Remove redundant inner `import re` and regex recompilation on every call in
_interpolate_env_vars. Add module-level _ENV_VAR_PATTERN compiled once.
Replace the separate _interpolate_value() in mcp_config.py (which used \w+
and would silently fail on env vars containing hyphens or dots) with the
shared _ENV_VAR_PATTERN from mcp_tool.py. Remove now-unused import re.
Some catalog endpoints (OpenCode Zen, etc.) sit behind a WAF that
returns 403 for the default Python-urllib/<ver> User-Agent. The
generic profile-based live fetch in providers/base.py was silently
failing for any such provider — falling through to the static catalog
and missing newly-launched models.
Set a generic 'hermes-cli/<version>' UA on the catalog probe so every
api_key provider profile benefits. Verified live against opencode-zen:
before this change, profile.fetch_models() raised HTTP 403; after, it
returns 42 models including gpt-5.5, gpt-5.5-pro, kimi-k2.6, glm-5.1
and the *-free variants the static catalog doesn't list.
Also strip the now-stale comment in validate_requested_model() claiming
opencode-zen's /models returns 404 against the HTML marketing site —
the API endpoint at /zen/v1/models returns 200 with valid JSON.
Surfaced by #2651 (@aashizpoudel) — fixes the same user-facing gap
their PR targeted, applied at the right layer so all api_key provider
profiles get live catalogs through the same code path.
Co-authored-by: Aashish Poudel <mr.aashiz@gmail.com>
Replace O(n²) string concatenation of truncated_response_prefix in the
length-continuation retry loop with a list + ''.join(). Functionally
equivalent: same partial response on early return, same prepend on
final assembly. The legacy retry path is capped at 3 iterations, so
the practical wall-clock win is small, but the new idiom matches the
rest of the codebase and removes a needless repeated allocation.
Salvaged from PR #2717 (the run_conversation portion only — trajectory
refactor dropped because it silently rewrote </tool_response> to </think>).
Co-authored-by: Teknium <127238744+teknium1@users.noreply.github.com>
When running with --yolo, all dangerous command approvals are bypassed.
Make this state visible so users don't forget:
- Banner: '⚠ YOLO mode — all approval prompts bypassed' line in red, only
shown when YOLO is active. Default case is silent (no extra line, no
always-on 'restricted' label).
- Status bar: '⚠ YOLO' fragment appended in red (#FF4444 bold) across all
three width tiers (<52, <76, ≥76) in both the plain-text fallback and
the fragments builder.
Closes#2663
Co-authored-by: Mibayy <Mibayy@users.noreply.github.com>
- Adds plugins/platforms/simplex docs page to the messaging sidebar
between LINE and Open WebUI.
- Maps louismichalot@hotmail.com -> Mibayy in scripts/release.py so the
attribution check on the salvage PR passes.
SimpleX Chat (https://simplex.chat) is a private, decentralised messenger
with no persistent user IDs — every contact is identified by an opaque
internal ID generated at connection time. This adds it as a Hermes
gateway platform via the plugin system.
The adapter connects to a local simplex-chat daemon via WebSocket,
listens for inbound messages, and sends replies. Originally proposed in
PR #2558 as a core-modifying integration; reshaped here as a self-
contained plugin under plugins/platforms/simplex/ with no edits to any
core file. Discovery is filesystem-based (scanned by gateway.config),
and the platform identity is resolved on demand via Platform("simplex").
Plugin contract:
- check_requirements() requires SIMPLEX_WS_URL AND the websockets package
- validate_config() / is_connected() accept env or config.yaml input
- _env_enablement() seeds PlatformConfig.extra (ws_url + home_channel)
- _standalone_send() supports out-of-process cron delivery
- interactive_setup() provides a stdin wizard for hermes gateway setup
- register() wires the adapter into the registry with required_env,
install_hint, cron_deliver_env_var, allowed_users_env, and a
platform_hint for the LLM.
Lazy dependency: the websockets Python package is imported inside the
functions that need it. The plugin is importable and discoverable even
when websockets is missing — check_requirements() simply returns False
until `pip install websockets` is run. No new pyproject extras are
introduced.
Environment variables:
SIMPLEX_WS_URL WebSocket URL of the daemon (required)
SIMPLEX_ALLOWED_USERS Comma-separated allowed contact IDs
SIMPLEX_ALLOW_ALL_USERS Set true to allow all contacts
SIMPLEX_HOME_CHANNEL Default contact for cron delivery
SIMPLEX_HOME_CHANNEL_NAME Human label for the home channel
Closes#2557.
