The include/exclude filter matched exact names only — glob-style entries
('*_radar_*') silently matched nothing, so a Cloudflare flat-mode config
meant to trim 3,320 tools to ~1,900 actually registered 3,319. Unmatched
patterns produced no warning.
- matches_name_filter(): exact membership first (O(1) for literal lists),
then fnmatch.fnmatchcase for entries containing * ? [ — same pattern
semantics as approvals.deny. Entries without metacharacters stay
strictly literal ('docs' never matches 'docs_search').
- _should_register() uses it for both include and exclude (symmetric)
- hermes mcp tools picker (mcp_config.py) pre-selection uses the same
matcher so the UI agrees with runtime registration
E2E against the live Cloudflare capture with the real exclude list:
3,320 -> 1,905 surviving (1,415 excluded); radar/DLP gone,
purge_cache/dns_records kept. 220/220 mcp_tool tests (4 new).
Teknium review changes on the tiered policy:
1. threshold_pct default 10 -> 5 (listing budget = min(5% of context,
listing_max_tokens)); unknown-context fallback 20K -> 10K.
2. Tier 2 no longer leaves the model blind: when even names-only doesn't
fit, the bridge description now carries a one-line-per-server summary
('cloudflare (3320 tools)') plus an instruction to search FIRST rather
than substitute a generic tool or claim the capability is missing —
the measured tier-2 failure mode (core-tool substitution) at zero
meaningful token cost (~50 tokens/server).
3. Listing degradation is now PER SERVER, largest first: one oversized
server (Cloudflare) collapses to its summary line while small
co-attached servers (Linear) keep their full per-tool listings
('mixed' form). Previously global: attaching Cloudflare next to
Linear silently cost Linear its listing. Greedy fit is deterministic
(size then label) so the rendered block stays byte-stable per catalog
— prompt-prefix cache safe.
E2E on real captures (defaults, 200K ctx): linear alone -> tier 1 full;
unreal alone -> tier 2 groups (5% budget) / tier 1 names at 1M;
cloudflare alone -> tier 2 groups; linear+cloudflare -> tier 1 MIXED
(linear fully listed, cloudflare summarized). 48/48 tests.
Tier 0: no MCP/plugin tools -> everything eager (pass-through).
Tier 1: deferred tools whose catalog listing fits min(threshold_pct%
of context, listing_max_tokens) -> bridge + skills-style
listing, degrading to names-only over budget.
Tier 2: listing over budget even names-only (Cloudflare's flat API
surface: 3,320 tools, names alone ~32K tokens) -> bare bridge,
discovery through tool_search only.
The old activation threshold (defer only when schemas > threshold_pct
of context) let mid-size catalogs ride eager and pay full schema cost;
with servers like Cloudflare (~597K tokens of schema, would not even
fit a 200K window) the binary gate is the wrong shape. Activation is
now driven purely by deferrable-tool presence; threshold_pct is
repurposed as the listing budget's context-relative leg.
- AssemblyResult gains tier + listing_form for observability
- listing_max_tokens default 4000 -> 20000 (cap 60000) so an 830-tool
catalog keeps a names-only listing while Cloudflare-scale drops to
bare bridge
- E2E verified against real captures: Linear 24 tools -> tier 1 full,
Epic UE 5.8 830 tools -> tier 1 names-only, Cloudflare 3,320 tools
-> tier 2 (both 200K and 1M context)
Deferred MCP/plugin tools become invisible once the tool_search bridge
activates — live benchmarking (48 runs, Claude Haiku 4.5) showed models
substituting visible core tools (terminal/web_search/browser) for deferred
capabilities or declaring them nonexistent instead of searching: 16/24
task success vs 24/24 with eager loading.
Skills never had this failure mode because every skill keeps a ~21-token
name+description listing line in the system prompt. This ports that exact
pattern to the tool bridge: when tool_search activates, a grouped manifest
of every deferred tool (name + first sentence of description, clipped to
60 chars, grouped per MCP server / toolset) is embedded in the tool_search
bridge description.
- tools/tool_search.py: build_catalog_listing() with deterministic
ordering (byte-stable across assemblies -> prompt prefix stays
cacheable); token-budget fallbacks full -> names-only -> legacy bare
count; bridge_tool_schemas(listing=...) embeds it and instructs the
model to skip tool_search when the exact name is visible (one fewer
round-trip per use)
- config: tools.tool_search.listing auto|on|off (default auto),
listing_max_tokens (default 4000, clamped 200..20000); legacy bool
shapes keep working
- tests: 8 new tests (config parsing/clamps, short-desc clipping,
deterministic rendering, budget fallbacks, bridge embedding, assembly
on/off paths); full file green (47 passed)
- docs: tool-search.md config table + rationale
- scripts/tool_search_livetest2.py: benchmark harness v2 with real
per-call token accounting (normalize_usage spy) and a third 'listing'
mode for A/B/C comparison
The background write guard decided ownership from `isinstance(usage_rec, dict)`,
so a local skill with NO usage record passed. That successful write called
bump_patch(), which created a `created_by: null` record — and the identical
write was refused from then on. "Allowed exactly once, then never" is a race
with our own bookkeeping, not a policy. Reproduced on main: patch #1 succeeds,
patch #2 with the same arguments is refused.
