The snapshot dirs were 0700 but every file inside landed umask-wide:
shutil.copy2 preserves Chrome's own 0644 profile-file modes and
sqlite3.connect creates the online-backup destinations as plain umask
files — so the copied Cookies / Login Data / Web Data (the user's live
session credentials) sat 0644. The 0700 parents contain it by default,
but the documented HERMES_HOME_MODE traversal hatch makes group/world-
readable children a real exposure.
snapshot_real_profile now reconciles every file (0600) and nested dir
(0700) inside the snapshot through the house helpers (_secure_file /
_secure_dir — managed-mode and container carve-outs included) at the
end of every pass, so snapshots written by older builds heal on their
next launch. Best-effort, never blocks a launch.
Tests: owner-only walk under umask 022 (fails on the pre-fix code —
sabotage-verified) + heal-on-refresh for a pre-existing 0644 Cookies.
The issue's other two findings are already fixed on main: mock-keychain
flags eliminated by the direct native-binary launch (#98249, salvage of
#96763); the 'Device not configured' TTY failure is superseded by the
same launch-path rework.
Sibling tests outside the salvaged PR's files created one-shots via bare
'30m', which is now a recurring interval per the corrected contract.
Fixtures whose assertions depend on kind='once' (run-claim clearing,
terminal-record rearm, web-server completed-snapshot) now use 'in 30m';
sites indifferent to kind keep the bare form.
Contract bug (2026-08-04): the cronjob tool schema documents '30m' as
'(every 30 minutes)' — recurring — but parse_schedule returned
kind='once' for bare durations, silently creating a one-shot job for a
recurring request (agent passed '30m' for 'every 30 min', job ran once
and died). Bare durations ('30m','2h','1d') now parse as recurring
intervals matching the documented contract; explicit one-shot by
duration is 'in 30m'/'in 2h' (fires once that far from now). ISO
timestamps stay one-shot.
Also fixes the sibling repeat-coercion class (#66824/#64520/#7142):
repeat='forever'/'once'/'N' strings now coerce in create_job instead of
raising "'<=' not supported between instances of 'str' and 'int'".
Tool description rewritten to teach the corrected contract and steer
relative requests to 'in Nm' (no more hand-computed ISO timestamps).
Supersedes the doc-only direction of #53739 while keeping its goal
(relative one-shots must be expressible) via the 'in X' form.
Signed-off-by: andrexibiza <84248988+andrexibiza@users.noreply.github.com>
The gateway's session-backed MCP OAuth flow (mcp.servers.oauth.start) binds
its browser-callback listener on the BACKEND machine's 127.0.0.1. When the
Desktop app connects to a remote backend (SSH/Tailscale), the user's browser
resolves that loopback to the user's machine, the redirect dies, and every
OAuth catalog server (ClickUp, Hospitable, ...) fails in-app with no working
path — the exact topology from the 'MCP Recurring erros' support thread.
Fix mirrors the Desktop's native gateway login (native-oauth-login.ts):
- gateway: mcp.servers.oauth.start accepts client_redirect_uri (loopback-only,
RFC 8252-style validation); when supplied no gateway listener is bound and
the OAuth redirect_uri pins to the client's listener.
- gateway: new mcp.servers.oauth.callback RPC relays the client-captured
code/state into the flow; state verification stays in
DashboardOAuthFlow.deliver_callback (constant-time compare, replay-safe).
- desktop: mcp-oauth-callback-ipc.ts hosts a one-shot 127.0.0.1 listener in
the main process (hermes:mcp-oauth:listen/wait/cancel via preload bridge).
- desktop: hermes-bots mcp-setup.tsx prefers the client listener for local
AND remote backends, falling back to the legacy gateway-listener flow on
older gateways (feature-detect via start rejection).
- docs: remote-host MCP OAuth section documents the automatic Desktop path.
Validation: 19 new gateway tests (validator allowlist, listener skip, relay
accept/reject/replay) — sabotage-verified; 5 new desktop tests against a real
ephemeral listener; E2E through the real session registry + flow bridge with
a stubbed provider probe; tsc electron+renderer builds clean.
platforms field added, description under the 60-char hardline, dangling
premium-webapp-ui related_skills ref dropped (user-profile skill, not in
the repo tree). Docs page + catalog row regenerated to match.
hermes skills install impeccable (and the docs-page install button) now
installs the impeccable frontend-design skill as an official optional-skills
entry. The local optional-skills/creative/impeccable/ dir is a catalog STUB:
its frontmatter declares metadata.hermes.upstream (repo + path), and
OptionalSkillSource.fetch() pulls the real 163-file bundle live from
pbakaus/impeccable:.hermes/skills/impeccable — the Hermes-native bundle
upstream maintains and verifies. Nothing vendored, never stale.
