Commit Graph

10038 Commits

Author SHA1 Message Date
Zeraphim e050ca97ff test(background-review): reanchor unresolved-failure coverage 2026-07-31 22:33:03 -07:00
Zeraphim 2ace68ad37 fix(background-review): reject unresolved failures as skills 2026-07-31 22:33:03 -07:00
spfcraze b004041498 fix(cron): close GitHub auth-header exemption abuse in prompt scanner
Two holes in _strip_cron_safe_constructs (one a regression from
70411a615, two days old):

1. The [^\n]* tail erased everything after api.github.com on the line,
   so a payload smuggled after ; && or | was never scanned. A cron
   prompt carrying a benign-looking GitHub curl followed by
   'cat ~/.hermes/.env' or 'rm -rf /' passed the scanner and persisted
   (verified end-to-end through the cronjob tool). Bound the tail to
   the URL path ([^\s;&|]*), so same-line payloads survive the strip.
2. The (?:/|\b) host boundary treated lookalike authorities
   (api.github.com.evil.com, api.github.com@evil.com) as the trusted
   GitHub construct, erasing even exfil of the GitHub token itself to a
   non-GitHub host. Require the exact host followed by /, whitespace,
   or end.

Also add SSH private-key files to the read_secrets pattern — a
coverage gap found during adversarial testing (cat ~/.ssh/id_rsa was
invisible to the scanner even outside the exemption).
2026-07-31 22:33:00 -07:00
Xipong 0af8fb05bf fix(delegation): prevent child HERMES_SESSION_ID leak into parent process env
AIAgent.__init__ calls set_current_session_id(self.session_id), which
mutated both the task-local ContextVar and the process-global os.environ.
Because _build_child_agent wraps construction in delegated_child_context(),
the ContextVar write is harmless (task-local), but the os.environ write
clobbered the parent's HERMES_SESSION_ID for the rest of the process —
leaking the child id into parent tools and subprocesses spawned after
the child was built.

Root cause of HermesPRDelegationSessionContext: parent
20260729_212118_5d797e dispatched child 20260730_160515_736ea1; later
parent terminal inherited HERMES_SESSION_ID=the child.

Fix: set_current_session_id() skips the process-global os.environ write
when called from within a delegated_child_context(). The child's own
tools and subprocesses still resolve their id through the ContextVar
(task-local), while the parent's process-wide env keeps the parent's
session identity. Root agents (CLI, gateway, cron) retain both paths.

Adds 7 regression tests covering single child, concurrent children (8
parallel), parent-tool observation after construction, and root-agent
session rotation backward compatibility. All pass; ruff clean.
2026-07-31 22:32:55 -07:00
Xipong abd10ba7c9 test(agent): cover malformed steer budget path 2026-07-31 22:32:52 -07:00
Xipong 0fd0db1a8c fix(agent): preserve /steer through turn-budget enforcement 2026-07-31 22:32:52 -07:00
praneshnikhar 35b44e0d5f fix(auth): apply same source-path write-through fix to non-pool xAI path
_save_xai_oauth_tokens had the identical self-sealing bug as
_sync_device_code_entry_to_auth_store: key-presence check before
_store_provider_state, which unconditionally creates the key.
Use _load_provider_state_with_source to decide write-through from
the actual grant source, not key presence.

Also update regression test per review: use the real
_write_through_provider_state_to_global_root helper and assert
rotated token pair values in the root store after each refresh
instead of just counting mock calls.
2026-07-31 22:32:48 -07:00
praneshnikhar 4e6299af48 fix(credential_pool): use source-path-based write-through to root (#74339)
_sync_device_code_entry_to_auth_store used key-presence on the profile
store to decide whether to write-through rotated tokens to the global
root.  _store_provider_state unconditionally creates that key, so every
refresh after the first self-disabled the write-through — root kept a
revoked refresh token and every other profile died with
refresh_token_reused / invalid_grant.

Fix: use _load_provider_state_with_source to learn where the grant was
resolved from.  When the source is the global root, write back only to
root and skip _store_provider_state so the profile never accrues a
shadowing providers.<id> key that blocks future root fallback.

