Commit Graph

14648 Commits

Author SHA1 Message Date
kshitijk4poor d72cbbcf5a test(docker): lockdown + operator --network none emits one flag; contradictory network fails closed
Trimmed from the contributor's five tests to the two contracts. Red on origin/main.
2026-09-05 18:19:58 +05:30
kshitijk4poor 9e23028e2e test(approval): deny rule blocks in every isolated backend under yolo/off; non-denied commands still skip
Red on origin/main (10 parametrized cases).
2026-09-05 18:08:00 +05:30
kshitijk4poor c957432685 test(security): corrupt-token and docker_env warnings never echo the value
Red on origin/main.
2026-09-05 18:05:15 +05:30
kshitijk4poor bde6f6dce2 test(docker): reuse probe never emits the Docker-only {{.Label}} template; egress-off posture is a label filter
Red on origin/main.
2026-09-05 18:04:52 +05:30
rainbowgits 179e988493 fix(terminal): JSON-serialize list/dict values in profile terminal scope 2026-09-05 18:04:00 +05:30
kshitijk4poor 5035fbde1c test(tools): plugin container backend gets the host-cwd guard on the file-tools path; non-container plugin keeps it
Red on origin/main, green with the fix.
2026-09-05 18:03:05 +05:30
RelaxJonh c851ef4d0f fix(tools): file-tools env creation uses _is_container_backend() for the cwd guard (#101013)
_create_terminal_env_for_file_ops tested the static _CONTAINER_BACKENDS set while the
terminal tool's sibling sites already go through _is_container_backend(), which also
honours plugin backends declaring is_container. A host cwd override on such a plugin
backend therefore reached the sandbox as its workdir from the file-tools path only.

Salvaged from #101389 by @RelaxJonh.
2026-09-05 18:03:05 +05:30
kshitijk4poor 52cf39c908 refactor(auth): reuse _CLEAR_STATUS and the merge's None short-circuit in the reset path
Behaviour-preserving cleanup of the salvaged fix:

- reset_statuses goes back to replace(e, **_CLEAR_STATUS, ...) instead of
  re-spelling the six status fields; every other clear site uses the
  constant, so a seventh field would otherwise drift here. The
  count/new_entries/cleared_ids trio collapses to the original stale-list
  shape, and entry.failure_reason is read through the dataclass's
  __getattr__ like the rest of the module.
- Both bypass sites (write_credential_pool, _update_root_pool_rows) pass
  disk_entry=None to _merge_disk_cooldown_state for a cleared id instead of
  adding a parallel branch; the helper already returns the entry unchanged
  for a missing disk row.
- The cleared-id set in _update_root_pool_rows is built once, not per disk
  row (an Iterable argument would also have been drained on the first row).
- persist_pool_entries passes status_cleared_ids plainly; the kwargs splat
  existed only for one test fake, which now accepts the kwarg.
- Docstrings trimmed to the WHY.

Same 116 targeted tests green; reverting the two source files to main still
fails the two regression tests and passes the guard test.
2026-09-05 17:43:45 +05:30
rodrigogs 8378551311 fix(auth): make hermes auth reset actually clear a binding cooldown
Port onto the split layout: persist_pool_entries now forwards
status_cleared_ids to BOTH writers — write_credential_pool (hermes_cli/
auth.py) and the root-store row merge for single-use-refresh providers
(_update_root_pool_rows), which the original fix predates. Both skip the
disk recency merge for deliberately-cleared entries; the kwarg is only
sent when non-empty so upstream fakes with the old signature keep
working. reset_statuses clears failure_reason (lives in extra, replace()
cannot reach it) alongside the status fields.

tests/agent/test_credential_pool.py: 62 passed; refresh-race suite: 3
passed (mutation: the reset/binding tests fail with the fix stashed).
The dashboard-auth-gate / user-providers failures are pre-existing on
pristine upstream/main (reproduced with changes stashed).
2026-09-05 17:43:45 +05:30
Bergmann89 2e24e06e55 fix(env): scope terminal config re-bridge to the true process profile
In a multiplex dashboard (one process serving every profile on the host),
a secondary profile's terminal.backend could leak into the shared
os.environ and silently override the launch profile's terminal backend.
A profile configured for terminal.backend: ssh would find itself running
every command locally because a sibling profile with backend: local had
polluted the shared environment.