The Zed ACP Registry path (uvx --from 'hermes-agent[acp]==X' hermes-acp)
gets a Python-only install. Browser tools depend on the agent-browser npm
package + Chromium, neither of which are in the wheel. Without an
explicit bootstrap, registry users have no path to working browser tools.
Ship a bundled, idempotent bootstrap script (Linux/macOS bash + Windows
PowerShell) inside acp_adapter/bootstrap/ as wheel package-data. New
entry points:
hermes acp --setup-browser # interactive; prompts before Chromium download
hermes acp --setup-browser --yes # non-interactive
hermes-acp --setup-browser
The terminal-auth flow (hermes acp --setup) also offers the browser
bootstrap as a follow-up after model selection, so first-run registry
users get the option without knowing the flag exists.
Key design choices:
- npm install -g --prefix $NODE_PREFIX so we never need sudo. System Node
on PATH is respected; only the install target is redirected to the
user-writable Hermes-managed Node prefix.
- tools/browser_tool.py::_browser_candidate_path_dirs() already walks
$HERMES_HOME/node/bin, so installed binaries are discovered with no
agent-side code change.
- System Chrome/Chromium detection short-circuits the ~400 MB Playwright
download when a suitable browser already exists.
- Bash + PowerShell live as ONE copy each under acp_adapter/bootstrap/.
Not duplicated under scripts/. install.sh and install.ps1 keep their
inline browser blocks for the source-checkout path.
E2E validated end-to-end:
bash bootstrap_browser_tools.sh --skip-chromium
→ installs agent-browser into ~/.hermes/node/bin/
tools.browser_tool._find_agent_browser()
→ returns the installed path
check_browser_requirements()
→ returns True (browser tools register)
Tests:
- tests/acp/test_entry.py: 11 tests covering --setup-browser dispatch
(linux + windows + --yes forwarding + failure propagation), the
terminal-auth follow-up prompt path, and a package-data wheel-shipping
assertion that catches any future pyproject.toml regression.
Docs: website/docs/user-guide/features/acp.md gains a 'Browser tools
(optional)' subsection with the two-line install + what-it-does.
Cron mutation operations (run/pause/resume/remove) and 'hermes cron edit'
now accept a job name in addition to the hex ID, with case-insensitive
matching. Before this, 'hermes cron run my_job_name' died with
'Job with ID my_job_name not found' and forced the user to look up the
hex ID first.
The original PR matched by name but silently picked the first match when
two jobs shared a name. This version refuses to act on an ambiguous name
and surfaces every matching job (id, name, schedule, next_run_at) so the
caller can pick a specific ID.
- cron/jobs.py:
- get_job() stays ID-only (preserves existing call-site semantics for
web_server/api_server/curator/scheduler/test code that always passes
real IDs).
- resolve_job_ref() is the new name-or-ID resolver, used by pause/
resume/trigger/remove_job. Exact ID match wins over a name match
even if a different job's name happens to equal that ID. Ambiguous
name match raises AmbiguousJobReference with all candidate IDs.
- tools/cronjob_tools.py: dispatch site uses resolve_job_ref, surfaces
ambiguous matches as a structured error with the matching IDs.
- hermes_cli/cron.py: 'cron edit' uses resolve_job_ref so editing by
name works and ambiguous names are reported with IDs.
- tests/cron/test_jobs.py: new TestResolveJobRef covering ID match,
case-insensitive name match, ID-wins-over-name, ambiguous refusal,
and that pause/resume/trigger/remove all refuse on ambiguity.
Closes#2627
Adds three pre-run gate recipes to the cron docs:
- file-change gate (stat + mtime + state file)
- external-flag gate (file presence)
- SQL-count gate (user's own database, not state.db)
These are the use cases @iankar8 proposed adding as a parallel
'trigger' subsystem in #2654. The existing `script` + `wakeAgent`
gate already covers all three at $0 — this lands the patterns as
documentation so users can find them, instead of adding a second
gating mechanism to the cron subsystem.
When the in-tree FAL path has no API key (and no managed gateway), the
handler used to return a bare 'FAL_KEY environment variable not set'
error. Users had no idea where to get a key, that a managed Nous
gateway exists, or that plugin-registered providers are an option.