Add regression test verifying write-through fires on refresh 2+, not
just the first call.
2026-07-31 22:32:48 -07:00
Gille 29eac371d1 fix(context): persist NVIDIA DeepSeek endpoint limit 2026-07-31 22:31:22 -07:00
Teknium 1737741730 fix(copilot): follow-ups for salvaged PR #58743
- Bound ALL reads of the on-disk JWT store through one _read_jwt_store()
  helper (load, eviction, save-merge) — the 1 MiB cap previously only
  covered the load path; eviction and save could still parse an
  oversized/corrupt store and rewrite it back out (sweeper finding).
- Fix the class, not the site: the recovery gates checked the literal
  provider == "copilot" while /model and profile configs can leave the
  alias spelling in place (the reporter's own log shows provider=copilot
  AND provider=github-copilot in one session — the aliased turns would
  have silently skipped recovery). Single owner:
  AIAgent._is_copilot_provider() (slug aliases + Copilot base-URL
  fallback), used by both run_agent recovery methods and both
  conversation_loop gates.
- Update the salvaged 401 test to current main's client-retirement
  contract (release deferred to GC — no synchronous .close()).
- Add copilot_stale_cred_retry_attempted to the TurnRetryState field
  contract test; add bounded-store and alias-gate regression tests.
2026-07-31 22:31:09 -07:00
dstkwll 7779409a76 fix(copilot): recover from stale/degraded token 400 AND expired IDE-token 401
Copilot degrades in two related ways that both abort a turn as non-retryable
and only clear on a gateway restart (a cold process re-runs the token exchange):

1. HTTP 400 model_not_available_for_integrator / model_not_supported — a
   raw/degraded token routes to the restricted copilot-language-server
   integrator whose allowlist omits enterprise-only models (e.g.
   claude-opus-4.8). Because it is a 400 (not 401), the existing 401 refresh
   path never fired. Prevented (retry-with-backoff exchange + on-disk JWT
   persistence + header guard at the client chokepoint) and self-healed at
   runtime (single-shot forced re-exchange + client rebuild + retry before
   fallback).

2. HTTP 401 'IDE token expired: unauthorized: token expired' — the short-TTL
   *exchanged* IDE token expires mid-turn. The clean-401 path DID fire and call
   _try_refresh_copilot_client_credentials(), but that method only re-resolved
   the stable raw ghu_ token and rebuilt the client — it never evicted the
   cached exchanged JWT or forced a fresh exchange, so the retry put the SAME
   expired token back on the wire, 401'd again, and the single-shot guard
   aborted the turn. Fix: force a fresh IDE-token exchange (evict cached JWT via
   evict_cached_exchanged_token + re-mint via get_copilot_api_token) before the
   client rebuild, mirroring the merged auxiliary-path recovery (#59837) and the
   400 recovery in this same PR. Graceful fallback to the resolved token if the
   exchange endpoint is unreachable; picks up the enterprise base_url on
   re-exchange.

Brings main-loop clean-401 recovery to parity with the merged auxiliary path
(#59837), using the newer on-disk-aware evict helper. Companion context: #58743
(this PR, expanded), #51313, #63204 (which assumed the 401 path already
recovered — it reached the method but the method was too weak).

Tests: exchange retry/persist round-trip, restart-blip disk reuse, stale-cred
400 classifier, 400 recovery, and 3 new 401 cases (fresh exchanged token on the
wire; network-blip fallback to resolved token). 58 copilot tests green on
current main.
2026-07-31 22:31:09 -07:00
Teknium df8e42877b
Merge pull request #75852 from NousResearch/fix/moa-completed-response-streaming-cluster
fix(moa): stream completed aggregator responses across all layers (#74031 + #74903 + #74543)
2026-07-31 22:30:47 -07:00
AKAZIK-py fdfddb55cb fix(moa): carry completed responses through the managed Relay path
Under managed Relay execution the provider factory runs lazily inside
provider_stream() on the Relay session's event loop. The MoA facade's
auxiliary call_llm(stream=True) is invoked from that callback, so the
eager final_response check added for the non-managed path never fires:
the inner ManagedLlmStream is returned to the outer stream, which then
synchronously iterates it on the same loop thread and dies with
RuntimeError: Cannot run the event loop while another loop is running
(the completed response effectively trapped one level deeper).

stream_current() now detects a running event loop and returns the raw
factory result instead of nesting a ManagedLlmStream: the outer managed
stream already provides Relay tracking for the enclosing attempt, and
its own completed_response_predicate traps the completed response as
final_response — the same contract the main streaming worker consumes
(chat_completion_helpers reads stream.final_response after the chunk
loop). Nested managed streams remain supported for genuinely streaming
providers via the outer stream's own iteration.