The tell is an asymmetric env state on the launch session:

    TERMINAL_ENV=local            # leaked from a sibling profile
    TERMINAL_SSH_HOST=10.10.0.103 # still the launch profile's, untouched

A restart does not help: as soon as the sibling profile is touched again
(a turn, a cron tick), the shared env is re-poisoned.

Root cause: env_loader._reapply_terminal_config_bridge() guards "only
re-bridge config into the shared os.environ when this load is for the
process's own profile" via _process_hermes_home(). That helper delegated
to get_hermes_home(), which follows the context-local
set_hermes_home_override a per-request task installs. When a per-turn
handler is scoped to a secondary profile and triggers a dotenv reload,
both sides of the comparison resolve to that secondary profile, the guard
passes, and the bridge writes the wrong profile's terminal.backend into
the shared environment. Because the secondary profile's config carries no
TERMINAL_SSH_* keys, only TERMINAL_ENV is overwritten, producing the
asymmetric state above.

The helper was introduced for the config-cache key (where following the
active home is correct) and later reused for the terminal bridge guard,
where the override-following semantics are wrong.

Fix: delegate _process_hermes_home() to get_process_hermes_home(), the
override-immune resolver built for exactly this. It reflects the scope the
process was launched under, ignoring per-task overrides. Both call sites
(the bridge guard and the secrets-cache reuse check) want the true process
home. Single-profile / CLI behaviour is unchanged: with no active
override the two resolvers are identical.

Complements the terminal_tool._active_environments session-key fix: that
scopes the per-session environment cache; this keeps the shared os.environ
the cache reads TERMINAL_ENV from uncontaminated in the first place.

Adds tests/hermes_cli/test_terminal_bridge_profile_scope.py covering both
the override-immune resolver and the no-leak reload behaviour.
2026-09-05 17:01:23 +05:30
kshitijk4poor 377118af86 test(cli): assert the short-terminal branch drops description rows entirely
The parametrized heights 5 and 8 exercise the renderer's zero-budget
branch (description too large to fit any row beside the reserved choice
rows), but the test never asserted what that branch draws. Pin it: no
description content and no omission notice, while the choices and key
hint stay visible.

Follow-up polish on #103350 by helix4u.
2026-09-05 16:45:59 +05:30
Gille 8f9d300ab9 fix(cli): keep radio choices visible below long descriptions 2026-09-05 16:45:59 +05:30
kshitijk4poor 07b161e241 refactor(context): fold simplify findings into oversized-file fallback
- Check text tokens BEFORE building the fenced block: an oversized file no
  longer allocates a second MB-scale string just to discard it, and the token
  estimate runs once instead of twice.
- Drop the companion warning: the fallback block alone carries the message,
  so the model no longer reads "too large to inline safely" twice (Context
  Warnings + Attached Context).
- Extract _on_disk_reference_block + _agent_visible_path shared by the binary
  and oversized blocks (stat/format_bytes/OSError fallback, container path
  translation, nudge text were copy-pasted).
2026-09-05 16:44:23 +05:30
Gille cfa1a90b8c fix(context): fall back for oversized file refs 2026-09-05 16:44:23 +05:30
杨瑾 d347fcaf97 test(desktop): cover live token in SPA index 2026-09-05 16:30:35 +05:30
thinkingsheep 1866921d33 fix(desktop): serve the current SSH session token 2026-09-05 16:30:35 +05:30
kshitijk4poor b499ab11fe fix(gateway): remote media fetch fails closed on unresolvable symlinks, skips strict mode, keys the sandbox by session id
readlink returning nothing no longer falls back to the unresolved name (a sandbox symlink to a
credential would otherwise be followed by [ -f ]). Strict delivery mode keeps its recency gate:
no fetch, since the copy lands in an allowlisted root. The active sandbox is looked up by the
HERMES_SESSION_ID the turn registered it under (per-session-isolated docker keys by task id, not
session key). MEDIA path normalisation (quotes/backticks/trailing punctuation) now matches the
host path; the denylist tables are built once at import.
2026-09-05 16:09:46 +05:30
kshitijk4poor 90db26ad55 test(gateway): sandbox MEDIA artifacts deliver; credentials and symlinks to them never leave the sandbox; fetch transport round-trips and caps size
Red on origin/main (module absent / paths dropped), green with the fix.
2026-09-05 16:09:46 +05:30
kshitijk4poor baf7ceeace refactor(environments): share the unset-prelude and client-env helpers; drop test-only shape from ssh
prepend_unset / client_env_with live beside resolve_passthrough_env so docker and ssh
post-process its output identically. The ssh tests build a real SSHEnvironment under
the existing connection stub instead of a half-initialised __new__ object, so the
production code no longer carries getattr fallbacks for it.
2026-09-05 15:54:39 +05:30
kshitijk4poor be6f0d296b test(ssh): passthrough goes out via SendEnv, values never in remote argv, provider keys held back
Red on origin/main (no SendEnv, no client env), green with the fix.
2026-09-05 15:54:39 +05:30
sgaofen 7456081d2a fix(ssh): forward skill/config env passthrough over SendEnv (#14091)
The SSH backend spawned `ssh … bash -c` with no env forwarding at all, so a
skill's `required_environment_variables` (and `terminal.env_passthrough`)
reached local and docker shells but never a remote host — the skill reported
ready while every remote command saw the variables unset.