Option B from the issue. Option A (split `session_review` from
`scheduled_curator` and let the session fork patch user-owned skills it
consulted) would widen autonomous write permission onto skills the user owns
with no user present to consent — wrong direction for a no-user-present actor.
- skill_manager_tool: missing and explicit-null records now resolve
IDENTICALLY, both fail closed. The refusal names the reason and points at
`hermes curator adopt <name>`.
- background_review: both review prompts told the reviewer to patch any skill
consulted in the session and claimed pinned skills could be improved, while
enforcement refused both. Prompts now list pinned, external, and user-owned
skills as protected, and tell the reviewer to RECOMMEND adoption instead of
attempting a write that will be refused.
- skill_usage: document that `created_by` is a curator-management policy flag,
not a provenance claim, and add `is_curator_managed()` so call sites read as
the question they ask. Field name retained — it is on disk in every
`.usage.json` and renaming would strand those records.
- curator CLI: `hermes curator list-unmanaged` itemizes unmanaged skills with
the reason each is unmanaged (completes the #67139 spec).
Foreground writes are untouched: a user-directed edit to a user-owned skill
still works, including on pinned skills.
Sibling tests: 9 failures in test_skill_manager_tool.py were fixtures that
created record-less skills to exercise OTHER guards (consolidation-delete,
read-before-write) and relied on ownership falling through. Fixed at the
fixture, since the real curator only ever operates on managed sediment. One
test asserted the old "manually authored" wording; rewritten to assert the
behavior contract instead of the string.
Validation: 274 targeted tests + all 7 background-review files (60 tests) pass.
E2E on a temp HERMES_HOME (30 checks) covers the flip, foreground writes,
adoption unblocking, pin semantics, prompt/enforcement parity, and the new verb.
Each new test sabotage-verified: revert the fix, confirm it goes red.
Fixes#67140
`hermes curator status` reported only the skills it manages, staying silent
about curation-eligible skills it can never touch. On a 237-skill library that
meant 112 skills were invisible to every automatic transition with no signal
anywhere — the curator looked broken when it was working as designed.
A skill becomes curator-managed only when `created_by: agent` lands on its
usage record, and only the background review fork writes that marker. Two
populations therefore never qualify: records written before the marker existed
(no key at all, authorship unknowable) and every foreground
`skill_manage(create)` (unset by design — those skills belong to the user).
- skill_usage: `list_unmanaged_skill_names()` / `unmanaged_report()` enumerate
the blind spot, tagging each row with `has_provenance_key` so the two causes
are distinguishable. `adopt_skill()` writes the marker on user declaration
and refuses bundled, hub-installed, external, and protected built-ins.
Adoption never resets the inactivity clock.
- curator CLI: status prints an `unmanaged (no provenance marker)` block on
BOTH the managed and no-managed-skills paths; new `adopt` verb takes names or
`--all-unmanaged`, with `--dry-run` and a confirmation prompt on bulk.
- skills_sync: `_backfill_optional_provenance()` matched candidates by
repo-derived path only, so a skill installed at `mlops/chroma` that upstream
later moved to `mlops/vector-databases/chroma` was skipped forever and
`hermes skills repair-optional` could not fix it. Falls back to an
unambiguous name match, still gated on identical content, and records the
ACTUAL install path.
Provenance stays a declaration, never an inference: a high patch count proves
the agent MAINTAINS a skill, not that it authored one, since Hermes edits
user-written skills on the user's behalf routinely. An "looks agent-made"
heuristic would eventually archive hand-written work.
Validation: 347 targeted tests pass. Each new test verified via sabotage run
(revert the fix, confirm the test goes red) — one initially passed for the
wrong reason because the fixture pinned `prune_builtins` off, masking the guard
under test; fixed to force the shipped default on.
The Codex image backend rejected our own request shape for every account, and
we then translated that rejection into "Image generation is not enabled for the
current Codex account. Switch the image provider to OpenAI API key, FAL, or
xAI." — telling every affected user to abandon a provider that had never
actually been tried. That message is why this reads as a setup failure rather
than a bug: the wire error was replaced with a confident, wrong diagnosis.
Removes the classifier and its exception, so any HTTP failure surfaces
verbatim. The paired request-shape fix (previous commit) is what makes the
400 stop happening; this commit makes the next one diagnosable.
Also fixes error-body truncation: bodies were head-truncated at 500 chars, and
Codex error payloads can carry hundreds of bytes of leading metadata, so the
user got a wall of padding and no message. _summarize_error_body() prefers the
parsed error.message and falls back to a truncated raw body.
Docs: drop the unqualified image-to-image claim for the Codex backend and note
that the hosted tool call cannot be forced, so it is best-effort.