Adds managed-execution regressions using the retained relay_turn
fixture: direct completed-response trapping, and the nested
facade-shaped stream_current call.
2026-07-31 22:30:33 -07:00
AKAZIK-py 8fde4ff9d8 test(moa): cover call_llm(stream=True) completed-response unwrap at the outermost seam 2026-07-31 22:30:33 -07:00
AKAZIK-py ada3663ce7 fix(moa): unwrap completed responses in the auxiliary streaming path 2026-07-31 22:30:33 -07:00
Teknium ed77a34730 fix(update): make the ancestor-PID lock handoff cross-platform via psutil
The stale-staged-updater deadlock is not Windows-specific: hermes-setup
under ~/.hermes is only refreshed by a full installer run
(copy_self_to_hermes_home no-ops during --update), so every desktop whose
staged updater predates the HERMES_UPDATE_HANDOFF_PID export (8c76fe19)
runs an old parent that never sends the env var against a new child that
demands it — exit 2 ('Hermes is still running') forever, on macOS and
Linux just as on Windows.

Replace the wmic ancestry walk (deprecated, absent on current Win11,
GBK decode juggling) with psutil.Process().parents() — psutil is already
a hard dependency and is the project's canonical no-kill process probe.
Drop the os.name == 'nt' gate so all platforms heal. Add tests: a marker
owned by our parent process is recognized as our orchestrator; a live
non-ancestor holder is still refused.
2026-07-31 22:28:46 -07:00
Teknium 859573d283 test: import LAZY_DEPS directly and make httplib2 pin a floor invariant
Replace the AST source-parse of tools/lazy_deps.py with a real import
(the module is importable; only setup.py legitimately needs AST since
it is a side-effectful standalone script), and convert the exact
httplib2==0.32.0 snapshot assertion into a >=0.32.0 floor so routine
future bumps don't break the test.
2026-07-31 22:28:21 -07:00
Yorkstone Supplies (sycamoregroupltd) 37e42808e7 fix(security): pin httplib2==0.32.0 in setup.py REQUIRED_PACKAGES (GHSA-j5g9-f88f-gfj3)
The previous fix (904ade32b) pinned httplib2==0.32.0 in pyproject.toml's
google extra and tools/lazy_deps.py's skill.google_workspace, but missed
a third install path: skills/productivity/google-workspace/scripts/setup.py
REQUIRED_PACKAGES. A user following the --install-deps path could still
resolve httplib2 via unpinned ranges.

This commit:
1. Exact-pins all four Google packages in REQUIRED_PACKAGES to match
   pyproject.toml and lazy_deps.py contracts exactly.
2. Adds a focused regression test that parses setup.py's REQUIRED_PACKAGES
   via AST and asserts every pin matches the other two install paths.

Changelog: fix(security), test(security)
2026-07-31 22:28:21 -07:00
Kyle 48ded07155
fix(codex): handle completed auxiliary responses 2026-07-31 21:52:36 -07:00
knocksen 743c4906d9
fix(moa): restore a valid preset after fallback model drift
build_moa_facade() reused agent.model as the preset name; a session
that had drifted to a fallback model crashed on restore with
MoAPresetNotFoundError. Validate the resolved preset against the
configured presets and fall back to the default preset.

Salvaged from PR #74903 by @liusencomic-cyber.
2026-07-31 21:52:36 -07:00
knocksen 716d274f58
test(moa): cover direct provider streaming for Codex-shim aggregators
Narrow the moa_aggregator Relay bypass to CodexAuxiliaryClient and add
coverage that call_llm(stream=True) returns the provider's direct
create() result for Responses-shim clients.

Salvaged from PR #74903 by @liusencomic-cyber.
2026-07-31 21:52:35 -07:00
knocksen 8e191af0fb
fix(moa): stream completed aggregator responses safely
Convert a completed MoA aggregator response into one valid Chat
Completions delta chunk at the MoA facade boundary, normalize completed
message.tool_calls into indexed stream deltas, and classify these local
MoA adapter-shape errors as non-fallback format errors so a local
compatibility bug cannot silently drift the user's MoA route to a
single model (#55933 follow-up).

Salvaged from PR #74903 by @liusencomic-cyber.
2026-07-31 21:52:35 -07:00
AKAZIK-py c23ff21d7c
fix(moa): carry completed responses through the managed Relay path
Under managed Relay execution the provider factory runs lazily inside
provider_stream() on the Relay session's event loop. The MoA facade's
auxiliary call_llm(stream=True) is invoked from that callback, so the
eager final_response check added for the non-managed path never fires:
the inner ManagedLlmStream is returned to the outer stream, which then
synchronously iterates it on the same loop thread and dies with
RuntimeError: Cannot run the event loop while another loop is running
(the completed response effectively trapped one level deeper).

stream_current() now detects a running event loop and returns the raw
factory result instead of nesting a ManagedLlmStream: the outer managed
stream already provides Relay tracking for the enclosing attempt, and
its own completed_response_predicate traps the completed response as
final_response — the same contract the main streaming worker consumes
(chat_completion_helpers reads stream.final_response after the chunk
loop). Nested managed streams remain supported for genuinely streaming
providers via the outer stream's own iteration.

