Brings Discord to parity with Telegram on the clarify tool's interactive
UX. Overrides BasePlatformAdapter.send_clarify on DiscordAdapter to attach
a button view when choices are present.

  - ClarifyChoiceView: one discord.ui.Button per choice (max 24, Discord's
    25-component view cap leaves one slot for Other) plus a final
    'Other (type answer)' button.
  - Numeric click -> tools.clarify_gateway.resolve_gateway_clarify(
    clarify_id, choice_text) using the canonical choice text from the
    gateway entry (falls back to the button label if the entry vanished).
  - Other click -> tools.clarify_gateway.mark_awaiting_text(clarify_id) so
    the gateway's text-intercept captures the next user message in this
    session as the response.
  - Auth via the shared _component_check_auth helper (same OR-semantics as
    ExecApprovalView / SlashConfirmView / UpdatePromptView / ModelPickerView).
  - Open-ended (no choices) path renders the prompt as a plain embed and
    relies on the existing text-intercept resolution.
  - Single-use: first valid click disables every button and updates the
    embed footer with who answered and what they chose.

No changes to BasePlatformAdapter.send_clarify or the gateway's
clarify_callback wiring -- the existing scaffolding already drives all
adapters; Discord just inherits the default text fallback today and gains
buttons by virtue of this override.

Test conftest extended: _FakeEmbed gains add_field() / set_footer() stubs
so tests can construct embedded views without monkey-patching per-test.

Original PR: #19249 by @LeonSGP43. This is a reshape of the contributor's
work onto current main's clarify infrastructure (clarify_id + entry-based
resolution shared with Telegram, instead of a parallel on_answer-closure
mechanism). The button view structure and UX shape are preserved.

Tests: 14 new tests in tests/gateway/test_discord_clarify_buttons.py.
391/391 existing Discord gateway tests still pass.

Co-authored-by: LeonSGP43 <cine.dreamer.one@gmail.com>

* test(ci): stabilize shared optional dependency baselines

* fix(install): preserve pip entry point when re-running on symlinked install

setup_path() writes the user-facing hermes shim with `cat >`, which
follows existing symlinks. Older installs created
`$command_link_dir/hermes` as a symlink to `$HERMES_BIN`
(`venv/bin/hermes`), so re-running install.sh stomped the pip entry
point with a bash shim that exec'd itself in an infinite loop.

`rm -f` the link target before writing so the shim lands at
`$command_link_dir/hermes` and the venv entry point is left intact.

Adds a regression test that reproduces the symlink-stomp end-to-end
(creates the symlink, drives the real shim-write block from setup_path,
asserts the venv pip script body survives and the shim is now a regular
file). Both new assertions fail on origin/main and pass with the fix.

Closes #21454.

* feat(discord): render clarify choices as buttons

Brings Discord to parity with Telegram on the clarify tool's interactive
UX. Overrides BasePlatformAdapter.send_clarify on DiscordAdapter to attach
a button view when choices are present.

  - ClarifyChoiceView: one discord.ui.Button per choice (max 24, Discord's
    25-component view cap leaves one slot for Other) plus a final
    'Other (type answer)' button.
  - Numeric click -> tools.clarify_gateway.resolve_gateway_clarify(
    clarify_id, choice_text) using the canonical choice text from the
    gateway entry (falls back to the button label if the entry vanished).
  - Other click -> tools.clarify_gateway.mark_awaiting_text(clarify_id) so
    the gateway's text-intercept captures the next user message in this
    session as the response.
  - Auth via the shared _component_check_auth helper (same OR-semantics as
    ExecApprovalView / SlashConfirmView / UpdatePromptView / ModelPickerView).
  - Open-ended (no choices) path renders the prompt as a plain embed and
    relies on the existing text-intercept resolution.
  - Single-use: first valid click disables every button and updates the
    embed footer with who answered and what they chose.

No changes to BasePlatformAdapter.send_clarify or the gateway's
clarify_callback wiring -- the existing scaffolding already drives all
adapters; Discord just inherits the default text fallback today and gains
buttons by virtue of this override.

Test conftest extended: _FakeEmbed gains add_field() / set_footer() stubs
so tests can construct embedded views without monkey-patching per-test.

Original PR: #19249 by @LeonSGP43. This is a reshape of the contributor's
work onto current main's clarify infrastructure (clarify_id + entry-based
resolution shared with Telegram, instead of a parallel on_answer-closure
mechanism). The button view structure and UX shape are preserved.

Tests: 14 new tests in tests/gateway/test_discord_clarify_buttons.py.
391/391 existing Discord gateway tests still pass.

Co-authored-by: LeonSGP43 <cine.dreamer.one@gmail.com>

* fix(cli): allow rotating broken OpenRouter / AI Gateway key in `hermes model` flow (#25750)

Before: when `OPENROUTER_API_KEY` (or `AI_GATEWAY_API_KEY`) was already
set in ~/.hermes/.env, `hermes model openrouter` / `hermes model
ai-gateway` skipped the API-key prompt entirely and jumped straight to
the model picker. Users with a broken / expired / wrong key had no way
to replace it without editing ~/.hermes/.env by hand or re-running
`hermes setup` from scratch.

Both flows now route through the existing `_prompt_api_key()` helper,
which surfaces [K]eep / [R]eplace / [C]lear when a key is already
configured — the same UX the generic API-key providers (z.ai, MiniMax,
Gemini, etc.) and the Daytona setup already use.

* fix(install.ps1): pin uv sync to venv\, verify baseline imports on Windows (#25755)

* fix(cli): allow rotating broken OpenRouter / AI Gateway key in `hermes model` flow

Before: when `OPENROUTER_API_KEY` (or `AI_GATEWAY_API_KEY`) was already
set in ~/.hermes/.env, `hermes model openrouter` / `hermes model
ai-gateway` skipped the API-key prompt entirely and jumped straight to
the model picker. Users with a broken / expired / wrong key had no way
to replace it without editing ~/.hermes/.env by hand or re-running
`hermes setup` from scratch.

Both flows now route through the existing `_prompt_api_key()` helper,
which surfaces [K]eep / [R]eplace / [C]lear when a key is already
configured — the same UX the generic API-key providers (z.ai, MiniMax,
Gemini, etc.) and the Daytona setup already use.

* fix(install.ps1): pin uv sync target to venv\, verify baseline imports

Two related Windows-installer bugs that produce a broken venv with
`ModuleNotFoundError: No module named 'dotenv'` on first `hermes` run.

## Bug 1: uv sync ignores VIRTUAL_ENV, syncs into .venv\ instead of venv\

`Install-Dependencies` creates the venv at `venv\` via `uv venv venv`,
sets `$env:VIRTUAL_ENV = "$InstallDir\venv"`, then runs
`uv sync --extra all --locked`. Modern uv (>=0.5) ignores `VIRTUAL_ENV`
for the `sync` subcommand and uses the project default `.venv\`
instead. Result: deps land in `$InstallDir\.venv\`, `venv\` stays
empty except for the python.exe stub from the earlier `uv venv` call,
`hermes.exe` ends up wired to the wrong site-packages.

The bash installer (`scripts/install.sh`) already worked around this in
`install_deps()` line 1127 by passing `UV_PROJECT_ENVIRONMENT` — that
flag tells uv exactly where to put the project env regardless of
`VIRTUAL_ENV`. Port the same fix to PowerShell.

## Bug 2: no post-install verification

If the sync still misdirects for any other reason (uv version drift,
filesystem quirk, user re-run scenarios), the installer reports success
and the user only finds out by running `hermes` and getting an
unhelpful traceback. Add a baseline-import probe that runs the venv's
own python against the four packages every `hermes` invocation needs
(`dotenv`, `openai`, `rich`, `prompt_toolkit`). On failure, throw
with a recovery command tailored to whether a sibling `.venv\` exists.

User report (Windows 11, Python 3.13.5, Hermes v0.13.0): manual repro
steps were exactly this — `uv sync` landed in `.venv\`, recovered by
junctioning `venv\` → `.venv\` to bridge the path mismatch.

* fix(telegram): escape dynamic markdown in callback flows

Use MarkdownV2 formatting for Telegram callback follow-ups and interactive prompts where dynamic names or user text can break legacy Markdown parsing. Add regression coverage for reload-mcp, model picker, approval callbacks, and update prompts.

* fix(telegram): restore model-switch success path + author map

The cherry-picked PR over-indented the edit_message_text block for
the mm: (model selected → switch) success path so the confirmation
edit lived inside the preceding 'except Exception as exc' branch and
only fired when the callback raised. Dedent the try/except back to
12-space indent so it runs after the callback succeeds, restoring
the original flow that removes the inline buttons and shows the
'Switched to ...' confirmation.

Add a regression test (test_model_selected_edits_message_on_success)
that asserts edit_message_text is awaited and the result text is
routed through format_message (MARKDOWN_V2 + backtick survival).

Add phuongvm to scripts/release.py AUTHOR_MAP.

* fix(memory): skip OpenViking upload symlinks

* fix(codex-runtime): retire wedged sessions + post-tool watchdog + OAuth refresh classify (#25769)

Mirrors openclaw beta.8's app-server resilience fixes so a stuck codex
subprocess can't burn the full turn deadline and so users get a
`codex login` pointer instead of raw RPC errors when their token expires.

- TurnResult.should_retire signals the caller to drop+respawn codex.
- Deadline-hit path and dead-subprocess detection set should_retire so
  the next turn doesn't ride a CPU-spinning or auth-broken process.
- Post-tool watchdog (post_tool_quiet_timeout=90s): if a tool item
  completes and codex goes silent past the threshold without further
  output or turn/completed, fast-fail instead of waiting the full 600s.
  Resets on any non-tool activity so normal think-after-tool flows are
  not affected.
- <turn_aborted> and <turn_aborted/> in agent text are treated as
  terminal — some codex builds tear down a turn that way without
  emitting turn/completed.
- _classify_oauth_failure() inspects RPC error message + stderr tail
  for invalid_grant / token refresh / 401 / etc. and rewrites
  user-facing errors to 'run codex login'. Conservative: generic
  failures still surface verbatim. Fires at turn/start failure,
  turn/completed failure, and dead-subprocess paths.
- thread/start cross-fill: tolerate thread.id, thread.sessionId,
  top-level sessionId/threadId so future codex schema drift doesn't
  KeyError us at handshake.
- run_agent.py: when run_turn returns should_retire=True OR raises,
  close + null self._codex_session so the next turn respawns.

Tests: +30 cases across session + integration suites.
  tests/agent/transports/test_codex_app_server_session.py 50/50 pass
  tests/run_agent/test_codex_app_server_integration.py 27/27 pass
  Broader codex scope (transports + cli runtime/migration) 376/376 pass

* chore(release): add AUTHOR_MAP entries for second new-contributor batch

Pre-stages AUTHOR_MAP for 7 new contributors in the upcoming batch:

- HxT9          (#25760)
- evgyur        (#25651)
- AsoTora       (#25624)
- oxngon        (#25603)
- yifengingit   (#25589)
- vanthinh6886  (#25562)
- Arkmusn       (#25559)

EthanGuo-coder, wesleysimplicio, and zccyman are already in the map.

* fix: read approvals.timeout from config in CLI approval callback

The _approval_callback method in HermesCLI hardcoded timeout=60
instead of reading the approvals.timeout config value. This meant
the config setting was silently ignored for CLI interactive prompts.

Other approval paths (callbacks.py, tools/approval.py) already read
the config correctly — only cli.py was missed.

* fix: use AUTOINCREMENT id for message ordering instead of timestamp

On WSL2 (and similar environments), time.time() is not strictly monotonic
due to NTP sync or host clock adjustments. When clock regression occurs
during a multi-tool flush, later-inserted rows get earlier timestamps,
causing ORDER BY timestamp, id to sort them before rows that were written
first. This breaks the tool_calls/tool_response adjacency invariant and
triggers HTTP 400 from the API.

Use ORDER BY id instead, since id (INTEGER PRIMARY KEY AUTOINCREMENT)
always reflects true insertion order regardless of system clock behavior.

* docs: clarify media impact on session context

* fix: stop retrying initial MCP auth failures

* fix(gateway): enable text-intercept for multi-choice clarify fallback (#25567)

* fix: restrict .env file permissions to 0600

Set file mode 0600 on ~/.hermes/.env after creation in the installer and
after every write via memory_setup._write_env_vars(). This ensures only
the file owner can read/write API keys and tokens, matching standard
practice for credential files (.netrc, .aws/credentials, .ssh/config).

Fixes #25477

* fix(gateway): forward image attachments to background agent tasks

When the gateway spawned a background agent (e.g. for delegation), media
URLs and types from the originating message weren't forwarded — the bg
agent saw the prompt but no attached images. Vision-enabled tasks
effectively lost their inputs.