Verified E2E against a local fake Codex backend: success path writes a real PNG
with no tool_choice on the wire; the 400 path now returns api_error carrying
"Tool choice 'image_generation' not found in 'tools' parameter" (148 chars)
instead of the entitlement message. Sabotage run confirms all 4 regression
tests fail when the old behavior is restored.
Refs #19505, #49008, #31335.
Some OpenAI-compatible endpoints — notably Tencent Copilot
(copilot.tencent.com) — only accept streaming chat requests; any
non-streaming call returns HTTP 400 (code 11101, 'Non-stream chat
request is currently not supported'). The main conversation loop already
streams, so interactive chat works, but every auxiliary task (title
generation, compression, web extraction) used the non-streaming path and
failed on each call.
_provider_requires_stream() detects stream-only endpoints
(copilot.tencent.com built in, plus user-configurable
auxiliary.stream_only_base_urls substring markers in config.yaml).
Matching sync auxiliary calls route through _create_with_progress
(force_stream=True) and async calls through the new
_acreate_with_stream, aggregating the chunk stream — including tool-call
deltas and reasoning deltas — into a complete response via the shared
_ChatStreamAccumulator.
Salvaged from PR #60686 by @kudi88 onto the progress-aware streaming
machinery from #71508, addressing both sweeper-review gaps: the async
path now consumes the stream with 'async for' (awaiting create() and
iterating synchronously raised on AsyncOpenAI streams), and tool-call
deltas are reassembled instead of dropped (MCP passes tools= through
call_llm). Under force_stream there is no silent non-streaming retry —
a stream-only provider rejects those by definition, so the original
error surfaces to the normal recovery chains.
The gateway's pre-agent session-hygiene compression killed the summary
call at a fixed 30s wall-clock deadline (compression.hygiene_timeout_seconds),
regardless of whether the summary model was hung or merely slow. A reasoning
model happily streaming a large summary was cut off mid-generation, the user
got '⚠️ Context compression timed out after 30.0s', and a 300s failure
cooldown left the session oversized — a doom loop for slow-but-healthy
auxiliary models.
Timeouts are now liveness-based instead of wall-clock-based:
- agent/auxiliary_client.py: new thread-local aux_progress_hook. When
installed (only by context compression today), the primary call_llm
attempt streams (stream=True) and aggregates chunks back into a complete
response, ticking the hook per chunk. The configured timeout then acts
per stream read (idle) instead of as a total budget. Providers that
reject streaming fall back to the plain non-streaming call; auth/payment/
rate-limit/transport errors propagate unchanged into the existing
recovery chains. Codex Responses (per SSE event) and Anthropic Messages
(per stream event, via the new create_anthropic_message on_stream_event
callback) tick the same hook from inside their wire adapters.
- agent/conversation_compression.py: CompressionCommitFence gains
touch_progress()/seconds_since_progress(); compress_context() installs
fence.touch_progress as the progress hook around the compress call.
- gateway/run.py: the hygiene wait loop treats hygiene_timeout_seconds as
an INACTIVITY budget — while the fence reports fresh progress the wait
extends, bounded by the new compression.hygiene_total_ceiling_seconds
(default 600s, clamped >= the idle budget) so a degenerate trickle
stream still dies. The timeout warning now says the summary model
produced no output, which is the only case that still triggers it.
- config/docs: hygiene_total_ceiling_seconds added to DEFAULT_CONFIG and
configuration.md; hygiene_timeout_seconds documented as inactivity-based.
Tests: tests/agent/test_aux_progress_streaming.py (hook plumbing, stream
aggregation incl. tool-call deltas and reasoning deltas, rejection
fallback, ceiling kill, fence progress surface); two new gateway tests
prove a slow-but-streaming worker survives past the fixed timeout
(sabotage-verified: fails with the old fixed deadline) and a
forever-trickling worker is still cut off at the ceiling.
Builds on this PR's diagnosis by @Frowtek: a missing workdir is
ambiguous (deleted project vs. an unmounted external volume / network
share / VPN not yet up), so it's not safe evidence for a destructive
GC sweep — especially one that runs unattended at startup.
- cli.py / gateway/run.py: the startup auto-maintenance sweep now
always passes delete_orphans=False to maybe_auto_prune_checkpoints().
It still prunes by retention_days, size cap, and legacy archives —
none of which require guessing whether a project was deleted or is
just temporarily unreachable.
- hermes_cli/config.py: drop the now-unused delete_orphans default.
- hermes_cli/checkpoints.py: `hermes checkpoints prune` (the explicit,
human-invoked path) now previews the orphan project list and asks
for confirmation before deleting, unless -f/--force is passed.
- Docs updated (EN + zh-Hans) to match.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Adds a 'Host integration' section to the ACP guide and a row in the
environment variable reference so the next ACP host implementer does not
have to read the adapter source.
Documents the exact contract the tests already pin: the value must be
exactly `1`; unset/empty/`0`/`false` keep the default behavior; only
globally configured config.yaml MCP discovery is skipped, and servers
supplied by the ACP session through session/new are still registered.
