grok-4.5 is xAI's newest release (their versioning is non-monotonic:
4.5 > 4.20) and is the model xAI's own docs use for the server-side
x_search tool. Users who explicitly pinned x_search.model keep their
choice; everyone else picks up the new default via the config
deep-merge — no _config_version bump needed.
- tools/x_search_tool.py: DEFAULT_X_SEARCH_MODEL
- hermes_cli/config.py: DEFAULT_CONFIG x_search.model + comment
- agent/reasoning_timeouts.py: 300s stale-timeout floor entry for
grok-4.5 (grok-4.20-reasoning entry kept for pinned users)
- docs: x-search.md en + zh-Hans (config sample + troubleshooting)
- tests: default-model assertion + timeout-floor positive case
* feat(delegation): live-viewable subagent transcripts for delegate_task
Each child now streams an append-only, human-readable log to
<hermes_home>/cache/delegation/live/<delegation_id>/task-<n>.log while it
runs, and the dispatch return includes the paths so the caller can tail
them immediately instead of waiting blind for the consolidated summary.
- New tools/delegation_live_log.py: LiveTranscriptWriter (per-event append
+ flush, one-line rendering with truncation, never raises into the agent
loop), wrap_progress_callback (tees the child's existing
tool_progress_callback events into the log, preserves the _flush
contract), dispatch-time creation with pre-headered files so tail -f
attaches immediately, manifest.json (goals/task count/per-task status),
and 7-day retention pruning on new dispatches.
- delegate_task: wraps each child's progress callback with the writer;
sync results and background dispatch responses gain live_transcripts
(+ hint field on dispatch); per-task result entries carry
live_transcript; transcripts finalized with exit-reason markers.
- async_delegation: dispatch_async_delegation_batch accepts an optional
delegation_id so the live/ dir name matches the returned handle; the
completion event carries live_transcripts.
- process_registry: consolidated batch-completion block references each
task's live transcript path.
- Tool schema description documents the live_transcripts return surface;
docs gain a 'Live Transcripts' section with a tail -f example.
Placement under cache/delegation means the logs are mounted read-only
into remote terminal backends for free. Side-channel only: zero changes
to message content, so prompt caching is unaffected. Transcript-OUT only
— no overlap with the subagent control surfaces of PR #66046.
* fix(delegation): label the kickoff transcript line as user — it is the child's one user message
Add an end-to-end developer guide for extending the native Hermes Desktop
app introduced in #60638: the HermesPlugin contract, PluginContext, every
contribution area (panes, routes, sidebar nav, status/title bar, palette,
keybinds, themes, composer, mount-scoped Contribute), the host API, the
React Query + nanostores data layer, the UI kit + theme variables, the
scoped ctx.rest/ctx.socket backend (plugin_api.py under /api/plugins/<id>)
and its separate enable gate, Settings/defaultEnabled/storage, bundled
plugins, the security model, pitfalls, and a full reference.
- Register the page in the sidebar under Extending -> Plugins.
- Disambiguate from the unrelated web-dashboard plugin SDK from both
directions, and add a map-table row + a desktop user-guide pointer.
- Fill the gaps in the agent-facing hermes-desktop-plugins skill
(ctx.rest/socket + backend, React Query, defaultEnabled, Contribute)
and point it at the new reference so agents know the SDK when writing
addons.
The reported confusion was an unblocked task 'unpredictably' ending up in
triage. unblock itself only ever routes to ready/todo; a subsequent same-cause
re-block hitting BLOCK_RECURRENCE_LIMIT is what escalates to triage. Document
this deterministic loop-breaker at the human-facing lifecycle level so users
stop reading it as an LLM decision.
- codex-app-server-runtime.md: add a Live display section covering the
stream/reasoning/tool-card bridge and show_commentary gating.
- release.py: AUTHOR_MAP entries for HaiderSultanArc, jjadeo-oss, juanfradb
(the latter two for forthcoming follow-up salvages of #62396 / #18050).