New mechanism (generic, not impeccable-specific):
- OptionalSkillSource._upstream_pointer(): parses/validates the upstream
pointer (owner/name repo, clean relative path, traversal rejected).
- _fetch_from_upstream(): delegates to GitHubSource.fetch(), relabels the
bundle official/<rel> at trust 'trusted' (curated endorsement, but
third-party content — dangerous scan verdicts still block).
- The live-repo fallback path redirects stubs the same way, so stale local
checkouts behave identically.
Three real gaps this surfaced, all fixed:
- GitHubSource.fetch() only downloaded SKILL.md plus paths linked from a
canonical support dir (references/, scripts/, ...). Impeccable keeps its
playbooks under reference/ (singular) and links scripts only from
reference files, so fetch shipped 1 of 163 files. fetch() now downloads
the full skill directory via the git tree (same approach as the
optional-skills live fetch), still rejecting symlinks/hidden/unsafe paths
and still failing on a missing SKILL.md-linked references/ path.
- The five env_exfil_* scanner patterns flagged loopback requests as
critical exfiltration: impeccable's live mode polls
http://localhost:PORT/status?token=TOKEN and scored two CRITICALs.
Scheme-anchored loopback exemption added; evil.com/?u=localhost decoys
still fire (10-case regex matrix in tests).
- unified_search() truncated to limit before ranking, so official catalog
entries got crowded out by skills.sh mirrors and bare-name installs
stalled on an ambiguity table. Results now stable-sort by trust rank
before the cut, and _resolve_short_name prefers a sole official exact
match over community mirrors.
Also fixes pre-existing test pollution: TestInstallPathSafety's fixture
monkeypatched the PEP 562 dynamic SKILLS_DIR, permanently shadowing dynamic
resolution and breaking the served_repo E2E tests in any combined run
(reproducible on main).
Validation: live E2E do_install("impeccable") against real GitHub —
resolves to official/creative/impeccable, verdict SAFE, 163 files on disk,
skill loads, /impeccable slash command registers. 128/128 targeted tests;
full-dir fetch test sabotage-verified. Docs: optional-skills catalog row,
generated skill page, sidebar.
Widens _natural_every_to_cron to consume comma/'and'-separated weekday
lists ('Monday, Wednesday at 9am' -> '0 9 * * 1,3') and applies the same
helper to schedules without the 'every' prefix, matching the exact forms
the Desktop dialog advertises in the #51975 repro.
`parse_schedule()` detected cron expressions with a digit-only field pattern
(`^[\d\*\-,/]+$`), so any field using named months or weekdays — `MON`, `JAN`,
and common ranges/lists like `MON-FRI` or `MON,WED,FRI` — failed detection and
fell through to a confusing "Invalid schedule" error, even though croniter
supports them and they're standard cron.
Allow letters in the field pattern so these route to croniter for validation.
Truly-invalid expressions (`0 9 * * FUNDAY`, `99 9 * * MON`) are still rejected
there with a clear "Invalid cron expression" message; duration/interval/ISO
parsing is unchanged.
Adds tests for named weekdays/months (incl. ranges and lists) and that an
invalid named field is still rejected.
The Desktop dialog's advertised form in #51975 omits the 'every' prefix.
Reuse _natural_every_to_cron() on the bare schedule so 'weekdays at 9am',
'monday at 9:30', and 'daily at 7am' parse to cron expressions. Also
switch the salvaged branch's HAS_CRONITER check to _ensure_croniter()
(lazy-import refactor landed after the PR was cut).
parse_schedule's "every " branch passed everything after the prefix
straight to parse_duration(), so documented natural-language schedules
like "every monday 9am" and "every day at 9am" (AGENTS.md, SKILL.md,
cron docs) were rejected with "Invalid duration". Convert weekday and
daily/weekday/weekend phrases to cron expressions before the duration
fallback; "every 30m"/"every 2h" interval parsing is unchanged.
The bundled plan skill's auto-generated slash command fell off the capped
Telegram/Discord command menus for most installs (skills are the only tier
trimmed at the platform caps, alphabetically — 'plan' sat past the cutoff at
index 57 of 82 bundled skills). Converting it to a first-class CommandDef
gives it a guaranteed core-tier menu slot on every platform.
- agent/plan_prompt.py: build_plan_prompt() — plan-mode rules + authoring
craft distilled from the retired skill; prompt-injection pattern like
/learn and /init (no engine, no model-tool footprint, cache-safe).