Now `image_generate_tool` returns a structured multi-line message:
- signup link (https://fal.ai)
- managed-gateway status (if Nous tools are enabled)
- pointer to `hermes tools` / `hermes plugins list` for alternate
backends, so users on a stale `image_gen.provider` know where to look
The schema is untouched — `check_fn` still gates the tool out of the
schema when no backend is reachable at startup, consistent with every
other conditional tool. This patch fixes the call-time failure modes:
managed-gateway 5xx, plugin provider disappearing mid-session, etc.
Inspired by #2546 / @Mibayy. The PR was ~5700 commits stale against
the new plugin-aware image_gen architecture, so this is a forward port
of the actionable-error idea rather than a cherry-pick.
Closes#2543
Co-authored-by: Mibayy <mibayy@users.noreply.github.com>
After the Mini Shai-Hulud supply chain campaign (May 2026) and the litellm
compromise (March 2026), codify the dependency pinning policy that was
established in PRs #2810 and #9801 but never written down for contributors.
Changes:
- pyproject.toml: Add tight upper bounds to the 5 deps that slipped
through as review escapes from external contributor PRs:
- hindsight-client>=0.4.22,<0.5 (was >=0.4.22)
- aiosqlite>=0.20,<0.23 (was >=0.20)
- asyncpg>=0.29,<0.32 (was >=0.29)
- alibabacloud-dingtalk>=2.0.0,<3 (was >=2.0.0)
- youtube-transcript-api>=1.2.0,<2 (was >=1.2.0)
Pre-1.0 packages get <0.(current_minor+2) — tight enough to block
hostile minor releases but loose enough to not require bumps every week.
- CONTRIBUTING.md: Add 'Dependency pinning policy' section under Security
with the full rationale, table of source types + treatments, and examples.
- AGENTS.md: Add concise 'Dependency Pinning Policy' section for AI coding
agents with the decision table and step-by-step checklist.
- supply-chain-audit.yml: Add dep-bounds job that fails PRs introducing
PyPI deps without <ceiling upper bounds. Fires on pyproject.toml changes.
Posts a PR comment with the specific unbounded specs found.
Refs: #2796#2810#9801#24205
Baileys' sock.sendMessage() can hang indefinitely while uploading
media to WhatsApp servers (and, less often, on text sends), pinning
the bridge's Express handler until the gateway's aiohttp timeout
fires — surfacing to the user as a 120s wait followed by an empty
error from the TTS/voice path.
Wrap every sock.sendMessage() call inside the bridge in a
sendWithTimeout() helper that rejects after WHATSAPP_SEND_TIMEOUT_MS
(default 60s) via Promise.race. The four call sites are /send,
/edit, and /send-media's primary send. Express handlers catch the
rejection in their existing try/catch and return a real 500 to the
gateway, which can then surface a retryable error.
Salvaged from #2608 — wysie diagnosed the hang and the
Promise.race shape; the other two parts of that PR (gateway HTTP
session pooling, base.py metadata kwarg removal) already landed on
main via separate routes and are no longer needed.
Co-authored-by: Teknium <127238744+teknium1@users.noreply.github.com>
ResponseStore.put() and .delete() now remove conversations rows that
reference evicted or deleted response IDs, preventing 404 errors when
a conversation name is reused after its backing response was purged.
Adds regression tests for delete, eviction, and handler-level reuse.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When a non-Anthropic provider (e.g. Morpheus proxy) returns a 429 with
`{"error": "Too Many Requests"}` instead of the expected
`{"error": {"type": ...}}` dict, _err_body.json().get("error", {})
returns the raw string and the next .get("type") line crashes with
AttributeError, taking down the message handler.
Guard with isinstance(_err_json, dict) so non-dict error bodies fall
through to the generic rate-limit hint.
Salvaged from PR #2587 by @KiraKatana. The PR's fallback-config
`base_url`/`api_key_env` fix was already implemented independently
on main (run_agent.py:8759-8780) with additional aliases and Ollama
Cloud host handling, so only the gateway guard is cherry-picked.
Co-authored-by: KiraKatana <kira.ops@proton.me>
was_auto_reset, auto_reset_reason, and reset_had_activity were not
included in SessionEntry.to_dict() / from_dict(), so a gateway restart
between session expiry and the user's next message would silently drop
the auto-reset notification and context note.
Add the three fields to the serialization roundtrip with safe defaults
(False / None / False) so existing sessions.json files load cleanly.
Add three roundtrip tests to test_session_reset_notify.py.
Adds Hugging Face's official skill catalog to the default GitHub taps and
classifies it as a trusted source alongside openai/skills and anthropics/skills.