Community feedback (@LSanapalli on X): the inline task-creation form is
cramped inside a ~280px column with no way to resize; board-level
workspace defaults can't be changed after board creation; and users
believe they must block a task, comment, then unblock just to talk to
a worker.
- Create-task dialog: replace the inline column form with a centered
modal (reuses hermes-kanban-dialog chrome, 36rem wide) with labeled
fields for title, assignee, priority, skills, workspace kind/path,
goal mode, and parent task. Same request shape; Enter/Escape behavior
preserved; submit disabled until a title is present.
- Board settings dialog: new Settings button in the board switcher opens
a modal to edit display name, description, and the board-level default
project directory (default_workdir). PATCH /boards/:slug now accepts
default_workdir (validated absolute existing dir; empty string clears;
omitted leaves unchanged) and returns the recomputed
default_workspace_kind so task-creation defaults follow immediately.
- Comment workflow hint: the task drawer's comment box now explains that
comments land on the thread immediately and reach the worker on its
next run/kanban_show() — no block/unblock dance needed — with a fuller
tooltip for when blocking IS the right tool.
- i18n: new keys optional in the kanban namespace with English fallbacks
in the bundle (established pattern; avoids churning 17 locale files).
- Docs: dashboard section updated for the dialog + Settings button.
* feat(browser): store full snapshots on truncation; make eval denylist opt-in
Two harness fixes motivated by BU_Bench results where fixed-verb + lossy
observation cost Hermes heavily vs code-driven browser agents:
1. Snapshot truncation no longer loses content. When a snapshot exceeds
the 8000-char threshold, the complete accessibility tree is saved to
cache/web (same truncate-and-store pattern as web_extract) and the
truncated view / LLM summary includes the file path plus a ready-made
read_file call. Element refs beyond the cut are recoverable without
re-snapshotting. Stored copies are force-redacted and capped at 2MB;
content-hash filenames dedupe repeated snapshots of the same page.
2. The browser_console(expression=...) sensitive-primitive denylist is
now opt-in via browser.restrict_evaluate (default false). The
names-based denylist blocked legitimate DOM extraction — any selector
or expression containing 'fetch', 'cookie', 'input', etc. — which
crippled the agent's only programmatic page-inspection path. The
SSRF/private-URL egress guards in _browser_eval are independent of
this policy and remain always-on. browser.allow_unsafe_evaluate keeps
its meaning (bypass the denylist) for configs that already set it.
* test: update None-guard test for stored-snapshot pointer in _extract_relevant_content
test_normal_content_returned pinned the exact return value; the summary
now carries a pointer to the stored full snapshot. Assert the summary
passes through and the pointer is present instead.
* feat(browser): align snapshot threshold with web_extract's 15k char budget
SNAPSHOT_SUMMARIZE_THRESHOLD 8000 -> 15000, matching
web_tools.DEFAULT_EXTRACT_CHAR_LIMIT so the snapshot and web_extract
truncate-and-store paths give the model the same per-page budget.
_truncate_snapshot's default max_chars now follows the constant.
Invariant test added; docs (en+zh) and CLI tip updated.
_clean_reasoning_effort kept its own whitelist that stopped at 'max',
silently dropping 'ultra' from MoA slot configs. Route it through
hermes_constants.parse_reasoning_effort — the same one-source-of-truth
fix the salvaged commit applies to the gateway — so future effort
levels can't drift here either. Docs updated to list ultra.
Follow-up to salvaged PR #64012.
Adds the proxied-callback option to the remote/headless OAuth section,
links the mcp-oauth-remote-gateway skill for fully headless gateways,
and documents the WAF pitfall behind redirect_host.
PR #36051's values went stale since May 31: session-store SCHEMA_VERSION
is now 21 (PR said 14), and the dashboard ships 8 built-in themes
(PR said 7). Also document the v16/v18/v20 data migrations added since.
