Design decisions belong to the orchestrator: decide naming schemes,
schemas, file formats, and API shapes before fanning out; never let two
subtree cards decide the same question; stamp every decision into each
dependent card body since workers cannot see sibling context. Mirrored
in the kanban docs (en + zh-Hans) with an exporter/importer worked
example, and bounded KANBAN_GUIDANCE size with an invariant test.
An unset browser.backend ("") now resolves to Browser Use mode whenever
the browser-use CLI is runnable (installed binary or uvx); otherwise the
built-in browser tools are kept so browsing never silently breaks.
Camofox setups always keep the built-in tools (no CDP surface), and
backend: off (including YAML 1.1 bare off -> False) forces the built-in
stack. hermes tools row highlighting follows the same effective-mode
resolution, and tests/tools/ pins CLI discovery off so host uvx installs
can't flip built-in-browser tests.
'Binary file - use appropriate tools' names a recovery the model may
not have — in a file-only toolset it thrashed for 41 turns / 178 tool
calls / 1.5M tokens on a PNG-behind-.txt (readtool eval, qwen3.8-max)
hunting for tools that did not exist. Name the type instead: 25 magic
signatures (images, archives, executables, media, SQLite), ftyp check
for ISO media, size in human units. 'Binary file (PNG image data,
4.1 KB) - cannot display as text.' answers what-is-this in one read.
Both ShellFileOperations refusal sites (read_file + read_file_raw) use
the shared describe_binary_file(); the extension-based guard keeps its
extension message (an extension is a claim; only sniffed content earns
a type name).
Reframe (per review): browser.backend: browser-use is now a DRIVER over
whatever browser source is configured, not a competing backend choice.
- browser_exec resolves its CDP endpoint through the same chain the
built-in tools use: BU_* env override > BROWSER_CDP_URL/browser.cdp_url
(/browser connect) > the configured cloud provider via browser_tool's
_get_session_info() — sharing the per-task session cache, expiry
replacement, inactivity reaper, and atexit cleanup instead of
duplicating them. Live-validated against Browserbase (session created,
driven, reaped) and gateway-provisioned Browser Use cloud browsers.
- Direct-API Browser Use configs skip provider resolution (the CLI talks
to their cloud natively via BU_AUTOSPAWN); the Nous-gateway variant
resolves through the provider, so subscribers get CLI mode without a
raw BROWSER_USE_API_KEY.
- Camofox: only true fallback — Firefox-based, custom HTTP API, no CDP
surface (its own health probes fail on CDP-schema calls). Active
Camofox setups keep the built-in browser tools even with
backend: browser-use set.
- hermes tools picker: provider rows and the Browser Use row are no
longer mutually exclusive; selecting a provider keeps the driver
choice, and both rows highlight when composed.
- Docs updated for driver-over-source semantics.
Camofox is selected via CAMOFOX_URL env var, not browser.cloud_provider —
so a Camofox user with a stray BROWSER_USE_API_KEY in .env matched the
legacy-migration predicate (cloud_provider unset + key present) and got
silently flipped into CLI mode, losing browser_* / Camofox entirely
(browser_exec cannot drive Camofox: its HTTP API exposes no CDP endpoint,
and the browser-use harness is CDP-only against Chromium).
is_legacy_browser_use_cloud_config() now defers to is_camofox_mode().
Follow-ups on the salvaged Browser Use CLI integration (PR #66476):
- browser_exec runs model-written Python on the host. Strip it at
tool-definition time for sessions whose resolved toolsets exclude
'terminal' so terminal-less surfaces (locked-down messaging configs)
don't silently regain host code execution through the browser toolset.
Session-level gate in model_tools, not a check_fn (check_fn results are
TTL-cached process-wide across sessions).
- Replace the live 'browser-use skill' schema fetch with a pinned helpers
digest: no third-party version-drifting text in the prompt, byte-stable
schema across machines. A/B benchmarked (108 runs, opus-4.8 + kimi-k3,
6 multi-step web tasks x 3 arms x 3 reps): pinned digest matches the
full skill dump 36/36 vs 36/36 at ~equal tokens; both cut total task
tokens ~60% vs the legacy browser_* toolset.
- Docs note for the terminal gate; contributor mapping for salvage.
The SDK-support flag is now bound lazily (startup-latency change); a
by-value module-level import freezes the pre-bind False. Read it off the
module after _ensure_mcp_sdk() so the test observes the real support
state — same contract, lazy-aware.
Cold CLI time-to-banner was ~1.8s (hermes) / ~2.8s (hermes -w). The banner
path was paying for work the session doesn't need before first input:
- aux availability probes built REAL OpenAI/httpx clients (openai import
~0.3s + SSL context) just to answer check_fns. New aux_probe_mode()
returns a cache-excluded stub; resolution policy unchanged.
- tools/mcp_tool imported the mcp SDK (~260ms, mcp.types pydantic model
construction) at module import even with zero MCP servers configured.
SDK import is now lazy behind _ensure_mcp_sdk(); _MCP_AVAILABLE is a
find_spec probe so every existing gate/test keeps its semantics.
- banner blocked 500ms on the update-check prefetch; now waits 50ms and
defers the warning line to a daemon thread (prints above the prompt).
- banner recomputed get_tool_definitions + skills scan + git state every
launch; now snapshotted to ~/.hermes/cache/banner_snapshot.json keyed on
(config.yaml, .env, checkout rev, toolsets) and replayed on warm launches
with a background refresh. Agent tool list is still computed fresh.
- _resolve_active_context_length probed the Nous portal /models (~200ms
network) per launch; the tool-search gate now prefers the on-disk
context cache when present.
- schema reconciliation re-executed SCHEMA_SQL in a scratch SQLite DB
(~85ms) per SessionDB(); the reference parse is now disk-memoized by
DDL hash (live-DB diffing still runs every startup).
- bundled-skills sync (~120-170ms rglob/hash) moved off the startup path
to a daemon thread; plugin discovery starts in the background and every
synchronous consumer joins via discover_plugins().
- hermes_cli.auth imported httpx eagerly (~30ms); now a lazy proxy that
test monkeypatching still reaches (setattr forwards to the real module).
- fast chat launch: unambiguous 'hermes'/'hermes chat' invocations skip
building all ~40 subcommand parsers (bails to full dispatch on anything
else, incl. container mode).
- -w path: git worktree add runs with checkout.workers=8 (0.6s→0.2s) and
overlaps HermesCLI construction; --skills preload runs in the background
and is folded in at agent init (finalize_preloaded_skills, same
fail-loud contract for fully-unknown skill lists); stale-worktree prune
moved off the banner path.