Adds managed-execution regressions using the retained relay_turn
fixture: direct completed-response trapping, and the nested
facade-shaped stream_current call.
2026-07-31 21:52:35 -07:00
AKAZIK-py 52705e496f
test(moa): cover call_llm(stream=True) completed-response unwrap at the outermost seam 2026-07-31 21:52:35 -07:00
AKAZIK-py 654915f187
fix(moa): unwrap completed responses in the auxiliary streaming path 2026-07-31 21:52:35 -07:00
Gille 991f5f1e9e fix(kanban): deliver notifications from non-dispatch gateways 2026-07-31 21:52:11 -07:00
Victor Kyriazakos 008f1efe08 refactor(providers): delegate is_official_openai_host to base_url_host_matches
Independent review pass: utils.base_url_host_matches already owns the
exact-or-dot-suffix hostname contract (userinfo/port stripped, lowercased,
trailing dot removed), so the predicate delegates instead of hand-rolling
a second suffix match to keep in sync. Also locks in the normalization
behavior the review verified empirically: uppercase+port, trailing-dot,
userinfo-stripped, and IPv6-literal cases added to the contract tests.
2026-07-31 21:31:56 -07:00
Victor Kyriazakos 173a73e191 fix(models): honor model.base_url in OpenAI discovery, cache identity, and listing authority
Three catalog-side defects from the same report, all downstream of the
exact-host assumption and the config/env asymmetry:

- Discovery read only $OPENAI_BASE_URL, so a config-set
  model.base_url (the supported way to select a data-residency host)
  was ignored and /model listed the catalog of api.openai.com, not the
  configured endpoint. New _openai_discovery_base_url() resolves
  env override -> matching model.base_url -> canonical default, the same
  precedence inference uses.

- _credential_fingerprint() hashed env vars only, so hermes config set
  model.base_url kept serving the previous endpoint's cached catalog
  until TTL expiry. The effective endpoint is now folded into the
  fingerprint for openai/openai-api.

- is_default_openai matched two literal URLs, so regional hosts (which
  serve the identical 120+ entry dump) bypassed the curated intersection
  and flooded the picker with whisper/tts/embedding/dall-e rows. Now uses
  the shared official-host predicate; custom OpenAI-compatible proxies
  keep the verbatim live list.

- validate_requested_model's curated-catalog soft-accept (#46850) no
  longer applies on official OpenAI hosts: their /v1/models listing is
  access-scoped and authoritative, so accepting an absent model
  manufactures a selection that 400s at first use. Custom proxies and
  other providers keep the #46850 fallback. The #37404
  empty-intersection -> curated picker fallback is deliberately left
  unchanged.
2026-07-31 21:31:56 -07:00
Victor Kyriazakos 33a2f29a63 fix(runtime): fall back to the provider's declared transport, not chat_completions
The P1 from the enterprise data-residency report: with
model.base_url=https://us.api.openai.com/v1, every tool-calling turn 400'd
('Function tools with reasoning_effort are not supported ... use
/v1/responses') because the runtime resolvers hardcoded
api_mode=chat_completions and consulted URL detection only. openai-api
declares codex_responses in its overlay; the declaration was never
consulted, so any OpenAI host that wasn't literally api.openai.com landed
on the wrong wire protocol.

New _fallback_api_mode(provider, base_url, model): URL detection first
(host-mandated wire shapes keep priority), then
providers.determine_api_mode() (the provider's declared transport), then
chat_completions only for genuinely unknown providers. All three runtime
fallback sites route through it: the pool-entry path, the explicit-runtime
path, and the API-key-provider path, so the lanes cannot drift apart.

Blast radius beyond openai-api: minimax, minimax-cn, and copilot-acp were
the other overlays whose declared non-chat transport fell through to
chat_completions on the same paths (same latent bug class). openrouter is
unaffected (declares openai_chat). _detect_api_mode_for_url also now uses
the shared official-host predicate, so regional hosts detect as
codex_responses on the direct-URL lane too.
2026-07-31 21:31:56 -07:00
Victor Kyriazakos 564e9b90af fix(providers): recognize OpenAI data-residency hosts via one shared predicate
Pointing openai-api at OpenAI's documented regional hosts
(us.api.openai.com / eu.api.openai.com, mandatory for customers with
data-residency obligations) silently degraded Hermes because three
subsystems tested 'is this OpenAI' with exact-hostname equality against
api.openai.com.

