logic is
  honored (previously only secrets.<name>.enabled was checked).
- Add BUILTIN_SOURCE_NAMES to the registry so plugin-vs-bundled is a
  single source of truth instead of a hard-coded set at the call site.
- Reconcile docs: rewrite the timing :::note to describe both the
  post-discovery re-pull and the remaining import-time limitation, and
  cross-link the first-process bootstrap section.
- Tests: real SecretSource subclasses, custom is_enabled activation
  (positive + negative), is_enabled-raises skip, builtin-only no-op,
  and a discovery-registration end-to-end re-pull check.
2026-08-12 16:25:10 -07:00
Bartok9 7a7e73d310 fix(plugins): re-pull plugin secret sources after discovery (#64177)
After plugins register SecretSource backends, reset the env-loader cache
and re-run load_hermes_dotenv when an enabled plugin secret source is
configured. Closes the first-process bootstrap gap where import-time env
load stale-outs plugin vaults (tommck / Community ask). Fail-open, no-op
without plugin sources.

Docs: first-process bootstrap timing on secret-source plugin guide.
Tests: unit coverage for noop / enabled re-pull / discover hook.
Part of #64182 plugin-interface expansion.
2026-08-12 16:25:10 -07:00
brooklyn! 6aaa181f0e
docs: present /export and /import as the second way to share a profile (#84668)
The distributions guide framed export/import as local backup only, so the
new slash commands read as a competing path instead of the lightweight
half of one story. Give profile-distributions.md a comparison table up
front (git repo vs single file: updates, versioning, setup cost, what
each carries), rewrite the Not-a-fit bullets that mislabeled export, and
add a full Export/import section covering the CLI, TUI, and desktop
entry points, the desktop.json overlay, and what an archive actually
contains — including that it can carry memories and sessions, which a
distribution never does.

Also register /export and /import in the slash-command reference (they
shipped undocumented), point the profile-command entries at their chat
and desktop doors, and cover the desktop Export/Import UI on the desktop
page.
2026-08-12 13:10:03 -05:00
Teknium 62a9c0f0e9
fix(file-safety): approval-gate ~/.ssh/config writes instead of hard-denying (#84663)
The write_file / patch file tools hard-denied ~/.ssh/config as a
"protected system/credential file", while the terminal tool only
*asked* for approval on ~/.ssh writes. That inconsistency meant a write
to ~/.ssh/config was refused via write_file but succeeded via terminal
after an approval prompt -- the same operation flip-flopping between
denied and OK depending on which tool ran it.

The SSH client config carries no private-key material, and editing it
(host aliases, ProxyJump, VS Code Remote-SSH targets) is a routine,
user-initiated task. It CAN carry ProxyCommand / Match exec directives
that run commands, so a free write is still inappropriate -- approval,
not a flat refusal, is the right policy, matching what the terminal tool
already does.

Changes:
- agent/file_safety.py: remove ~/.ssh/config from the flat credential
  deny; add build_write_approval_paths() + is_write_approval_required(),
  and short-circuit it out of the ~/.ssh/ prefix deny so the file is
  allowed at the classifier layer. Private keys, authorized_keys, and
  everything else under ~/.ssh/ stay hard-denied.
- tools/file_tools.py: _check_approval_required_write() routes ssh config
  writes through the shared _run_approval_gate (once/session/always,
  honors --yolo, fail-closed with no human), wired into write_file_tool
  and patch_tool right after the protected-instruction gate.
- Non-interactive consumers fail closed: the ACP file bridge
  (copilot_acp_client) rejects approval-required paths outright, and the
  TTS output-path picker refuses them as before.
- Docs + tests updated (security.md exception note;
  TestSshConfigApprovalGate covers config approval-gated, keys still
  hard-denied).
2026-08-12 11:04:45 -07:00
Brooklyn Nicholson 8a6deaaacf docs: present /export and /import as the second way to share a profile
The distributions guide framed export/import as local backup only, so the
new slash commands read as a competing path instead of the lightweight
half of one story. Give profile-distributions.md a comparison table up
front (git repo vs single file: updates, versioning, setup cost, what
each carries), rewrite the Not-a-fit bullets that mislabeled export, and
add a full Export/import section covering the CLI, TUI, and desktop
entry points, the desktop.json overlay, and what an archive actually
contains — including that it can carry memories and sessions, which a
distribution never does.