Forwards media_urls/media_types through the bg-task spawn path and
runs the same vision-enrichment step the main flow uses, so the bg
agent gets image descriptions inlined into its prompt.

Closes #25614.

Salvage of #25603 by @oxngon (manually re-applied — original branch
was severely stale against current main).

* fix(terminal): prevent safety filter false positives on keywords inside quoted strings

The _foreground_background_guidance() function matched background-wrapper
keywords (nohup/disown/setsid) anywhere in the command text, including
inside quoted strings, Python -c code, commit messages, and PR body text.

Two-layer fix:
1. Strip single-quoted, double-quoted, and backtick-quoted content before
   pattern matching via _strip_quotes() helper.
2. Tighten the regex to only match keywords at command-start positions
   (after ^, ;, &, &&, ||, or $() — not mid-argument.

Both layers are needed: quote stripping handles the common case of keywords
in string literals, and the position-aware regex handles unquoted cases
like 'export FOO=setsid' (word boundary match, wrong position).

Fixes #20064

* chore(release): map oswaldb22 noreply email for AUTHOR_MAP

Co-Authored-By: Oswald <oswaldb22@users.noreply.github.com>

* test(toolsets): lock web search into default platform coverage

Adds regression tests pinning web search into the WhatsApp and api-server
default platform-coverage toolsets. Pure test additions, no runtime change.

Salvage of the test-addition commit from #25692 by @wesleysimplicio.
(The AUTHOR_MAP fixup commit from the same PR landed separately as
529ec85c7.)

* fix(update): refresh lazy-installed backends on hermes update (#25766)

Pyproject's [all] extra was slimmed down in May 2026 — ~20 optional
backends moved to tools/lazy_deps.py and only install on first use.
hermes update runs uv pip install -e .[all] which doesn't touch any of
them, so pin bumps in LAZY_DEPS (CVE response, transitive fixes) were
silently ignored on already-activated backends.

Two changes:

1. _is_satisfied() now parses the spec and checks the installed version
   against the constraint via packaging.specifiers. Previously it
   returned True the moment the package name was importable, which made
   ensure() a name-presence gate rather than a version-pin gate.

2. New active_features() / refresh_active_features() pair: lists every
   feature with at least one of its packages currently installed, then
   re-runs ensure() on each. Refresh is invoked at the end of
   _cmd_update_impl, right after the [all] install completes. Cold
   backends (never activated) stay quiet — no churn for them.

Output during update is one summary block:
  → Refreshing 4 active lazy backend(s)...
    ↑ 1 refreshed: provider.anthropic
    ✓ 3 already current
or
    ⚠ memory.honcho failed to refresh: <pip stderr>

Failures never raise out of update — backends keep their previously-
installed version and we tell the user to rerun once upstream is fixed.
security.allow_lazy_installs=false is honored: features get marked
"skipped" with the reason shown.

Tests: 18 new unit tests covering version-aware satisfaction (exact pin,
range, extras blocks, missing package, malformed spec), active feature
discovery, and refresh status reporting. All 61 lazy_deps tests pass.

* fix(agent/gemini-cloudcode): seed delta defaults for reasoning-only stream chunks

_make_stream_chunk built delta_kwargs with only `role`, so a reasoning-only
chunk produced a SimpleNamespace without a `.content` attribute. Downstream
consumers that read `delta.content` then raised AttributeError on Gemini 2.5
Flash, where the thinking delta arrives before any content delta.

Seed `content`, `tool_calls`, `reasoning`, and `reasoning_content` as None
up front, matching the pattern already used in gemini_native_adapter.py.
Key-present arguments still override the defaults.

Fixes #24974
References: Related open PR #24984 (luyao618) applies the same 1-line fix; this PR adds a regression test that #24984 omits
Co-Authored-By: Claude <noreply@anthropic.com>

* fix(install): support non-sudo service-user installs on apt distros (#25814)

The Debian/Ubuntu branch of install_node_deps() ran 'npx playwright install
--with-deps chromium' unconditionally. Playwright invokes sudo interactively
to apt-install Chromium's system libraries, which blocks the installer for
non-sudo users (systemd service accounts, unprivileged operator users) on
an unsatisfiable password prompt.

Changes:
- install.sh: gate --with-deps behind a sudo capability check on the apt
  branch (matches the existing Arch/pacman branch pattern). Non-sudo users
  fall back to 'npx playwright install chromium' alone and the installer
  prints the exact 'sudo npx playwright install-deps chromium' command an
  administrator can run separately.
- install.sh: add --skip-browser (alias --no-playwright) to skip the
  Playwright step entirely for headless installs that don't need browser
  automation. Mirrors the existing --no-venv / --skip-setup shape.
- installation.md: add a 'Non-Sudo / System Service User Installs' section
  covering the admin/service-user split, the --skip-browser flag, and the
  ~/.local/bin PATH gotcha (the root cause of the 'No module named dotenv'
  error users hit when running the repo source 'hermes' script with system
  Python instead of the venv launcher).
- test_install_sh_browser_install.py: regression coverage for the
  --skip-browser flag and the sudo-gate on the apt branch.

Reported by @ssilver in Discord.

* skill(comfyui): add template-integrity reference from @purzbeats (#25828)

Adds references/template-integrity.md covering safe conversion of the
official comfyui-workflow-templates package from editor format to API
format — Reroute bypass via link tracing, dotted dynamic-input keys
(values.a, resize_type.width) that must NOT be flattened, server-error
"patch don't rebuild" loop, Cloud quirks (302 redirect to signed GCS
URL, free-tier 1 concurrent job, 1920x1080 OOM on RTX 5090), and a
Discord-compatible ffmpeg stitch recipe (yuv420p + xfade/acrossfade).

SKILL.md lists the new reference so the agent loads it when starting
from an official template. purzbeats added to author list and to
scripts/release.py AUTHOR_MAP.

Co-authored-by: purzbeats <97489706+purzbeats@users.noreply.github.com>

* fix(whatsapp): drop status broadcasts and channel newsletters before agent dispatch (#25845)

WhatsApp pseudo-chats (Status updates / Stories, Channels / Newsletters,
broadcast lists) were being routed through the full agent pipeline. A
user's gateway.log showed the agent replying to a contact's Story
('status@broadcast') with 345 chars plus title-generation cost, which
also shows up in the contact's status feed.

Drop these JIDs at _should_process_message() before the policy gate so
they're filtered regardless of dm_policy or allowlist state. Covers:
- status@broadcast (Stories)
- *@newsletter (Channels)
- *@broadcast (broadcast lists, future-proofing)

The bridge.js already filters these on the fromMe outbound path, but
inbound events on self-chat mode skipped that check.

Tests:
- status@broadcast dropped on open policy
- broadcast filter wins over allowlisted senders
- real DMs still pass through
- helper unit cases (case-insensitive, whitespace-tolerant)

26/26 tests/gateway/test_whatsapp_group_gating.py pass; 59/59 adjacent
WhatsApp test suites pass.

* fix(ci): stabilize shared test state after 21012

* fix(telegram): set REQUIRES_EDIT_FINALIZE so final MarkdownV2 edit is not skipped

When the final streamed text is identical to the last plain-text edit,
stream_consumer._send_or_edit short-circuits and never calls
adapter.edit_message(finalize=True).  For Telegram, this skips the
plain-text → MarkdownV2 conversion, leaving raw Markdown syntax visible
to the user.

Set REQUIRES_EDIT_FINALIZE = True on TelegramAdapter so the finalize
edit is always delivered, matching the existing DingTalk pattern.

Fixes #25710

* fix(gateway): load streaming config from nested gateway.streaming key

`hermes config set gateway.streaming.*` writes the streaming block
nested under a `gateway:` key in config.yaml, but the config loader
only checked for a top-level `streaming:` key — silently ignoring
the nested variant.

Fall back to `yaml_cfg['gateway']['streaming']` when the top-level
key is absent, matching the pattern already used for other nested
config sections.

Closes #25676

* fix(gateway): prevent duplicate final send when only cosmetic edit failed

When the stream consumer's got_done handler successfully delivers the
final response content via _send_or_edit but the subsequent edit
(e.g. cursor removal) fails, final_response_sent remains False even
though the user has already received the final answer. The gateway's
fallback send path then re-delivers the same content, causing the
user to see the response twice on Telegram.

Introduce a new _final_content_delivered flag on the stream consumer,
set by the got_done handler when the final content has reached the
user. The _run_agent suppression logic now treats this flag as an
additional signal (alongside final_response_sent and
response_previewed) that final delivery is already complete.

This preserves the existing behavior for intermediate-text-only
streams (where already_sent=True but no final content has been
delivered) — those still receive the gateway's fallback send, matching
the test expectation in test_partial_stream_output_does_not_set_already_sent.

Adds TestFinalContentDeliveredSuppression with two cases covering
both the suppression (content delivered + edit failed) and the
non-suppression (intermediate text only) branches.

* fix(agent): keep image tool results from poisoning text-only sessions

* fix(codex-app-server): attach redacted stderr tail to generic failures (#25929)

When codex app-server fails outside the OAuth-classified path
(non-auth turn/start errors, plain TimeoutErrors, generic turn-ended
status, subprocess silently exits, hard deadline timeout), the user
got a bare 'Internal error' / 'turn/start failed: ...' with no
context. Diagnosing config/provider/auth-bridge issues forced a
re-run with verbose codex flags.

Add a _format_error_with_stderr helper that appends the last few
stderr lines via agent.redact.redact_sensitive_text(force=True),
and use it at every catch-all error site:

- ensure_started() failures (codex init / thread/start) now return
  a TurnResult.error with should_retire=True instead of bubbling
- non-OAuth turn/start CodexAppServerError / TimeoutError
- subprocess-died branch (previously dumped raw stderr_blob[-300:]
  with no redaction — a leak risk)
- turn ended with non-completed status
- hard turn-timeout deadline

OAuth-classified failures and the post-tool quiet watchdog already
produce clean hints and stay unchanged. The redactor catches sk-*,
gh*_*, Authorization: Bearer, query-string tokens, JWTs, private
keys, etc., so provider error payloads can't leak into chat output
or trajectories.

Inspired by openclaw#80718, adapted for our app-server transport.

* fix(cli): batch resize history replay

* chore(release): map @1000Delta in AUTHOR_MAP

* fix(voice): remove per-tool-call beep in CLI voice mode (#25967)

The spinner already shows tool activity visually; the 1.2 kHz tone on
every tool.started event was unwanted noise (especially on WSL2, where
each beep also triggers Windows Terminal's bell notification).

Removed the play_beep call in _on_tool_progress entirely. Record
start/stop beeps (gated by voice.beep_enabled) are unaffected.

* fix: preserve ansi output history on resize replay

* chore(release): map @LeonSGP43 commit email in AUTHOR_MAP

* fix(cli): clamp scrollback box widths + suppress status bar after resize (#25975)

When the terminal shrinks, already-printed box-drawing rules (response,
reasoning, streaming TTS, background-task Panels) reflow into multiple
narrower rows — visible as duplicated horizontal separators / ghost
lines in scrollback. Similarly, prompt_toolkit redraws a fresh status
bar on SIGWINCH on top of one the terminal just reflowed, producing
double-bar artifacts on column shrink.

Two surgical changes:

1. Decorative scrollback boxes now use a new
   `HermesCLI._scrollback_box_width()` helper that clamps to
   `max(32, min(width, 56))`. The live TUI footer is unaffected and still
   uses the full width. Covers: streaming response box (open + close),
   reasoning box (open + close, both streaming and post-stream paths),
   streaming-TTS box close, final-response Rich Panel, and the
   background-task Rich Panel.

2. `_recover_after_resize()` now also sets a new
   `_status_bar_suppressed_after_resize` flag so the dynamic status bar
   and both input separator rules stay hidden until the next user input.
   The flag is cleared in the process loop the moment the user submits
   their next prompt, restoring chrome cleanly.

Tests:
- New `test_input_rules_hide_after_resize_until_next_input` covers the
  flag's effect on rule heights.
- New `test_scrollback_box_width_caps_to_resize_safe_value` covers the
  helper at floor / cap / mid-range / overflow.
- Existing resize-recovery test extended to assert the flag flips.

Refs: #18449 #19280 #22976
Salvage of #24403.

Co-authored-by: Szymonclawd <szymonclawd@mac.home>

* fix(ui-tui): heal same-dimension alt-screen resize drift

- Treat same-dimension resize events in alt-screen mode as a repaint
  signal, because terminal hosts can reflow or restore the physical
  buffer without changing columns/rows.
- Ensure pending resize erases are emitted even when the virtual diff
  is empty, so stale physical glyphs are still cleared.
- Extract alt-screen resize repaint into prepareAltScreenResizeRepaint()
  for readability.
- Add defensive clearTimeout in prepareAltScreenResizeRepaint so rapid
  resize bursts don't stack redundant delayed repaints.
- Add a focused regression test for same-dimension alt-screen resize
  healing.