Adds providers.is_official_openai_host(): canonical host plus dot-suffix
subdomains of api.openai.com, hostname-parsed only. Lookalike hosts
(api.openai.com.attacker.test) and path spoofs (proxy.test/api.openai.com/v1)
stay rejected, preserving the #32243 hardening: a genuine *.api.openai.com
subdomain requires control of openai.com DNS.

host_mandated_api_mode() now routes through the predicate, so regional
hosts mandate codex_responses exactly like the canonical host.
2026-07-31 21:31:56 -07:00
teknium1 dc87d15586 feat(terminal): raise Docker sandbox /dev/shm to 1g by default (configurable)
Port from nanocoai/nanoclaw#2748: Docker's built-in 64 MB /dev/shm silently
breaks shared-memory-hungry workloads inside the sandbox — Chromium/Playwright
renderers crash tabs, and PyTorch DataLoader workers die with 'bus error' /
'insufficient shared memory'. tmpfs is lazily allocated, so the higher ceiling
costs nothing until actually used, and usage still counts against the
container's --memory cgroup limit.

- tools/environments/docker.py: --shm-size 1g in resource args (not
  cgroup-gated; tmpfs mount option). Skipped when docker_extra_args already
  sets --shm-size, or when configured empty/'0' (Docker default).
- terminal.docker_shm_size config key (DEFAULT_CONFIG + all three
  config->TERMINAL_DOCKER_SHM_SIZE env bridges: CLI, gateway, config.py map)
- tests: default emit, custom value, opt-out, extra_args precedence,
  helper edge cases (sabotage-verified: default/custom tests fail without
  the emit)
2026-07-31 21:31:51 -07:00
teknium1 950fe236d0 fix(security): extend secret redaction to GitLab token families
Port from openclaw/openclaw#112954. The redactor knew GitHub, Slack,
Google, Stripe, AWS access-key-ID and ~25 other vendor prefixes but had
zero GitLab coverage — glpat-/gloas-/gldt-/glrt-/glrtr-/glcbt-/glptt-/
glft-/glimt-/glagent-/glsoat-/glffct-/glwt- tokens and legacy GR1348941
runner registration tokens passed through display and log surfaces
verbatim. Follow-up explicitly invited when #4541 was closed.

Each pattern keeps a full literal prefix so the _PREFIX_SUBSTRINGS
pre-screen (derived at module load) stays false-negative-free; routable
runner tokens allow dotted segments. Sibling site: skills_guard's
credential-exposure scan gains a gitlab_token_leaked pattern.
2026-07-31 21:31:10 -07:00
teknium1 9704ed86c1 feat(cli): ! shell mode — run a command without spending a model turn 2026-07-31 21:21:20 -07:00
teknium1 5686ea43d4 test(stash): drop source-text keybinding assertions (banned antipattern)
Two tests read cli.py's source to prove handlers exist. Root AGENTS.md bans
that outright: it passes when a handler is wired wrong and fails on a correct
rename. The #4771 rebase-loss regression is guarded by the state-machine
tests every handler delegates to.
2026-07-31 21:21:16 -07:00
teknium1 a55a52c72f feat(cli): complete the Ctrl+S prompt stash — keybinding, state machine, tests
Finishes the input stash started in the preceding commit from PR #4771.
That PR shipped only the panel renderer: its `@kb.add('c-s')` handler and
stash-state initialization were lost in a rebase, so the panel predicate
read undefined `_stash_panel_open` / `_stash_list` and the feature was
unreachable. This adds the missing half and the tests the PR never had.

Resolves the review feedback on #4771:

- Rebuilt the stash on current main's keybinding setup. The `c-s` key was
  unbound repo-wide, so there is no conflict.
- Extracted the state machine into `hermes_cli/prompt_stash.py` as pure
  functions (no prompt_toolkit import) so it is directly unit testable —
  the PR was cli.py-only with zero tests.
- Dropped the PR's unrelated changes: delegation `supervisor_model` /
  `execution_model` config aliases, and stale reverts of the banner
  builder, worktree pruning, logging setup, and MCP toolset validation
  that its 14k-commit-old base dragged along.
- Fixed the 📌 double-width measurement for real. Three commits in the PR
  ("subtract 1 from len()", "use bare len()", "subtract 1 again") were
  chasing this by tweaking `len()`; all horizontal math now goes through
  `_status_bar_display_width` (prompt_toolkit `get_cwidth`), which also
  keeps CJK previews inside the border. Narrow terminals fall back to
  compact header/footer labels instead of overflowing — caught by a
  parametrized width test, not by eyeballing.

Gesture (the contributor's design, kept):

- Composer has content → push onto the stash, clear the input.
- Composer empty, one stashed → pop it straight back.
- Composer empty, 2+ stashed → open the browse panel (↑↓ / Enter / D / Esc).
- Panel open → Ctrl+S closes it.