Names travel as `-o SendEnv=NAME`; values ride the ssh client's own
environment, so no secret ever enters the remote `bash -c` argv. Hermes
provider credentials stay behind the same blocklist docker uses, `.env`
fills in variables unset in the shell, and profile-scoped names missing
from the active scope are unset remotely under multiplex. The remote sshd
must `AcceptEnv` the names (documented).

A ControlMaster only relays the SendEnv names it was started with, so
passthrough commands ride a per-name-set master socket (verified live
against a real sshd: the shared master silently dropped every variable).

Salvaged from #14414 by @sgaofen.
2026-09-05 15:54:39 +05:30
kshitijk4poor 03e1a9bbdf test(gateway): session stores + sidecars + named-board kanban.db are denied; neighbouring attachments still deliver
Red on origin/main (all nine paths delivered), green with the fix.
2026-09-05 15:54:34 +05:30
kshitijk4poor 9835b2fd69 chore: map contributor email for salvaged #41071 (pprism13) 2026-09-05 15:54:34 +05:30
kshitijk4poor 0af92098f2 test(agent): split the Kimi lookalike-host case into its own test 2026-09-05 15:54:14 +05:30
kshitijk4poor 562383ad31 test(agent): Kimi Code fallback lands on anthropic_messages; lookalike host stays on chat_completions
Red on origin/main (chat_completions), green with the fix.
2026-09-05 15:54:14 +05:30
Teknium d20a8e4475 feat(models): OpenRouter, Nous Portal, and Alibaba Token Plan pickers carry Qwen3.8-Max-0902
Alibaba shipped qwen3.8-max-0902 (alias qwen3.8-max-2026-09-02), the upgraded
snapshot of Qwen3.8-Max: 1M context / 131K output, $2 in / $6 out. Both
aggregators now serve it and dropped the bare slug from their catalogs
(verified 2026-09-02: OpenRouter /v1/models + a 200 completion echoing the
slug; Nous Portal /v1/models).

- OPENROUTER_MODELS (feeds the nous list too): qwen/qwen3.8-max -> qwen/qwen3.8-max-0902
- _ALIBABA_TOKEN_PLAN_MODELS: qwen3.8-max-preview -> qwen3.8-max-0902
- test_empty_model_fallback fixture follows the nous catalog slug
- model-catalog.json regenerated

No new metadata: DEFAULT_CONTEXT_LENGTHS substring-matches qwen3.8-max (1M),
reasoning floor prefix fires (180s), both aggregator routes bill via
official_models_api. alibaba/alibaba-cn/opencode-go/setup.py left unchanged
(out of scope).
2026-09-05 02:31:06 -07:00
Teknium 41e6b60249 test(update): fold the #97332 plan-kind cases into one invariant test 2026-09-05 00:24:40 -07:00
Teknium 1cce7c6dd8 fix(update): unmapped gateway stops no longer fail the fleet check with "no rows"
A gateway with no profile mapping (or one whose relaunch could not be armed) is
SIGTERMed and listed under "Restart manually" — by design it has no successor and
publishes no fleet-matrix row. It still counted in ``killed_pids`` and the
pre-restart snapshot, so ``_fleet_probe_expected_runtimes`` demanded rows that
could not exist and a fully successful update exited 1 with "Fleet version check
returned no rows even though gateway runtimes were expected", leaving the
fleet_restart_pending marker behind and every later CLI start warning about it.