Warm results (PTY time-to-banner, 5-run): hermes 1.80s → 0.38-0.40s;
hermes -w -s hermes-agent-dev --yolo 2.82s → 0.57-0.69s.
read_file's .ipynb extraction previously dropped cell outputs entirely,
so a notebook's training logs, tracebacks, and printed results were
invisible to the model. Ported LobeHub's token-efficient conversion:
- stream text and error tracebacks are kept (ANSI-stripped, \r
progress-bar rewrites collapsed to the final frame)
- execute_result/display_data prefer text/plain over the HTML twin
- base64 images become sized placeholders ([image/png output — 3 KB,
omitted]); widget state and script-bearing HTML are omitted
- legacy nbformat v3 pyout/pyerr flat-field shapes handled
- per-cell output block capped at 20k chars
ShellFileOperations.read_file previously ran sed -n '{off},{end}p' bare, so
a file with one pathological line (e.g. a 50MB+ minified bundle on a single
line) shipped the entire line across the exec transport before Python's
per-line clamp (_add_line_numbers, MAX_LINE_LENGTH=2000) could trim it.
read_file now pipes through 'cut -b1-{4*max_line_length+1}' so the shell
bounds every line to 8001 bytes before the bytes ever reach Python.
UTF-8 finding: GNU 'cut -c' is byte-based despite its name (verified:
cutting a line of 2-byte 'é' at -c8004 splits a codepoint, leaving a bare
0xC3 lead byte). The transport decodes with errors='replace', so a split
codepoint becomes U+FFFD rather than raising — but a clamp of
max_line_length+1 BYTES would deliver under max_line_length CHARS for
multibyte text, so the Python clamp would never fire and truncation would
be silent. Using 4*max_line_length+1 bytes (UTF-8 max 4 bytes/codepoint)
guarantees any line longer than max_line_length chars still decodes to
more than max_line_length chars, so len(line) > max_line_length always
triggers the existing '... [truncated]' suffix, and any boundary U+FFFD
lands past char max_line_length where the clamp removes it — verified
empirically with fixtures ('é'*4001 splits at the byte boundary yet the
result contains no U+FFFD and ends with the truncated suffix). 'cut -b'
is used explicitly to document the byte semantics.
cut (unlike sed -n p) always newline-terminates its output, which would
grow a phantom empty final line on files without a trailing newline; the
final-page path now probes the last byte (tail -c 1 | wc -l) and strips
the artifact.
read_file_raw is untouched: it is documented as no-per-line-truncation.
Benchmark (50MB single-line fixture, /usr/bin/time -v, median of 3):
before: 191.1 MB peak RSS, 1260 ms wall
after: 97.8 MB peak RSS, 490 ms wall
Correctness identical in both arms: monster line returns the clamped
2000-char form + '... [truncated]', offset=2 returns the trailing normal
lines intact.
Tests: 153 passed, 0 failed, 4 skipped across the file-ops suites plus a
new tests/tools/test_read_shell_line_clamp.py pinning the monster-line
clamp, offset-past-monster reads, no-trailing-newline preservation, both
UTF-8 boundary cases, and read_file_raw's exemption. Two existing mocks
asserting the exact sed command string were updated for the pipeline.
Same stale-mock class as the previous commit — the sweep missed
test_file_operations_edge_cases.py. Verified no bare wc -c mocks
remain anywhere under tests/.
The combined [ -f ]/wc -c probe changes the first shell command each
read issues; update the stale mocks that only answered bare 'wc -c'.
The fifo tool-layer test now accepts the merged stat-guard's
success=False note (a fact, not an error) with the shell sentinel
behind it.
The size probe every read path starts with — `wc -c < path` — opens the
path. On a FIFO with no writer, a socket, or a character device that never
reaches EOF, that read never returns, and read_file/read_file_raw/
read_file_bytes all pass no timeout to _exec. The turn wedges until the
process is killed.
The device blocklist in tools/file_tools.py cannot close this: it matches
literal /dev/* names, so it can only ever cover paths someone thought to
enumerate. A FIFO is a file type and can sit at any path.
Gate the probe behind `[ -f ]`, which stats instead of opening, and report
a path that exists but is not a regular file as such. A missing path keeps
its existing not-found handling.
A read past EOF returned content '900|' (a phantom line-number prefix
that looks like a real line) and an empty file returned '1|' — both
ambiguous silence: indistinguishable, from inside the model, from a
broken tool, so it re-reads and widens windows. Name the dead end and
its recovery instead: 'offset 900 is beyond the end of the file (412
lines total). Retry with offset <= 412.' / 'File is empty (0 bytes).'
Notes, not errors — a fact about the file is not a failure.
Boundary pinned by test: offset == total_lines still reads (an
off-by-one in a resume hint is a silently corrupted read).
Measured (file-only arm, 3 reps, control vs feature): qwen3.8-max
-18% tokens, -26% tool calls, -17% turns across the two affected
tasks; opus-4.8 flat (within rep noise); accuracy held 1.00.
NFC/NFD, narrow no-break space (U+202F), and curly quotes render
identically in a terminal — a model retyping a visually-correct path
gets 'file not found' and can never discover the byte mismatch on its
own. On not-found, canonicalize the requested name and compare against
directory entries; exactly ONE equivalent spelling reads transparently
with an explanatory note. Zero or several matches (homoglyph twins)
fall through — never guess between collisions.
Also: difflib.SequenceMatcher >=0.8 fallback in _suggest_similar_files
catches near-miss typos (AGENT.md -> AGENTS.md) that substring scoring
misses entirely.
Measured (file-only arm, 3 reps, control=guard-only vs feature):
unicode task qwen3.8-max 31k->16k tok (-48%), turns 6.7->3.7;
opus-4.8 57k->33k tok (-42%), turns 8.3->5.0; accuracy held 1.00.
near-miss: opus mildly better, qwen flat, no regressions.
read_file on a workspace FIFO/socket blocked until the exec timeout —
the existing device guard is name-based (/dev/*, /proc/*) and cannot
see an arbitrary special file. Add _special_file_kind(): one os.stat
on the resolved path, refusing FIFO/socket/char/block devices with a
plain note ('no read was attempted') instead of hanging. Host-visible
filesystems only; regular files, dirs, and missing paths unchanged.
Also adds evals/readtool/: an A/B harness that runs the real AIAgent
against hostile-file fixtures (huge lockfile, one-line bundle, FIFO,
NFD filenames, lying extensions) and measures accuracy, turns, tool
calls, and tokens. Measured for this guard (3 reps, file-only arm):
qwen3.8-max fifo task tokens 122k -> 26k (-79%), turns 9.3 -> 5.0;
opus-4.8 tokens 40k -> 23k; accuracy held 1.00 both arms.
Optional skills merged to main after a user's install was cut were
invisible to 'hermes skills install official/...' until they ran
'hermes update' — the OptionalSkillSource only scanned the local
optional-skills/ checkout.
Now, when an official/<category>/<skill> identifier is not found
locally, OptionalSkillSource resolves it against the live default
branch of NousResearch/hermes-agent: one Trees API call enumerates
optional-skills/*/SKILL.md dirs (cached on disk via the shared index
cache, 1h TTL), then the full skill directory is downloaded byte-exact
(including root-level install scripts, LICENSE, tests/ — files the
generic GitHubSource.fetch path drops). search() and inspect() also
surface remote-only skills so discovery works pre-update too.
Local checkout always wins when present; offline degrades to the old
local-only behavior; traversal and ambiguous bare names are refused;
provenance stays official/builtin.
_normalize_bundle_path rejected absolute paths, .. traversal, and a bare
drive-letter prefix, but permitted a colon inside a later path component.