Pushing onto a stack rather than a single slot is what makes repeated
Ctrl+S safe: a second stash never silently overwrites the first, and with
2+ parked the panel asks rather than guessing which to restore. A `📌 N`
status-bar badge and a composer placeholder advertise the parked draft so
it cannot be silently forgotten.

Deliberate departures from the PR:

- No auto-restore after the agent responds, and no `display.stash_auto_restore`
  config key. The PR itself had already defaulted this to false as
  "avoids surprising the user"; a keystroke the user pressed should not
  cause text to reappear on its own, so the dead default is dropped
  rather than carried as config surface.
- Nothing is persisted to disk. Drafts routinely contain pasted
  credentials and NDA material, so the stash is session-scoped and
  in-memory only. Any future persistence must route through
  `get_hermes_home()`.
- Suppressed while a modal prompt owns the composer (sudo / secret /
  approval / clarify / slash-confirm / model picker) so Ctrl+S can never
  stash a password.
- Restoring images extends `_attached_images` instead of replacing it, so
  an attachment added since the stash was taken is not silently dropped.
- `buf.reset()` on stash (not `text = ""`) clears completion state,
  selection, and undo stack with the text.

Tests: 95 new tests across two files — 66 on the state machine (empty
buffer is a no-op, exact round-trips including newlines/tabs/CJK/fences,
no-clobber ordering, cap eviction, indicator states, panel cursor
clamping and deletion, the full resolve_ctrl_s decision table) and 29 on
the cli.py wiring (per-instance stash, keybinding registration guard,
layout slot, panel bounded at 8 widths, status-bar indicator lifecycle).
The keybinding-registration test asserts the `c-s` handler exists in
source specifically so the rebase loss that broke #4771 cannot recur.

Verified: 153 passed, 0 failed across the two new files plus
tests/cli/test_cli_init.py and tests/cli/test_cli_extension_hooks.py.
ruff check clean; check-windows-footguns clean.

Docs: Ctrl+S added to the CLI keybindings table.

Co-authored-by: CK iRonin.IT <cyprian@ironin.pl>
2026-07-31 21:21:16 -07:00
teknium1 7fb5d2bc39 fix(process): decode background process output with incremental UTF-8 decoders
Port from openclaw/openclaw#112325: multibyte UTF-8 characters split
across a 4096-byte pipe or PTY read boundary were decoded statelessly
per chunk with errors='replace', corrupting both halves into U+FFFD
mojibake in background process output (poll/log/wait/completion
notifications). The foreground path already used an incremental decoder
(tools/environments/base.py::_wait_for_process); this applies the same
treatment to the background reader loops:

- _reader_loop (select and blocking paths): one
  codecs.getincrementaldecoder('utf-8') per reader holds partial
  sequences across chunks; the finally block flushes a truncated tail
  as a single U+FFFD instead of dropping it.
- _pty_reader_loop: same treatment for ptyprocess byte chunks
  (pywinpty str chunks pass through unchanged).

Genuinely invalid bytes keep errors='replace' behavior.
2026-07-31 21:21:13 -07:00
Teknium 89f920901b feat(mcp): warn on hidden whitespace in MCP config values
Inspired by Claude Code v2.1.219: MCP config string values with hidden
leading/trailing whitespace (pasted tokens with trailing newlines, URLs
with leading spaces) now trigger a startup warning naming the server and
the dotted key path, instead of failing later as an opaque auth/connect
error.

Advisory only: values are never mutated, secrets are never logged (only
key paths), and warnings dedupe to once per process per (server, path).
Checked after ${VAR} interpolation so whitespace inside referenced env
vars is caught too.
2026-07-31 21:21:10 -07:00
Brooklyn Nicholson 2b039d90e3 test(gateway): cover the session.reclaimed broadcast contract 2026-07-31 23:04:44 -05:00
Austin Pickett e444d16580
fix(vision): make desktop image uploads reachable from profile Docker sandboxes (#69575) (#75671)
* fix(vision): mount images/ upload dir into sandboxes and permit host read (#69575)

Desktop, clipboard, and PDF uploads land in the flat top-level
HERMES_HOME/images/ dir, but Docker sandboxes only mounted the cache/
subtree and the vision resolver only permitted host reads from the media
caches. So vision_analyze on any desktop-app upload failed under a Docker
backend with "not reachable inside the sandbox".

- Add ("images", "images") to _CACHE_DIRS so the uploads dir is bind-mounted
  into sandbox containers through the existing profile-scoped cache-mount and
  reverse-mapping mechanism.
- Add home/"images" to _media_cache_roots() so the non-local host-read
  allowlist permits reading uploads directly from the host filesystem.
- Cover the mount entry, the container path mapping, and the Docker-mode
  resolver read for a profile-scoped upload.