Also register /export and /import in the slash-command reference (they
shipped undocumented), point the profile-command entries at their chat
and desktop doors, and cover the desktop Export/Import UI on the desktop
page.
2026-08-12 12:57:18 -05:00
kshitij a871948d8d fix: correct Lightpanda fallback docs — remove nonexistent PDF/upload/clipboard actions
Hermes has no browser PDF, file upload, or clipboard tools. The fallback
mechanism only covers commands in _FALLBACK_ELIGIBLE (open, snapshot,
screenshot, eval, click, fill, scroll, back, press, console, errors).
The original docs described Lightpanda's general limitations, not
Hermes's actual behavior.
2026-08-12 20:19:26 +05:30
Katie Brown 0a81935a9d docs(browser): document Lightpanda local engine 2026-08-12 20:19:26 +05:30
Teknium f20d16fbf1
fix(windows): SSH ControlMaster gating + stop hijacking the user's python (#84452)
* fix(windows): SSH ControlMaster gating + stop hijacking the user's python

Two Windows environment-integrity fixes:

1. tools/environments/ssh.py (#73927): Windows OpenSSH has no
   Unix-domain-socket ControlMaster support, so unconditionally passing
   ControlPath/ControlMaster/ControlPersist failed EVERY tool call on a
   Windows-hosted ssh terminal backend with 'getsockname failed: Not a
   socket'. Gate the three multiplexing options behind a module-level
   _SSH_MULTIPLEX = (os.name != 'nt'); the scp upload path is gated the
   same way. On Windows the backend now works without connection pooling
   (each command a fresh connection); POSIX behavior is unchanged. The
   teardown 'ssh -O exit' is naturally inert because the socket never
   exists on Windows.

2. scripts/install.ps1 (#83797): the installer put the whole
   venv\Scripts directory on the user PATH, which contains python.exe /
   pythonw.exe / pip.exe and so silently hijacked the 'python' command in
   every terminal on the machine — unrelated projects started resolving
   python to Hermes' runtime interpreter. Now copy only the launchers
   (hermes.exe, hermes-acp.exe) into a dedicated $InstallDir\bin and put
   THAT on PATH. Existing installs are migrated: the legacy venv\Scripts
   entry is stripped from the user PATH on the next install/update. The
   new bin dir is under $InstallDir (…\hermes-agent), which the uninstall
   PATH sweep already matches via its \hermes-agent marker.

Updated the stale hermes_cli/update_cmd.py docstring that described the
old venv\Scripts-on-PATH layout.

Tests: SSH ControlMaster gating pinned both directions (multiplex on →
flags present; off → absent but BatchMode/StrictHostKeyChecking retained).
install.ps1 parses clean via the PowerShell AST parser.

* docs: update windows-native install docs for the bin\ launcher layout

CI (test_windows_native_docs) pins the docs and installer to the same
PATH layout. The #83797 fix moved the PATH entry from venv\Scripts to a
dedicated $InstallDir\bin holding only the hermes launchers, so update
the Windows-native guide to match: PATH-after-install section, the
install-steps list, the directory-layout table, the Get-Command
verification line, and the 'command not found' pitfall. Test now asserts
the bin\ layout and guards against a regression back to venv\Scripts on
PATH.

* fix: keep install.ps1 pure ASCII (PowerShell 5.1 codepage safety)

The two comments I added in the #83797 PATH-hijack fix used em-dashes,
tripping tests/test_install_ps1_ascii_only.py — Windows PowerShell 5.1
reads a BOM-less .ps1 in the system ANSI codepage (not UTF-8), so a
non-ASCII byte can misdecode into a stray quote and desync the parser
(issues #66994/#67000). Replace the em-dashes with ASCII '--'.
2026-08-12 02:56:33 -07:00
Teknium 14692ec917
fix: make verify_on_stop opt-in everywhere (default False, not auto) (#84383)
* fix: make verify_on_stop opt-in everywhere (default False, not auto)

The verify-on-stop nudge was already judged more noise than signal: the
v31 migration flips existing installs off, the v32 migration catches the
baked-in literal-true population, and the docs tell users to 'treat off
as the effective default and opt in explicitly'. But DEFAULT_CONFIG still
shipped the "auto" sentinel, so exactly one population kept getting the
nudges: fresh installs (and any config missing the key), where "auto"
resolves ON for CLI/TUI/desktop surfaces. Live symptom: repeated
'[System: You edited code ... run verification]' interruptions the user
never asked for and had to hunt down in source to disable.