Framed as a host-set process marker rather than user configuration - the
same shape as the existing HERMES_KANBAN_TASK entry - so it does not read
as a behavioral setting that belongs in config.yaml.
Co-authored-by: amanning3390 <adam.manning@pro-serveinc.com>
Signed-off-by: amanning3390 <adam.manning@pro-serveinc.com>
Add authenticated GET /api/model/options to the gateway API server,
sharing the dashboard/TUI picker payload builder so external clients
can sync to the user's configured Hermes provider catalog instead of
scraping the single OpenAI-compatible /v1/models alias.
- new shared hermes_cli.inventory.build_model_options_payload() wraps
build_models_payload with the stable picker shape and safe
custom-provider probe policy (probe current only on normal open,
probe all + cache bust on explicit refresh)
- dashboard web_server and TUI gateway model.options refactored onto
the shared builder; dashboard build moved off the event loop via
run_in_threadpool
- capabilities endpoint advertises model_options
- docs for both API server and programmatic integration
Salvaged from PR #54689 by @abundantbeing.
Follow-ups on the salvaged #54426 routing contract:
- Bare `model` without `provider` on the OpenAI-compatible endpoints
(/v1/chat/completions, /v1/responses) is now opt-in via
gateway.platforms.api_server.direct_model_requests (default off) —
generic OpenAI clients hardcode model names ('gpt-4o', ...) and
existing deployments rely on those falling back to the gateway
default. Explicit `provider` requests and the Hermes-native
session-chat + /v1/runs surfaces are always honored.
Idea credit: PR #22825 by @mssteuer.
- A model_routes alias with no `model` key can no longer leak the
alias string as the executing model name (defensive; parse-time
validation already drops such routes).
- Fix mis-indented _run_agent call args in _handle_session_chat_stream.
- Docs: document the opt-in flag.
Carry model, provider, and model_options through the API server's
execution surfaces (session chat, Chat Completions, Responses, /v1/runs)
without mutating global configuration. Precedence: session /model
override -> model_routes alias -> direct request selection -> global
defaults. Conflicting route/provider mixes fail closed with 400.
model_options stays request-scoped regardless of which selection wins.
Salvaged from PR #54426 by @abundantbeing.
The design-md skill documented the Apr 2026 (0.1.x) CLI behavior, which
has since drifted:
- Lint rules: the skill listed 7 rules that no longer exist by those
names (duplicate-section, invalid-color, wcag-contrast,
unknown-component-property); the 0.3.0 linter runs 9 rules
(contrast-ratio, orphaned-tokens, missing-primary, missing-typography,
section-order, unknown-key, token-summary, missing-sections,
broken-ref). Verified against live lint output.
- Colors: any CSS color is now valid (oklch/rgb/named), not hex-only.
- Export: json-tailwind (v3) + css-tailwind (Tailwind v4 @theme CSS)
formats; 'tailwind' is a back-compat alias. New exit-code semantics
(export exits 0 regardless of source lint findings).
- Section order / duplicate headings are lint warnings, not file
rejection (verified: duplicate + out-of-order sections exit 0).
- Windows: documented the designmd dot-free bin alias (the design.md
bin name collides with the .md file association); skill declares
platforms: [windows].
- New pitfall: typography sub-property typos (fontwight) are silently
dropped with no finding as of 0.3.0.
All claims verified by running @google/design.md 0.3.0 live (lint,
export, duplicate-section, oklch token, starter template lints clean).
Docs page regenerated via generate-skill-docs.py.
Auto-gen page slugs, catalog rows/paths, sidebar entries, and zh-Hans
mirrors follow the directory renames. Also updates the install path
official/creative/audiocraft -> official/creative/audiocraft-audio-generation
in the songwriting-and-ai-music pointer section.
Adds a device authorization grant flow alongside the existing loopback
OAuth flow, so `hermes setup` can connect to Honcho cloud from SSH and
other no-browser environments.
- oauth.py: new HTTP seams — _http_post_form_status (non-raising, since
RFC 8628 polling reads the OAuth error off a 400) and _http_get_json
for the RFC 8414 metadata probe
- oauth_flow.py: DeviceCode, request_device_code, poll_for_token with
slow_down backoff (+5s, capped at 60s) bounded by expires_in, typed
errors (AccessDenied, DeviceCodeExpired, AuthorizationTimeout), and
supports_device_login (fail-closed metadata gate); device flow ends in
the same install_grant tail as loopback so refresh/status work
unchanged
- oauth_flow.py: loopback callback now serves a "sign-in was not
completed" page on consent cancel instead of the success page
- cli.py: cloud menu offers oauth / device / apikey; the device option
only appears when the host advertises the grant, and becomes the
default when no browser is detected
- 18 new tests covering the full flow against a local fake AS, backoff
schedule, error mapping, deadline bound, metadata gate, and wizard
branches
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Audited every reference against ground truth (COMMAND_REGISTRY, argparse
--help output, TOOLSETS dict, provider profiles, DEFAULT_CONFIG) and
corrected drift the restructure had carried over verbatim:
- slash-commands.md: rebuilt from the live registry. Removes the phantom
/skill command (never existed — skills load via /skills, hermes -s, or a
skill's own /<name> command) and the wrong /q alias on /quit (/q belongs
to /queue) — both reported by @liuhao1024 in #50608 and @gauravsaxena1997
in #50613. Adds ~25 real commands that were missing (/learn, /memory,
/pet, /hatch, /bundles, /moa, /suggestions, /blueprint, /whoami, …) with
correct aliases and CLI/GW scoping.