- tools/skills_guard.py: huggingface/skills -> TRUSTED_REPOS
- tools/skills_hub.py: GitHubSource.DEFAULT_TAPS += huggingface/skills (skills/)
- website/docs: list it under default taps + trusted-source examples
Closes#2549.
Co-authored-by: teknium1 <127238744+teknium1@users.noreply.github.com>
When a user quotes a file message (type=3) and @bot, the quote's desc field
only contains the filename without a ybres:// resource reference. The existing
QuoteContextMiddleware only extracted media refs from desc using the ybres regex,
which always returned empty for file quotes.
Fix: add a transcript lookup fallback in QuoteContextMiddleware.handle() —
when quote_media_refs is empty but reply_to_message_id is set, search the
session transcript for the quoted message_id and extract ybres anchors from
its content.
Also fix message_type classification: when quote media resolves non-image files,
override message_type to DOCUMENT so gateway/run.py's document injection logic
properly prepends the file path and content for the agent.
The freeform /goal judge was capped at max_tokens=200, which reliably
truncated the JSON verdict on reasoning-heavy models (deepseek-v4-pro,
qwq, etc.) — the model burns tokens on hidden reasoning before emitting
visible content, and the first /goal turn's prompt is larger than later
turns, blowing past 200. Symptom: agent.log shows
`judge reply was not JSON: '{"done": true, "reason": "The agent successfully'`
followed by repeated `judge returned empty response` lines, then the
goal pauses with a misleading 'judge model isn't returning the required
JSON verdict' message.
Diagnosed live by @helix4u — empirically verified that raising the
budget on an unmodified worktree makes the failures go away on the
exact configs users were hitting on Nous Plus subscription paths.
Changes:
- DEFAULT_JUDGE_MAX_TOKENS = 4096 (up from 200)
- New auxiliary.goal_judge.max_tokens config knob for tuning in
specifically constrained setups
- _goal_judge_max_tokens() resolves the value with fail-open semantics
(non-int / non-positive / load failure → default). load_config() is
mtime-cached so per-turn lookup is cheap.
Scoped narrowly to the verified root cause — does not introduce a
submit_verdict tool-call schema (see #26162 / #23671 for that direction;
they can land separately if we want them).
Tests: tests/hermes_cli/test_goals.py + tests/cli/test_cli_goal_interrupt.py
+ tests/gateway/test_goal_verdict_send.py — 62/62 passing.
E2E verified: config override honored (8192), missing/garbage/zero
values fall back to 4096, no-auxiliary-section falls back to 4096.
Co-authored-by: helix4u <4317663+helix4u@users.noreply.github.com>
Credits:
- @helix4u (Gille) — diagnosed the max_tokens=200 truncation via live
testing on an unmodified worktree, drafted the original fix shape
in #26162.
- @AhmetArif0 — flagged the freeform judge fragility in #23671 from
the tool-call angle.
- @0xharryriddle (HarryRiddle.eth) — reported the issue from a Nous
Plus subscription setup in #23876 with full debug reports.
Closes#23876
Supersedes #26162, #23671, #23881
#25975 (salvaging #24403) clamped decorative scrollback Panels and
streaming box rules to `max(32, min(width, 56))` as a defense against
terminal-emulator reflow when columns shrink. On any modern wide
terminal this made the response/reasoning borders look stubby — 56
cols inside a 200-col viewport.
#26137 (salvaging #25981, by @OutThisLife) landed a more fundamental
fix: prompt_toolkit's `_output_screen_diff` is monkey-patched so its
reserve-vertical-space cursor move no longer pushes chrome into
scrollback at all. With that in place, the clamp is no longer
load-bearing for the chrome-into-scrollback class of bugs — the
remaining risk is purely cosmetic reflow of *already stamped*
Panel borders during an aggressive column shrink, which we now
accept as a tradeoff for restoring proper full-width rendering.
Changes:
- `_scrollback_box_width()` returns `max(32, width)` (just the floor,
no upper cap). All 10 call sites stay valid.
- Updated `test_scrollback_box_width_caps_to_resize_safe_value` to
the new `test_scrollback_box_width_returns_viewport_width` asserting
full-width passthrough above the 32-col floor.
Floor of 32 is kept so `'─' * (w - 2)` math stays positive on tiny
terminals.
Refs #18449#19280#22976 (the original reflow class) and #25975
(the clamp this reverts).