- DEFAULT_CONFIG: agent.verify_on_stop "auto" -> False (opt-in).
- verify_on_stop_enabled(): missing/unrecognized value now falls back
  OFF instead of surface-aware; explicit "auto" still selects the
  legacy surface-aware behavior, explicit bools unchanged, and the
  HERMES_VERIFY_ON_STOP env override is untouched.
- No migration needed: v31/v32 already normalized existing installs,
  and this only changes the merged default for configs without the key.
- Docs updated; default-path E2E test now asserts OFF, plus a new
  missing-value regression test. Also added the standard win32 skip
  marker to the symlink-based temp-dir test (pre-existing Windows
  failure, same class as tests/cron/test_cron_script.py).

* test: update config goldens — verify_on_stop=False is now stripped as default

With the DEFAULT_CONFIG flip to False, the migration-write invariant
(_persist_migration / save_config strip_defaults) no longer materialises
verify_on_stop: false to disk unless the user explicitly set the key:

- V20 floor fixture (agent: {} on disk): v31's write is stripped —
  agent stays {} and load_config() supplies False at read time.
- V12 floor fixture (explicit verify_on_stop: true on disk): the key is
  a user-set path, so the v32 flip stays materialised as false.
- Partial-write and _persist_migration regressions now assert the key is
  absent from disk and (for the merge case) that the merged view still
  resolves False.

Behavior verified with a one-shot migrate_config run against both
fixture shapes.
2026-08-12 01:15:25 -07:00
fangliquanflq 87af576e60
fix(auxiliary): honor main model for title generation (#83636) 2026-08-11 23:36:47 -05:00
victor-kyriazakos e9579a9896
feat(relay): ambient token endpoint mode for gateway.idp.token_url (#84074)
* feat(relay): ambient token endpoint mode for gateway.idp.token_url

When gateway.idp.token_url is configured WITHOUT client_id/client_secret,
treat the URL as a metadata-server-style ambient credential endpoint:
plain GET, response body is the token (raw JWT or {"access_token": ...}
JSON envelope). Covers workload-identity proxies such as Domino's
$DOMINO_API_PROXY/access-token, which mint short-lived user-scoped OIDC
tokens with no client registration.

Previously this configuration was a hard error (client_id/client_secret
missing), so no working deployment changes behaviour: creds present keeps
the OAuth2 client_credentials POST, no token_url keeps Nous Portal. The
misconfig error now self-diagnoses (names the ambient fallback and how to
select the client_credentials grant instead).

* fix(relay): reject short plain-text bodies in ambient token shape gate

Review finding: the shape gate accepted any base64url-alphabet word, so an
IdP answering the ambient GET with a terse error body ('unauthorized',
'error', 'null') had that word returned as a bearer token instead of the
fail-closed misconfiguration error. Tighten the gate to JWT-like dotted
tokens (3+ segments) or long opaque tokens (>= 32 chars); short bare words
now raise the self-diagnosing ambient error.

* fix(relay): partial IdP client credentials keep the loud error, never select ambient GET

The ambient-endpoint dispatch used 'not client_id or not client_secret',
so configuring exactly one credential (a mistyped client_credentials
setup) silently issued a GET at the IdP token endpoint and then raised
'no client_id/client_secret configured' — factually wrong for that
operator, and a stray request the old hard error never made.

Ambient mode now requires NEITHER credential; a partial pair raises
immediately, names the missing key, and issues no HTTP request (tests
assert urlopen is never called). Docstring and relay.md now say
'neither' instead of 'without'.

* fix(relay): ambient JSON envelope requires a string access_token, no coercion

Review finding (P2): the JSON-envelope branch accepted any truthy
access_token via str() coercion — a number became '12345…', a boolean
became 'True', an object became its Python repr — bypassing the fail-
closed contract and deferring the failure to the connector, where it
hides the real endpoint problem.

The envelope value must now be a non-empty string, the same contract the
client_credentials path enforces on its token response. Deliberately NO
shape gate on envelope values: an envelope is an intentional token
response (mode-1 symmetry), and opaque tokens may use the standard-base64
alphabet the raw-body gate rejects. Mutation check: reverting the branch
to str() coercion sends the 3 coercion tests red (3 failed, 15 passed).