On NTFS a bundle member named scripts/helper.py:payload writes a hidden
Alternate Data Stream into the visible file scripts/helper.py. The skill
scanner walks with rglob('*'), which does not enumerate streams, so both
operator review and the guard scanner miss the executable bytes.
Reject a colon in any component (the whole class, not just the trailing
one). This subsumes the previous bare drive-letter check, which is folded
into the single colon guard. '/' is the only legal separator once
normalized, so no portable bundle path needs a colon.
Adds an OS-independent quarantine_bundle regression plus a direct
normalizer unit test covering leading/mid/trailing-component colons,
bare/qualified drive letters, and the empty stream name.
Reported-by: JoaoMarcos44 <87440198+JoaoMarcos44@users.noreply.github.com>
Six test files still selected an OS branch with a faked host. Each one now
carries the marker for the host that owns the branch, or derives the
expectation from the real host:
- test_clipboard: macos_only on the has_clipboard_image dispatch. The fake
picked the branch, but _macos_has_image needs osascript.
- test_claw: windows_only on the tasklist/powershell scan, with return_value
in place of a side_effect list that pinned the call count.
- test_linux_desktop_entry: the parametrize over "darwin"/"win32" becomes one
marked test per host. A fake left POSIX paths and a POSIX XDG layout.
- test_graphical_browser_detection: linux_only on the display-server arm. The
$BROWSER check runs before the platform branch, so its test stays unmarked.
- test_auth_nous_provider: the fixture pinned linux so the macOS certifi
fallback could not change the result. The assertion now reads the host, so
the macOS lane covers the fallback too.
- test_tts_macos_output and test_voice_mode: the afplay policy exists because
CoreAudio init raises a TCC prompt, which no Linux runner reproduces.
tests/conftest.py refuses collection when one test carries two OS markers.
Each marker skips on all but one host, so two of them make a test that runs
nowhere while every lane reports green. tests/test_os_marker_gating.py pins
that behavior.
The docstring on TestConfirmDestructiveSlash said the Windows job runs it.
The class has no marker, so -m windows_only deselects it.
many tests patched sys.platform or a module's _IS_WINDOWS flag, then
ran on linux ci. the patch selects the branch under test, but the host
does not have the behavior the branch exists for. the test proves the
patch, not the platform. some gated assertions never ran on any host.
this commit adds three markers: linux_only, macos_only, windows_only.
a conftest hook skips a marked test on the other hosts, with a clear
reason. no test fakes a host now. two documented fakes remain
(android/termux, freebsd) because no ci runner exists for them.
each fake site got one of four treatments:
- gate it: the real host supplies the platform; mocks cover real
dependencies only, never host identity
- patch the module's own probe when the subject is the probe's consumer
- assert against the real host when the fake stood in for any non-x host
- delete the patch when it set the value the host already has
bare skipif(sys.platform != ...) guards became markers too. the lane
model skips these on linux and never imports them on windows, so they
ran on no host. platform parametrize tables are now one marked test
per os.
running on real hosts found real errors: a chrome-sandbox failure in
test_gui_command that main hides, and two windows failures fixed here.
the agents.md testing section now documents the policy.
Two bugs reported on the docker terminal backend (desktop app, sandboxed
profiles with container_persistent: false):
1. A NEW chat's container inherited the PREVIOUS session's workspace,
bind-mounted rw at /workspace, because the mount source was the
process-global TERMINAL_CWD env var (written by the workspace picker,
outliving its session) and all sessions shared one 'default' container.
2. Every command failed with exit 126 because the desktop gateway recorded
the HOST launch directory as the session cwd, and each command was
prefixed with 'cd /Users/<user>/...' inside the container.
Fixes (class-wide, single owners):
- container_persistent: false + docker now keys containers PER SESSION:
fresh container per chat, removed at session close/idle. delegate_task
children share the parent's container via an explicit alias registry.
container_persistent: true keeps the documented ONE-long-lived-container
contract unchanged.
- _resolve_task_host_cwd() is the single owner of the cwd->/workspace mount
policy across all four env-creation sites; under isolation it refuses
process-global cwd sources and mounts only the session's own attached
workspace (tui_gateway now tags overrides with cwd_source).
- _resolve_command_cwd() gains the same host-path guard the env-creation
sites already had (#50636/#54447 sibling site): a recorded host cwd is
discarded on container backends instead of cd-ing every command into a
nonexistent path.
E2E-tested against real Docker: distinct containers per session, no stale
mount in a fresh session, no exit 126 from host cwd records, containers
removed at session teardown.
- Remove dead use_systemd_scope = False assignment (leftover from
the old try/except pattern, immediately overwritten).
- Update stale log label supervisor= -> in_supervised_gateway=
to match the renamed variable.
- Convert autouse _mark_gateway_process fixture to opt-in
_gateway_identity so negative tests start from a clean slate
instead of undoing the fixture's env/PID mocks.
- Parametrize 4 near-duplicate negative tests (2 scenarios x
pipe/PTY) into 2 parametrized tests, reducing ~130 lines to ~80.
76 tests pass, ruff clean, net -32 LOC.
The #70716 regression fix changes popen_start_new_session from False to
True in the systemd-scope branch. Update the assertion in
test_wraps_in_systemd_scope_when_supervisor_and_available and the
docstring in test_systemd_post_spawn_failure_never_kills_gateway_process_group.
Agent Plugins v1 packages with 'streamable-http' mcp.json entries now load
through Hermes' existing URL-based MCP client instead of being reported and
skipped. The stdio-only limitation was the agreed follow-up slice from
PR #81196.
Boundary rules from the v1 spec (§7.2.1) are enforced:
- URL must be absolute http(s), no user information, no fragment; plain
HTTP only for localhost/loopback hosts.
- Configured package headers are never forwarded across a cross-origin
redirect: translation marks entries strict_redirect_headers, and the
redirect hook in the native runtime strips those headers (plus
Authorization) whenever a redirect leaves the original origin. On mcp <
1.24.0, where the client cannot hook redirects, such servers fail closed
with an actionable upgrade message.
- Legacy 'sse' entries remain reported and skipped.
The redirect hook is extracted into a testable module-level factory
(_make_redirect_header_stripper); default behavior for native config
servers is unchanged (Authorization-only stripping).
Per review: upscaling should be the default behavior (like the original
flux-2-pro chain), not agent opt-in. Policy: every image model whose
native output is below ~2MP now sets upscale=True in its catalog —
users never silently get low-res images. Native hi-res models
(Seedream 5 Pro/Lite, Krea 2 Large) stay off to avoid paying to
upscale already-large output.
- FAL catalog: 16 models flipped to upscale=True (klein, z-image,
nano-banana pro/2/2-lite, gpt-image 1.5/2, ideogram v3/v4, recraft
v4/v4.1, qwen image/3, krea-2 medium on FAL, MAI 2.5 pro).
- Krea plugin: per-model upscale defaults (medium + medium-turbo ON at
1.5K native; large OFF at 2K native), precedence explicit kwarg >
image_gen.krea.upscale config > catalog default.
- The 'upscale' tool param remains as a per-call override in both
directions (false = fast draft, true = force on hi-res/edits).