Adds 16 unit tests covering the light/dark terminal detection path
introduced in the previous commit:
- Env override priority (HERMES_LIGHT, HERMES_TUI_LIGHT,
HERMES_TUI_THEME, HERMES_TUI_BACKGROUND, COLORFGBG)
- Detection cache stickiness
- _maybe_remap_for_light_mode() no-op in dark mode
- Known dark-mode color remap (#FFF8DC -> #1A1A1A etc)
- Case-insensitive lookup
- Unknown color passthrough
- Status-bar paired colors (#C0C0C0, #888888, #555555, #8B8682) are
intentionally NOT remapped — regression guard for the patch-11 fix,
since remapping them would produce dark-on-dark on the status bar's
navy bg
- SkinConfig.get_color() wrapper is installed and idempotent
- SkinConfig.get_color() does remap in light mode and passes through
in dark mode
We don't try to fake an OSC 11 reply — that path is exercised
end-to-end in real Terminal.app; the env-override path covers the
algorithmic logic.
Two long-standing prompt_toolkit bugs in the base hermes CLI:
1. Resize duplication. Column-shrink resize used to push 40+ rows of
duplicate chrome (status bar, input rules) into terminal scrollback
every resize. Same wall as pt issues #29 (open since 2014), #1675,
#1933 — aider/xonsh/ipython all use alt-screen to dodge it.
Root cause (verified by reading prompt_toolkit/renderer.py):
_output_screen_diff (renderer.py L232-242) deliberately moves the
cursor to the bottom of the canvas after every paint 'to make sure
the terminal scrolls up'. In non-fullscreen mode this scrolls chrome
content into terminal scrollback on every render — not just on
resize.
Fix: monkey-patch prompt_toolkit.renderer._output_screen_diff to
bypass the reserve-vertical-space cursor move. When pt's logic checks
'if current_height > previous_screen.height', we inflate the previous
screen height so the branch falls through. ~30-line wrapper, no fork
of pt, no alt-screen, no DECSTBM scroll region.
Verified empirically in real Terminal.app: 10 resizes (mixed
shrinks/widens 1300→500→1400) during streaming produced ZERO
scrollback delta, full agent response preserved, status bar pinned
at bottom, no visible duplicates. pt is pinned to ==3.0.52 so the
private-function patch is safe; future pt bumps will need to
re-verify the signature matches.
2. Light-mode terminal visibility. Hardcoded skin colors (#FFF8DC
cornsilk, #FFD700 gold, #B8860B dark goldenrod) are tuned for dark
Terminal.app — invisible on light/cream backgrounds.
Port ui-tui/src/theme.ts detectLightMode() to Python so the base CLI
adapts. Detection priority: HERMES_LIGHT/HERMES_TUI_LIGHT env →
HERMES_TUI_THEME=light|dark → HERMES_TUI_BACKGROUND=#RRGGBB →
COLORFGBG env (xterm/Konsole/urxvt) → OSC 11 query
(\x1b]11;?\x1b\\) with 100ms timeout → default dark. OSC 11 is
tty-gated so gateway/cron/batch/subagent code paths don't pay the
timeout cost.
When light mode is detected, dark-mode colors auto-remap to readable
equivalents (#FFF8DC → #1A1A1A, #FFD700 → #9A6B00, etc). Hooked at
three points:
- _hex_to_ansi() — auto-remaps any color emitted via the ANSI helper
- _build_tui_style_dict() — rewrites pt style strings (chrome bg/fg)
- SkinConfig.get_color() — wrapped at module load so Rich Panel
borders/body text get the remap too
Status-bar foreground colors (#C0C0C0, #888888, etc.) are explicitly
skipped because they're paired with a dark navy bg — remapping them
would make them invisible in dark mode.
3. Other visibility fixes: [thinking] reasoning preview now uses ANSI
dim+italic (\x1b[2;3m) instead of #B8860B so it inherits terminal
default fg color. Input/prompt area defaults to terminal default fg
(was #FFF8DC cornsilk → invisible on cream).
Co-authored-by: Brooklyn Nicholson <brooklyn.bb.nicholson@gmail.com>
Discord's CDN serves attachments with Content-Encoding: br. aiohttp's
compression_utils tries 'import brotlicffi as brotli' first and falls back
to google's Brotli, but Brotli<1.2.0's Decompressor.process() is 1-arg
while aiohttp calls it with 2 args (data, max_length). Result: every
.txt/.md/.doc uploaded to a Discord-gateway session fails to decode at
att.read() with 'Can not decode content-encoding: br' / 'TypeError:
process() takes exactly 1 argument (2 given)', the agent never sees the
bytes, and falls back to filesystem guessing.