Track the unmapped stops on the restart outcome and subtract them from the
row-predicting signals (``fleet_probe_signals``); relaunched/systemd gateways
still predict rows exactly as before.
2026-09-05 00:24:40 -07:00
liuhao1024 b8e3c5c700 fix(update): scope fleet-probe runtime expectation to gateway-kind plan records
A dashboard-only runtime plan (gateway never started) made
_fleet_probe_expected_runtimes() return True from the unfiltered
'plan.runtimes is non-empty' check. collect_fleet_versions() reports
gateway identities only, so the probe waited for rows that cannot exist,
printed the incomplete-verification warning, and exited 1 after a
successful update (#97332).

Key the plan-derived expectation on kind == 'gateway' records — the same
row-capability rule already applied to the Windows resume token (#93406)
— and update the two tests that pinned the old object() placeholder so
they pin the runtime-kind distinction. Restart-phase, killed-PID, and
pre-restart-PID signals still fail closed unchanged.
2026-09-05 00:24:40 -07:00
Teknium e17dd8b428 fix(update): protect the whole hermes_cli.update_* family from the stale-module purge
Widen the salvaged receipt protection to every updater-owned module: the
pre-update plan's ``RuntimeRecord`` dataclass (``update_inventory``) has the same
failure — the plan is built before the purge and the post-restart reconciliation
filters with ``isinstance``, so an evicted module means a fresh class, zero matches,
and an empty runtime-outcome report. One prefix rule instead of a name list that
has to be re-fixed per symptom.
2026-09-05 00:24:40 -07:00
WolveBrown fada877519 fix(update): preserve active receipt across module purge 2026-09-05 00:24:40 -07:00
kshitijk4poor 5ac75e91e2 test(tools_config): assert display/runtime parity for disabled composite toolsets
The runtime-only assertion passed on unfixed main (it exercised
model_tools, not _get_platform_tools). Replace it with the contract the
fix exists for: a toolset is listed iff at least one of its tools survives
_select_tool_names.
2026-09-05 12:21:28 +05:30
aydnOktay 2494eadb39 fix(tools): align inspection surfaces with disabled composite toolsets
hermes tools --summary and CLI /tools used name-level disabled_toolsets subtraction, so disabling debugging still showed terminal/web/file as enabled while runtime stripped those tools. Prune platform toolsets after tool-level subtraction and pass disabled_toolsets into CLI get_tool_definitions calls.

Fixes #97015

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-05 12:21:28 +05:30
kshitijk4poor ec1e6d50bc test(distributions): keep two invariant tests for grouped entries
Drop the literal-key assertion (change-detector) and the seeded 500-roll
loop (leaked global RNG state; vacuous if neither member rolls). Exercise
the fallback against a throwaway distribution so the contract no longer
depends on which browser_tasks entry has the highest probability.
2026-09-05 12:21:21 +05:30
falkoro 6ba09c8cc3 fix(distributions): keep browser+web_search co-occurrence at 97% via grouped roll
Independent 97% rolls for browser and search co-occur only ~94% of the
time, versus 97% when web_search was bundled inside the browser toolset
(hermes-sweeper review). Grouped "+"-compound entries roll once and
select every member together; browser_tasks now uses "browser+search".
Deterministic tests cover the hit/miss/fallback/invalid-member contracts
and a 500-sample co-occurrence invariant.
2026-09-05 12:21:21 +05:30
falkoro decacbac35 fix(toolsets): stop disabled browser from stripping web_search
web_search belongs to the web/search toolsets, but the browser toolset
also listed it as a member. Because disabled_toolsets is a strict
end-of-pipeline subtraction (#17309), disabling browser — a natural
choice for headless/Docker deployments with no Chromium — stripped
web_search from every session even when web was enabled.

Remove web_search from the browser composite so its membership no longer
couples web search to browser availability. The browser_tasks RL
distribution kept web_search via browser, so add the search toolset there
to preserve its effective tool availability.

Fixes #64503
2026-09-05 12:21:21 +05:30
Sohom Sahaun 1e69c12b64 feat(slack): interactive Block Kit model picker for /model
Cherry-picked from PR #101542 by @sohomsahaun.

Two-step drill-down: provider static_select → model static_select,
with Back/Cancel buttons. Resolves through the same gateway callback
as Discord/Telegram, so persistence and failed-switch rollback
semantics come for free.