- Video unchanged: opt-in only (default-on would double every video's
cost and latency).
- Sibling tests updated: routing/payload tests pass upscale=False where
the assertion targets the generation submit; catalog test now pins
the native-resolution policy instead of the flux-2-pro snapshot.
The generated-media surface previously had almost no upscaler coverage:
only fal-ai/flux-2-pro chained Clarity Upscaler (hardcoded catalog
default), every other image model returned ~1MP output with no high-res
path, and video had no upscaler at all. Krea's API treats the enhancer
as a standard second pass; this brings the same shape to Hermes.
- image_generate: new optional 'upscale' boolean in the tool schema.
Explicit true chains the backend upscaler on ANY model (including
edits); explicit false disables flux-2-pro's automatic default;
omitted keeps per-model catalog behavior. Response now reports
'upscaled' so the agent knows which resolution it got.
- FAL image path: explicit flag overrides the catalog 'upscale' default
(Clarity Upscaler, 2x). Failure falls back to the native image.
- Krea plugin: upscale=true chains Krea Enhance
(/generate/enhance/krea/enhance, 2x, prompt-guided) through the same
BYO/managed base URL + auth as generation, with a best-effort poll
loop that never fails a successful generation.
- video_generate: new optional 'upscale' boolean; FAL video plugin
chains ByteDance SeedVR2 (fal-ai/seedvr/upscale/video, 2x factor
mode). Providers without upscalers ignore the kwarg per the ABC
contract (documented in both ABCs).
Validation: targeted suites green (123 tests across 6 files, including
new coverage for override-wins/default-kept/failure-fallback on all
three paths); live E2E on direct FAL verified both chains end-to-end
(klein 9b + Clarity upscaled image; pixverse-v6 1s 360p + SeedVR2
upscaled video).
_run() used text=True without an encoding, so Windows decoded git's
UTF-8 output with the locale code page (cp932) and raised
UnicodeDecodeError on non-ASCII filenames or diff content, breaking
the "Never raises on git failure" contract in its docstring. Match
the utf-8 + errors="replace" policy checkpoint_manager's _run_git
already uses. Legacy cp932-encoded blob content degrades to
replacement characters instead of crashing; a test pins that
trade-off so it stays a documented choice.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Fixes the read_file half of #80308 and the class behind #80261, #80250,
The binary sniff sampled files via 'head -c 1000' through the terminal
transport, which decodes stdout with errors="replace". A multibyte
character cut at byte 1000 therefore arrived as U+FFFD, and
_is_likely_binary treated any U+FFFD as binary — flagging valid CJK and
emoji text as unreadable. At the text layer a stored replacement char
and a transport-manufactured one are indistinguishable, which is why
per-callsite adjustments kept leaving siblings open.
Sample as 'head -c 1000 | base64' so raw bytes survive the transport
(fail-open to the legacy heuristic when the transport cannot produce
clean base64), then classify bytes: NUL => binary; valid UTF-8 allowing
one incomplete multibyte sequence at the sample end => text; mid-stream
invalid UTF-8 (latin-1, true binaries) => read-only, preserving the
anti-mojibake guarantee the old check existed for. Files legitimately
containing U+FFFD become readable.
`tests/hermes_cli/test_plugins_cmd.py::TestNoAutoActivation::test_compressor_default_ignores_plugin`
fails on every Windows machine:
UnicodeDecodeError: 'charmap' codec can't decode byte 0x8f in
position 47744: character maps to <undefined>
The test reads `run_agent.py` back as text to assert a removed comment is
gone, but called `open()` with no `encoding=`. Python then falls back to
the locale preferred encoding, which is cp1252 on a default Windows
install rather than UTF-8. `run_agent.py` contains nine bytes cp1252
leaves undefined, so the read raises before the assertion is reached. On
Linux and macOS the preferred encoding is UTF-8 and the same line is
fine, which is why CI never caught it.
That one line is the only active failure. The rest of this change closes
the same gap in the files it touches, which `scripts/check-windows-footguns.py`
flags and which the #71014 read_text campaign has been working through
elsewhere in the tree:
- `tests/hermes_cli/test_plugins_cmd.py`: nine bare `write_text`/`read_text`
calls writing YAML manifests, config and plugin sources
- `tests/tools/test_web_tools_truncate.py`: reads stored extracted web text,
which is arbitrary content from the internet
- `tests/stress/test_atypical_scenarios.py`: writes and reads worker task
ids and a barrier file
All three files are now clean under `check-windows-footguns.py`.
Reads go through `Path.read_text(encoding="utf-8")` rather than
`open(...).read()`, which also closes the handle instead of leaving it to
the garbage collector. On Windows a live handle blocks tmpdir cleanup, so
that part is not cosmetic either.
No new test. The repaired test is the regression coverage: it fails
before this change and passes after, on Windows.
Complements the cherry-picked contributor fixes and closes out the
remaining sites of the 'missing explicit encoding' bug class, which is
now permanently gated by ruff PLW1514 (enabled repo-wide in
pyproject.toml and enforced by the blocking `ruff check .` step in
.github/workflows/lint.yml):
- tools/memory_tool.py: read MEMORY.md/USER.md via utf-8-sig so a
Notepad BOM never glues U+FEFF onto the first entry (issue #10878,
PR #10888 by @easyvibecoding — strict-decode contract of
_read_raw_checked preserved rather than errors="replace", so
undecodable files still refuse read-modify-write instead of being
lossily rewritten). Regression tests included.
- tools/skills_tool.py: SKILL.md and skill file reads pinned to
utf-8-sig + errors="replace" — deterministic across platforms instead
of the locale fallback proposed in PR #51701 (superseded: falling back
to cp1252/GBK makes the same skill render differently per host); .env
reader aligned with the canonical utf-8-sig dialect in hermes_cli/config.py.
- agent/shell_hooks.py, hermes_cli/main.py, gateway/slash_commands.py:
explicit utf-8 on the remaining fdopen/open text-mode sites flagged by
the AlexFucuson9 sweep series (#56033#56940#65565#66782#66791).
Co-authored-by: easyvibecoding <easyvibecoding@users.noreply.github.com>
Co-authored-by: AlexFucuson9 <AlexFucuson9@users.noreply.github.com>
Co-authored-by: flyingdoubleg <wangzhe00zju@gmail.com>
Co-authored-by: LeonSGP43 <cine.dreamer.one@gmail.com>
Review asked for a BOM-prefixed JSON case alongside the existing
control-character coverage. The sandbox script now also feeds
json_parse a \ufeff-prefixed document and asserts the parsed value
round-trips (fails against the pre-fix helper, passes with the
BOM strip).
Adds tools/skill_linter.py — a soft companion to the hard frontmatter
validator. It encodes the CONTRIBUTING 'Skill authoring standards
(HARDLINE)' conventions that today only a human reviewer catches:
- shell-utility references in prose (`grep`/`sed`/`cat`...) that should
name the native tool (search_files/patch/read_file)
- missing version/author/license/metadata.hermes block
- name != directory, invalid name format
- description over the 60-char prompt budget, marketing words
- dangling references/ links, forbidden scaffolding files
- POSIX-only script primitives without a platforms: gate
Findings are ADVISORY. skill_manage(create) attaches them as
lint_warnings + lint_hint in the success result; nothing is blocked
(the hard rejects already run in _validate_frontmatter). A CLI
(python -m tools.skill_linter <dir>) exits 1 only on ERROR-severity
findings so CI can gate on structural breakage without failing on nits.