Co-authored-by: JonthanaHanh <92574114+JonthanaHanh@users.noreply.github.com>
Co-authored-by: webtecnica <75556242+webtecnica@users.noreply.github.com>

* fix(tui_gateway): write image uploads under the session's profile home (#69575)

The attach RPCs (image.attach_bytes, clipboard.paste, pdf.attach) wrote
uploads to the gateway's module-cached launch home via _hermes_home/"images".
Those RPCs run before prompt.submit installs the session's profile HERMES_HOME
override, so in a multi-profile / root-gateway deployment the file landed in
the launch home while the sandbox mount and the vision host-read allowlist
both resolve the session profile's images/ at run time — the agent could
never see the upload it was handed.

Add _session_images_dir(session), which anchors the write on the session's
stored profile_home when present (matching the mount/read scope) and falls
back to the launch home otherwise. Route both write sites through it, keeping
per-profile isolation.

Co-authored-by: webtecnica <75556242+webtecnica@users.noreply.github.com>

---------

Co-authored-by: JonthanaHanh <92574114+JonthanaHanh@users.noreply.github.com>
Co-authored-by: webtecnica <75556242+webtecnica@users.noreply.github.com>
2026-07-31 17:43:37 -04:00
brooklyn! 4b60979dc1
Merge pull request #75583 from NousResearch/bb/hide-kanban-worker-sessions
Kanban worker runs stop appearing as chats in the sidebar
2026-07-31 14:09:01 -05:00
Brooklyn Nicholson c2872cf53b fix(kanban): key the worker-session retag per board, not per database
The retag gate was global, so once one board reclaimed its legacy rows a
second board on the same state.db never got swept. Key the state_meta gate
on the workspaces root and skip reopening state.db on every spawn via an
in-process set. Align the dispatcher-spawn test with the worker's own
`kanban` source tag and cover the per-board gate.
2026-07-31 14:03:32 -05:00
Ben Barclay 4a8eeb5d1c
fix(gateway): relay semantic thread rename — register eagerly, poll send-result feedback at fire time (#75581)
Staging re-test (2026-07-31, post-74482 image roll): auto-created
threads still stuck on their initial titles; connector telemetry shows
zero thread_rename ops. Root cause is an ordering flaw in the 74482
consume path: BOTH the title-callback registration gate and the
schedule gate read the send-result feedback cache
(_relay_auto_thread_info) — but registration runs BEFORE delivery on
the non-streaming lane, and the auto-title thread races delivery even
when registration survives. The cache read can only succeed AFTER the
connector answers the send, so the rename lane deterministically
disqualified itself on the title turn.

Fix — decide shape early, facts late:
- New _is_relay_discord_channel_lane: SHAPE-only predicate (relay
  Discord channel event, no thread) used by the registration and
  schedule gates; no cache read before delivery.
- _rename_discord_auto_thread_for_session_title: on the relay lane,
  poll the adapter's feedback cache (0.5s ticks, ≤10s) — delivery is
  typically right behind the title. True miss (connector didn't
  auto-thread: policy off, DM, send failed) no-ops exactly as before.

Tests: shape-gate matrix; late-arriving feedback -> rename fires with
only_if_current_name guard; never-arriving feedback -> no-op. Relay
suite 174 passed.
2026-07-31 11:55:05 -07:00
Brooklyn Nicholson 805c483ca5 test(kanban): cover worker session tagging and retag 2026-07-31 13:53:04 -05:00
ethernet 6ecd335aa8
Merge pull request #75037 from NousResearch/sec-fixes
fix(sec): patch vulnerable deps + add publication-age floors and npm script allow-list