Changes:
- send_model_picker() posts Block Kit provider/model picker via chat_postMessage
- _handle_model_picker_action() dispatches provider/model/back/cancel actions
- _model_picker_state bounded dict (cap=100, workspace-scoped keys)
- Expired-state UX: missing state rewrites message to expiry notice
- Failure header: both exception and gateway error-prefix get 'Failed' header
- Index-based option values avoid Slack's 75-char value cap
- 21 tests covering send, action dispatch, gateway integration

Co-authored-by: Sohom Sahaun <ssahaun19@gmail.com>
2026-09-05 11:05:17 +05:30
kshitijk4poor f5832f81ed test(streaming): drive the Relay finalizer through its collector
The chat_completions finalizer now reads collector-observed chunks, not the
consumer loop, so the test feeds the captured on_chunk before calling it —
the same ordering Relay guarantees.
2026-09-05 10:54:19 +05:30
kshitijk4poor 74de0fd4fe fix(relay): build the chat-completions Relay response from collector-observed chunks
Relay invokes its finalizer as soon as the provider stream ends, concurrently with
Hermes' consumer thread, so any finalizer that reads the consumer loop's closures
races the last chunk. #103104 moved `usage` onto the collector; the same race still
truncated the final tool-call `arguments` delta, dropped the last content delta, and
downgraded `finish_reason` to "stop" in Relay's annotated response (reproduced ~50%
of runs). Every other Relay integration (Anthropic, Bedrock, Codex) already
rebuilds from collector-observed chunks; this makes chat_completions match via
`_RelayChatAccumulator` and removes the single-field nonlocal stopgap.

Test: the ordering harness is shared, and a second invariant test pins the
tool-call/finish_reason case (fails on the stopgap, passes here). Hermes' own
returned response was never affected.
2026-09-05 10:54:19 +05:30
mnajafian-nv 2cf5e68c5d fix(relay): retain usage from trailing chat completion chunks
Signed-off-by: mnajafian-nv <mnajafian@nvidia.com>
2026-09-05 10:54:19 +05:30
Austin Pickett 79445a496c fix(desktop): macOS parent-death watchdog treats ps: marker drift as inconclusive (#103172)
* fix(desktop): treat a macOS ps: parent-marker mismatch as inconclusive, not death

`ps -o lstart=` is a TZ/locale-rendered wall-clock string. Electron caches it
once per app lifetime; the backend re-renders it per spawn. A timezone change
(travel, or the DST boundary) while the app stays open makes the SAME instant
differ byte-for-byte, and _is_serve_orphaned() treated that as proof the parent
died -- os._exit(0) ~5ms after HERMES_BACKEND_READY, silently, on every respawn
until a full quit.

Route mismatches through _parent_start_marker_mismatch_is_conclusive(): linux:/
win:/winms: machine markers stay conclusive (PID-reuse defence intact); any ps:
side degrades to the PID-liveness check the legacy Desktop path already uses.
Log one warning before os._exit(0) so the exit is no longer traceless.

Fixes #95693
Fixes #93958

Co-authored-by: Ahmett101 <Ahmett101@users.noreply.github.com>

* fix(desktop): reject truncated ps: parent markers; blank marker env means absent

A ps: marker that got whitespace-split in env plumbing (`ps:Sat`) passed
_valid_parent_start_marker and armed a watchdog that could never match, so
the backend exited 0 right after HERMES_BACKEND_READY. Require a full
lstart value (>=4 tokens, a 4-digit year, a time). Treat empty
HERMES_PARENT_START_MARKER / HERMES_PARENT_NONCE as absent so a blank
inherited value degrades to PID-only tracking instead of disarming or
misfiring.

* chore: map contributor email for drewTuzson

* fix(desktop): log when the parent-death watchdog disarms on an unusable marker

Disarming is the fail-safe branch (the backend keeps serving) but it also
means this backend will never reap itself when the Desktop dies. Leave one
warning naming the rejected marker so that downgrade is not traceless.

* test(desktop): live macOS proof that a TZ-drifted ps: marker no longer kills the backend

Runs the real start_server in a subprocess against the host ps, with the
marker rendered under Europe/Paris and the backend under America/New_York.
Asserts READY + still alive after several watchdog polls, then that the
backend still exits once the stand-in parent is killed. Fails on main with
the reported symptom (exit 0, live parent); macos_only lane.