Calibrated against the bundled skills/ tree: 76 advisory findings, exit 0,
no false positives after excluding repo-root scripts/ refs.
Inspired by MiniMax Code's skill-creator lint step; adapted to our
existing validator + skill_utils rather than a parallel system.
Salvage of PR #17973 by @TKCen (Sebastian Hänisch), re-implemented on
current main to preserve speed/instructions/provider params,
prepare_spoken_text normalization, OPUS_VOICE_PLATFORMS, is_write_denied
path security, microsecond timestamps, and the streaming-TTS gate.
- Split long TTS text into provider-safe chunks instead of truncating
- Pack generated audio against platform upload limits (Discord 10MB,
Telegram 50MB, configurable via tts.delivery_profiles)
- Combine chunks with ffmpeg (OGG/Opus re-encoded, MP3 stream-copied)
- Multi-file delivery when combination fails or would exceed limits
- Remove hard [:4000] truncation from all callers (cli.py, voice.py,
gateway/run.py, gateway/platforms/base.py)
- Gemini TTS raises ValueError instead of silently truncating when
composed prompt exceeds the provider limit
Simplify-code fixes: removed dead all_touched_paths set, added
try/finally for scratch file cleanup on exception, clean error response
on chunk failure instead of leaking stale file_path.
Desktop-gated (desktop_ui toolset) metadata-only window awareness: the agent
can ask which application window sits directly behind the Hermes window
(app, title, bounds — never pixels). Rides the same blocking bridge as
read_terminal: the gateway emits window.read.request and the renderer
answers window.read.respond.
The coverage warning listed bare page ranges, which tells the agent
WHERE the gaps are but not WHAT they contain — its only options were
guessing or OCRing everything. Each gap is now labeled with the last
text extracted before it (usually a section divider page), so the agent
can decide which gaps it actually needs and render/OCR only those.
Gap list capped at 20 entries with a summary line for pathological
alternating documents.
Follow-ups on the salvaged commit:
1. get_cache_directory_mounts() now CREATES missing staging dirs instead of
skipping them. Docker snapshots the mount list at container creation, so
a dir born later (first attachment, first clipboard image) dangled for
the life of a persistent container. Empty bind mount costs nothing.
2. to_agent_visible_cache_path() translates per-backend instead of
docker-only: docker/modal -> /root/.hermes, ssh/daytona/vercel_sandbox ->
~/.hermes (shell-expanded remotely; bytes arrive via file sync), local/
singularity keep the host path (apptainer auto-binds the host home).
Mirrors the proven _agent_cache_base_for_env heuristics.
Updated the two mount-list tests pinning the old skip behavior; added
per-backend translation coverage.
When extraction of a binary document format (.pdf, .docx, .xlsx, Office,
EPUB…) fails for a specific reason — the anydoc size cap, an encrypted or
malformed file — read_file previously swallowed the ExtractionError at
debug level and fell through to the generic 'Cannot read binary file'
guard, so the agent never saw the actionable reason (e.g. 'Document too
large to convert (N bytes, limit is 52,428,800)').
read_file now returns the specific extraction failure for binary document
formats. Fallthrough behavior is preserved where a raw read is still
useful: .ipynb (plain JSON) and converter-unavailable PDFs keep their
historical raw-read path, and the 'Unsupported document type' shape (no
extra information) keeps the generic guard.
Follow-up to #80004, where the size-cap message was being generated but
never reached the agent.
Follow-up on the cherry-picked contribution from @michaelsam94 (#51794):
replace display-string/exact-value snapshot assertions with invariant
checks per the no-change-detector-tests policy. Live-tested
fal-ai/nano-banana-2 and fal-ai/nano-banana-2/edit through the real
payload builders: both pass.
Four fix-forwards from the adversarial post-merge audit of the Aug 7
unreviewed merge batch:
- estop (#81148): is_engaged() now fails SAFE (engaged) on stat errors;
the gateway estop gate lets recognized slash commands and replies owned
by in-flight work (update prompts, clarify, slash-confirm, tool
approvals, running sessions) through instead of consuming them; new
gateway /pause [reason|off] command gives messaging-only operators an
in-band engage/resume path (busy_policy=dispatch so it works mid-run).
- cron monitor mode (#81138): execution-mode invariants (monitor x
no_agent, monitor_script x monitor_url, no_agent-requires-script) now
have ONE owner (_validate_job_mode_invariants) called from BOTH
create_job and update_job, so the create-time invariant can no longer
be silently violated through the update door.
- cron notepad (#81139): remove_job now clears the job's notepad rows
(clear_notepad was dead code -> orphaned KV state forever); clear is
best-effort and no-ops without creating notepad.db.
- delegation batch gate (#81141): template-marker regex narrowed to
multi-word placeholder shapes only (<feature name>, {file_path}) so
generics (Vec<T>), HTML tags, JSON snippets, glob braces and f-string
style no longer reject legitimate batches; duplicate-goal rejection
removed (best-of-N fan-outs are legitimate).
The salvaged bytes path (_extract_anydoc_bytes) bypassed the coverage
check added in #81680. Materialize transferred PDF bytes in a host temp
file for the pdftotext scan, and name the backend-visible path in the
recovery command rather than the temp file.
Video (plugins/video_gen/fal): Seedance 2.5, MiniMax H3, Seedance 2.0
Mini, FLUX 3, Grok Imagine 1.5, Gemini Omni Flash (i2v-only). New
family capability flags:
- duration_int: endpoints that take duration as a JSON integer
- resolution_aliases: maps 720p/1080p-style values onto non-standard
enums (H3's 768P/2K/4K)
- image_drop_keys: strips keys the family's i2v endpoint rejects
(aspect_ratio on Seedance 2.5 / H3 / Grok 1.5)
Image (tools/image_generation_tool): Seedream 5.0 Pro (+edit) and
Lite, Ideogram V4 instant + fast, Qwen Image 3 (+edit), MAI Image 2.5
Pro, Nano Banana 2 Lite (+edit), Recraft V4.1.
Every new endpoint live-tested against fal.run through the real
payload builders + submit path: 18/18 pass (t2v, i2v, t2i, and edit
probes). Note: several new endpoints return HTTP 409 from the Nous
Portal FAL proxy allowlist until it is updated portal-side; BYOK
FAL_KEY works today and the existing 4xx guidance message covers it.
Force-redact every terminal exception and traceback field before JSON serialization, including environment creation, background startup, exhausted foreground retries, and the outer catch-all. Preserve the current command-aware, opt-out-respecting redact_terminal_output(output, command) behavior for successful output.
anydoc converts the PDF text layer only and emits no image placeholders
or page markers, so a mostly-scanned PDF extracts 'successfully' into
section headers with empty bodies — silent data loss the model cannot
detect. Count per-page text via poppler pdftotext and prepend an
EXTRACTION COVERAGE WARNING naming the empty pages and the recovery
path (pdftoppm + vision_analyze, or the ocr-and-documents skill).