Addresses #18449
Related to #17961

* chore(release): map @luoyuctl in AUTHOR_MAP

* feat(proxy): local OpenAI-compatible proxy for OAuth providers (#25969)

Adds 'hermes proxy start' — a local HTTP server that lets external apps
(OpenViking, Karakeep, Open WebUI, ...) use a Hermes-managed provider
subscription as their LLM endpoint. The proxy attaches the user's real
OAuth-resolved credentials to each forwarded request, refreshing them
automatically; the client can send any bearer (it gets stripped).

Ships with one adapter — Nous Portal. The UpstreamAdapter ABC and
registry in hermes_cli/proxy/adapters/ are designed for additional
OAuth providers to plug in by name without server changes.

Commands:
  hermes proxy start [--provider nous] [--host 127.0.0.1] [--port 8645]
  hermes proxy status
  hermes proxy providers

Allowed Portal paths: /v1/chat/completions, /v1/completions,
/v1/embeddings, /v1/models. Anything else returns 404 with a clear
error pointing at the allowed list.

aiohttp is gated like gateway/platforms/api_server.py (try-import,
clean runtime error if missing). No new core dependency.

Tests: 24 unit tests + 1 separate E2E that spawns the real subprocess
and verifies the upstream receives the right bearer with the client's
header stripped.

* feat(discord): channel history backfill for multi-user sessions

Adds optional channel-context backfill for Discord shared-channel sessions
so the agent can see recent messages it missed between its own turns
(typically when require_mention=true filters out most traffic).

Previously the agent only saw the @mention message that triggered it, which
led to disorienting replies in active multi-user channels where the
conversation context was invisible. With backfill enabled, a configurable
number of recent messages are fetched per-turn and prepended to the trigger
message as a context block, kept separate from sender-prefix logic so
attribution remains clean.

This re-opens the work from #13063 (approved by @OutThisLife on 2026-04-20,
closed when I closed the branch to address the simpolism:main head-branch
issue plus an ordering bug I caught later in live use). Filing against the
freshly-rewritten problem statement in #13054 so the design is grounded in
the failure mode rather than the implementation shape.

The implementation follows the **push-mode last-self-anchored** design from
the two options laid out in #13054. See the issue for the trade-off
discussion vs pull-mode (#13120 was an earlier closed PR using that shape).
Treating this as a reference implementation — happy to rewrite as
last-trigger anchoring or as a hybrid with #13120 if maintainers prefer.

Changes:

- gateway/platforms/discord.py:
  - new `_discord_history_backfill()` / `_discord_history_backfill_limit()`
    helpers (config.extra > env > default), mirroring the existing
    `_discord_require_mention()` shape
  - new `_fetch_channel_context()` that scans `channel.history()` backwards
    from the trigger to the bot's last message (or limit), formats as
    `[Recent channel messages] / [name] msg / ...`, respects DISCORD_ALLOW_BOTS,
    skips system messages
  - per-channel `_last_self_message_id` cache to narrow the fetch window
    on hot paths (avoids full history scan when the bot has spoken recently)
  - **IMPORTANT**: passes `oldest_first=False` explicitly to `channel.history()`.
    discord.py 2.x silently flips the default to True when `after=` is supplied,
    which would select the EARLIEST N messages after our last response instead
    of the LATEST N before the trigger. In high-traffic windows this would
    return stale tool traces and drop the actual final answer the user is
    asking about. See regression test below. Caught in live use during a
    Codex tool-trace burst on May 13 2026.
- gateway/config.py: discord_history_backfill + discord_history_backfill_limit
  settings + yaml→env bridge
- gateway/platforms/base.py: channel_context field on MessageEvent
- gateway/run.py: prepend channel_context after sender-prefix so the
  [sender name] tag applies to the trigger message alone, not to the backfill
- hermes_cli/config.py: defaults for new discord.history_backfill and
  discord.history_backfill_limit keys
- cli-config.yaml.example: documented defaults
- tests/gateway/test_discord_free_response.py: 7 new tests covering
  cold-start backfill, self-message stop boundary, other-bot filtering,
  cache hot-path narrowing, stale-cache fallback, shared-channel +
  per-user backfill paths, and the ordering regression test
  (`test_fetch_channel_context_cache_uses_latest_window_when_after_set`)
- tests/gateway/test_config.py: yaml→env bridge tests
- tests/gateway/test_session.py: prefix-order edge cases
- website/docs/user-guide/messaging/discord.md: env vars + config keys +
  usage docs

Tested on Ubuntu 24.04 — empirically validated in my own multi-bot Discord
research server for the past three weeks.

Fixes #13054
Supersedes #13063 (closed)

* feat(discord): default history backfill on, expand to per-user + threads

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.

* fix(web): make sync-assets script cross-platform

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.

* fix(lsp): shift baseline diagnostics into post-edit coordinates (#25978)

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.

* fix(web): cross-platform sync-assets + surface build errors on failure

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.

* fix(web): handle non-UTF8 Windows console encodings in _build_web_ui

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.

* chore(release): map agorgianitisj@hotmail.com -> johnisag

* fix(proxy): suppress false-positive windows-footgun on guarded add_signal_handler

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.

* fix(cli): wire /sessions slash command in the classic CLI

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.

* chore(release): map phil.thomas@gametime.co -> explainanalyze

* chore(release): map phil.thomas@gametime.co -> explainanalyze

* fix(browser): use correct env var for --no-sandbox bypass

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.

* fix(browser): honor pre-set AGENT_BROWSER_ARGS and document the bypass

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.

* fix(cli): fall back to SelectSelector when kqueue can't watch stdin

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.

* chore(release): add AUTHOR_MAP entry for outdoorsea

* fix(aux): surface Nous auth-unavailable warning in auxiliary client

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

* feat: add ACP registry metadata for Zed

* chore(release): bump ACP Registry assets in lockstep with pyproject

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.

* chore: remove Atropos RL environments and tinker-atropos integration (#26106)

* chore: remove Atropos RL environments, tools, tests, skill, and tinker-atropos submodule

Delete:
- environments/ (43 files — base env, agent loop, tool call parsers, benchmarks)
- rl_cli.py (standalone RL training CLI)
- tools/rl_training_tool.py (all 10 rl_* tools)
- tests: test_rl_training_tool, test_tool_call_parsers, test_managed_server_tool_support,
  test_agent_loop, test_agent_loop_vllm, test_agent_loop_tool_calling,
  test_terminalbench2_env_security
- optional-skills/mlops/hermes-atropos-environments/
- tinker-atropos git submodule + .gitmodules

* chore: remove RL/Atropos references from Python source

- toolsets.py: remove rl toolset block + update comment
- model_tools.py: remove rl_tools group + update async bridging comment
- hermes_cli/tools_config.py: remove RL display entry, _DEFAULT_OFF_TOOLSETS,
  setup block, and rl_training post-setup handler
- tools/budget_config.py: remove RL environment reference in docstring
- tests/test_model_tools.py: remove rl_tools from expected groups
- tests/run_agent/test_streaming_tool_call_repair.py: fix stale cross-reference

* chore: remove rl/yc-bench extras and tinker-atropos refs from pyproject.toml

- Remove rl extra (atroposlib, tinker, fastapi, uvicorn, wandb)
- Remove yc-bench extra
- Remove rl_cli from py-modules
- Remove [tool.ty.src] exclude for tinker-atropos
- Remove [tool.ruff] exclude for tinker-atropos
- Regenerate uv.lock

* chore: remove tinker-atropos from install/setup scripts

- setup-hermes.sh: remove entire tinker-atropos submodule install block
- scripts/install.sh: remove both tinker-atropos blocks (Termux + standard)
- scripts/install.ps1: remove tinker-atropos block
- nix/hermes-agent.nix: remove tinker-atropos pip install line

* chore: remove RL references from cli-config.yaml.example

* docs: remove Atropos/RL references from README, CONTRIBUTING, AGENTS.md

* docs: remove RL/Atropos references from website

- Delete: environments.md, rl-training.md, mlops-hermes-atropos-environments.md
- sidebars.ts: remove rl-training and environments sidebar entries
- optional-skills-catalog.md: remove hermes-atropos-environments row
- tools-reference.md: remove entire rl toolset section
- toolsets-reference.md: remove rl row + update example
- integrations/index.md: remove RL Training bullet
- architecture.md: remove environments/ from tree + RL section
- contributing.md: remove tinker-atropos setup
- updating.md: remove tinker-atropos install + stale submodule update

* chore: remove remaining RL/Atropos stragglers

- hermes_cli/config.py: remove TINKER_API_KEY + WANDB_API_KEY env var defs
- hermes_cli/doctor.py: remove Submodules check section (tinker-atropos)
- hermes_cli/setup.py: remove RL Training status check
- hermes_cli/status.py: remove Tinker + WandB from API key status display
- agent/display.py: remove both rl_* tool preview/activity blocks
- website/docs: remove RL references from providers.md + env-variables.md
- tests: remove TINKER_API_KEY from conftest, set_config_value, setup_script

* chore: remove RL training section from .env.example

* feat(acp-registry): switch to uvx distribution, drop npm launcher

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.

* fix(deps): pin brotlicffi so aiohttp can decode Discord's Brotli attachments

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>

* fix(cli): kill resize scrollback duplication + light-mode visibility

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>

* test(cli): cover light-mode detection + SkinConfig.get_color remap

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.

* revert(cli): drop scrollback box width clamp (#25975), restore full-width borders (#26163)

#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).

* fix(goals): raise judge max_tokens 200 → 4096, make configurable

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

* ci: add PyPI publish workflow (salvaged from #25901) (#26148)

* ci(pypi): add publish workflow for automated PyPI releases

Triggered by CalVer tag pushes from scripts/release.py (v20* pattern).
Three jobs: build (uv build) → publish (OIDC trusted publishing) → sign
(Sigstore + attach to existing GitHub Release).

- workflow_dispatch as manual escape hatch
- skip-existing for safe re-runs
- Graceful skip when GitHub Release not found (sign job)
- Top-level permissions: contents: read (CodeQL compliant)

Requires one-time setup: PyPI trusted publisher + GitHub pypi environment.

Co-authored-by: dmahan93 <44207705+dmahan93@users.noreply.github.com>

* fix(release): address review findings

- Stage acp_registry/agent.json in version bump commit (was silently left unstaged)
- Add missing return when no previous tags found without --first-release
- Fix get_pr_number return type annotation (str -> str | None)
- Prefer uv build over python -m build (matches CI workflow), with fallback
- Use unit separator (%x1f) in git log format to handle | in author names
- Add explicit encoding='utf-8' to .release_notes.md write

Workflow hardening:
- Gracefully skip signing when GitHub Release not found (env var gate
  instead of exit 1, so PyPI publish still shows green)

* fix(ci): harden PyPI workflow — SHA-pin actions, guard workflow_dispatch, explicit build flags

- Pin all actions to commit SHAs (supply-chain hardening for id-token:write)
- workflow_dispatch now requires confirm_tag input + checks out that tag
- Both uv build paths explicitly pass --sdist --wheel

---------

Co-authored-by: dmahan93 <44207705+dmahan93@users.noreply.github.com>

* feat(yuanbao): add _parse_resource_id and update _extract_text for ybres anchors

* feat(yuanbao): add quote_media_refs extraction to QuoteContextMiddleware

* feat(yuanbao): prioritize quote media refs over history backfill in DispatchMiddleware

* fix(yuanbao): resolve quoted file/image via transcript lookup when quote desc lacks ybres

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.

* refactor(yuanbao): improve quote media fallback — move to DispatchMiddleware, tighten conditions

* feat(skills-hub): add huggingface/skills as trusted default tap (#2549)

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>

* fix(session): persist auto-reset state across gateway restarts

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.

* fix(gateway): isinstance-guard string-form 429 error body

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>

* fix: clean stale conversation mappings on response eviction/deletion

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>

* chore(release): add AUTHOR_MAP entry for CoinTheHat

* fix(whatsapp): fail fast when Baileys sendMessage hangs

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>

* security(deps): add upper bounds to 5 loose deps + document supply chain policy (#24226)

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

* feat(image-gen): actionable setup message when no FAL backend is reachable (#26222)

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>

* docs(cron): worked recipes for the wakeAgent pre-run gat…

…ne (#1)

* feat(web): extend ABC with supports_crawl and async-extract semantics

Two ABC additions to cover the surface area of the remaining four
providers (exa, parallel, tavily, firecrawl) which were untouched by the
initial spike:

1. supports_crawl() + crawl() — Tavily natively crawls a seed URL via
   its /crawl endpoint. Exposing supports_crawl=True lets the crawl
   tool's dispatcher route to Tavily when configured, falling back to
   the auxiliary-model summarization path otherwise. Firecrawl could
   add this in a follow-up (the SDK supports it; we just don't surface
   it as a tool today).