Cross-checked website/docs against the source at main HEAD and corrected
documented commands, env vars, config keys, headers, and default values
that don't match the code. Docs-only; no behavioral changes.
Refs #36048
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Fixes#62452. Two amplifiers turned one slow auxiliary route into a
per-turn multi-minute stall:
1. Fallback candidates inherited the exact effective_timeout the primary
was called with. When the primary's deadline was short (tuned or
already burned), an independently healthy fallback died on the same
clock — the reporter's 163k-token compression needed ~90s on the
fallback and got the primary's 30s, every turn. fallback_chain
entries may now declare their own 'timeout' (seconds); both fallback
candidate call sites (sync + async) resolve it via
_fallback_entry_timeout, label-scoped so only configured-chain
candidates are affected. No entry timeout → task-level timeout,
preserving existing behavior.
2. A session whose transcript structurally cannot be summarized within
the deadline re-attempted every 60s, re-burning the full timeout on
every subsequent turn. Consecutive timeout-class failures now
escalate the cooldown 60s → 300s → 900s (capped); any successful
summary or session reset clears the streak. Timeout classification
takes precedence over the streaming-closed 30s rung ('timed out'
also matches _is_connection_error) and now recognizes the SDK's
'Request timed out.' phrasing.
Fail-safe behavior is unchanged: all messages are preserved when every
candidate fails; the cooldown only spaces out retries.
Document that safe-root violations are hard-blocked (not approval-gated),
add a security guide section for write_file/patch guards, and link cron
and verifier docs so users trust the footer over agent summaries.
- Nudge text now warns that repeated protocol violations will block the
task and require manual intervention, so the model understands the
consequence of ignoring the nudge.
- Kanban docs restructured to clearly separate the two defense layers:
agent-side prevention (nudge, from #64350) and dispatcher-side
recovery (bounded retry, from this PR).
- Two new integration tests verifying the nudge mentions blocking and
that the agent-side and dispatcher-side budgets are independent.
Fold in kevinb361's suggested lifecycle wording (#61817 conceded in favor of
this PR) and update the second stale site his sweep didn't cover: the
task-events table still said the dispatcher 'auto-blocks immediately instead
of retrying'. Both now describe the violation-only streak: protocol_violation
fires on every violation (its payload marker feeds the budget), below-budget
runs return the task to ready, and gave_up + auto-block happen only when the
consecutive streak reaches _PROTOCOL_VIOLATION_FAILURE_LIMIT (default 3,
per-task max_retries overriding).
The salvaged SelfHostedBackend made self-hosted servers reachable via
mem0.json / MEM0_HOST, but the setup wizard still offered only Platform
and OSS — exactly the gap users hit (Discord report: 'At memory setup
there's only 2 options'). Adds a third wizard mode:
- interactive picker: Platform / Self-hosted server / Open Source
- non-interactive: hermes memory setup mem0 --mode selfhosted
--host http://... [--api-key ...] [--dry-run]
- host -> mem0.json (behavioral), API key -> .env as MEM0_API_KEY
(secret), optional key for AUTH_DISABLED servers
- best-effort reachability check against the server, non-fatal
- README + memory-providers docs updated with the wizard path
Review follow-ups on the salvage:
- get_all() pruned from the ABC and all three backends: mem0_list (its
only caller) was removed by the recall-tuning commit, leaving new,
tested, unreachable code — including SelfHostedBackend's _MAX_TOP_K
over-fetch workaround. Tests for it dropped; fake-class stubs remain
harmlessly. (The #52921 true-total fix lives on in the PR history if
a lister ever returns.)
- The persisted rerank config key was write-only (setup prompted for it,
nothing read it). initialize() now parses it into _rerank_default and
mem0_search uses it when the model doesn't pass rerank explicitly;
per-call args still win. Guard test added.
- Platform-mode setup now warns when MEM0_HOST is set in the environment:
the json host-clear can't help there (_load_config seeds host from the
env var, docs tell users to put it in .env) — the user would silently
keep routing to the self-hosted server.