---------

Co-authored-by: ygd58 <buraysandro9@gmail.com>
Co-authored-by: Ahmett101 <Ahmett101@users.noreply.github.com>
Co-authored-by: Drew Tuzson <drew.tuzson@uqual.com>
2026-09-04 20:24:51 -04:00
Gille a99340c247 fix(dashboard): prevent PTY input from blocking event loop (#93565)
* fix(dashboard): prevent PTY input from blocking event loop

* fix(win-pty): don't terminate a healthy ConPTY on write cancellation; log leaked write workers

Review follow-up to the backpressure fix.

CancelledError on WinPtyBridge.write() ran the same path as a timeout and
force-terminated the ConPTY. Cancellation means the owning socket went away
mid-write, which is the keep-alive session's normal reattach case, not a
wedged child; killing the process there defeats the PTY-outlives-socket
design. Give the in-flight write the shutdown grace window and only
terminate if it never lands.

When terminate() fails to unblock pywinpty, the worker stays parked in the
default executor. That was swallowed by a bare except; log it so a slow
thread-pool starvation is diagnosable.

---------

Co-authored-by: Austin Pickett <pickett.austin@gmail.com>
2026-09-04 20:24:24 -04:00
Austin Pickett 04fd0172cd fix(dashboard): stop the embedded TUI repainting on every OS app-switch (#103165)
* feat(pty_bridge): mark the dashboard-spawned TUI with HERMES_PTY_HOST

Ink needs to know when its emulator is the dashboard's xterm.js rather
than a native terminal, so it can drop hidden-tab recovery work that only
makes sense for emulators that coalesce output.

Co-authored-by: Raymond <supere989@users.noreply.github.com>

* fix(tui): skip the focus-in erase+repaint under the dashboard PTY

Ink answers a DECSET 1004 focus-in with a full clear+repaint to heal rows
a native emulator may have dropped while the tab was hidden. xterm.js fed
by the dashboard WebSocket never drops frames, and it reports focus on
every OS window blur/focus, so under the dashboard that repaint was a
visible "session reloaded" flash on every alt-tab. Keep the mode
re-assert and keep delivering the focus report to TerminalFocusProvider
(the composer hides its cursor on blur); only the repaint is skipped.

Co-authored-by: Raymond <supere989@users.noreply.github.com>

* fix(web): restore terminal focus after an OS app-switch

Alt-tabbing away and back lands browser focus on <body>, so Ctrl+V never
reached the composer. Pull focus back into xterm on window focus under
the same ownership rule tab activation already uses, extracted into
shouldRestoreTerminalFocus so both paths share it.

Co-authored-by: Raymond <supere989@users.noreply.github.com>

---------

Co-authored-by: Raymond <supere989@users.noreply.github.com>
2026-09-04 20:24:02 -04:00
Teknium f159e581c7 feat(models): add GPT-6 Astra + Astra Pro with fast/flex speed tiers to Nous Portal and OpenRouter
Six slugs land in the nous and openrouter curated lists, above the gpt-5.6 line:
openai/gpt-6-astra{,-fast,-flex} and openai/gpt-6-astra-pro{,-fast,-flex}.

Nous Portal serves the tiers as distinct slugs (verified live: each echoes its id, service_tier
default/priority/flex, cost 1x/2x/0.5x). OpenRouter serves them as ENDPOINTS of the base model
(tags openai/fast, openai/flex) and silently routes an unknown suffix to the standard tier at
standard price, so the OpenRouter profile rewrites a tier slug to its base wire model and pins
provider.only to that tier's endpoints (OPENROUTER_ENDPOINT_PINS). The base slug is pinned to
openai/azure/azure-us so default routing never lands on a flex or fast endpoint.

Provider-agnostic metadata: one DEFAULT_CONTEXT_LENGTHS entry (gpt-6-astra: 1,050,000, live on
OpenRouter for both models; substring-matches -pro and the tier suffixes). Pricing is skipped:
both routes bill via official_models_api. Reasoning floor not added (no evidence of long thinks).
2026-09-04 15:58:59 -07:00
kshitijk4poor 5a0b1ba766 test(local-models): assert _assign_default reaches the real assignment body
Follow-up to the salvaged fix from #102994. The quickstart leg tests
stubbed web_deps.late itself, so the resolution path that regressed
(late() -> web_server facade -> getattr) was never exercised; the PR's
proposed tests pinned the module string instead, which fails on any
future move of the symbol even when the call site is updated.