- cli-reference.md: verified flags (-z/--oneshot, --tui/--cli, --safe-mode),
real subcommand sets for config/setup/sessions/skills/gateway/mcp/profile/
auth/webhook/cron/skin/pets, added missing top-level commands (fallback,
project, moa, logs, console, hooks, security, backup); condensed tables.
- providers-and-models.md: rebuilt from the 36 shipped provider profiles
with their actual env vars (was 21 rows, several stale); folds in the
alias system and fallback-chain command.
- configuration.md: toolset table matches TOOLSETS (adds coding,
computer_use, video_gen, context_engine, project; drops nonexistent
messaging/rl), config sections match DEFAULT_CONFIG, STT/TTS provider
lists match the shipped set.
- background-systems.md: curator verbs match the argparse surface.
- troubleshooting/security-privacy/windows-quirks/contributor-guide: fixed
dangling 'section above/below' references from the body split; moved the
reset-permissions playbook to security-privacy.md (its routing home).
Reported-by: liuhao1024 <sunsky.lau@gmail.com>
Reported-by: gauravsaxena1997
Flips the default fan-out cadence from per_iteration (advisors re-run on
every tool iteration, multiplying advisor spend by tool-loop depth) to
user_turn (advisors run once on the first message of each user turn; the
acting aggregator works the rest of the tool loop with that turn's
advice). Until per-mode benchmarks justify a costlier default, MoA
defaults to the cheapest, lowest-impact cadence (#67199).
One default for everyone — no split legacy/new-preset semantics; presets
that want per-step advising set fanout: per_iteration explicitly. All
three modes (user_turn / per_iteration / every_n:N) remain selectable;
every_n:1 still collapses to per_iteration (semantic identity), while
unparseable values now fall to user_turn (the default).
Docs updated with a default-change note; the per-iteration rerun test
pins its mode explicitly.
Co-authored-by: skyer-flyyy <188930297+skyer-flyyy@users.noreply.github.com>
Every SKILL.md description over 60 chars was silently truncated to
57 chars + '...' in the system-prompt skill index
(extract_skill_description, agent/skill_utils.py), destroying the
routing signal for 69 of 179 skills — some descriptions ran to
1,005 chars.
Rewrites follow the authoring standard: <=60 chars, one sentence,
ends with a period, trigger front-loaded, no marketing words, no
skill-name repetition. Excess detail already lives in each skill's
body.
Includes the touchdesigner-mcp trim from PR #32361 (credit:
@JeliTron) and aligns with the router-precision direction of PR
#48780 (@John-Lussier). Docs catalogs + per-skill pages regenerated
via website/scripts/generate-skill-docs.py.
Co-authored-by: JeliTron <287797501+JeliTron@users.noreply.github.com>
Make the x_search / xurl boundary explicit in the skill, feature docs,
toolset metadata, setup note, and reference pages, while keeping the
model-facing x_search schema generic (no static xurl name).
Regression tests assert behavioral routing invariants rather than frozen
prose snapshots. Drop the stale CI-only plugin/hangup hunks already on
main so this rebases cleanly.
skills/computer-use/SKILL.md sat at the root of the bundled skills
tree as an uncategorized single-skill directory. Move it to
skills/autonomous-ai-agents/computer-use/ alongside claude-code,
codex, opencode, and hermes-agent.
- git mv skills/computer-use -> skills/autonomous-ai-agents/computer-use
(history preserved)
- root-level-skill docstring examples (commands.py,
generate-skill-docs.py) now use a generic placeholder instead of
naming a specific skill, since categorizing root-level skills is
ongoing
- docs: move the bundled page to autonomous-ai-agents-computer-use,
update sidebars.ts, skills-catalog.md, and the two skill-path
references in features/computer-use.md
E2E validated: fresh sync_skills() copies to the new nested path;
existing installs with the old flat copy keep it untouched (manifest
name-keyed, hash unchanged -> skipped, no duplicate);
_get_category_from_path resolves 'autonomous-ai-agents'; docusaurus
build green; 396 targeted tests pass.
Claude Code's /simplify was renamed away, community-restored, and rebuilt
since our 3-agent port (v2.1.63 -> v2.1.154+). This brings simplify-code
in line with the current upstream design, re-expressed in our own wording
and layered onto our existing risk-tier/confidence machinery:
- New Reviewer 4 (Altitude): flags band-aid fixes layered on shared
infrastructure — special cases, symptom patches with unfixed sibling
sites, workaround stacks — and points at the deeper mechanism fix.