- SelfHostedBackend: connect-level retries (httpx.HTTPTransport(retries=2))
so a single transient blip doesn't count toward the provider breaker;
transport now injectable and the test helper uses the real __init__
instead of mirroring it via __new__.
- plugin.yaml description no longer leads with reranking (off by default,
platform-only); docs em-dash typo fixed.
Salvage of #55614 by @kartik-mem0 (mem0 maintainer). Adds a SelfHostedBackend
that talks to a self-hosted Mem0 Docker server over httpx (X-API-Key auth,
/search + /memories routes), gated behind `host`. Also folds in the mem0
research-team recall tuning that rides with it: rerank defaults to false across
all modes, the mem0_list tool is removed (5->4 tools), search guidance is
de-shouted, and self-hosted get_all reports the true stored total (#52921).
Supersedes the self-hosted portion of #52487 (@liuhao1024, first-submitted).
Closes#52478Fixes#52921
* docs(secrets): secret-source plugin developer guide + sidebar registration for 1Password page
- New developer-guide/secret-source-plugin.md: SecretSource contract
(never raises/prompts, fetch-only, timeout budget), framework-vs-plugin
ownership table, mapped-vs-bulk shape guidance, run_secret_cli()
subprocess-safety, registration + timing note, conformance kit usage,
ErrorKind reference.
- Register user-guide/secrets/onepassword in the sidebar (page shipped
in #59498 but was not listed, so it was unreachable from nav).
- Cross-link the user-guide plugin section to the new dev guide.
* docs: group all plugin guides under a Plugins subcategory in Extending
- Move guides/build-a-hermes-plugin.md -> developer-guide/plugins/index.md
(both locales) and make it the category landing page (slug pinned to
/developer-guide/plugins).
- New sidebar subcategory Developer Guide > Extending > Plugins holding
the general guide + all 8 provider-plugin docs (llm-access, memory,
context-engine, secret-source, model, image-gen, video-gen, web-search);
provider-doc URLs unchanged.
- Client redirect /guides/build-a-hermes-plugin -> /developer-guide/plugins.
- Update 30 cross-links across both locales.
/model switches, primary-model fallback, and credential-pool key
rotation all change the prompt-cache key (model and/or account), so
the next turn re-reads the entire conversation at full input price.
Add cost warnings everywhere docs recommend or describe these paths:
- reference/slash-commands.md: cost note on both /model rows
- user-guide/features/fallback-providers.md: warning admonition
- user-guide/features/credential-pools.md: warning admonition
- user-guide/configuring-models.md: mid-session switch warning
- guides/tips.md: expand cache tip + /model tip
- reference/faq.md: warning on the switch-back-and-forth example
- user-guide/desktop.md: composer picker bullet
- developer-guide/context-compression-and-caching.md: new
cache-aware design pattern (model identity is part of the key)
Inspired by Claude Code v2.1.199 (July 2, 2026): stacked slash-skill
invocations load all leading skills (up to 5), not just the first.
- agent/skill_commands.py: split_stacked_skill_commands() consumes leading
/skill tokens (stops at the first non-skill token so slash-path arguments
are never swallowed); build_stacked_skill_invocation_message() composes
the multi-skill turn reusing the existing bundle scaffolding markers so
extract_user_instruction_from_skill_message() keeps memory providers
storing the user's instruction, not N skill bodies.
- cli.py + gateway/run.py: dispatch the stacked path on both surfaces.
- 11 new tests + docs section in skills.md.
A single-model Hermes agent never sends temperature; the provider default
applies. MoA hardcoded reference_temperature=0.6 / aggregator_temperature=0.4,
and the coercion float(preset.get(key, 0.6) or 0.6) made unset IMPOSSIBLE to
express: absent, null, empty, and even an explicit 0 all collapsed to the
baked-in default. Every MoA advisor and aggregator therefore ran at 0.6/0.4
while the same model running solo used the provider default — silently
skewing solo-vs-MoA comparisons and overriding provider-tuned defaults.