2. Async-or-sync extract() — Parallel's SDK is natively async
   (AsyncParallel.beta.extract); Exa and Tavily are sync; Firecrawl is
   sync but called inside asyncio.to_thread() with a 60s timeout. The
   ABC docstring now permits either shape: implementations declare
   their own sync/async signature and the dispatcher uses
   inspect.iscoroutinefunction to detect and await.

Also adds get_active_crawl_provider() to web_search_registry mirroring
the search/extract resolvers, with web.crawl_backend as the explicit
override config key.

No behavior change on its own — these are scaffolds for the four
remaining provider migrations.

* feat(web): exa plugin — first multi-capability migration (search + extract)

Migrates Exa from the inline `_exa_search()` / `_exa_extract()` helpers in
tools/web_tools.py to a bundled plugin at plugins/web/exa/.

This is the first plugin in this PR to advertise supports_extract=True,
exercising the multi-capability ABC path that the initial three migrations
(brave_free, ddgs, searxng — all search-only) did not cover.

Both Exa methods are sync — the SDK is sync-only. The web_extract_tool
dispatcher in tools/web_tools.py will continue to call them inline until
Task "dispatch-extract-all" cuts it over to the registry.

Behaviour preserved bit-for-bit aside from the ABC method-name change:
  - is_configured()  -> is_available()
  - provider_name()  -> name (property)
  - "exa" stays as the registered name
  - Module-level `_exa_client` cache + lazy `from exa_py import Exa`
    preserved at the new location.
  - Errors (ValueError for missing API key, ImportError for missing SDK,
    generic Exception) caught and surfaced as {"success": False, "error": ...}
    instead of raising.

Adds "exa" to _WEB_PLUGIN_SKIPLIST in hermes_cli/tools_config.py so the
hardcoded TOOL_CATEGORIES["web"] row and the plugin-injected row don't
duplicate during the spike. The skip-list goes away in the cleanup phase
along with the hardcoded row.

The legacy inline `_exa_search` / `_exa_extract` / `_get_exa_client` /
`_exa_client` in tools/web_tools.py are NOT deleted yet — the dispatcher
still references them. They go away in the next dispatcher-cutover commit.

E2E verified:
  - Plugin discovers + registers
  - .supports_search/.supports_extract/.supports_crawl = (True, True, False)
  - .get_setup_schema() returns the picker row shape
  - resolve(): explicit exa + EXA_API_KEY -> exa; without key -> exa (registered
    but unavailable, dispatcher surfaces "EXA_API_KEY not set" error)

* feat(web): parallel plugin — first async-extract plugin

Migrates Parallel.ai from inline `_parallel_search()` / `_parallel_extract()`
in tools/web_tools.py to a bundled plugin at plugins/web/parallel/.

First plugin in the codebase to expose an async :meth:`extract`:

  - search() is sync — Parallel.beta.search
  - extract() is **async def** — AsyncParallel.beta.extract

The ABC's docstring on supports_extract() already permits sync-or-async;
this commit is the first to exercise the async path. The web_extract_tool
dispatcher (next commit) detects coroutines via
inspect.iscoroutinefunction and awaits accordingly.

Behavior preserved:
  - PARALLEL_API_KEY required (raises ValueError if missing → surfaced
    as {"success": False, "error": "..."} instead)
  - PARALLEL_SEARCH_MODE env var honored (agentic|fast|one-shot, default
    agentic), validated via _resolve_search_mode()
  - Limit capped at 20 server-side via min(limit, 20)
  - Per-URL failure mode preserved: response.errors[] each become a
    result dict with an "error" field rather than raising
  - Module-level _parallel_client / _async_parallel_client caches kept
    (mirrors legacy singleton pattern)

Adds "parallel" to _WEB_PLUGIN_SKIPLIST in hermes_cli/tools_config.py so
the picker doesn't double-list.

The legacy inline _parallel_search, _parallel_extract, _get_parallel_client,
_get_async_parallel_client in tools/web_tools.py are NOT deleted yet — the
dispatcher still calls them. They go away when the dispatcher cuts over.

E2E verified:
  - inspect.iscoroutinefunction(p.search) -> False
  - inspect.iscoroutinefunction(p.extract) -> True
  - extract() returns a coroutine (not a list)
  - 5 providers register correctly (brave-free, ddgs, exa, parallel, searxng)

* feat(web): tavily plugin — first three-capability plugin (search + extract + crawl)

Migrates Tavily from inline _tavily_request() / _normalize_tavily_*
helpers in tools/web_tools.py to a bundled plugin at plugins/web/tavily/.

First plugin in the codebase to advertise supports_crawl=True. Tavily is
unique among built-in backends in offering a native /crawl endpoint that
walks linked pages from a seed URL with optional natural-language
instructions and depth ("basic" or "advanced").

Capabilities:
  - supports_search()  -> True (Tavily /search)
  - supports_extract() -> True (Tavily /extract)
  - supports_crawl()   -> True (Tavily /crawl)
  All sync (httpx.post under the hood).

The crawl method accepts forward-compat kwargs (instructions, depth,
limit) and is gated against unsafe URLs/policy by the dispatcher in
web_crawl_tool — exactly as before.

Behavior preserved:
  - TAVILY_API_KEY required (ValueError → typed error response)
  - TAVILY_BASE_URL env override honored
  - /crawl requires both body auth AND Bearer header — preserved
  - failed_results[] and failed_urls[] response keys mapped to per-URL
    items with error fields rather than raising
  - max_results capped at 20 server-side

Adds "tavily" to _WEB_PLUGIN_SKIPLIST.

The legacy inline _tavily_request / _normalize_tavily_search_results /
_normalize_tavily_documents / _TAVILY_BASE_URL in tools/web_tools.py are
NOT deleted yet — search/extract dispatch and the entire web_crawl_tool
function still reference them. They go away when those dispatchers are
cut over to the registry.

E2E verified:
  - Tavily registers with all 3 capabilities
  - Provider list now: brave-free, ddgs, exa, parallel, searxng, tavily

* feat(web): firecrawl plugin — largest migration (search + async extract + dual auth)

Migrates Firecrawl from inline code in tools/web_tools.py to a bundled
plugin at plugins/web/firecrawl/. By line count this is the largest of
the seven provider migrations: the firecrawl path captured most of the
file's vendor-specific complexity.

What moved into the plugin (all previously in tools/web_tools.py):

  Lazy Firecrawl SDK proxy
    - _load_firecrawl_cls() — caches the imported SDK class
    - _FirecrawlProxy + Firecrawl singleton — defers ~200ms of SDK
      imports until first construction or isinstance check.

  Client construction (dual auth)
    - _get_direct_firecrawl_config()  — direct FIRECRAWL_API_KEY/URL path
    - _get_firecrawl_gateway_url()    — managed Nous tool-gateway URL
    - _is_tool_gateway_ready()        — gateway URL + Nous token check
    - _has_direct_firecrawl_config()  — direct config present?
    - _get_firecrawl_client()         — combined client construction
                                        honoring web.use_gateway
    - check_firecrawl_api_key()       — top-level "is firecrawl usable"
    - _firecrawl_backend_help_suffix() — managed-gateway help string
    - _raise_web_backend_configuration_error() — typed misconfig error

  Response shape normalization (vendor-specific)
    - _to_plain_object(), _normalize_result_list() — SDK→dict helpers
    - _extract_web_search_results() — handles SDK/direct/gateway shapes
    - _extract_scrape_payload()     — nested-data unwrap for scrape

  Per-URL extract loop
    - 60s asyncio.wait_for timeout per URL
    - Pre-scrape website-policy gate
    - Post-scrape redirect-aware SSRF re-check
    - Format-aware content selection (markdown / html / auto)
    - Per-URL errors returned as {"error": str} entries, no raises

Extract is declared `async def` — each URL is scraped in
asyncio.to_thread(...). This is the second async-extract plugin after
parallel.

The plugin re-exports `Firecrawl` (the lazy proxy) and
`check_firecrawl_api_key()` so existing tests doing
`patch("tools.web_tools.Firecrawl")` or
`monkeypatch.setattr(web_tools, "check_firecrawl_api_key", ...)` keep
working — tools/web_tools.py re-exports both names in the next
dispatcher-cutover commit.

Note: web_crawl_tool still has its own Firecrawl crawl path inline
(separate from extract); the Firecrawl SDK supports /crawl but we don't
expose supports_crawl=True on this plugin yet. Tavily handles crawl
today. Adding Firecrawl crawl is a clean follow-up.

Adds "firecrawl" to _WEB_PLUGIN_SKIPLIST.

E2E verified:
  - All 7 providers register: brave-free, ddgs, exa, firecrawl,
    parallel, searxng, tavily
  - inspect.iscoroutinefunction(firecrawl.extract) -> True
  - Firecrawl proxy is a callable lazy proxy at module level
  - check_firecrawl_api_key reflects FIRECRAWL_API_KEY presence

* refactor(web): dispatch all three tools through web_search_registry

Cuts over web_search_tool, web_extract_tool, and web_crawl_tool in
tools/web_tools.py to dispatch through agent.web_search_registry
instead of the legacy hardcoded if-elif backend chains.

Per-tool changes:

  web_search_tool (sync)
    Replace 5 backend branches (parallel, exa, registry-3-providers,
    tavily, firecrawl-fallthrough) with a single registry path:
      1. _get_search_backend() resolves the configured name
      2. _wsp_get_provider(name) for explicit-config-wins semantics
      3. get_active_search_provider() fallback for typo / unknown name
      4. provider.search(query, limit) — sync for all 7 providers

  web_extract_tool (async)
    Replace 4 backend branches (parallel-async, exa-sync, tavily-sync,
    search-only-error, firecrawl-perurl-loop) with:
      1. Same provider resolution as search.
      2. When configured backend IS registered but doesn't support
         extract (search-only providers like brave-free), surface a
         typed "search-only" error matching the legacy text — tests
         assert that wording.
      3. inspect.iscoroutinefunction(provider.extract) detects sync vs
         async: parallel + firecrawl are async; exa + tavily are sync.
         Sync extracts run in asyncio.to_thread() so we don't block.

  web_crawl_tool (async)
    Replace tavily-specific branch + search-only-error block with:
      1. _wsp_get_provider(backend) — explicit config first
      2. Search-only typed error when the configured name doesn't
         support crawl (matches legacy phrasing)
      3. get_active_crawl_provider() fallback otherwise
      4. provider.crawl(url, **kwargs) — async-or-sync dispatch as above
      5. Response post-processing (LLM summarization, trimming) stays
         unchanged — it's not provider-specific.
    When no plugin advertises supports_crawl, falls through to the
    existing Firecrawl-via-web-summarize path below (unchanged).

Test updates (2 tests in tests/tools/test_web_tools_config.py):
  - test_web_search_clamps_limit_before_backend_call:
      patch("tools.web_tools._parallel_search") -> patch the registry
      provider returned by agent.web_search_registry.get_provider
  - test_search_error_response_does_not_expose_diagnostics:
      patch("tools.web_tools._get_firecrawl_client") -> same pattern

Tests unchanged (still pass):
  - All TestXBackendWiring classes (test _get_backend / _is_backend_available
    config-resolution, independent of dispatch)
  - All TestXSearchOnlyErrors classes (test the search-only error path
    via web_extract_tool / web_crawl_tool — error text preserved)
  - 141 passing web tests total, 0 regressions.

Dead-code cleanup deferred to a follow-up commit so this diff stays
focused on the cutover. After this commit:
  - tools.web_tools._exa_search / _exa_extract / _parallel_search /
    _parallel_extract / _tavily_request / _normalize_tavily_* /
    _get_firecrawl_client / _extract_web_search_results /
    _extract_scrape_payload / _to_plain_object / _normalize_result_list
    are no longer called by the dispatchers, but still exist.
  - The config-resolution layer (_get_backend, _is_backend_available,
    _is_tool_gateway_ready, _has_direct_firecrawl_config) IS still in
    use and must stay.
  - The Firecrawl proxy and check_firecrawl_api_key are still imported
    by integration tests and patched by unit tests — must stay (or be
    re-exported from the plugin).

* fix(web): preserve firecrawl crawl + website-policy gate after migration

Two regressions discovered by running the full tests/tools/ suite after
the dispatcher cutover, both fixed in this commit:

1. web_crawl_tool incorrectly errored "search-only" for firecrawl
---------------------------------------------------------------------
The cutover treated any provider with supports_crawl()==False as a
search-only backend and returned the typed search-only error. But
firecrawl can crawl via the legacy multi-page-extract path inside
web_crawl_tool — it just doesn't expose supports_crawl on the plugin
(adding native firecrawl crawl is a clean follow-up).