Found on a 311-page HOA resale package where 198 scanned pages
(CC&Rs, Bylaws, Articles, insurance certs) vanished without a trace.
Closes the last two emission gaps from #77484:
- tools/terminal_tool.py: both exception paths (generic except and
TERMINAL_DEGRADED_MODE=fail) returned raw str(e) + traceback.format_exc()
to the model — only the logger copy was redacted. Exception text can
embed the failing command line and any secrets inline in it; both fields
now pass through redact_sensitive_text.
- acp_adapter/entry.py: _setup_logging cleared root handlers and installed
a plain logging.Formatter, bypassing redaction entirely on ACP stderr.
Now uses RedactingFormatter like every other logging surface.
The other three gaps from #77484 (process(list), *_KEY regex variants,
control-char splits) were fixed in #80964/#80965.
image_generate and video_generate forwarded model-supplied local paths to
provider plugins, which read them off the HOST filesystem regardless of
terminal backend — inconsistent with the confinement boundary vision/video
analysis enforce (GHSA-gpxw-6wxv-w3qq), and broken for sandbox-only files.
New dispatch-layer chokepoint (_confine_source_images): under a non-local
backend, path-like image_url / reference_image_urls resolve through
tools.image_source (media-cache host reads, bounded in-sandbox exec-read,
lazy env bring-up, credential guard, 50MB cap) and reach every provider as
data: URLs — which all backends already accept. URLs/data: pass through;
local backend is a no-op. xai_video_edit/extend already require public
HTTPS URLs, so no change needed there.
Under the Docker terminal backend, vision_analyze's first exec-read
sometimes returned empty / non-zero against a freshly started container,
producing 'could not read <path> inside the sandbox' on a file the agent
could cat seconds later. Cold pipe setup on the first exec against a
new container, not a permissions or mount problem.
Retry once after a short delay (150 ms covers Docker exec warm-up
without making a real failure feel sluggish). When every attempt still
fails, fold the container's first stderr line into the raised error so
the user can tell 'no such file' from 'permission denied' instead of
staring at one opaque message.
Tests cover the retry-then-succeed path, the diagnostic-on-exhausted
path, and confirm the existing single-attempt raise is preserved.
Follow-up on the salvaged commit: replace the hand-rolled file_ops python3
exec-read with tools.image_source.resolve_image_source(permitted=('video',)),
so video_analyze gets the same pipeline as vision_analyze — media-cache host
reads, bounded head -c sandbox exec (no python3 dependency in the sandbox
image, no unbounded base64 stream), lazy env bring-up (#62825), the
credential-read guard, and the 50MB ingest cap.
The _bash_exec_payload delegation rejected short-option bundles with
letters outside bash's alphabet, so 'zsh -yc', 'dash -Vc' and 'ksh -Gc'
scripts stopped being scanned — a fail-open regression for shells the
guard's _SHELL_EXECUTABLES explicitly covers. Try the bash grammar
first (catches operand-hidden -c), then fall back to the permissive
positional scan; a block-guard fails closed.
bisect sat in _KNOWN_GIT_BUILTINS and was allowed in the running source
root, yet it repeatedly checks out commits — the exact module-version
skew this guard exists to prevent. Move it to _WORKTREE_MUTATIONS.
The guard's _shell_script_arg treated any leading option containing 'c'
as -c and looked no further, so 'bash -o pipefail -c "git checkout
main"' returned None and the script was never scanned (fail-open).
approval.py's _bash_exec_payload already parses bash's real option
grammar (-O/-o consume operands, short-option bundles, --init-file);
delegate to it instead of keeping a second, weaker parser.
`worktree` sat in _KNOWN_GIT_BUILTINS, so the guard returned safe for the
whole family. That allowed `git worktree remove [--force] <root>` and
`git worktree move <root> <dest>` against the very checkout this process
runs from, which the guard already treats as a source root when its .git
is a linked-worktree file.
Both name their target as an argument rather than acting on the cwd, so
they also slipped past the "is the cwd inside root" gate when run from
outside. Resolve the target against the command's cwd and block it when
it lands on the running root, from any directory. `worktree add`, list,
prune, lock, unlock, and operations on other worktrees stay allowed.
Wire the self-repo guard in next to the gateway lifecycle hard-block,
before the force check — force=True cannot make the command safe, only
delay the crash. Local backend only: sandboxed backends cannot reach the
host checkout. The block message explains the version-skew mechanism and
redirects to git worktree add / a temp clone, or running the command
outside hermes with a restart after.
When hermes runs from a source/editable install, a git checkout/reset/pull
in its own repo swaps code on disk under the live interpreter. Modules
imported before the switch stay old while later lazy imports load new code,
producing delayed signature TypeErrors and tracebacks that don't match the
source, typically losing the in-flight turn.
New tools/self_repo_guard.py detects working-tree/ref mutations (checkout,
switch, reset, rebase, merge, pull, restore, stash, clean, cherry-pick,
revert) whose target repo is the source root the process runs from, via
cwd, git -C, cd chains, and subshell segments. Read-only git, commits,
fetch, and git worktree add stay allowed; packaged installs (no .git) are
inert.
dispatch() called logger.exception with the exception interpolated into the
message. exc_info renders the same exception again in the traceback, so a
failing tool wrote its error body to the log twice. Every tool exception
passes through this one handler, so a large HTTP error body from any tool
landed here at full size.
Bound the message copy. The traceback still renders the exception once,
which is what an operator needs to place the failure.
Same double-write @arimu1 fixed in the vision, image, and TTS handlers in
#75938.
The debug line that fires when an error body is truncated interpolated the
whole untruncated body, so capping the model-facing copy still wrote the
original to the log. A large HTTP error body — a Cloudflare challenge page
or a proxy 502 — reached the log at full size on every failed call.
Log a bounded prefix instead. It stays longer than the model-facing cap so
an operator still has something to diagnose with, but it no longer grows
with the size of the response body.
Reported for the logging handlers in #75938 by @arimu1; the same pattern
was present here.
tool_error() caps its message at _MAX_TOOL_ERROR_CHARS (2048), logging
the full body at DEBUG before trimming the context-bound copy.
Handlers that serialize exceptions directly -- json.dumps({"error":
str(exc), ...}) -- bypass that helper, so _normalize_handler_result
also runs every string result through _bound_json_error_result: if it
parses as a JSON object with an oversized string error field, only
that field is trimmed and the payload re-serialized. Non-error
results, non-JSON strings, and multimodal envelopes pass untouched.
Open the selected microphone at its reported default rate and convert each capture block to the 16 kHz frame expected by wake-word engines. Add a regression covering a 48 kHz WASAPI device.
Co-authored-by: clyu168 <clyu168@126.com>
An auth failure on the very first connect returned out of the run loop
instead of parking. That ended the run task, and the task is the only
listener on _reconnect_event — so the server stayed dead for the life of
the process. `hermes mcp login`, a /mcp refresh, and the 300s self-probe
all had nothing left to wake, and the only cure was a full restart.