- moa_config normalization: temperatures coerce to None when absent/blank/
invalid (new _coerce_float_or_none); explicit values incl. 0 honored.
- moa_loop: _preset_temperature() resolves preset values; None flows to
call_llm, which already omits the parameter when None (same contract as
max_tokens). Aggregator still inherits the acting agent's own configured
temperature when the preset doesn't pin one.
- conversation_loop (context-mode MoA): same resolution, no more hardcoded
0.6/0.4 at the call site.
- DEFAULT_CONFIG preset + web_server payload models + docs updated: unset
is the default, pinning stays available.
MoA per-turn latency is dominated by advisor GENERATION: turn wall time
correlates ~0.88 with output tokens and ~-0.03 with input tokens (measured over
52 turns). Each turn waits for the slowest advisor to finish writing, and
advisors were uncapped — writing multi-thousand-token essays the aggregator
only needs the gist of.
Add an opt-in per-preset reference_max_tokens knob (mirrors reference_temperature)
that caps ADVISOR output only; the acting aggregator is never capped. Default
None = uncapped, so existing presets are byte-for-byte unchanged (no regression).
Wired through both MoA execution paths (MoAChatCompletions.create and
aggregate_moa_context).
E2E: same task, closed preset uncapped vs reference_max_tokens=600 -> 59s to 33s
(~44% faster), final answer identical/correct.
- hermes_cli/moa_config.py: _coerce_int_or_none helper + reference_max_tokens
in _normalize_preset/_default_preset/flattened view
- agent/moa_loop.py: read preset.reference_max_tokens, pass to reference fan-out
- agent/conversation_loop.py: pass reference_max_tokens on the per-turn path
- tests + docs
Live DM testing showed a reply to a DM cron brief did NOT continue the job.
Root cause: for a 1:1 DM the governing knob is dm_top_level_threads_as_sessions
(default True), NOT reply_in_thread / cron_continuable_surface. Under the
default, each top-level DM keys to a per-message session (…:dm:<chat>:<ts>),
so a reply mints a new ts and can never converge with the flat …:dm:<chat>
session the cron seed creates.
A 1:1 DM has no thread-vs-timeline split, so "in_channel" has no coherent
meaning for a DM — cron_continuable_surface is a channel concept and is a
no-op for DMs. DM continuation is governed entirely by
dm_top_level_threads_as_sessions:
- false → all top-level DMs share …:dm:<chat> → seed + reply converge → works
- true (default) → per-message sessions → no continuation (cron or interactive)
Option A (chosen): document the requirement; no code change (the flat-DM seed
from the prior commit already lands correctly when the knob is false). Adds a
":::note 1:1 DMs" admonition to cron.md + the zh-Hans mirror.
Verification (real inbound handler, not a hard-coded assumption — the mistake
that made the earlier DM E2E falsely pass): tests/manual/cron_inchannel_dm_e2e.py
drives the REAL _handle_slack_message for a top-level DM under both knob values
and asserts false→converges (…:dm:D_TESTDM == seed), true→diverges
(…:dm:D_TESTDM:<ts>). See decisions.md D9.
Add a per-platform `cron_continuable_surface` extra key
(`thread` default | `in_channel`) so a continuable cron job can deliver
FLAT into a Slack channel — no dedicated thread — and still be
replied-to. In `in_channel` mode the scheduler skips the thread-open
branch (leaves `thread_id=None`); the shipped origin-mirror then seeds
the `(slack, chat_id, None)` shared-channel session — the same bucket
`reply_in_thread: false` routes inbound channel replies to — so a plain
channel reply continues the job in context.
Design: specs/cron-inchannel-continuable (D1–D7, F5). Model B
(shared-channel session), NOT anchoring to the delivery `ts` — on Slack
replying to a specific message IS threading, so a `ts` anchor would only
relocate the thread, never deliver true threadless continuable.
- gateway/platforms/base.py: `supports_inchannel_continuable` capability
flag (default False → unsupported platforms fail SAFE to `thread`).