Pin brotlicffi==1.2.0.1 in both surfaces:
- tools/lazy_deps.py 'platform.discord' tuple: Discord users on the
lazy-install path get it on first discord.py import.
- pyproject.toml [messaging] extra: users who explicitly install
hermes-agent[messaging] (skipping the lazy path) get it eagerly.
brotlicffi wins aiohttp's import race regardless of what else is
installed (try brotlicffi / except: import brotli), so existing setups
that already pulled google's Brotli transitively don't change behavior
beyond the bug fix. ~1.5 MB wheel, manylinux/macOS/Windows coverage.
E2E verified: round-trip decode of Brotli-compressed payload via
aiohttp.compression_utils.brotli succeeds with brotlicffi pinned; same
test against Brotli==1.1.0 alone reproduces the reported TypeError.
Credit to @Korkyzer for the original diagnosis and fix shape in #15744;
the lazy-deps gating layer was added on top to keep brotlicffi out of
the install path for users who don't run a Discord gateway.
Fixes#12511.
Closes#15744.
Co-authored-by: Korky <korkyzer@gmail.com>
The ACP Registry schema supports uvx as a first-class distribution method
alongside npx and binary. Pointing the registry directly at the existing
hermes-agent PyPI release removes:
- the @nousresearch npm scope (we don't own it)
- a separate npm publish step on every weekly release
- 90 lines of Node launcher + tests in packages/hermes-agent-acp/
The Zed registry now installs Hermes via:
uvx --from 'hermes-agent[acp]==<version>' hermes-acp
This is the same command the npm launcher was shelling out to anyway, so
end-user behavior is unchanged. Registry CI validates the PyPI URL +
version-pin exact match automatically.
Changes:
- acp_registry/agent.json: distribution.npx -> distribution.uvx
- delete packages/hermes-agent-acp/ entirely
- scripts/release.py: drop npm-launcher bump paths, keep manifest lockstep
- tests/acp/test_registry_manifest.py: assert uvx shape + version pin
- tests/scripts/test_release_acp_registry.py: rewrite for uvx-only shape
- docs (user-guide + dev-guide): drop all npm-launcher references
- delete docs/plans/acp-registry-zed-integration.md (stale, npm-shaped)
Validated against agentclientprotocol/registry agent.schema.json via
jsonschema. hermes-agent==0.13.0 is already live on PyPI.
The ACP Registry manifest (acp_registry/agent.json), the npm launcher
package.json, and the launcher's HERMES_AGENT_VERSION constant must all
match pyproject.toml exactly — tests/acp/test_registry_manifest.py
enforces this lockstep.
Without a release-script hook, the next weekly version bump fails that
test until someone hand-edits four files. Extend update_version_files()
to drive the ACP bump alongside __init__.py and pyproject.toml, and
add tests covering the lockstep and the missing-files no-op path.
Also map adam.manning@gmail.com -> am423 for the salvage commit.
When the auxiliary client falls through Nous (e.g. no stored auth, or
runtime credential mint failed), users currently see only `debug`-level
lines, so the next provider in the fallback chain takes over silently.
Promote the no-auth path to a warning that tells operators to run
`hermes auth`, and add a debug breadcrumb on the rarer
mint-failed-but-stored-auth-still-present fallback path so the existing
behavior (use the raw stored token) is preserved while staying
investigable.
Salvaged from #23881 by @0xharryriddle. The contributor's original
patch also short-circuited the second branch with a return, which broke
the pool-entry fallback path covered by
`test_try_nous_uses_pool_entry` — kept the warning intent, dropped the
return so the fallback still works. Dropped the contributor's changes
to `hermes_cli/goals.py` because the goal-pause path is unreachable
when the auxiliary client is None (`judge_goal` returns
`parse_failed=False`, which resets `consecutive_parse_failures`),
so the reason string they added never surfaces in the pause message.
Refs #23876
On macOS with uv-managed cPython 3.11, the default kqueue selector cannot
register fd 0, so prompt_toolkit's loop.add_reader raises
OSError(EINVAL) ("[Errno 22] Invalid argument") from kqueue.control()
and the agent crashes immediately on startup (#5884, also reported in
#6393).
Probe KqueueSelector.register(0, EVENT_READ) before launching
prompt_toolkit. If it fails, install an event-loop policy that returns a
SelectorEventLoop backed by SelectSelector — select() works fine on
stdin in this Python build, so add_reader succeeds and the agent
launches normally.