_classify_mcp_failure already calls 401/403 "permanent" and documents
that run() parks those immediately; the early return above it meant auth
was the one permanent failure that never got there. Park it with the
others and keep the tailored log line, now pointing at `hermes mcp
login <server>`.
The windows-compat change-detector checked for the literal string
'start_new_session=True', but the systemd scope isolation path
conditionally uses start_new_session=False (the scope creates its own
session/cgroup). Assert 'start_new_session=' instead — the value may
now be a variable.
When Hermes runs as a systemd gateway with MemoryHigh/MemoryMax limits,
local background terminal commands (terminal(background=true)) inherit the
gateway's cgroup. A memory-heavy executor (Codex, tests, Node) can push
the whole cgroup past MemoryMax and trigger systemd-oomd to kill the
ENTIRE gateway — taking down the messaging control plane and silently
losing the active turn.
Root cause: tools/process_registry.py::spawn_local() uses
start_new_session=True (creates a process session/group, NOT a resource
cgroup). The spawned process tree stays in the gateway's systemd cgroup.
Fix: when running under a service manager (detected via the existing
is_gateway_supervisor_process() helper), wrap the pipe-mode spawn command
in 'systemd-run --user --scope --unit=hermes-worker-<id>' so the worker
gets its own transient cgroup. An OOM in the worker then kills only the
worker, not the gateway.
The systemd-run availability is probed once (a no-op /bin/true in a
transient scope) and cached, because the binary can exist on PATH while
the user D-Bus session is unavailable (system services, containers). If
unavailable, fall back to the current start_new_session=True behavior
with a debug log.
Scope: this covers the common background pipe-mode path. PTY mode
(PtyProcess.spawn) is left as future work — it uses a different spawn
mechanism and is used for interactive CLI tools where cgroup isolation
has additional considerations.
vision_analyze reads container-only images by exec-reading them inside the
sandbox, but unlike terminal_tool it never triggered environment creation. Under
a non-local backend (ssh, docker, ...), a session whose first action was
vision_analyze on a remote path failed with 'no active sandbox session' until an
unrelated terminal command happened to establish the connection.
Add terminal_tool.ensure_task_env(task_id), a public lazy get-or-create that
reuses the terminal tool's own creation machinery, and call it from
image_source._resolve_container_fallback before the in-sandbox read. Extract the
ssh/container config-dict builders so both paths derive settings identically
(no duplication). Best-effort and fail-closed: a failed bring-up leaves the
existing 'no active sandbox' error intact, never a host read.
Fixes#62825
The modal/browserbase test file replaces tools.environments.base with a
SimpleNamespace stub; terminal_tool now imports EnvironmentConnectionError
from that module, so the stub must provide it too.
Connection-class infrastructure failures on remote terminal backends (SSH
host unreachable/timed out, Docker daemon down or missing, remote file
sync failing on a dead link) previously surfaced to the model as raised
RuntimeError tracebacks. The model got a stack blob with no guidance and
the failure was indistinguishable from a tool bug.
Now:
- New EnvironmentConnectionError(RuntimeError) in tools/environments/base.py
carrying a reason + retry_hint. Subclassing RuntimeError keeps every
existing catcher working.
- ssh.py classifies connect-refused, connect-timeout, scp, remote mkdir,
bulk upload/download, and remote rm failures as connection errors.
- docker.py classifies all four _ensure_docker_available() failure paths
(missing exe, non-executable exe, daemon timeout, `docker version`
failure).
- terminal_tool catches EnvironmentConnectionError and returns a
structured tool result the model can act on:
{"status": "degraded", "reason": ..., "retry_hint": ..., "exit_code": -1}
The failed backend is evicted from the environment cache so a later
call retries from scratch — recovery is automatic once the backend is
reachable again.
- Config gate terminal.degraded_mode: warn|fail (default warn) in
config.yaml, bridged as TERMINAL_DEGRADED_MODE across all four bridge
sites (cli.py env_mappings, gateway/run.py _terminal_env_map,
TERMINAL_CONFIG_ENV_MAP, DEFAULT_CONFIG). "fail" preserves the
historical error+traceback tool result.
- Command failures (nonzero exit, command-not-found) are NOT touched —
only infrastructure failures classify as degraded.
Tests: tests/tools/test_terminal_degraded_mode.py (15 tests) covering
exception classification for ssh+docker, structured degraded results,
no-caching of degraded envs, recovery after the backend returns,
nonzero-exit results unaffected, fail-mode preservation, invalid-mode
fallback to warn, and the four-site config bridge invariant.
Inspired by: Claude Cowork degraded-backend behavior (idea-level,
docs-only evidence).
Per-task `output_schema` (JSON Schema object) on task items plus the
top-level single-goal form — a one-time static addition to the tool
schema (never varies per call).
- Child side: the schema is appended to the child's context as an
explicit OUTPUT CONTRACT block before spawn.
- Completion side: the parent validates the child's final answer with
jsonschema; on failure it sends exactly ONE bounded retry turn
carrying the validation errors verbatim (no schema re-paste).
- Result entries gain schema_valid (+ schema_retries, and schema_errors
on final failure) ONLY when a schema was requested; schema-less calls
keep a byte-identical result shape.
- Malformed schemas are rejected loudly at dispatch (coerce_output_schema
meta-validates via jsonschema's validator_for/check_schema).
- New helpers in tools/delegation_output_schema.py: coerce, contract
block, fence/prose-tolerant extraction+validation, retry message.
Pattern from: github/copilot-cli ctx.agent(prompt,{schema}) — PATTERN
ONLY, zero code/prompt text copied (proprietary); proven consumer:
delegate-task-output-patterns skill.
Tests: tests/tools/test_delegate_output_schema.py (24 tests — valid
first try, invalid->retry->valid, invalid twice -> schema_valid false +
errors surfaced, retry-exception degrade, no-schema legacy shape pin,
dispatch rejection, contract plumbing). Delegation suite: 221/221 green.
Add an optional `region: [x1, y1, x2, y2]` parameter to vision_analyze
(pixel coordinates in the ORIGINAL image space). The crop is applied
with Pillow BEFORE the downscale/embed-cap pipeline, so the cropped
region gets the full resolution budget — a zoom for reading small text
or UI details after a full shot.
- New `_crop_image_region` helper: clamps out-of-bounds coordinates to
the image, rejects zero-area/inverted/malformed regions with an error
naming the actual image dimensions so the model can retry sensibly.
- Wired into both the native fast path (`_vision_analyze_native`) and
the legacy aux-LLM path (`vision_analyze_tool`).
- Schema gains one static optional param (byte-stable thereafter); the
description documents the intended flow: full shot first, then zoom.
- No region supplied = behavior unchanged (regression-guarded).
Tests: tests/tools/test_vision_region.py (11 tests — crop applied,
clamping, zero-area rejection with dims, malformed input, pre-downscale
full-budget zoom, schema shape, handler pass-through, no-region
unchanged). Widened one narrow fake_native stub in test_vision_tools.py
to be kwargs-tolerant.