- CLI: _handle_plan_command mixin handler (pending-input injection).
- Gateway: /plan branch rewrites event.text and falls through (role
alternation preserved).
- TUI: command.dispatch branch ('plan' was already in
_PENDING_INPUT_COMMANDS).
- Removed skills/software-development/plan/ + docs pages (EN + zh-Hans),
catalog rows, sidebar entry, related_skills references.
- PROTECTED_BUILTIN_SKILLS is now empty (mechanism kept); dependent
curator/usage tests moved to monkeypatched sentinels.
Salvages #67292 by @webtecnica (credit: first /plan command submission,
issue #67264); reworked from inline planning prompt to the prompt-injection
pattern with workspace-saved plans. Closes#67264, closes#36821 (empty
/plan infers task from conversation context).
The grant_existing_profile key was removed in PR #98057; sweep the mode
table, opt-in section, runtime-lifecycle notes, config example, and CLI
reference that still documented it.
#95620 removed computer_use's cua_browser_* actions entirely
(browser_route.py, the action enum, and their dispatch/escalation hint) —
computer_use is desktop-only now, and page content goes through the
separate browser_navigate/browser_click/... toolset (or browser_exec
under the Browser Use CLI backend).
The skill doc never caught up: it still taught the model to call
cua_browser_state/cua_browser_prepare/etc. and to escalate to a "page"
rung that _enrich_escalation can no longer recommend. Following that
guidance fails schema validation on the first call.
- SKILL.md: replace the "Typed browser page rung" section (including the
existing_profile authorization walkthrough, which described a
model-facing action parameter that no longer exists anywhere in
schema.py/tool.py) with a short pointer to the current browser toolset;
drop "page" from the escalation.recommended union and the ladder step
that referenced it.
- website/docs/user-guide/features/computer-use.md: grant_existing_profile
and the rest of the permission-mode config are still real and current
(cua_backend.py still reads them for the runtime launch grant) — only
reworded the one sentence naming cua_browser_prepare as the mechanism
that consumes the grant, since driving a signed-in browser window now
goes through the standard capture/click/type actions instead.
- Regenerated the mirrored skill doc via
website/scripts/generate-skill-docs.py rather than hand-editing it, per
its own header. Kept the diff scoped to computer-use only.
Completes the #90953 salvage on post-#98237 main:
- New _merge_request_overrides helper defines the precedence contract:
explicit delegation.request_overrides merges OVER runtime/parent-derived
overrides — explicit top-level keys win; extra_body is deep-merged one
level so runtime extra_body keys survive unless redefined. Inputs are
copy.deepcopy'd so transport-side mutation can't leak into config or the
provider runtime cache.
- Direct base_url branch: explicit key now merges over the #98237
provider-alongside-base_url runtime overrides instead of being a separate
return shape; max_output_tokens preserved.
- Named-provider branch and parent-inherit branch now honor the key too, so
delegation.request_overrides never silently no-ops.
- _build_child_agent honors override_request_overrides whenever set
(previously only when override_provider was set), enabling the inherit
branch's merged value to reach the child.
- DEFAULT_CONFIG: delegation.request_overrides entry with comment.
- Tests: expanded tests/tools/test_delegate_request_overrides.py — deep-copy
proofs, explicit-over-runtime precedence on the provider-alongside-base_url
path, named-provider branch, inherit branch, and merge-helper unit tests.
- Docs: configuration.md delegation section + features/delegation.md document
the key, precedence, and example YAML (OpenRouter extra_body.provider.sort).
The direct base_url branch of _resolve_delegation_credentials returned no
request_overrides key, so a direct OpenRouter delegation (provider=custom,
base_url=openrouter.ai/api/v1) could not pass routing hints to its children.
The named-provider branch already forwards runtime request_overrides; this
gives the direct branch the same contract, honouring delegation.request_overrides
from config (dict → forwarded, anything else → None).
Primary use: extra_body.provider = {"sort": "throughput"} so delegation
children route to the fastest OpenRouter provider for their model, per the
fab-swarm throughput work (#901).
Follow-up hardening on the two cherry-picked contributor commits:
- try_activate_fallback: replace the blanket request_overrides.pop('extra_body')
with KEY-SCOPED removal — only keys the OLD provider's custom_providers
entry contributed (value unchanged since the init-time merge) are dropped.
Caller/profile-provided extra_body keys survive the swap, matching the
caller-over-provider precedence in agent_init._merge_custom_provider_extra_body.