Matches our AGENTS.md 'fix the class, not the site' rubric.
- Explicit cleanup-vs-bug-hunt boundary: this skill improves working
code; correctness review stays with requesting-code-review.
- Inline single-pass fallback when delegate_task is unavailable (leaf
subagents, delegation disabled) — previously the skill just broke;
now all four angles run sequentially with honest disclosure.
- Finding format gains a concrete-cost field.
- Efficiency reviewer adds closure-capture scope-retention leaks.
- Pitfalls: fan-out cap 3 -> 4, band-aid-vs-deliberate-boundary caveat,
no-bug-hunting drift guard.
Kept our value-adds upstream lacks: SAFE/CAREFUL/RISKY tiers,
Chesterton's Fence via git blame, dry-run/focus/scope modifiers.
The yuanbao skill is platform-specific guidance for Tencent Yuanbao
group chats — niche for the default bundled set. Per the
'when in doubt, optional' rule, ship it as an optional skill.
Install via: hermes skills install official/yuanbao/yuanbao
The nano-pdf description repeated the skill name ('via nano-pdf CLI'),
violating the skill authoring standard, and spent its char budget
restating the name instead of distinguishing the skill from the
structural pdf skill. New description: 'Edit text in existing PDFs via
natural-language prompts.' (56 chars) — no name repetition, and
'text in existing PDFs' contrasts cleanly with pdf's
'Create, merge, split, fill, and secure PDF files.'
Propagated to the auto-generated docs pages and zh-Hans locale
(catalog row + per-skill page) for locale parity.
Per the 'when in doubt, optional' rule — zero-shot image segmentation
via SAM is a niche computer-vision capability with heavy deps
(torch, transformers), not something most users load.
Install via: hermes skills install official/mlops/segment-anything
Both are heavy-dep, GPU-bound local music-generation skills (8-16GB VRAM,
torch stacks, manual source patches) that were bundled in two different
categories (media/ and mlops/models/). Per the 'when in doubt, optional'
rule they now sit side by side in optional-skills/creative/, and the
bundled songwriting-and-ai-music skill points at them for local generation.
- git mv skills/media/heartmula -> optional-skills/creative/heartmula
- git mv skills/mlops/models/audiocraft -> optional-skills/creative/audiocraft
- cross-link related_skills both ways + songwriting-and-ai-music
- new section 10 in songwriting-and-ai-music with install commands
- docs: bundled pages -> optional pages (en + zh-Hans), catalogs, sidebar
Install via:
hermes skills install official/creative/heartmula
hermes skills install official/creative/audiocraft
The hermes-agent skill body was a 51KB monolith loaded in full on every
trigger. It is now a lightweight hub (~12KB): identity, quick start, the
tmux orchestration guide (kept in-body — the autonomous-ai-agents category
contract), surface orientation, and hard invariants, with a routing table
into 18 reference files that carry the depth.
Absorbed four Hermes-specific skills as first-class references so their
content gains a discoverable home and room to grow without bloating any
primary body:
- skills/hermes-themes -> references/themes.md + templates/skin.yaml
- skills/hermes-desktop-plugins -> references/desktop-plugins.md + templates/plugin.js
- skills/productivity/tui-widgets -> references/tui-widgets.md + templates/clock.mjs
- skills/productivity/petdex -> references/petdex.md
New references extracted from the old body: cli-reference, slash-commands,
providers-and-models, configuration, project-context-files,
security-privacy, background-systems, windows-quirks, troubleshooting,
contributor-guide (native-mcp and webhooks already existed). Also commits
delegate-task-concurrency-diagnosis and portal-auth-for-third-party-apps,
which the old body referenced but the repo never shipped.
Description updated to cover the widened scope:
'Use, configure, theme, extend, and orchestrate Hermes Agent.' (60 chars)
skills/dogfood/SKILL.md sat at the root of the bundled skills tree,
making it one of the few uncategorized skills (Discord /skill
autocomplete listed it under 'uncategorized'; hermes_cli/commands.py
cited it as the example). Move it to
skills/software-development/dogfood/ alongside the other QA/testing
skills (test-driven-development, systematic-debugging,
requesting-code-review).
- git mv skills/dogfood -> skills/software-development/dogfood
(history preserved)
- fix test fixture path in tests/tools/test_browser_console.py
- update root-level-skill docstring examples (commands.py,
generate-skill-docs.py) to cite computer-use, which is still root-level
- drop 'dogfood' from the category list in hermes-agent-skill-authoring
SKILL.md (en + zh-Hans docs mirrors)
- docs: regenerate/move the bundled page to
software-development-dogfood (en + zh-Hans), update sidebars.ts,
skills-catalog.md, and the adversarial-ux-test related-skills link
E2E validated: fresh sync_skills() copies to the new nested path;
existing installs with the old flat copy keep it untouched (manifest is
name-keyed, hash unchanged -> skipped, no duplicate);
_get_category_from_path resolves 'software-development'; docusaurus
build green.