Fix: only emit the search-only error when the provider supports
NEITHER crawl NOR extract (brave-free / ddgs / searxng). When the
provider supports extract but not crawl (firecrawl), fall through to
the legacy firecrawl-via-extract path below.

2. firecrawl plugin's check_website_access wasn't patchable
---------------------------------------------------------------------
The plugin imported `from tools.website_policy import check_website_access`
INSIDE the extract() function body, so monkeypatching the name on
plugins.web.firecrawl.provider had no effect — the inner import re-bound
the name on every call.

Fix: hoist the import to module level. Cheap (website_policy itself
has no heavy deps) and makes the standard
monkeypatch.setattr(firecrawl_provider, "check_website_access", ...)
pattern work.

Test updates (tests/tools/test_website_policy.py — 4 tests):
  - test_web_extract_short_circuits_blocked_url
  - test_web_extract_blocks_redirected_final_url
    Both: patch the gate at plugins.web.firecrawl.provider (where it
    runs after migration) and force the firecrawl plugin to be the
    active extract provider via FIRECRAWL_API_KEY.
  - test_web_crawl_short_circuits_blocked_url
  - test_web_crawl_blocks_redirected_final_url
    Both: unchanged — the dispatcher-level gate at tools.web_tools.py
    line 1651 still uses the imported `check_website_access` name and
    the firecrawl-fallthrough path is exercised as before.

Verified: 22/22 tests/tools/test_website_policy.py pass.

* refactor(web): delete inline vendor helpers, re-export from plugins

Removes ~580 lines of dead code from tools/web_tools.py that were
superseded by the plugin migration but kept around in the cutover commit
to keep the diff focused. Replaces them with thin re-export shims so
existing tests and external callers that reach for the legacy
``tools.web_tools.<name>`` paths continue to work transparently.

Deleted from tools/web_tools.py
--------------------------------
- Lazy Firecrawl SDK proxy (_load_firecrawl_cls, _FirecrawlProxy,
  _FIRECRAWL_CLS_CACHE, the Firecrawl singleton)
- Firecrawl client section (_get_direct_firecrawl_config,
  _get_firecrawl_gateway_url, _is_tool_gateway_ready,
  _has_direct_firecrawl_config, _raise_web_backend_configuration_error,
  _firecrawl_backend_help_suffix, _get_firecrawl_client)
- Parallel client section (_get_parallel_client,
  _get_async_parallel_client, _parallel_client, _async_parallel_client)
- Tavily client section (_TAVILY_BASE_URL, _tavily_request,
  _normalize_tavily_search_results, _normalize_tavily_documents)
- Generic SDK normalizers (_to_plain_object, _normalize_result_list,
  _extract_web_search_results, _extract_scrape_payload)
- Exa client section (_get_exa_client, _exa_client, _exa_search,
  _exa_extract)
- Parallel helpers (_parallel_search, _parallel_extract)
- Duplicate inline check_firecrawl_api_key

Net: tools/web_tools.py drops from 2227 → 1613 lines (-614 lines).

Re-exports added at top of tools/web_tools.py
---------------------------------------------
- From plugins.web.firecrawl.provider:
  Firecrawl, _FirecrawlProxy, _FIRECRAWL_CLS_CACHE, _load_firecrawl_cls,
  _get_direct_firecrawl_config, _get_firecrawl_gateway_url,
  _is_tool_gateway_ready, _has_direct_firecrawl_config,
  _firecrawl_backend_help_suffix, _raise_web_backend_configuration_error,
  _get_firecrawl_client, _to_plain_object, _normalize_result_list,
  _extract_web_search_results, _extract_scrape_payload,
  check_firecrawl_api_key
- From plugins.web.tavily.provider:
  _tavily_request, _normalize_tavily_search_results,
  _normalize_tavily_documents
- From plugins.web.parallel.provider:
  _get_parallel_client, _get_async_parallel_client
- From plugins.web.exa.provider:
  _get_exa_client

Plus retained module-level imports for backward-compat with tests:
- httpx (tests patch tools.web_tools.httpx for tavily request mocking)
- build_vendor_gateway_url, _read_nous_access_token,
  resolve_managed_tool_gateway, managed_nous_tools_enabled,
  prefers_gateway (tests patch tools.web_tools.<name>)

Plugin indirection pattern (key technique)
------------------------------------------
For functions inside the firecrawl/parallel/exa plugins to honor
unit-test patches that target ``tools.web_tools.<name>``, the plugin
implementations now do ``import tools.web_tools as _wt`` at call time
and read helper names through that module (``_wt._read_nous_access_token``,
``_wt.Firecrawl``, ``_wt.prefers_gateway``, etc.). This makes the
existing test patches transparently reach the plugin code without any
test changes.

The cached client globals (_firecrawl_client, _firecrawl_client_config,
_parallel_client, _async_parallel_client, _exa_client) also now live on
tools.web_tools so existing test setup_method handlers that reset
``tools.web_tools._<vendor>_client = None`` between cases keep working.
The plugins read/write the cache via getattr/setattr on the web_tools
module.

Verified
--------
- 173/173 targeted web tests pass:
  test_web_providers.py, test_web_providers_brave_free.py,
  test_web_providers_ddgs.py, test_web_providers_searxng.py,
  test_web_tools_config.py, test_web_tools_tavily.py,
  test_website_policy.py, test_config_null_guard.py
- Compile-clean (py_compile.compile passes)
- All inline implementations now exist in exactly one place
  (plugins.web.<vendor>.provider)

Follow-up clean-up
------------------
- Drop _WEB_PLUGIN_SKIPLIST + hardcoded TOOL_CATEGORIES["web"] rows
  (next commit)
- Delete tools/web_providers/ directory entirely
- Add tests/plugins/web/ coverage
- Full tests/tools/ + tests/gateway/ regression sweep before promoting PR

* refactor(tools): drop hardcoded web picker rows + skiplist; plugins are sole source

Removes the seven hardcoded TOOL_CATEGORIES["web"] provider rows that
duplicated the plugin-registered providers, and deletes the
_WEB_PLUGIN_SKIPLIST that existed to prevent duplicate picker rows
during the migration. The Web Search & Extract category now derives its
provider rows entirely from agent.web_search_registry via
_plugin_web_search_providers(), matching how Spotify, Google Meet, and
the image_gen plugins are surfaced.

Removed (deduplicated against plugin schemas):
  - Firecrawl Cloud         → plugins.web.firecrawl
  - Exa                     → plugins.web.exa
  - Parallel                → plugins.web.parallel
  - Tavily                  → plugins.web.tavily
  - SearXNG                 → plugins.web.searxng
  - Brave Search (Free Tier) → plugins.web.brave_free
  - DuckDuckGo (ddgs)       → plugins.web.ddgs (post_setup hook preserved)

Retained in TOOL_CATEGORIES["web"]:
  - Nous Subscription   — requires requires_nous_auth +
                          managed_nous_feature + override_env_vars
                          to drive the managed-gateway UX. Not a
                          provider — a different *setup flow* for the
                          firecrawl backend.
  - Firecrawl Self-Hosted — points firecrawl at a private Docker URL
                            via FIRECRAWL_API_URL only. Same reason:
                            UX setup-flow row, not a provider.

These two rows describe alternative auth/billing paths for the
firecrawl backend; they intentionally share web_backend="firecrawl"
with the plugin row but light up different env-var prompts.

Plugin schema extensions
------------------------
- ddgs plugin's get_setup_schema() now emits `post_setup: "ddgs"` so
  selection still triggers the pip-install hook in _run_post_setup().
- _plugin_web_search_providers() passes `post_setup` through verbatim
  when present in the schema (other future plugins like camofox / a
  hypothetical playwright-web plugin can opt in the same way).
- Picker rows now carry both `web_backend` (legacy field consumed by
  setup + selection helpers) and `web_search_plugin_name`
  (informational marker), so behavior is identical between hardcoded
  and plugin-registered rows.

Net diff
--------
- hermes_cli/tools_config.py: -141/+50 lines (~91 lines net)
- plugins/web/ddgs/provider.py: +7/-4 (post_setup field + badge polish)

Verified
--------
- Compile-clean for both files
- Picker shows: 2 hardcoded rows (Nous Subscription, Firecrawl
  Self-Hosted) + 7 plugin rows (alphabetically: Brave Search,
  DuckDuckGo, Exa, Firecrawl, Parallel, SearXNG, Tavily). DuckDuckGo
  row carries post_setup="ddgs" for first-time install.
- 173 web-specific tests still pass.

* refactor(web): delete legacy tools/web_providers/ directory + migrate ABC tests

Removes the legacy in-tree provider scaffolding that PR #25182 fully
replaced with the plugin architecture:

  tools/web_providers/__init__.py        (6 lines)
  tools/web_providers/base.py            (89 lines — old ABCs)
  tools/web_providers/ARCHITECTURE.md    (73 lines — old design doc)

These were the staging-ground ABCs and provider modules that the
plugin migration absorbed. All seven web providers now implement the
single :class:`agent.web_search_provider.WebSearchProvider` ABC and
live under ``plugins/web/<vendor>/``. Nothing else in the tree imports
``tools.web_providers`` — verified via grep before deletion.

Test migration (tests/tools/test_web_providers.py)
--------------------------------------------------
Rewrote ``TestWebProviderABCs`` to test the new unified ABC at
:mod:`agent.web_search_provider`:

  - test_cannot_instantiate_abc_directly — abstract ``name`` + ``is_available``
  - test_concrete_search_only_provider_works — exercise default
    ``supports_extract=False`` / ``supports_crawl=False`` flags
  - test_concrete_multi_capability_provider_works — exercise all three
    capabilities, async extract supported (declared sync here for
    simplicity; real plugins like parallel + firecrawl use async)
  - test_search_only_provider_skips_extract_and_crawl — verify
    ``supports_*()`` flags default to False so search-only providers
    don't have to implement extract() or crawl()

The 9 other tests in the file (per-capability backend selection,
DEFAULT_CONFIG merge, dispatcher routing) test public helpers in
``tools.web_tools`` that still exist and pass unchanged.

agent/web_search_provider.py docstring updated to reflect that the
legacy ABCs no longer exist; the response-shape contract is preserved
bit-for-bit so external consumers see no behavioral change.

Net diff
--------
- tools/web_providers/ removed (-168 lines)
- tests/tools/test_web_providers.py rewritten ABC section (+78/-30 net,
  same coverage, new API)
- agent/web_search_provider.py docstring (-3/+5 lines)

Verified
--------
- 173/173 targeted web tests pass
- 12/12 ABC contract tests pass with the new interface
- No remaining grep hits for ``tools.web_providers`` outside of
  intentional historical references in plugin docstrings.

* test(plugins): tests/plugins/web/ — coverage for the 7-plugin migration

Adds 44 focused tests under tests/plugins/web/ covering the surface that
the PR #25182 web-provider migration introduced. Complements the
existing tests/tools/ coverage which is dispatcher-centric; this file is
plugin-centric and tests each plugin + the registry directly.

Test classes (44 tests, ~1.1s on 4 workers)
-------------------------------------------

TestBundledPluginsRegister (16 tests)
  - All seven plugins present in the registry after
    _ensure_plugins_discovered()
  - Per-plugin parametrized capability-flag assertions
    (brave-free / ddgs / searxng: search-only;
     exa / parallel / firecrawl: search + extract;
     tavily: search + extract + crawl)
  - Every plugin exposes name + display_name properties
  - Every plugin returns a picker-compatible get_setup_schema() dict

TestIsAvailable (7 tests)
  - Each premium plugin reports is_available()==False when its env var is
    absent and True once set (brave-free / searxng / tavily / exa /
    parallel)
  - firecrawl recognizes either FIRECRAWL_API_KEY or FIRECRAWL_API_URL
    as a "configured" signal
  - ddgs is the always-on fallback and must not raise from is_available()

TestRegistryResolution (4 tests)
  - Option B semantics validated end-to-end:
    1. Explicit configured provider wins even when is_available()==False
       (dispatcher surfaces typed credential errors, no silent switch)
    2. Unknown/typo name falls back to first available legacy-preference
       provider
    3. Asking for extract via a search-only backend falls back to an
       extract-capable available provider (capability-incompatible
       branch in _resolve())
    4. No config + no credentials → None (or ddgs if installed)

TestAsyncExtractDispatch (4 tests)
  - parallel + firecrawl extract() are coroutine functions (async path
    in dispatcher uses await)
  - exa + tavily extract() are sync (dispatcher wraps in
    asyncio.to_thread)

TestErrorResponseShapes (7 tests)
  - Plugins return typed error dicts (success=False + "error" key) when
    credentials are missing, never raise
  - async extract() returns list of per-URL error dicts
  - tavily crawl() returns {"results": [{"error": ...}]} on missing
    credentials

Design notes
------------
- All tests use real imports of plugin modules — no mocking of provider
  classes themselves — so they catch drift in the ABC, registry, and
  glue layer simultaneously. Per the hermes-agent-dev skill's E2E
  testing guidance.
- The autouse _isolate_env fixture clears every web-provider env var
  before each test so is_available() reflects the test's setup.
- Resolution tests use the lower-level _resolve() directly rather than
  rebuilding the HERMES_HOME config dance — same observable behavior,
  no sys.modules.pop side-effects that would break the ABC isinstance
  check inside ctx.register_web_search_provider().