---------

Co-authored-by: Ben Barclay <ben@nousresearch.com>
2026-08-12 10:06:28 +10:00
Trevin Chow c8f235a106 feat(gateway): allow selective multiplex profile serving 2026-08-10 22:48:24 -07:00
Eva acb7547dac fix(runtime): make nofile soft limit configurable 2026-08-10 17:02:56 -07:00
Gille ee4bb75b53 docs(teams): correct devtunnel webhook protocol 2026-08-11 04:17:50 +05:30
Teknium b614f70361 feat(kanban): teach workers to flag collision hotspots instead of piling on
Adds the comment-based hotspot convention (no new primitives) across three
guidance surfaces:

- KANBAN_GUIDANCE worker lifecycle: new step 7 — when a file keeps colliding
  with siblings or appears in other cards' recent comments, leave a
  'hotspot: <path> — <reason>' kanban_comment and repeat it in completion
  metadata so the orchestrator can decompose the file first.
- kanban.md (en + zh-Hans): 'Collision hotspots in parallel campaigns'
  subsection — the convention, the orchestrator response (2+ flags on one
  path => dedicated decomposition card before queuing more work touching
  it), and the cross-link to merge-reconciler for conflicts that already
  happened.
- merge-reconciler SKILL.md Pitfalls: repeated conflicts on the same file
  across rounds are a hotspot signal — flag for decomposition rather than
  serially reconciling.

Live-verified: guidance renders once via real import (6152 chars); hotspot
comment round-trips through add_comment -> list_comments -> worker context
on an isolated HERMES_KANBAN_DB; kanban tools, review-surfaces, and
merge-reconciler skill tests green (45 passed).
2026-08-10 13:11:19 -07:00
Teknium 11b0271243 feat(kanban): add split-brain decision-ownership contract to orchestrator guidance
Design decisions belong to the orchestrator: decide naming schemes,
schemas, file formats, and API shapes before fanning out; never let two
subtree cards decide the same question; stamp every decision into each
dependent card body since workers cannot see sibling context. Mirrored
in the kanban docs (en + zh-Hans) with an exporter/importer worked
example, and bounded KANBAN_GUIDANCE size with an invariant test.
2026-08-10 13:04:56 -07:00
Jakub Wolniewicz 0acf49b16f fix(kanban): isolate review handoff ownership 2026-08-10 12:43:46 -07:00
Jakub Wolniewicz 6d7e86c262 fix(kanban): enforce review lifecycle invariants 2026-08-10 12:43:46 -07:00
Jakub Wolniewicz 4ab998a7de fix(kanban): close review graph race gaps 2026-08-10 12:43:46 -07:00
Jakub Wolniewicz c230d1202f fix(kanban): clarify downstream review inspection 2026-08-10 12:43:46 -07:00
Jakub Wolniewicz 0fe4d90223 fix(kanban): harden review graph handoffs 2026-08-10 12:43:46 -07:00
Jakub Wolniewicz ae23b1f676 fix: complete kanban review lifecycle
Close the autonomous implement-review-rework loop, preserve parent gating and implementer provenance, distinguish downstream review cards, and surface legacy review dependency deadlocks immediately.

Co-authored-by: kaishi00 <6590895+kaishi00@users.noreply.github.com>
2026-08-10 12:43:46 -07:00
Nikita Barkov 16accefd2f feat(kanban): add first-class "review" handoff lifecycle
Add a non-terminal "review" status so a worker that finished implementation
can hand off for human review without abusing kanban_block. The old
kanban_block(reason="review-required: ...") convention routed the handoff
through the unblock-loop breaker, so a normal review -> changes -> review
cycle was falsely escalated to triage.