Maintainer scoping decision for the #51226 salvage: document that
select_context() is for engines that must REPLACE per-request context
(retrieval/routing) — pre_llm_call is inject-only by documented cache
design; that observation-only plugins should implement a MemoryProvider
(sync_turn) rather than a context engine, with on_turn_complete scoped
as the observation mirror for engines that already select; and that a
non-no-op select_context naturally changes the prompt-cache prefix on
turns where the selection changes — engines should return stable
selections when nothing changed.
- website guide: on_turn_complete() now carries the same best-effort coverage
caveat as the ABC docstring (fires from the finalization seam; abnormal
early-return paths bypass it) — removes the doc/code inconsistency.
- test: finalization seam emits on_turn_complete with usage=None + the
interrupted flag for an interrupted finalized turn. Docstring records that
the negative early-return-bypass half is best-effort and deferred to a
shared-seam follow-up rather than pinned via a full run_conversation harness.
- _apply_context_engine_selection: reject an empty list. all([]) is True, so
a [] returned by a failing/buggy engine previously replaced a valid request
with an empty message list the downstream sanitizers can't restore; now it
falls open to the unmodified request (honors the fail-open contract).
Thanks @johnnykor82 for catching this on #41918's review.
- test: empty list keeps the original request (fail-open regression).
- docs: document select_context()/on_turn_complete() in the public
context-engine plugin guide (were still describing only the old contract).
Routine automatic compression stays silent-by-design on chat platforms
(default unchanged, byte-identical). New opt-in config key
compression.progress_notices (bool, default false) opens a gate on the
gateway noise filter (_prepare_gateway_status_message) that lets ROUTINE
compression progress statuses through to chat surfaces.
- Membership is derived from the #69550 status template constants in
agent/conversation_compression.py (compiled to a literal-escaped regex,
never re-inlined wording), so unrelated noisy statuses (aux failures,
provider retry/rate-limit chatter) stay suppressed even when enabled.
- The compaction completion notice (COMPACTION_DONE_STATUS, #69546
lifecycle 'compacted' edge) already flows through the status path and
passes the filter — no new emit site needed.
- Config wired everywhere: hermes_cli/config.py DEFAULT_CONFIG,
cli-config.yaml.example, gateway raw-YAML read (live, mtime-cached),
gateway hot-reload cache-busting key list, website configuration docs.
- Failure notices and manual /compress feedback remain always-visible;
VISIBLE_COMPRESSION_MESSAGES and emit sites untouched.
Design by @havok-training (issue #52995).
Per the 'when in doubt, optional' rule — the live-kernel workflow needs
uv + JupyterLab + a running server + a cloned hamelnb repo, a niche
setup that shouldn't ship active by default.
Renamed jupyter-live-kernel -> jupyter-notebook (skill name, page slugs,
catalogs, sidebar, zh-Hans mirror, darwinian-evolver related_skills).
Install via: hermes skills install official/data-science/jupyter-notebook
Extends the fanout enum with 'every_n:<N>' (N >= 2): advisors run on the
first iteration of each user turn and every Nth tool iteration after it;
off-cadence iterations REUSE the cached guidance from the last on-cadence
run via the same cache mechanism the user_turn fanout uses, so the
aggregator still gets advice on every step. The cadence counter is scoped
per user turn (resets on a new user message) and only advances when the
advisory state actually changes, so streaming retries never consume a
cadence slot. Mapping form {mode: every_n, n: N} normalizes to the
canonical string. Unknown/degenerate values fall back to per_iteration.
Addresses issue #63393 (advisor fan-out multiplies turn latency/cost by
the tool-iteration count). Redesigned from PR #63448: the submitted shape
skipped references entirely on off-cadence iterations (aggregator ran
advice-less); this version keeps the last advice in play, credited for
the idea and cadence framing.
Config-gated, default-off (default fanout remains per_iteration).
Co-authored-by: webtecnica <75556242+webtecnica@users.noreply.github.com>
Follow-up fixes on top of the salvaged #22566 mechanism:
- N-collector now counts only REAL actionable user turns via
_is_actionable_user_turn + _is_synthetic_compression_user_turn —
the same filter pair _find_last_user_message_idx uses post-#69291.
The contributor's bare role=='user' + _is_context_summary_content
check let blank platform echoes and continuation/todo rows consume
N slots, silently degrading the guarantee.
- Default flipped 3 -> 1 (behavior-preserving): a default of 3 was
measured to change the tail cut on transcripts whose budget covers
only the last turn. min_tail_user_messages=1 delegates to the
existing single-user anchor; N>1 is opt-in, and the call site is
gated so the default path is byte-identical to main.
- Hardened config parse in agent_init (bool rejected, fractional
floats rejected, floor 1) matching the max_attempts parser shape.
- Wired the recurring external-PR config gaps: hermes_cli/config.py
DEFAULT_CONFIG + cli-config.yaml.example (PR only had cli.py).