Also extend the existing #6393 fallback handler to recognize EINVAL /
EBADF / "Invalid argument" so that any future selector failure on stdin
shows the friendly "reinstall Python via pyenv or Homebrew" guidance
instead of an opaque traceback.
Verified on macOS (Darwin 24.6.0) with uv-managed cPython 3.11.15: the
kqueue probe fails, the policy switch fires, and `hermes` launches
cleanly. No effect on platforms where kqueue can register fd 0.
Follow-up to the sandbox-bypass env-var fix:
- Update the opt-out gate so a user-provided AGENT_BROWSER_ARGS is also
respected, not just the legacy AGENT_BROWSER_CHROME_FLAGS. Previously
the gate only checked the broken legacy var, so a user who pre-set
AGENT_BROWSER_ARGS would still get clobbered by Hermes's auto-injection.
- Document AGENT_BROWSER_ARGS in .env.example, the browser feature page,
and the env var reference, with notes about the auto-injection on
AppArmor-restricted systems (Ubuntu 23.10+, DGX Spark, containers).
- Add Anadi Jaggia to AUTHOR_MAP.
AGENT_BROWSER_CHROME_FLAGS is not read by agent-browser CLI.
The correct env var is AGENT_BROWSER_ARGS, with comma-separated values.
This fixes Chrome 'No usable sandbox' crash on Ubuntu 23.10+ systems
where AppArmor restricts unprivileged user namespaces. The detection
logic was correct but the fix used the wrong environment variable name
and space-separated instead of comma-separated args.
The 'sessions' command has been registered in the central command
registry since #20805 (May 2025) and surfaces in /help and tab-completion,
but the classic CLI's process_command() never had an elif branch for it.
The canonical name fell through and printed 'Unknown command: sessions'.
The TUI side was wired up correctly via the SessionPicker overlay; only
the legacy CLI was missing the dispatch.
Adds _handle_sessions_command() which mirrors /resume's no-arg behavior
inline (the CLI has no overlay primitive equivalent to the TUI picker):
- /sessions and /sessions list → print the recent-sessions table
- /sessions <id_or_title> → delegates to _handle_resume_command
Includes regression tests covering the dispatcher wiring (the original
bug) plus the three handler branches.
The call site at line 246 is already wrapped in try/except NotImplementedError
(added in #25969). The checker just doesn't peek at surrounding context.
Mark with the suppression comment so the blocking check passes.
Codex review pointed out that even with the sync-assets fix applied,
_build_web_ui still crashes on a stock Windows console before reaching
npm: Python stdout defaults to cp1252 (or similar) and raises
UnicodeEncodeError when print() hits the arrow/check glyphs used for
status messages (→, ✗, ⚠, ✓). Reproduced locally in PowerShell:
$ PYTHONIOENCODING=cp1252 python -c "from hermes_cli.main import _build_web_ui; _build_web_ui(Path('web'), fatal=True)"
UnicodeEncodeError: 'charmap' codec can't encode character '\u2192' ...
The previous PR body claimed "end-to-end verified on Windows 11", but
that was under the venv's default (utf-8) stdout. A plain `py` or
PowerShell invocation would still fail before sync-assets ever ran.
Fix: inner _say() helper that falls back to
text.encode(sys.stdout.encoding, errors="replace")
when print() raises UnicodeEncodeError. Glyphs degrade to '?' on
ASCII / cp1252 consoles; utf-8 consoles are unaffected. Verified the
full build pipeline runs to completion with PYTHONIOENCODING=cp1252.
Scoped tightly to _build_web_ui (the function this PR already touches);
other call sites in the codebase with the same risk are out of scope.
Three Windows-only bugs in the web-dashboard build path. Each is small,
scoped, and verified end-to-end on Windows 11 — including under a stock
cmd.exe / PowerShell console with its default cp1252 encoding.
1. `sync-assets` shells out to Unix-only commands
web/package.json hard-codes `rm -rf … && cp -r …`. Neither exists on
Windows cmd.exe. `hermes_cli/main.py::_build_web_ui` runs npm via
subprocess (which on Windows defaults to cmd.exe), so the prebuild
hook crashed before Vite ever ran and the dashboard never built.
Fix: web/scripts/sync-assets.mjs — ~20 lines of Node using fs.rmSync
+ fs.cpSync (stdlib, Node >= 16.7). No new deps, identical behavior
on POSIX and Windows.