The fallback provider's own extra_body is then merged back in.
- switch_model: the live _primary_runtime snapshot it rebuilds now carries
request_overrides, so a post-switch transport recovery or fallback restore
reinstates the switched-to identity's overrides instead of dropping them.
- Tests: activation-level stale-key removal + caller-override preservation
(test_provider_fallback.py), switch-then-recover / switch-then-restore
(test_primary_runtime_restore.py).
Cache-safety: none of these paths mutate past context or rebuild the system
prompt — only outbound request kwargs change.
Fixes#75091
`try_activate_fallback()` re-resolved `reasoning_config` for the new
fallback provider (fix for #21256), but never re-resolved `extra_body`.
The primary provider's `extra_body` (e.g. `reasoning_effort: "none"`)
rode along onto the fallback provider, which is a different API that
may reject those fields.
Example: primary has `extra_body: {reasoning_effort: "none"}`, fallback
is OpenRouter. After failover, every request to OpenRouter carries both
the stray top-level `reasoning_effort` AND the nested `reasoning` object,
and OpenRouter rejects the pair:
HTTP 400: "reasoning_effort" and "reasoning.effort" are both provided
The fallback is dead precisely when it is needed.
Fix: after swapping provider/model/base_url, clear the primary's
extra_body from request_overrides, then re-resolve from the fallback
provider's config using the existing _merge_custom_provider_extra_body
helper. Same pattern as the reasoning_config re-resolution above.
Port the PR #52432 regression (fast turn then normal turn on a cached
gateway agent) onto the current _run_agent harness: the original test's
host file context no longer exists on main after the TurnRunner
extraction, so the scenario is re-expressed with the existing
_CapturingAgent fixture. Asserts init-time custom-provider extra_body
survives both a /fast turn (service_tier layered on top) and the
following normal turn (only the stale fast-mode key drops).
Salvaged-from: #52432
Co-authored-by: Heng Cai <abtion@outlook.com>
Addresses the hermes-sweeper review on #53765. The in-place /model switch
helper (_apply_switched_provider_request_overrides) derived a custom
provider's extra_body by provider *name* only, while build-time matching in
agent_init._merge_custom_provider_extra_body matches by provider key, base_url,
AND model. So a different model selected at the same named endpoint could
inherit an extra_body configured for another model.
Reuse the shared agent_init._custom_provider_extra_body_for_agent matcher
(provider key + base_url + model), sourcing custom_providers from the
init-time agent._custom_providers cache (fresh-load fallback if absent). A
stale extra_body is always cleared when no entry matches; non-provider
overrides (service_tier / speed from /fast) are preserved.
Tests: add nonmatching-model and endpoint-mismatch regressions; update the
existing switch tests onto the model/base_url-aware matcher.
Follow-up to the previous commit (which fixed the default/fallback
provider path). A mid-session `/model` switch stores a per-session
override bundle in `_session_model_overrides` that omitted
`request_overrides`, and the two consumers
(`_resolve_session_agent_runtime` fast path and
`_apply_session_model_override`) only copied
provider/api_key/base_url/api_mode. So switching *to* a custom provider
via `/model` did not apply its `extra_body`.
- `ModelSwitchResult` gains a `request_overrides` field, derived for the
switched provider via `_get_named_custom_provider` /
`_custom_provider_request_overrides` (the same overrides
`resolve_runtime_provider` surfaces for the default path).
- Both `/model` override-storage sites in slash_commands.py persist it.
- Both consumers apply it; `_apply_session_model_override` also clears a
stale value when switching to a provider that has none.
Extends tests/gateway/test_turn_request_overrides.py (3 new cases).
A `custom_providers` entry can carry an `extra_body` (e.g.
`chat_template_kwargs` to toggle a local vLLM model's thinking).
`resolve_runtime_provider()` correctly surfaces it as `request_overrides`
on the resolved runtime dict, but the gateway never plumbed it through to
the per-turn agent:
- `_resolve_runtime_agent_kwargs()` rebuilt the runtime dict from a fixed
key whitelist that omitted `request_overrides`.
- `_resolve_turn_agent_config()` rebuilt `runtime` from the same whitelist
and set `route["request_overrides"]` solely from `/fast` service-tier
overrides (`{}` otherwise).
- The per-turn `agent.request_overrides = turn_route.get(...)` assignment
then clobbered the value `_merge_custom_provider_extra_body()` applied at
agent construction.
Net: on the gateway, a custom provider's configured `extra_body` never
reached the model -- only `/fast` overrides survived. The CLI/TUI path
(which does not go through `_resolve_turn_agent_config`) and the auxiliary
client (which sends `extra_body` directly) were unaffected.