- Regression tests: blank echoes / synthetic rows don't count toward
N; tool-call/result pairs never split by the N-boundary (no-orphan
both directions); N-guarantee wins over tail_token_budget and the
_MAX_TAIL_MESSAGE_FLOOR (floor is a minimum, not a cap); default
parity pin; DEFAULT_CONFIG pin.
The phase-1 tool-result prune only runs inside compress(), which fires
near 50% of the context window, so it never triggers on large-window
models; old tool outputs then ride in history and are re-sent every turn.
Add prune_tool_results_only(): the same no-LLM prune on a separate, low
proactive_prune_tokens trigger, run as an elif to the compression branch.
Opt-in (default 0), protects the recent tail by message count.
Add the method to the ContextEngine base as a no-op default so pluggable
engines inherit it safely (the post-tool-call path never AttributeErrors on
a non-built-in engine); the built-in compressor supplies the real prune.
Register both keys under the top-level compression config with defaults and
document them.
Add --long-description / --long-description-file to `hermes slack
manifest` so the generated app manifest can carry Slack's
display_information.long_description (175–4,000 characters), with
validation of the length bounds, mutual-exclusion with --slashes-only,
and UTF-8 file input. Also propagate the manifest command's exit status
through cmd_slack so validation failures reach the shell.
Squash of the two commits from PR #65256 — one commit per contributor
on this salvage branch.
Salvaged from #65256
Build the full reaction pipeline on top of the #29916 base:
- Opt-in gate: slack.reaction_triggers (default OFF — reaction events
stay acked-and-dropped so busy channels don't wake the agent on every
emoji). 'true' routes reactions on the bot's OWN messages; an explicit
emoji-name list routes those emojis from any message (handoff flows).
- reaction_removed events now route too, distinguished by the
cross-platform text convention reaction:added:<emoji> /
reaction:removed:<emoji> (matches the Feishu and Photon adapters, so
agents and skills see one shape everywhere).
- Authorization: the reactor becomes the synthesized message's user, so
the early _is_user_authorized gate and allowed_channels whitelist
apply exactly as for typed messages. _hermes_force_process only skips
the mention requirement (a reaction on the bot's own message is
definitionally addressed to the bot), mirroring Feishu/Photon.
- Gateway hooks (#33111 by @johnkattenhorn): every human reaction on a
message item fires reaction:added / reaction:removed through the new
BasePlatformAdapter.set_reaction_handler → GatewayRunner
._handle_reaction_event → HookRegistry.emit, independent of the
routing opt-in. Documented in hooks.md.
- Channel handoff (#45265 by @Kev-fs): slack.reaction_trigger_target
routes the reaction turn to a configured channel (top-level via
_hermes_no_thread_response + reply-anchor suppression in
gateway/platforms/base.py) or C123:<ts> thread.
- Manifest: reaction_removed event subscription added alongside
reaction_added/reactions:read.
- Docs: slack.md Reaction Triggers section; hooks.md event table rows.
Also credits #44508 by @harrisonmedmedmetrics (inbound reaction_added
handling — same plumbing class, superseded by this consolidated shape).
Co-authored-by: johnkattenhorn <john.kattenhorn.personal@gmail.com>
Co-authored-by: Kev-fs <kevin@fleetsmarts.net>
Co-authored-by: harrisonmedmedmetrics <harrison@medmetricsrx.com>
Documents user-facing wave-1+2 Slack behavior that had no docs coverage:
- decision table for require_mention / free_response_channels /
require_mention_channels / thread_require_mention / strict_mention /
ignore_other_user_mentions and how they compose
- 'Accepting messages from other bots' section with the post-#69483
semantics: allow_bots=mentions requires a CURRENT mention from
peer bots (text or Block Kit blocks); thread state never admits them
- clarify one-tap buttons (choice buttons + Other free-text mode,
in-place resolution, double-click guard, expiry message)
- slash replies are ephemeral: replace-ack, chunking, 5-post cap with
explicit truncation notice, postEphemeral fallback, never-public rule
- cron deliver targeting (slack -> home channel, slack:C... channel,
slack:U... resolved to DM) incl. standalone sender + MEDIA uploads
- send_message media + bare-user-ID DM resolution and caption behavior
Refs #26184.
Salvaged from #45765 by @navahc09 — kept the PR's callout structure
and placement, rewrote the content to match current behavior:
Slack blocks native slash commands in threads and never delivers them,
so Hermes recognises a leading '!' as an alternate command prefix.
Post-C3 command fixes the bang form also works behind a mention
(@Hermes !cmd) and with leading whitespace; unknown '!' tokens pass
through to the agent unchanged. Cross-linked the detailed
slack.md section.
- Add SLACK_THREAD_REQUIRE_MENTION, SLACK_IGNORE_OTHER_USER_MENTIONS and
SLACK_REQUIRE_MENTION_CHANNELS to the conftest behavioral-env force-clear
list so config-loader side effects can't leak between tests (same class
of leak the existing SLACK_* entries guard against).
- Document thread_require_mention and require_mention_channels in the
Slack messaging guide next to the other mention-gating options.