- kanban_db: request_review (running/ready -> review, non-block, emits
  review_requested), reopen_review_task (review -> ready/todo, review_reopened),
  complete_task accepts review -> done, and a review_dispatch gate (default off,
  shared by the dispatcher loop and the gateway health probe).
- kanban_request_review worker tool + `request-review` / `reopen-review` CLI
  verbs; tool wired through toolsets, EXPOSED_TOOLS, _POLISHED_TOOLS.
- Gateway notifier wakes the origin subscriber on review_requested and
  block_loop_detected; the subscription survives until done/archived, so every
  review cycle re-notifies.
- Dashboard PATCH + bulk route the review transitions (request_review /
  reopen_review_task) and render the review column.
- goals.py goal-loop and KANBAN_GUIDANCE recognize review as a terminator.
- Docs (reference tables, user guide, AGENTS.md, zh-Hans mirrors) + tests.

needs_input / failed are unchanged: they still route through kanban_block,
still count toward block_recurrences, and still escalate to triage.
2026-08-10 12:43:46 -07:00
Jeffrey Quesnelle 5b8cbd5ef2
Merge pull request #83404 from NousResearch/fix/blender-mcp-compromise
fix(security): remove blender MCP catalog entry and skill after upstream compromise
2026-08-10 15:30:33 -04:00
Teknium 8d8bc85dca feat(browser): make Browser Use mode the default browser backend
An unset browser.backend ("") now resolves to Browser Use mode whenever
the browser-use CLI is runnable (installed binary or uvx); otherwise the
built-in browser tools are kept so browsing never silently breaks.
Camofox setups always keep the built-in tools (no CDP surface), and
backend: off (including YAML 1.1 bare off -> False) forces the built-in
stack. hermes tools row highlighting follows the same effective-mode
resolution, and tests/tools/ pins CLI discovery off so host uvx installs
can't flip built-in-browser tests.
2026-08-10 12:28:10 -07:00
ethernet 37e46c774c cleanup: remove references to simple-term-menu
we migrated away long ago.
clean up all docs references the dependency itself
2026-08-10 15:13:29 -04:00
Hermes Agent bdbdfead04
fix(security): remove blender MCP catalog entry and skill after upstream compromise
The upstream ahujasid/blender-mcp and ahujasid/ableton-mcp GitHub repos
were hijacked on 2026-08-08: the maintainer (@sidahuj) publicly reported
his account was compromised and ownership stripped, and both repos now
redirect to an attacker-controlled org (MCPBlender, created the same
day, pushing new commits since).

Although our catalog pinned blender-mcp==1.6.4 from PyPI (pre-compromise,
sha256 verified unchanged), the server is only half the bridge: the
manifest's post-install instructions and the optional skill directed
users to download addon.py — arbitrary Python executed inside Blender —
from the now-compromised GitHub repo (the raw URL currently 404s, and
the addon ships in no PyPI artifact). There is no trustworthy source
for the addon half, so the entry cannot be installed safely end-to-end.

Removing the catalog entry and skill entirely until the maintainer
confirms account recovery; re-adding is a follow-up PR once upstream
is verified clean.

- optional-mcps/blender/: removed
- optional-skills/creative/blender-mcp/: removed
- docs: catalog rows, sidebar entry, skill pages (en + zh-Hans) removed
- cross-references in unreal-mcp and kanban-video-orchestrator cleaned
2026-08-10 12:12:11 -07:00
Teknium e5bc6b2186 fix(attribution): correct AI_AGENT id to registry value and carry harness markers into all terminal backends
The Hugging Face agent-harness registry matches standard-var values
EXACTLY against the harness id. Our registry id is 'hermes-agent'
(huggingface.js agent-harnesses.ts), so AI_AGENT=hermes was counted as
'unknown' — fixed at both entry points.

Remote terminal backends (Docker/SSH/Modal/Daytona/Singularity/Vercel)
never inherit the Hermes process env, and the cross-session leak guard
deliberately strips HERMES_SESSION_* from subprocess envs in engaged
multi-session hosts — so hf/huggingface_hub traffic from those shells was
unattributable. _wrap_command now exports AI_AGENT/HERMES_AGENT inside
every wrapped command with ${VAR:-default} semantics (outer harness is
never clobbered), and the snapshot dump excludes both names so a baked
value can never shadow a later outer harness.

E2E: verified against real huggingface_hub 1.27.0 detect_agent() with a
cached registry — 'hermes-agent' detected via AI_AGENT and via
HERMES_SESSION_ID; old 'hermes' value reproduced the 'unknown' bug.
2026-08-10 11:07:22 -07:00
Teknium e47a931d33 Port from earendil-works/pi#7493: advertise AI_AGENT env var for child-process attribution
CLI and gateway entry points now set AI_AGENT=hermes (the emerging
cross-agent standard read by e.g. huggingface_hub agent detection) and
HERMES_AGENT=true, via setdefault so an outer harness is never
clobbered.
2026-08-10 11:07:22 -07:00