Fix: carry `request_overrides` through the runtime resolvers
(`_resolve_runtime_agent_kwargs`, `_try_resolve_fallback_provider`) and
merge the provider overrides into the per-turn route, layering any `/fast`
service-tier overrides on top (top-level keys, no collision with
`extra_body`).
Adds tests/gateway/test_turn_request_overrides.py.
Known follow-up: the mid-session `/model`-switch override path
(`_session_model_overrides` / `ModelSwitchResult`) does not yet carry
`request_overrides`.
Preserve initialization-time request overrides (custom-provider extra_body
merged at agent construction) while replacing only the previous turn's
routing overrides during the per-turn agent refresh. This keeps
custom-provider extra_body settings without leaving stale fast-mode
service_tier or speed values on cached agents.
Reimplemented from PR #52432 at the code's current location (the per-turn
refresh moved into the TurnRunner path since the original patch), keeping
the original merge semantics: snapshot this turn's route overrides in
agent._gateway_turn_request_overrides, evict only unchanged previous-turn
keys, then layer the new turn overrides on top.
Salvaged-from: #52432
Co-authored-by: Heng Cai <abtion@outlook.com>
Third in the series. The gateway rebuild path (previous two commits)
carries a custom provider's `request_overrides` (`extra_body`, e.g.
`chat_template_kwargs`) into the agent, but the *in-place* live switch used
by the TUI dashboard and the CLI — `agent.switch_model()` ->
`agent_runtime_helpers.switch_model()` — swapped
model/provider/base_url/api_key without ever updating `request_overrides`.
So a `/model` switch to a thinking-enabled custom provider in the TUI/CLI
kept the previous provider's `extra_body`.
`switch_model()` now re-derives the switched-to provider's
`request_overrides` (via `_get_named_custom_provider`) and applies it in
place, preserving non-provider overrides (`service_tier`/`speed` from
`/fast`). Logic factored into `_apply_switched_provider_request_overrides`
for testability.
Adds tests/agent/test_switch_model_request_overrides.py.
Carry provider-derived request_overrides through runtime resolution,
fallback projection, session /model state, restart rehydration, and
turn-route merge so named custom providers keep extra_body and related
overrides.
Salvaged from #56876 (cron half only; the delegation half is superseded
by #98237). run_job's ephemeral AIAgent constructor passed api_key /
base_url / provider / api_mode from the resolved runtime but dropped
request_overrides, so cron jobs on custom providers silently lost
extra_body / extra_headers request settings.
Extends PR #98250's classic-CLI status-bar upgrades to the Ink TUI:
- tui_gateway/server.py _get_usage() now emits cache_hit_pct,
avg_latency_s, avg_tps (reads the same per-call deque history from
agent/conversation_loop.py; keys omitted when no data — Codex
app-server has no latency, zero cache reads show no %)
- StatusRule renders the three read-outs as width-budgeted tail
segments (breakpoints 96/104/110 cols, lowest priority — they shed
first on narrow terminals)
- display.status_bar.fields (the SAME key the classic CLI honors)
filters TUI segments too: cache_hit, latency, tps, duration,
compressions, bg_tasks, bg_subagents, voice, battery, title,
context_pct, context_detail
- values ride the existing usage payload/ticker; constants between
events so the usage==last dedup keeps suppressing repaints
- 3 new server tests, 5 new TUI tests; full ui-tui suite 1727 green
Users reported no GUI switch for browser.use_real_profile — the only
desktop home was the generic Settings → Config editor, which nobody
found. The Browser toolset detail pane now renders a 'Use My Real
Browser Profile' ToggleRow above the backend/provider matrix.
- new BrowserRealProfilePanel: reads the shared profile-scoped config
record cache, optimistic write-through, rollback on failure
- saveHermesConfigRecord: capability-scoped PUT /api/config counterpart
of getHermesConfigRecord, so the Capabilities scope selector writes
the profile it points at (possibly another gateway)
- i18n: en/ja/zh/zh-hant keys (ar inherits en via defineLocale)
- docs: browser.md desktop pointer corrected to the real location
Live E2E on the built app over CDP: clicking the switch flipped
browser.use_real_profile true→false→true in the sandbox HERMES_HOME
config.yaml, GET reflected it, no layout glitches (screenshots in PR).
Profiles can now grant narrowly scoped tools to the background review runtime whitelist while unrelated tools remain denied. Document the configuration and cover it with a real-config regression test.
Agent: codex
Teknium