* feat(web): firecrawl plugin natively supports crawl; delete legacy inline path

The web-provider migration originally left firecrawl crawl as the only
provider-specific code remaining inline in tools/web_tools.py (~250
lines of Firecrawl-specific crawl orchestration that didn't fit the
plugin's existing surface). This commit closes that gap.

What this adds
--------------
1. plugins/web/firecrawl/provider.py: implement async ``crawl(url, **kwargs)``
   - Accepts the same kwargs as the dispatcher passes to any crawl
     provider (``instructions``, ``depth``, ``limit``); Firecrawl's
     /crawl endpoint ignores ``instructions`` and ``depth`` so we log
     and drop with a clear info message.
   - Wraps the sync SDK ``crawl()`` call in asyncio.to_thread so the
     gateway event loop isn't blocked on a multi-page crawl.
   - Preserves the response-shape normalization across pydantic /
     typed-object / dict variants that the legacy inline code did.
   - Preserves per-page website-policy re-check (catches blocked
     redirects after the SDK returns).
   - Returns the same {"results": [...]} shape so the dispatcher's
     shared LLM-summarization post-processing path works unchanged.
   - Sets supports_crawl() to True so the dispatcher routes through
     the plugin instead of the legacy fallthrough.

2. tools/web_tools.py: delete the entire legacy firecrawl crawl block
   that used to run after "No registered provider supports crawl" —
   ~270 lines including:
   - check_firecrawl_api_key gate + typed error
   - inline SSRF + website-policy seed-URL gate (dispatcher already
     does this)
   - Firecrawl client setup with crawl_params
   - 100+ lines of pydantic/dict/typed-object normalization
   - Per-page LLM-processing loop (kept in the dispatcher's shared
     post-processing path; that's where it always belonged)
   - trimming + base64 image cleanup (still done in the dispatcher's
     shared path)

   Replaced with a single typed-error branch when no crawl-capable
   provider is available: "web_crawl has no available backend. Set
   FIRECRAWL_API_KEY (or FIRECRAWL_API_URL for self-hosted), or set
   TAVILY_API_KEY for Tavily."

Test updates
------------
- tests/tools/test_website_policy.py:
  - test_web_crawl_short_circuits_blocked_url: dispatcher seed-URL
    gate still runs on web_tools.check_website_access (no change to
    that patch), but the firecrawl client lockdown moved to the
    plugin module — patch firecrawl_provider._get_firecrawl_client
    instead of web_tools._get_firecrawl_client. The dispatcher
    short-circuits before the plugin runs, so the test still passes.
  - test_web_crawl_blocks_redirected_final_url: patch the per-page
    policy gate at plugins.web.firecrawl.provider.check_website_access
    (where it now runs) AND on web_tools (where the seed-URL gate
    still runs). Patch firecrawl_provider._get_firecrawl_client for
    the FakeCrawlClient injection. Both checks flow through the same
    fake_check function.
- tests/plugins/web/test_web_search_provider_plugins.py:
  - Update parametrized capability-flag spec: firecrawl supports_crawl
    is now True.
  - Add test_firecrawl_crawl_returns_error_dict_when_unconfigured —
    verifies inspect.iscoroutinefunction(p.crawl) is True and that
    the async crawl returns a per-page error dict (not a raise) when
    FIRECRAWL_API_KEY is missing.

Verified
--------
- 218/218 web tests pass (was 173, +44 plugin tests + 1 new firecrawl
  crawl test from this commit = 218 with the test deduplication).
- Compile-clean (py_compile passes on both files).
- Provider capabilities matrix confirmed end-to-end:
    name        search  extract  crawl   async-extract?  async-crawl?
    firecrawl   True    True     True    True            True
    tavily      True    True     True    False           False
  Both crawl-capable providers exercise the dispatcher's
  inspect.iscoroutinefunction async-or-sync detection.

Net diff
--------
- tools/web_tools.py: -254 lines (legacy inline crawl gone)
- plugins/web/firecrawl/provider.py: +185 lines (crawl method)
- test_website_policy.py: +14/-9 lines (patch locations)
- test_web_search_provider_plugins.py: +22/-1 lines (capability flag
  + new firecrawl crawl test)
- Total: -32 net LoC; tools/web_tools.py is now 1509 lines (was 1763
  before this commit, 2227 before the migration started).

* fix(web): align _LEGACY_PREFERENCE with legacy 7-provider order + doc cleanup

Self-review of the plugin migration surfaced one warning and a handful of
doc/dead-code cleanups. None affect production behaviour through the main
dispatcher (which always calls `tools.web_tools._get_backend()` first and
preserves the full 7-provider walk), but direct callers of
`agent.web_search_registry.get_active_*_provider()` previously diverged
from the legacy order and could return `None` for users with credentials
but no explicit `web.backend` config key.

Changes
-------
1. `_LEGACY_PREFERENCE` was shipped as a 4-tuple
   `("brave-free", "firecrawl", "searxng", "ddgs")` while the PR
   description and the legacy `_get_backend()` candidate order both
   call for the 7-tuple
   `(firecrawl, parallel, tavily, exa, searxng, brave-free, ddgs)`.
   Replaced with the 7-tuple. Verified empirically: with TAVILY+EXA keys
   and no config, `get_active_search_provider()` now returns tavily
   (was None); with EXA+PARALLEL it returns parallel (was None); with
   BRAVE+FIRECRAWL it returns firecrawl (was brave-free).

2. `agent/web_search_registry.py` — module docstring, `_resolve` step-3
   docstring, and inline comment all listed the old 4-tuple and claimed
   "brave-free first because it was the shipped default". The legacy
   default is `"firecrawl"`. Rewritten to match the new ordering and
   reference `tools.web_tools._get_backend()` as the source of truth.

3. `agent/web_search_registry.py` — `get_active_crawl_provider`
   docstring said "only Tavily implements it among built-in providers".
   Firecrawl also advertises `supports_crawl=True` after the previous
   commit. Updated to "Tavily and Firecrawl".

4. `plugins/web/tavily/provider.py` — module docstring said "Tavily is
   the only built-in backend that natively crawls". Updated.

5. `agent/web_search_provider.py` — ABC docstring mentioned only
   `search` / `extract` capabilities. Added `crawl` for accuracy.

6. `plugins/web/{firecrawl,parallel,exa}/provider.py` — dead plugin-level
   cache globals (`_firecrawl_client`, `_parallel_client`,
   `_async_parallel_client`, `_exa_client`) were declared but never read
   (all reads/writes go through `_wt.*` per the `extracting-inline-
   helpers-to-plugins` recipe). Removed the dead declarations; the
   reset-for-tests helpers in firecrawl + parallel now clear the
   canonical `_wt._<name>` slots, matching the pattern exa already used.

Tests
-----
218/218 web-targeted tests still pass (no test changes needed). 4910/4910
in `tests/tools/` still green.

* fix(web): preserve top-level error envelope on unconfigured systems

Surfaced by local E2E behavior-parity testing of PR vs origin/main: the
plugin-migrated dispatchers were quietly changing the error envelope
shape returned to function-calling models on unconfigured systems.

Two findings, both from per-result error wrapping bleeding into the
pre-flight configuration error path:

1. **search**: ``firecrawl.search()`` caught the
   ``ValueError("Web tools are not configured...")`` from
   ``_get_firecrawl_client()`` and returned it as
   ``{"success": False, "error": ...}``, losing the legacy
   ``{"error": "Error searching web: ..."}`` envelope that
   ``tool_error()`` emits on main. Models that special-case the
   ``error`` key still detect the failure, but the prefix is part of
   the legacy contract some users rely on.

2. **crawl**: ``firecrawl.crawl()`` caught the same pre-flight
   ``ValueError`` and wrapped it as a per-page error inside
   ``results[0]``. Main short-circuits on ``check_firecrawl_api_key()``
   BEFORE dispatching, so its unconfigured response is
   ``{"success": False, "error": "web_crawl requires Firecrawl..."}``
   at the top level. The PR's per-page burying hid the failure inside
   ``results[]`` where models that check ``result.get("error")`` would
   miss it.

Fix:
- ``plugins/web/firecrawl/provider.py``: pull
  ``_get_firecrawl_client()`` outside the broad ``try`` in
  ``search()``. Pre-flight ``ValueError`` / ``ImportError`` propagate
  to the dispatcher's top-level exception handler. In-flight SDK
  errors still get wrapped as ``{"success": False, ...}``.
- ``tools/web_tools.py``: mirror main's upstream availability gate in
  ``web_crawl_tool``. When the resolved crawl provider is
  ``is_available()==False``, short-circuit BEFORE dispatching with the
  same top-level error shape main emits.
- ``tests/tools/test_web_providers.py``: 2 regression tests
  (``TestUnconfiguredErrorEnvelopeParity``) lock in the behavior so
  future plugin work can't undo this.

Verified via local subprocess-based parity test (14/14 scenarios match
origin/main shape exactly) and full 210/210 web test suite green.

* fix(honcho): respect HOME-anchored default profile fallback

* fix(tests): exercise profile-mode HERMES_HOME for honcho fallback

The cherry-picked tests from #6173 set HERMES_HOME outside Path.home()/.hermes,
which forces get_default_hermes_root() down its Docker branch and returns
HERMES_HOME directly — so _get_default_hermes_home() never resolves to the
~/.hermes directory the tests were trying to assert about.

Rewire both tests to use the real profile layout (HERMES_HOME pointing at
~/.hermes/profiles/<name>) so _get_default_hermes_home() resolves back to
~/.hermes and the default-profile fallback is actually exercised.

* fix(clipboard): reject non-png clipboard images when png normalization fails

* fix(clipboard): only read PNG signature bytes, not entire file

Tighten _is_png_file() to read just the 8-byte PNG magic via path.open()
+ read(8), instead of slurping the entire image into memory only to check
the prefix.

* feat(goals): /subgoal — user-added criteria appended to active /goal (#25449)

* feat(goals): /subgoal — user-added criteria appended to active /goal

Layers a /subgoal command on top of the existing freeform Ralph judge
loop. The user can append extra criteria mid-loop; the judge factors
them into its done/continue verdict and the continuation prompt
surfaces them to the agent. No new tool, no agent self-judging — the
existing judge model just sees a richer prompt.

Forms:
  /subgoal                  show current subgoals
  /subgoal <text>           append a criterion
  /subgoal remove <n>       drop subgoal n (1-based)
  /subgoal clear            wipe all subgoals

How it integrates:

- GoalState gains `subgoals: List[str]` (default []), backwards-compat
  for existing state_meta rows.
- judge_goal accepts an optional subgoals kwarg; non-empty switches to
  JUDGE_USER_PROMPT_WITH_SUBGOALS_TEMPLATE which lists them as
  numbered criteria and asks 'is the goal AND every additional
  criterion satisfied?'
- next_continuation_prompt picks CONTINUATION_PROMPT_WITH_SUBGOALS_TEMPLATE
  when non-empty so the agent sees what to target.
- /subgoal is allowed mid-run on the gateway since it only touches the
  state the judge reads at turn boundary — no race with the running
  turn.
- Status line shows '... , N subgoals' when present.

Surface:
- hermes_cli/goals.py — field, prompt blocks, manager methods, judge weave
- hermes_cli/commands.py — /subgoal CommandDef
- cli.py — _handle_subgoal_command
- gateway/run.py — _handle_subgoal_command + mid-run dispatch
- tests/hermes_cli/test_goals.py — 15 new tests (backcompat, mutation,
  persistence, prompt template selection, judge-prompt content via mock,
  status-line rendering)

77 goal-related tests passing across goals + cli + gateway + tui.

* fix(goals): slash commands don't preempt the goal-continuation hook

Two findings from live-testing /subgoal:

1. Slash commands queued while the agent is running landed in
   _pending_input (same queue as real user messages). The goal hook's
   'is a real user message pending?' check returned True and silently
   skipped — but the slash command consumes its queue slot via
   process_command() which never re-fires the goal hook, so the loop
   stalls indefinitely. Now the hook peeks the queue and only defers
   when a non-slash payload is present.

2. The with-subgoals judge prompt was too soft — opus 4.7 said 'done,
   implying all requirements met' without verifying. Tightened to
   demand specific per-criterion evidence (file contents, output line,
   command result) and explicitly reject phrases like 'implying it was
   done.'