2. Build failures were silent
_build_web_ui ran both subprocess calls with capture_output=True and
never relayed the captured buffers on failure. Users saw 'Web UI
build failed' and nothing else — no stdout, no stderr, no hint that
the real problem was 'rm is not recognized'.
Fix: inner _relay() helper that decodes and prints stdout + stderr
(utf-8, errors='replace') whenever a step returns non-zero. Replaces
the existing stderr_tail-only relay on the build path; success path
is unchanged. (stderr_tail is preserved for the stale-dist fallback
branch added by #23817.)
Salvaged from #13368 by @johnisag onto current main. Conflict
resolution preserves main's improvements:
- _run_npm_install_deterministic() (replaces bare subprocess.run for
npm install)
- npm-build retry-after-sleep for Windows boot-time races (#23817)
- stale-dist fallback for non-interactive callers (#23817)
Closes#25073, #13368.
Pre-existing diagnostics below an edit point used to surface as 'LSP
diagnostics introduced by this edit' whenever the edit deleted or
inserted lines. The delta-filter key included the diagnostic's
range, so the same logical error reported at a different line in
the post-edit snapshot looked like a brand new diagnostic.
Concrete case: deleting 14 lines in cli.py caused Pyright errors at
lines 9873, 10590, 12413, 13004 (unrelated to the edit) to be
reported as introduced by it.
Fix: build a piecewise-linear line-shift map (via difflib's
SequenceMatcher) from pre and post content, and remap baseline
diagnostics into post-edit coordinates before the set-difference.
Diagnostics in deleted regions drop out cleanly; diagnostics below
the edit shift by the right amount; diagnostics above are untouched.
The strict (range-aware) equality key stays — so a genuinely new
instance of an identical error class at a different line still
surfaces as new.
Pieces:
- agent/lsp/range_shift.py — build_line_shift, shift_diagnostic_range,
shift_baseline. Pure functions, no LSP state.
- agent/lsp/manager.py — LSPService.get_diagnostics_sync gains an
optional line_shift kwarg; baseline is shift_baseline'd before
computing the seen-set. _diag_key keeps the strict range key.
- tools/file_operations.py — write_file captures pre_content for any
LSP-handled extension (not just LINTERS_INPROC) and passes pre/post
to _maybe_lsp_diagnostics, which builds the shift map.
- New _lsp_handles_extension helper guards the pre_content read.
Trade-offs preserved:
- Genuinely new same-class errors at different lines still surface
(content-only key would have swallowed them).
- Pre-existing errors at unshifted positions still get filtered
(covered by the strict-key path with no shift).
- Best-effort: when pre_content can't be captured (file didn't
exist, permissions), the unshifted comparison still catches
most pre-existing errors; the edge case it misses is a new file
with a non-empty baseline, which is structurally impossible.
The prebuild step used `rm -rf` and `cp -r`, which fail on Windows
(`'rm' is not recognized`). Replace with an inline Node one-liner
using fs.rmSync / fs.cpSync so the build works on Windows, macOS,
and Linux without adding a dependency.
Follow-up to snav's PR #25463 contribution: flip default to on, broaden
scope so backfill fires whenever require_mention gates the bot (not just
shared-session channels).
Why:
- The mention-gate creates a session-transcript gap regardless of whether
the channel is shared or per-user. In per-user sessions, Alice's session
is still missing other participants' messages and her own pre-mention
messages — backfill fills both gaps.
- Threads naturally scope to thread-only history because discord.py's
channel.history() on a thread returns only that thread's messages.
- DMs still skip — every DM triggers the bot, so the session transcript
is already complete.
Changes:
- hermes_cli/config.py: discord.history_backfill default → true
- gateway/platforms/discord.py: drop the _is_shared gate, keep _is_dm
skip and _needed_mention gate; env var DISCORD_HISTORY_BACKFILL
default → 'true'
- cli-config.yaml.example + website docs: update defaults and prose;
add the DISCORD_HISTORY_BACKFILL / _LIMIT env var rows that were
documented in the PR description but missing from the env-var table
- tests/gateway/test_discord_free_response.py:
- flip test_discord_per_user_channel_does_not_backfill →
test_discord_per_user_channel_backfills_too (new behavior)
- add test_discord_dm_does_not_backfill (DM skip is invariant)
- give FakeThread a no-op history() so existing thread tests don't hit
a fake discord.Forbidden when backfill now fires on threads too
Tests: 160/160 in target files; 400/400 across all tests/gateway/ -k discord.