- plugins/platforms/slack/adapter.py: flag=True; `_cron_continuable_surface()`
resolver (coerces to the two-value enum); `_warn_if_inchannel_without_flat_reply`
connect-time warning (D5: warn, not hard-require — the misconfig fails safe).
- gateway/config.py: shared-key bridge line (top-level OR nested config).
- cron/scheduler.py: read the key generically from platform config, gate
the `in_channel` branch on the adapter capability flag, skip thread-open.
No new seed function (reuses the existing mirror — G6).
Pairing (docs): `in_channel` + `reply_in_thread: false` +
`require_mention: false` (or a free-response channel). Missing
`reply_in_thread: false` fails safe to a threaded continuation.
Gateway-side config flag — `/restart` to apply; NO Slack app reinstall.
Tests (from inside the worktree, PYTHONPATH=$PWD):
- +6 cron scheduler tests (in_channel skips thread-open; seeds flat
channel session with thread_id=None; thread-mode regression;
fail-safe on unsupported platform; value coercion). Prove-fail:
removing the `and not in_channel_surface` guard turns the two
load-bearing tests RED; restore → GREEN.
- +10 slack resolver/capability/warning tests; +2 config-bridge tests.
- tests/manual/cron_inchannel_e2e.py: offline E2E driving BOTH real
legs (delivery seed + inbound reply keying) → both converge on
(slack, C, None).
- No regressions: test_slack.py 216 passed alone; broader sweep green
(4 pre-existing cross-file-ordering failures reproduce identically on
pristine origin/main).
Docs: cron.md + slack.md + zh-Hans mirrors of both.
Registers PowerShell (.ps1/.psm1/.psd1) in the LSP server registry,
spawning PowerShellEditorServices over stdio via a pwsh/powershell
host. PSES ships as a GitHub release zip (no npm/go/pip recipe), so it
sits in the manual install tier alongside rust-analyzer and clangd.
The spawn builder resolves the module bundle from (in order) the
lsp.servers.powershell.command override, init bundlePath, the
PSES_BUNDLE_PATH env var, or <HERMES_HOME>/lsp/PowerShellEditorServices,
then launches Start-EditorServices.ps1 -Stdio with a non-interactive,
no-profile host. hermes lsp status/list report it as manual-only until
pwsh is present.
Docs and tests included.
Cron pre-run scripts were capped at 120s by default, which surprised
users running long data-collection scripts on crons (the whole point of
crons being to offload long work). Raise _DEFAULT_SCRIPT_TIMEOUT to 3600s
(1 hour).
This bounds the script only — skill/agent jobs already run on a separate
inactivity budget (HERMES_CRON_TIMEOUT, default 600s idle, 0=unlimited),
not a wall-clock cap. Scripts dispatch to a persistent thread pool and do
not hold the tick lock, so a long script doesn't starve other due jobs.
Docs clarified to make the script-vs-agent timeout distinction explicit.
env/config overrides (HERMES_CRON_SCRIPT_TIMEOUT,
cron.script_timeout_seconds) unchanged and still take precedence.
Add a `pre_verify` user/plugin/shell hook fired once per turn when the agent
edited code and is about to finish, after the existing verify-on-stop guard. A
hook can keep the agent going one more turn (run a check, defer it, tidy the
diff) by returning {"action":"continue","message":...} (the Claude-Code Stop
shape {"decision":"block","reason":...} is accepted too). Hooks receive coding,
attempt, final_response, and sorted changed_paths so they can self-scope and
self-throttle; the path is bounded by agent.max_verify_nudges and preserves
message-role alternation.
Hermes still ships its default coding guidance (agent.verify_guidance, on by
default), but it now rides the evidence-based verify-on-stop missing-evidence
nudge instead of a separate default pre_verify continuation, so it costs no
extra model turn of its own. Guidance reuses the shared utils.is_truthy_value
parser rather than a local copy.