Live verified: /subgoal injected mid-loop now correctly forces the
judge to refuse done until the new criterion is met. Agent gets the
continuation prompt with subgoals listed, updates the script, judge
confirms done with specific evidence cited.

* fix(cli): harden skin yaml parsing for invalid section types

* fix(tests): correct skin engine test API call

The salvaged regression test called skin.get_spinner_list() which
doesn't exist on SkinConfig. Replace with direct dict access on
skin.spinner — same intent (verify default empty spinner is preserved
when user override is invalid).

* fix: simplify ACP approval bridging

Previously ACP dangerous-command approvals mixed an invalid ACP
payload shape with partial Hermes option mapping, and the callback
plumbing was shared across worker threads. This commit uses ACP
tool-call updates, preserves Hermes once/session/always semantics,
and scopes approval callbacks to the current worker thread.

- Build permission requests with `update_tool_call` and unique
  `perm-check-*` ids in `acp_adapter/permissions.py`
- Keep ACP option mapping explicit and fail closed on unknown outcomes
  or request failures
- Set approval callbacks inside the ACP executor worker and read them
  from thread-local state in `tools/terminal_tool.py`
- Replace duplicated ACP bridge coverage with focused tests in
  `tests/acp/test_permissions.py` and add a thread-local callback test

* chore(release): add AUTHOR_MAP entry for mrshu

Maps mr@shu.io to the mrshu GitHub handle so the release script
attributes the salvaged ACP approval bridging commit correctly.

* chore(release): add AUTHOR_MAP entries for 25-PR new-contributor batch

Pre-stages AUTHOR_MAP for 12 new contributors whose PRs are being salvaged
in the upcoming batch:

- 1RB        (#25462)
- ayushere   (#25342)
- domtriola  (#25424)
- ephron-ren (#25358)
- freqyfreqy (#25423)
- fu576      (#25369)
- kfa-ai     (#25398)
- magic524   (#25361)
- PaTTeeL    (#25359)
- pearjelly  (#25388)
- raymaylee  (#25394)
- Tianyu199509 (#25421)

* docs(user-guide): point tirith link to correct repo

* docs(lsp): replace "git worktree" with "git repository" in LSP docs

The word "worktree" (a git subcommand feature for parallel checkouts)
was used interchangeably with "repository" in the LSP docs, causing
confusion. LSP only requires a git-initialized directory, not an actual
worktree.

Fixes two instances: section "When LSP runs" and the troubleshooting
"Editing a file outside any git repo" heading.

* fix(agent): add Xiaomi MiMo to reasoning_content echo-back providers

Xiaomi MiMo emits reasoning via OpenAI's reasoning_content field and
requires reasoning_content on every assistant tool-call message when
replaying history. Without echo-back, subsequent API calls fail with
HTTP 400 — same shape as DeepSeek and Kimi/Moonshot thinking modes.

Adds _needs_mimo_tool_reasoning() detection (provider == 'xiaomi',
'mimo' in model, or xiaomimimo.com base url) and wires it into the
_needs_thinking_reasoning_pad() check.

Salvage of #25358 by @ephron-ren (manually re-applied — original branch
was severely stale against current main).

* fix(discord): handle forwarded messages via message_snapshots

Discord introduced message_snapshots for forwarded messages — text and
attachments live inside snap.content / snap.attachments rather than on
the parent message. _handle_message wasn't reading them, so forwards
showed up empty.

Defensively extracts snapshot text (when raw_content is empty) and
appends snapshot attachments to the working all_attachments list used
for type detection and media routing. hasattr/getattr guards keep this
safe on older discord.py installs without the field.

Salvage of #25462 by @1RB (manually re-applied — original branch was
stale against current main).

* fix(auxiliary): skip providers without credentials immediately

When the auxiliary client fallback chain reaches a provider that has no
credentials configured (no API key, no pool entry), the current code
just returns (None, None) which counts toward the per-call timeout
budget on the next attempt. Mark the provider unhealthy with a short
TTL so the chain advances quickly to the next viable option.

Closes #25384.

Salvage of #25395 by @AllynSheep.

* fix: gateway PID detection fails on Windows (two issues)

- _read_process_cmdline: /proc and 'ps' are unavailable on Windows,
  so process cmdline was always empty. Add psutil fallback (already
  a hard dependency used by _pid_exists in the same module).

- _record_looks_like_gateway: argv paths use backslashes on Windows
  but patterns use forward slashes/dots, so the fallback record check
  always failed. Normalize backslashes to forward slashes before
  matching.

Together these caused get_running_pid() to return None on Windows
even when the gateway process is alive, making the dashboard report
gateway as 'stopped' despite it functioning normally.

* feat(whatsapp): surface quoted reply metadata

* fix: show context compaction status

* fix(gateway): make Feishu ws connect override sync to preserve context manager

The Feishu adapter wrapped lark-oapi's Connect() callable to inject
ping_interval/ping_timeout overrides, but made the wrapper async. The
underlying library uses Connect() as an async context manager (async
with Connect(...) as ws:), which requires the call itself to be sync
and return an AsyncContextManager — making it async meant the wrapper
was awaited eagerly and ws never bound.

Restoring the sync wrapper preserves the protocol while still injecting
the overrides.

Salvage of #25388 by @pearjelly (manually re-applied — original branch
was severely stale against current main).

* fix: do not inherit api_mode when delegating across providers

Cross-provider delegation (e.g. MiniMax parent → DeepSeek child) must not
inherit the parent's api_mode, because each provider uses a different API
surface: MiniMax uses 'anthropic_messages' while DeepSeek uses
'chat_completions'. Inheriting the wrong mode causes 404 errors.

When the effective provider differs from the parent's provider, derive
api_mode from the target provider's defaults instead (None triggers
re-derivation).

Refs: Bug #20558, PR #20563

* fix(gateway): keep QQBot reconnect loop alive

* fix(auxiliary): forward custom_providers to compression model context-length detection

When auxiliary.compression.provider is "auto", the compression model
reuses the main model's provider and base_url.  The main model's
context_length was correctly picking up custom_providers per-model
overrides (via _custom_providers stored during __init__), but the
auxiliary compression model's context-length detection path in
_check_compression_model_feasibility was not passing custom_providers,
causing it to skip step 0b and fall through to models.dev.

This meant that for providers like NVIDIA NIM where the user has a
per-model context_length in custom_providers (e.g. 196608 for
minimax-m2.7), the auxiliary model would use the models.dev value
(204800) instead of the user-configured one — a subtle discrepancy
that could lead to silent compression issues when the auxiliary model
doesn't actually support the detected context length.

Fix: pass self._custom_providers (already stored as an instance attr
during __init__) to the get_model_context_length() call for the
auxiliary compression model.

* fix(background-review): silence memory provider teardown output leak

Background review fork redirected stdout/stderr around run_conversation()
so its iteration messages stay silent.  But the memory-provider teardown
(shutdown_memory_provider() and review_agent.close()) fired in the outer
finally block AFTER the redirect_stdout context exited — so provider
teardown prints (Honcho disconnect, Hindsight sync, etc.) leaked into
the parent terminal at end of every turn.

Moves the teardown inside the redirect_stdout scope on the success path
(and nulls review_agent so the finally safety-net skips double-shutdown).
The finally block is rewritten as an exception-path safety net that
re-opens a devnull redirect, since the original 'with' context has
already exited by the time finally runs.

Salvage of #25342 by @ayushere (manually re-applied + merged conflict
with current main's set_thread_tool_whitelist wiring).

* feat: add NovitaAI as LLM provider

Add NovitaAI as a first-class provider with dedicated model selection
flow, live pricing, and authoritative context length resolution.

- Register provider in PROVIDER_REGISTRY, HERMES_OVERLAYS, and all
  alias/label maps (ID: novita, aliases: novita-ai, novitaai)
- Add dedicated _model_flow_novita() with 3-tier model list fallback:
  Novita API → models.dev → static curated list
- Fetch live pricing from /v1/models with correct unit conversion
  (input_token_price_per_m is 0.0001 USD per Mtok)
- Add Novita-specific context length resolution (step 4b) in
  get_model_context_length(), prioritized over models.dev/OpenRouter
- Register api.novita.ai in _URL_TO_PROVIDER to prevent early return
  from the custom-endpoint code path
- Add models.dev mapping (novita → novita-ai)
- Add default auxiliary model (deepseek/deepseek-v3-0324)
- Add NOVITA_API_KEY to test isolation (conftest.py)
- Update docs: providers page, env vars reference, CLI reference,
  .env.example, README, and landing page

* docs: update NovitaAI description to "90+ models, pay-per-use"

* test(novita): cache pricing, add provider test coverage, AUTHOR_MAP entry

Follow-up to Alex-wuhu's NovitaAI provider commit. Adds:

- _pricing_cache hit/write in _fetch_novita_pricing (was missing — every
  pricing fetch was re-hitting the network), mirroring the
  fetch_ai_gateway_pricing pattern. force_refresh now also propagates
  from get_pricing_for_provider.
- TestNovitaProvider in tests/hermes_cli/test_api_key_providers.py
  covering profile load, alias resolution, registry auto-registration,
  model list parity between main.py and models.py, _URL_TO_PROVIDER,
  _PROVIDER_PREFIXES, context_size in _CONTEXT_LENGTH_KEYS, pricing
  unit conversion, and pricing cache behavior.
- AUTHOR_MAP entry for yanglongwei06@gmail.com → @Alex-yang00.

* docs: update NovitaAI provider positioning (#25532)

* fix(install): preserve pip entry point when re-running on symlinked install

setup_path() writes the user-facing hermes shim with `cat >`, which
follows existing symlinks. Older installs created
`$command_link_dir/hermes` as a symlink to `$HERMES_BIN`
(`venv/bin/hermes`), so re-running install.sh stomped the pip entry
point with a bash shim that exec'd itself in an infinite loop.

`rm -f` the link target before writing so the shim lands at
`$command_link_dir/hermes` and the venv entry point is left intact.

Adds a regression test that reproduces the symlink-stomp end-to-end
(creates the symlink, drives the real shim-write block from setup_path,
asserts the venv pip script body survives and the shim is now a regular
file). Both new assertions fail on origin/main and pass with the fix.

Closes #21454.

* feat(discord): render clarify choices as buttons

Brings Discord to parity with Telegram on the clarify tool's interactive
UX. Overrides BasePlatformAdapter.send_clarify on DiscordAdapter to attach
a button view when choices are present.

  - ClarifyChoiceView: one discord.ui.Button per choice (max 24, Discord's
    25-component view cap leaves one slot for Other) plus a final
    'Other (type answer)' button.
  - Numeric click -> tools.clarify_gateway.resolve_gateway_clarify(
    clarify_id, choice_text) using the canonical choice text from the
    gateway entry (falls back to the button label if the entry vanished).
  - Other click -> tools.clarify_gateway.mark_awaiting_text(clarify_id) so
    the gateway's text-intercept captures the next user message in this
    session as the response.
  - Auth via the shared _component_check_auth helper (same OR-semantics as
    ExecApprovalView / SlashConfirmView / UpdatePromptView / ModelPickerView).
  - Open-ended (no choices) path renders the prompt as a plain embed and
    relies on the existing text-intercept resolution.
  - Single-use: first valid click disables every button and updates the
    embed footer with who answered and what they chose.

No changes to BasePlatformAdapter.send_clarify or the gateway's
clarify_callback wiring -- the existing scaffolding already drives all
adapters; Discord just inherits the default text fallback today and gains
buttons by virtue of this override.

Test conftest extended: _FakeEmbed gains add_field() / set_footer() stubs
so tests can construct embedded views without monkey-patching per-test.

Original PR: #19249 by @LeonSGP43. This is a reshape of the contributor's
work onto current main's clarify infrastructure (clarify_id + entry-based
resolution shared with Telegram, instead of a parallel on_answer-closure
mechanism). The button view structure and UX shape are preserved.

Tests: 14 new tests in tests/gateway/test_discord_clarify_buttons.py.
391/391 existing Discord gateway tests still pass.

Co-authored-by: LeonSGP43 <cine.dreamer.one@gmail.com>

* fix(cli): allow rotating broken OpenRouter / AI Gateway key in `hermes model` flow (#25750)

Before: when `OPENROUTER_API_KEY` (or `AI_GATEWAY_API_KEY`) was already
set in ~/.hermes/.env, `hermes model openrouter` / `hermes model
ai-gateway` skipped the API-key prompt entirely and jumped straight to
the model picker. Users with a broken / expired / wrong key had no way
to replace it without editing ~/.hermes/.env by hand or re-running
`hermes setup` from scratch.

Both flows now route through the existing `_prompt_api_key()` helper,
which surfaces [K]eep / [R]eplace / [C]lear when a key is already
configured — the same UX the generic API-key providers (z.ai, MiniMax,
Gemini, etc.) and the Daytona setup already use.