Ported from: QwenLM/qwen-code zoom-image.ts (Apache-2.0)
write_file/patch targeting AGENTS.md, CLAUDE.md, SOUL.md, .cursorrules, or a
project-local .hermes config dir now ALWAYS prompt the human for approval —
even under --yolo/auto-approve — and fail closed when no human channel
exists. These files steer future agent behavior, so an injected write to
them is a prompt-injection persistence vector.
Design:
- New _check_protected_instruction_write() in tools/file_tools.py, a
sibling of _check_sensitive_path that returns approval-required rather
than a hard error. It realpaths before matching (symlink lesson from
#41351), matches basenames case-insensitively in ANY directory, rejects
'./x/../AGENTS.md' traversal via normpath, and gates files whose
immediate parent dir is `.hermes` (project-local config) while exempting
the authoritative ~/.hermes home (governed by its own guards).
- Approval is ONE-OPERATION only: no session/permanent persistence, no
yolo bypass — intentionally does not route through _run_approval_gate.
Gateway sessions get the button round-trip with allow_permanent and
allow_session both False; CLI uses the per-thread approval callback;
no channel at all = BLOCKED (fail closed).
- Multi-file V4A patches: ONE protected file gates the ENTIRE patch (a
single prompt lists all protected targets; deny applies nothing).
- Config: security.protected_instruction_files (default true) and
security.protected_instruction_extra_patterns (fnmatch on basename).
Config read failure keeps the gate ON.
Tests: 22 new cases in tests/tools/test_file_write_safety.py covering the
adversarial checklist — deny/approve/yolo-bypass attempt, symlink at a
protected target, case variants, relative traversal, arbitrary-directory
basenames, project-local .hermes, checkout-nested-under-~/.hermes
non-gating, patch replace + V4A multi-file atomicity, gateway round-trip,
fail-closed with no human, config off/extra patterns.
Ported from: RooCodeInc/Roo-Code RooProtectedController (Apache-2.0);
companion: #58631 (terminal vector), symlink lesson from #41351.
Adds a per-server `trust: full|untrusted` config key
(mcp_servers.<name>.trust). On an untrusted server, every write-capable
tool call — any tool whose discovery-time annotations do not carry
readOnlyHint=True — routes through the existing approval surface
(tools.approval.request_elicitation_consent, same lazy-import +
surface-routing pattern the MCP elicitation handler uses) before the RPC
fires. Denied/cancelled/errored approvals fail closed: the RPC never
runs, including the lazy first-use server spawn.
Design points:
- Classification happens at CALL TIME from metadata captured at
DISCOVERY (_record_tool_trust_metadata in _register_server_tools and
the lazy cache-registration path). No toolset/schema mutation, so the
toolset stays byte-stable and prompt caching is preserved.
- readOnlyHint is a server-supplied HINT: on an untrusted server a lying
server can at most skip approval for tools it claims read-only — it
can never widen access. Trust tiering itself is operator config.
- Missing/malformed annotations => write-capable (fail closed).
- Unrecognized trust values => untrusted (fail closed); missing key =>
full (backward compatible, documented in mcp-config-reference).
- The schema cache now persists readOnlyHint so lazy-registered servers
gate identically on next startup without spawning.
Tests: tests/tools/test_mcp_trust_gating.py (11 tests, TDD red->green):
approval invoked + accept proceeds, deny/cancel blocks RPC, readOnlyHint
=true skips gate, trusted/unconfigured servers skip gate, explicit
readOnlyHint=false gated, approval exception fails closed, trust
normalization, discovery-time capture (SDK objects and cached dicts).
Ported from: cloudflare-os classifyTool() (Apache-2.0), corroborated by
Claude Cowork (idea-level).
MCP servers generated from Rust/TypeScript union types commonly emit
closed value sets as const unions:
{"anyOf": [{"const": "red"}, {"const": "green"}, {"const": "blue"}]}
Strict tool-calling backends reject or mishandle these; the equivalent
property-level enum form is universally supported. Add
collapse_const_unions() to tools/schema_sanitizer.py and wire it into
the _normalize_mcp_input_schema discovery pipeline after the nullable
strip.
Rules:
- Collapse only when EVERY non-null branch is a pure const of the same
primitive type (bool never merges with integer).
- Mixed unions, non-uniform const types, and mismatched declared types
pass through untouched.
- A single {"type": "null"} branch is tolerated: consts -> enum,
null -> nullable: true hint (matches strip_nullable_unions, which
leaves null+multi-const unions alone by its one-non-null-branch rule).
- Outer title/description/default/examples carried onto the replacement.
- Deterministic, branch-order-preserving, non-mutating — applied at
discovery only, so schemas stay byte-stable per conversation.
Ported from: block/goose tool_schema_normalize.rs (Apache-2.0)
Two small config-gated features:
1. Kanban orphaned-card reconciliation (kanban.reconcile_orphans, default
true, config.yaml): a running card with broken claim bookkeeping
(claim_lock or claim_expires NULL — crash mid-claim, manual SQL, DB
restore) is invisible to all existing recovery paths
(release_stale_claims requires claim_expires NOT NULL,
detect_crashed_workers requires host-local lock + pid,
detect_stale_running is config-disabled by default) and shows Running
forever. New reconcile_orphaned_running() pass in kanban_db.py runs
each dispatch_once tick: requeues orphans to ready with an explanatory
comment, closes any leaked run, emits a 'reconciled' event, and defers
when the recorded PID is still alive on this host (never requeue
beside a live worker). Surfaced via DispatchResult.reconciled_orphans.
2. Per-server MCP identity header (mcp_servers.<name>.identity_header,
config.yaml): optional {name, value_from: static|profile, value}
mapping; the header is attached to that server's HTTP/SSE transport
requests. 'static' sends the config value; 'profile' resolves the
active Hermes profile name once at connect time (no per-call
mutation). Explicit per-server headers of the same name (any casing)
win. Invalid blocks warn-and-ignore; stdio servers warn-and-ignore.
Tests: tests/gateway/test_kanban_reconcile_orphans.py (9),
tests/tools/test_mcp_identity_header.py (13), all written first (RED)
then implemented (GREEN). No new HERMES_* env vars.
Inspired by: openai/symphony tracker reconciliation (Apache-2.0) +
Poke per-user MCP identity (idea-level).
Each serialized result entry now carries cost_usd (rounded to 6 dp)
and cost_status (the child's session_cost_status — 'estimated',
'reported', 'included', or 'unknown') alongside tokens/api_calls/
duration, so the parent model can see what each delegation cost.
The internal _child_cost_usd field is still stripped before
serialization and the parent session cost rollup is untouched.
Tool schema is unchanged (byte-stable).
Inspired by: Perplexity Agent API result shape (idea-level)
Teknium
Laith Weinberger
Drexuxux
kshitij
ethernet
bgrablin
rob-maron
Sora-bluesky
Ayush Nangia
Adolanium
nankingjing
Theophilus Chinomona
Brooklyn Nicholson
michaelsam94
fangliquanflq
Coy Geek
Ahmett101
dsad
Erosika
Gille
Dominic Bejar
toprakeker
GodsBoy
PRATHAMESH75