Stub only the leaf (web_server_config._apply_model_assignment_sync) so
the real late() runs, and add one invariant test: _assign_default must
call it with ("main", "llamacpp", model_id, "", "", ""). Red on base
(AttributeError), green with the fix; not tied to where the symbol lives.
Drop the docstring parenthetical that described test mechanics.
2026-09-05 00:29:42 +05:30
Leanolf aef409343d fix(local-models): point _assign_default's late-bound model assignment at web_server_config
The whole-codebase refactor moved _apply_model_assignment_sync from the
web_server facade into web_server_config, but _assign_default in
web_routers/local_models.py still resolved it through the default late()
module (web_server), which no longer carries the symbol. A local-model
quickstart therefore failed its final 'making it your default' step with
AttributeError: module 'hermes_cli.web_server' has no attribute
'_apply_model_assignment_sync'.

Pass the defining module explicitly to web_deps.late() so the call
resolves against hermes_cli.web_server_config, matching how the sibling
models.py router imports the same helper. Update the two quickstart test
stubs to accept the module argument the real late(name, module=...) takes.
2026-09-05 00:29:42 +05:30
Nacho Avecilla a6e10e693f fix(gateway): stop dropping the first message after an Azure agent sleeps (#99736)
* feat(gateway): let NAS broker the scale-to-zero suspend where the guest has no lever

* fix(gateway): require the going_idle ack and outlast the broker before suspending

* fix(gateway): release the redial hold on every path that abandons the suspend

* fix(gateway): hold the re-dial only for the brokered lever, and require it

* fix(gateway): make the re-dial hold contract real and fence the in-guest suspend too

* refactor(gateway): share the watcher-iteration and descriptor helpers across the sleep tests

* refactor(gateway): move the sleep tests' repeated setup into their fixtures

* refactor(gateway): one docstring line per sleep test, and parametrise the abort and lever paths

* fix(gateway): fence the freeze gap, cool down aborts, and stop clobbering a shutdown drain

* fix(gateway): slice the Fly freeze fence on the wall clock and widen it for larger machines
2026-09-04 15:41:27 -03:00
Teknium 13e72fb205 Merge pull request #102986 from NousResearch/fix/browser-exec-packaged-chromium
browser_exec local mode drives the packaged Chromium instead of the user's Chrome
2026-09-04 08:42:27 -07:00
Teknium 9e13ac2f01 fix(browser): browser_exec local mode drives the packaged Chromium, not the user's Chrome
Symptom: with Browser Use mode (the default) and no cloud provider / CDP
override, browser_exec left BU_CDP_* unset, so the browser-use harness ran
its own local discovery — hunting for the user's INSTALLED Chrome on its
default profile. That path needs the chrome://inspect remote-debugging
toggle plus an "Allow remote debugging?" popup per run, is blocked outright
on Chrome >=136, and on a headless host (or one without Chrome) fails with
"chrome-not-running: no supported Chromium-family browser is running". The
built-in browser_* tools never had this problem: they drive the Chromium
Hermes installs, launched through agent-browser.

Change: `_resolve_backend_cdp` step 4 becomes the local ENGINE —
lightpanda when configured, otherwise `_resolve_managed_chromium_cdp`,
which runs `agent-browser --session <key> get cdp-url` through the legacy
`_run_browser_command` (Chromium preflight/auto-install, per-key session
cache, inactivity reaper, atexit) and exports the returned ws:// endpoint
as BU_CDP_WS. Each cache key (task, or bu-named-<session>) gets its own
Chromium, so named sessions are private and skip the own-tab preamble.
Running `get cdp-url` on every call also refreshes agent-browser's idle
timer (it never sees the harness's direct CDP traffic) and follows a
relaunch after the reaper closed the browser.

Live: before, browser_exec on origin/main → exit 1 "chrome-not-running";
after → new_tab/page_info succeed on a cold start, warm reuse, post-reap
relaunch, and a named session; a missing Chromium surfaces the install
hint instead of the harness's Chrome hunt.
2026-09-04 08:30:32 -07:00
Teknium 8924b3aed9 fix(skills): lead the lesson-layer contract with the primary purpose — how to do the task, to the user's specifications 2026-09-04 08:15:22 -07:00