* fix(install.ps1): pin uv sync to venv\, verify baseline imports on Windows (#25755)

* fix(cli): allow rotating broken OpenRouter / AI Gateway key in `hermes model` flow

Before: when `OPENROUTER_API_KEY` (or `AI_GATEWAY_API_KEY`) was already
set in ~/.hermes/.env, `hermes model openrouter` / `hermes model
ai-gateway` skipped the API-key prompt entirely and jumped straight to
the model picker. Users with a broken / expired / wrong key had no way
to replace it without editing ~/.hermes/.env by hand or re-running
`hermes setup` from scratch.

Both flows now route through the existing `_prompt_api_key()` helper,
which surfaces [K]eep / [R]eplace / [C]lear when a key is already
configured — the same UX the generic API-key providers (z.ai, MiniMax,
Gemini, etc.) and the Daytona setup already use.

* fix(install.ps1): pin uv sync target to venv\, verify baseline imports

Two related Windows-installer bugs that produce a broken venv with
`ModuleNotFoundError: No module named 'dotenv'` on first `hermes` run.

## Bug 1: uv sync ignores VIRTUAL_ENV, syncs into .venv\ instead of venv\

`Install-Dependencies` creates the venv at `venv\` via `uv venv venv`,
sets `$env:VIRTUAL_ENV = "$InstallDir\venv"`, then runs
`uv sync --extra all --locked`. Modern uv (>=0.5) ignores `VIRTUAL_ENV`
for the `sync` subcommand and uses the project default `.venv\`
instead. Result: deps land in `$InstallDir\.venv\`, `venv\` stays
empty except for the python.exe stub from the earlier `uv venv` call,
`hermes.exe` ends up wired to the wrong site-packages.

The bash installer (`scripts/install.sh`) already worked around this in
`install_deps()` line 1127 by passing `UV_PROJECT_ENVIRONMENT` — that
flag tells uv exactly where to put the project env regardless of
`VIRTUAL_ENV`. Port the same fix to PowerShell.

## Bug 2: no post-install verification

If the sync still misdirects for any other reason (uv version drift,
filesystem quirk, user re-run scenarios), the installer reports success
and the user only finds out by running `hermes` and getting an
unhelpful traceback. Add a baseline-import probe that runs the venv's
own python against the four packages every `hermes` invocation needs
(`dotenv`, `openai`, `rich`, `prompt_toolkit`). On failure, throw
with a recovery command tailored to whether a sibling `.venv\` exists.

User report (Windows 11, Python 3.13.5, Hermes v0.13.0): manual repro
steps were exactly this — `uv sync` landed in `.venv\`, recovered by
junctioning `venv\` → `.venv\` to bridge the path mismatch.

* fix(telegram): escape dynamic markdown in callback flows

Use MarkdownV2 formatting for Telegram callback follow-ups and interactive prompts where dynamic names or user text can break legacy Markdown parsing. Add regression coverage for reload-mcp, model picker, approval callbacks, and update prompts.

* fix(telegram): restore model-switch success path + author map

The cherry-picked PR over-indented the edit_message_text block for
the mm: (model selected → switch) success path so the confirmation
edit lived inside the preceding 'except Exception as exc' branch and
only fired when the callback raised. Dedent the try/except back to
12-space indent so it runs after the callback succeeds, restoring
the original flow that removes the inline buttons and shows the
'Switched to ...' confirmation.

Add a regression test (test_model_selected_edits_message_on_success)
that asserts edit_message_text is awaited and the result text is
routed through format_message (MARKDOWN_V2 + backtick survival).

Add phuongvm to scripts/release.py AUTHOR_MAP.

* fix(memory): skip OpenViking upload symlinks

* fix(codex-runtime): retire wedged sessions + post-tool watchdog + OAuth refresh classify (#25769)

Mirrors openclaw beta.8's app-server resilience fixes so a stuck codex
subprocess can't burn the full turn deadline and so users get a
`codex login` pointer instead of raw RPC errors when their token expires.

- TurnResult.should_retire signals the caller to drop+respawn codex.
- Deadline-hit path and dead-subprocess detection set should_retire so
  the next turn doesn't ride a CPU-spinning or auth-broken process.
- Post-tool watchdog (post_tool_quiet_timeout=90s): if a tool item
  completes and codex goes silent past the threshold without further
  output or turn/completed, fast-fail instead of waiting the full 600s.
  Resets on any non-tool activity so normal think-after-tool flows are
  not affected.
- <turn_aborted> and <turn_aborted/> in agent text are treated as
  terminal — some codex builds tear down a turn that way without
  emitting turn/completed.
- _classify_oauth_failure() inspects RPC error message + stderr tail
  for invalid_grant / token refresh / 401 / etc. and rewrites
  user-facing errors to 'run codex login'. Conservative: generic
  failures still surface verbatim. Fires at turn/start failure,
  turn/completed failure, and dead-subprocess paths.
- thread/start cross-fill: tolerate thread.id, thread.sessionId,
  top-level sessionId/threadId so future codex schema drift doesn't
  KeyError us at handshake.
- run_agent.py: when run_turn returns should_retire=True OR raises,
  close + null self._codex_session so the next turn respawns.

Tests: +30 cases across session + integration suites.
  tests/agent/transports/test_codex_app_server_session.py 50/50 pass
  tests/run_agent/test_codex_app_server_integration.py 27/27 pass
  Broader codex scope (transports + cli runtime/migration) 376/376 pass

* chore(release): add AUTHOR_MAP entries for second new-contributor batch

Pre-stages AUTHOR_MAP for 7 new contributors in the upcoming batch:

- HxT9          (#25760)
- evgyur        (#25651)
- AsoTora       (#25624)
- oxngon        (#25603)
- yifengingit   (#25589)
- vanthinh6886  (#25562)
- Arkmusn       (#25559)

EthanGuo-coder, wesleysimplicio, and zccyman are already in the map.

* fix: read approvals.timeout from config in CLI approval callback

The _approval_callback method in HermesCLI hardcoded timeout=60
instead of reading the approvals.timeout config value. This meant
the config setting was silently ignored for CLI interactive prompts.

Other approval paths (callbacks.py, tools/approval.py) already read
the config correctly — only cli.py was missed.

* fix: use AUTOINCREMENT id for message ordering instead of timestamp

On WSL2 (and similar environments), time.time() is not strictly monotonic
due to NTP sync or host clock adjustments. When clock regression occurs
during a multi-tool flush, later-inserted rows get earlier timestamps,
causing ORDER BY timestamp, id to sort them before rows that were written
first. This breaks the tool_calls/tool_response adjacency invariant and
triggers HTTP 400 from the API.

Use ORDER BY id instead, since id (INTEGER PRIMARY KEY AUTOINCREMENT)
always reflects true insertion order regardless of system clock behavior.

* docs: clarify media impact on session context

* fix: stop retrying initial MCP auth failures

* fix(gateway): enable text-intercept for multi-choice clarify fallback (#25567)

* fix: restrict .env file permissions to 0600

Set file mode 0600 on ~/.hermes/.env after creation in the installer and
after every write via memory_setup._write_env_vars(). This ensures only
the file owner can read/write API keys and tokens, matching standard
practice for credential files (.netrc, .aws/credentials, .ssh/config).

Fixes #25477

* fix(gateway): forward image attachments to background agent tasks

When the gateway spawned a background agent (e.g. for delegation), media
URLs and types from the originating message weren't forwarded — the bg
agent saw the prompt but no attached images. Vision-enabled tasks
effectively lost their inputs.

Forwards media_urls/media_types through the bg-task spawn path and
runs the same vision-enrichment step the main flow uses, so the bg
agent gets image descriptions inlined into its prompt.

Closes #25614.

Salvage of #25603 by @oxngon (manually re-applied — original branch
was severely stale against current main).

* fix(terminal): prevent safety filter false positives on keywords inside quoted strings

The _foreground_background_guidance() function matched background-wrapper
keywords (nohup/disown/setsid) anywhere in the command text, including
inside quoted strings, Python -c code, commit messages, and PR body text.

Two-layer fix:
1. Strip single-quoted, double-quoted, and backtick-quoted content before
   pattern matching via _strip_quotes() helper.
2. Tighten the regex to only match keywords at command-start positions
   (after ^, ;, &, &&, ||, or $() — not mid-argument.

Both layers are needed: quote stripping handles the common case of keywords
in string literals, and the position-aware regex handles unquoted cases
like 'export FOO=setsid' (word boundary match, wrong position).

Fixes #20064

* chore(release): map oswaldb22 noreply email for AUTHOR_MAP

Co-Authored-By: Oswald <oswaldb22@users.noreply.github.com>

* test(toolsets): lock web search into default platform coverage

Adds regression tests pinning web search into the WhatsApp and api-server
default platform-coverage toolsets. Pure test additions, no runtime change.

Salvage of the test-addition commit from #25692 by @wesleysimplicio.
(The AUTHOR_MAP fixup commit from the same PR landed separately as
529ec85c7.)

* fix(update): refresh lazy-installed backends on hermes update (#25766)

Pyproject's [all] extra was slimmed down in May 2026 — ~20 optional
backends moved to tools/lazy_deps.py and only install on first use.
hermes update runs uv pip install -e .[all] which doesn't touch any of
them, so pin bumps in LAZY_DEPS (CVE response, transitive fixes) were
silently ignored on already-activated backends.

Two changes:

1. _is_satisfied() now parses the spec and checks the installed version
   against the constraint via packaging.specifiers. Previously it
   returned True the moment the package name was importable, which made
   ensure() a name-presence gate rather than a version-pin gate.

2. New active_features() / refresh_active_features() pair: lists every
   feature with at least one of its packages currently installed, then
   re-runs ensure() on each. Refresh is invoked at the end of
   _cmd_update_impl, right after the [all] install completes. Cold
   backends (never activated) stay quiet — no churn for them.

Output during update is one summary block:
  → Refreshing 4 active lazy backend(s)...
    ↑ 1 refreshed: provider.anthropic
    ✓ 3 already current
or
    ⚠ memory.honcho failed to refresh: <pip stderr>

Failures never raise out of update — backends keep their previously-
installed version and we tell the user to rerun once upstream is fixed.
security.allow_lazy_installs=false is honored: features get marked
"skipped" with the reason shown.

Tests: 18 new unit tests covering version-aware satisfaction (exact pin,
range, extras blocks, missing package, malformed spec), active feature
discovery, and refresh status reporting. All 61 lazy_deps tests pass.

* fix(agent/gemini-cloudcode): seed delta defaults for reasoning-only stream chunks

_make_stream_chunk built delta_kwargs with only `role`, so a reasoning-only
chunk produced a SimpleNamespace without a `.content` attribute. Downstream
consumers that read `delta.content` then raised AttributeError on Gemini 2.5
Flash, where the thinking delta arrives before any content delta.

Seed `content`, `tool_calls`, …

Brings Discord to parity with Telegram on the clarify tool's interactive
UX. Overrides BasePlatformAdapter.send_clarify on DiscordAdapter to attach
a button view when choices are present.

  - ClarifyChoiceView: one discord.ui.Button per choice (max 24, Discord's
    25-component view cap leaves one slot for Other) plus a final
    'Other (type answer)' button.
  - Numeric click -> tools.clarify_gateway.resolve_gateway_clarify(
    clarify_id, choice_text) using the canonical choice text from the
    gateway entry (falls back to the button label if the entry vanished).
  - Other click -> tools.clarify_gateway.mark_awaiting_text(clarify_id) so
    the gateway's text-intercept captures the next user message in this
    session as the response.
  - Auth via the shared _component_check_auth helper (same OR-semantics as
    ExecApprovalView / SlashConfirmView / UpdatePromptView / ModelPickerView).
  - Open-ended (no choices) path renders the prompt as a plain embed and
    relies on the existing text-intercept resolution.
  - Single-use: first valid click disables every button and updates the
    embed footer with who answered and what they chose.

No changes to BasePlatformAdapter.send_clarify or the gateway's
clarify_callback wiring -- the existing scaffolding already drives all
adapters; Discord just inherits the default text fallback today and gains
buttons by virtue of this override.

Test conftest extended: _FakeEmbed gains add_field() / set_footer() stubs
so tests can construct embedded views without monkey-patching per-test.

Original PR: NousResearch#19249 by @LeonSGP43. This is a reshape of the contributor's
work onto current main's clarify infrastructure (clarify_id + entry-based
resolution shared with Telegram, instead of a parallel on_answer-closure
mechanism). The button view structure and UX shape are preserved.

Tests: 14 new tests in tests/gateway/test_discord_clarify_buttons.py.
391/391 existing Discord gateway tests still pass.

Co-authored-by: LeonSGP43 <cine.dreamer.one@gmail.com>