Co-authored-by: Kingsley Wong <7207924+datanerdie@users.noreply.github.com>
Co-authored-by: viky <vikyw89@gmail.com>
Co-authored-by: FT_IOxCS <237263164+ft-ioxcs@users.noreply.github.com>
Co-authored-by: 方明元 <fmy3@qq.com>
Co-authored-by: Yorkstone Supplies <58149681+sycamoregroupltd@users.noreply.github.com>
Co-authored-by: Steven Cuz Leath <Steven.Leath@gmail.com>
Co-authored-by: Kyle French <248366920+Dadmin88@users.noreply.github.com>
Co-authored-by: Eugeniusz Gilewski <egilewski@egilewski.com>
Co-authored-by: Christopher Gara <79837758+christopherrobin88@users.noreply.github.com>
Co-authored-by: LironTTG <147833337+LironTTG@users.noreply.github.com>
Co-authored-by: Austin Porada <bbasketballer75@gmail.com>
Co-authored-by: cresslank <9219265+cresslank@users.noreply.github.com>
Co-authored-by: Ion Mudreac <mudreac@gmail.com>
Co-authored-by: martinramos002 <262243228+martinramos002-bot@users.noreply.github.com>
Co-authored-by: Sensie-Agents <agents@joinsensie.com>
Co-authored-by: alexwill87 <173086651+alexwill87@users.noreply.github.com>
Co-authored-by: BullishMomentum56 <218643122+BullishMomentum56@users.noreply.github.com>
Co-authored-by: pintadoai <240097310+pintadoai@users.noreply.github.com>
Co-authored-by: Alfred Sahlberg <dinmail@gmail.com>
Co-authored-by: liuhao1024 <sunsky.lau@gmail.com>
Co-authored-by: Richard Ham <richard.ham@live.com>
Co-authored-by: jrcrittenden <jrcrittenden@gmail.com>
Co-authored-by: 峯岸 亮 <1920071390@campus.ouj.ac.jp>
Co-authored-by: Marcus Martini <6473852+napoleonmm83@users.noreply.github.com>
2026-07-31 14:07:32 -04:00
brooklyn! 0324849fe4
Merge pull request #61173 from NousResearch/bb/desktop-kanban
feat(desktop): Kanban — the founding plugin on the desktop SDK
2026-07-31 13:00:10 -05:00
ethernet e803c5aeac fix(npm): self-upgrade a managed npm when engines.npm rejects it
The repo's .npmrc sets engine-strict=true and package.json pins
engines.npm, so an npm outside that range aborts every npm ci /
npm install we run inside the checkout:

    npm error code EBADENGINE
    npm error notsup Required: {"npm":"<11.10.0 || >=12.0.0"}
    npm error notsup Actual:   {"npm":"11.10.0"}

Our callers made that worse: _run_npm_install_deterministic sees
`npm ci` fail and falls through to `npm install`, which fails
identically, so the user got a buried EBADENGINE and no remedy.

React to the failure instead of predicting it. npm states the
required range in its own error, so there is no need for a version
probe on the happy path or a semver range matcher — the recovery
reads the constraint out of the output it just produced, upgrades,
and retries once.

Scope is deliberately narrow. Hermes only upgrades an npm inside its
own managed Node tree ($HERMES_HOME/node), installing with --prefix
so bin/npm keeps resolving to the upgraded lib/node_modules/npm; a
managed install writes prefix=~/.local into node/etc/npmrc, so
without the override the "upgrade" would land elsewhere while the
managed npm stayed stale. A system / nvm / brew / Nix npm belongs to
the user, so that case prints the exact command and lets the original
failure stand.

The upgrade runs from a temp cwd with npm_config_min_release_age=0,
otherwise the checkout's own min-release-age gate would refuse the
npm release we need.

_run_npm_install_deterministic's capture_output=False callers (the
desktop install) streamed npm output and returned stderr=None, which
would leave the recovery nothing to read — stderr is now teed, so
live output is unchanged and the text stays inspectable.

Verified end to end against real npm binaries on copies of a managed
tree: managed npm 11.10.0 -> EBADENGINE -> upgraded to 12.0.2 ->
retry exits 0; a foreign npm 11.10.0 hard-fails with the manual
command and is left untouched.
2026-07-31 13:42:04 -04:00
ethernet a7efeb0829 fix(sec): update mcp to 1.28.1
mcp 1.26.0 has 3 known vulnerabilities: PYSEC-2026-3481,
PYSEC-2026-3482, PYSEC-2026-3483

they're fixed in >= 1.28.1
2026-07-31 13:42:03 -04:00
Yi Lok Enoch Lam 5835201de1
fix: keep queued paste payloads atomic (#74797)
Co-authored-by: eloklam <22125285+eloklam@users.noreply.github.com>
Co-authored-by: Orca <help@stably.ai>
2026-07-31 12:04:59 -04:00
rob-maron 126ff7071b
Portal free user vision fix + flux3 polling improvements (#75448)
* flux3 polling improvments

* poll gap to 4s

* back to 5s

* vision model fix

* minor fix
2026-07-31 10:17:55 -04:00
Austin Pickett 74fdc578cc fix(cron): set headers for chronos JWKS requests
The chronos cron-fire verifier constructed PyJWKClient without explicit
headers, so its JWKS fetch to the NAS portal hit the same WAF 403 the
dashboard-auth providers already guard against. It reaches the same
portal issuer, so it's the same bug class — mirror the fix here and add
a constructor-contract regression test.

Co-authored-by: James Hodgkinson <james@terminaloutcomes.com>
2026-07-31 10:17:30 -04:00