feat(feishu): add require_mention config option for group chats by Leegenux · Pull Request #4591 · NousResearch/hermes-agent

Leegenux · 2026-04-02T13:07:54Z

Summary

Adds a require_mention config option for Feishu/Lark group chats, allowing users to control whether @mention is required for the bot to respond.

Changes

Add require_mention field to FeishuAdapterSettings dataclass
Add FEISHU_REQUIRE_MENTION environment variable (default: true)
Add feishu.require_mention config.yaml option (mapped to env var)
Update _should_accept_group_message() to respect the setting

Usage

Users can disable @mention requirement via:

# ~/.hermes/config.yaml
feishu:
  require_mention: false  # Respond to all group messages without @mention

Or via environment variable:

export FEISHU_REQUIRE_MENTION=false

Behavior

require_mention=true (default): Only respond when bot is @mentioned or @_all
require_mention=false: Respond to all allowed group messages

This matches the existing Discord require_mention pattern for consistency.

Add feishu.require_mention config option (default: true) to control whether @mention is required for bot to respond in group chats. Previously, group_policy="open" would bypass @mention check, but this was hardcoded behavior. Now users can configure this independently: - require_mention=true (default): Only respond when bot is @mentioned or @_all - require_mention=false: Respond to all allowed group messages without @mention Configuration via config.yaml: feishu: require_mention: false Or via environment variable: FEISHU_REQUIRE_MENTION=false This matches the pattern used by Discord's require_mention setting. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>

Copilot

Pull request overview

Adds a Feishu/Lark configuration switch to control whether the bot requires an @mention to respond in group chats, aligning the behavior with other gateway adapters that support mention-gating.

Changes:

Add require_mention to Feishu adapter settings and apply it during adapter initialization.
Bridge feishu.require_mention from config.yaml into FEISHU_REQUIRE_MENTION (env var takes precedence).
Update Feishu group-message routing gate to respect require_mention (defaulting to enabled).

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 2 comments.

File	Description
`hermes_cli/config.py`	Adds a default `feishu.require_mention: True` entry to the generated/example config.
`gateway/platforms/feishu.py`	Introduces `require_mention` setting and uses it to bypass mention checks when disabled.
`gateway/config.py`	Maps `config.yaml` `feishu.require_mention` to `FEISHU_REQUIRE_MENTION` when the env var isn’t set.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-04-02T13:11:59Z

                str(extra.get("webhook_path") or os.getenv("FEISHU_WEBHOOK_PATH", _DEFAULT_WEBHOOK_PATH)).strip()
                or _DEFAULT_WEBHOOK_PATH
            ),
+            require_mention=os.getenv("FEISHU_REQUIRE_MENTION", "true").strip().lower() not in ("false", "0", "no"),
        )


require_mention is currently only read from FEISHU_REQUIRE_MENTION. Since _load_settings() already accepts extra (and other Feishu settings like app_id, connection_mode, webhook_* can be configured via config.extra / gateway.json), it would be more consistent to also honor extra.get("require_mention") when present (e.g., bool or truthy/falsey string) and fall back to the env var otherwise. As-is, platforms.feishu.extra.require_mention (including values bridged into PlatformConfig.extra) has no effect.

Copilot · 2026-04-02T13:11:59Z

        if not self._allow_group_message(sender_id):
            return False
+        # If require_mention is disabled, accept all allowed group messages
+        if not self._require_mention:
+            return True


There are existing unit tests for _should_accept_group_message() in tests/gateway/test_feishu.py, but none currently cover the new require_mention=false behavior. Please add a test case asserting that when FEISHU_REQUIRE_MENTION=false (and group policy allows the sender), a group message without mentions is accepted, and that the default behavior remains unchanged when the env var is unset.

- Allow require_mention from extra.get() (platforms.feishu.extra) with env var fallback - Add TestRequireMentionDisabled test class covering: - require_mention=false accepts messages without @mention - require_mention=true requires @mention (default) - Default behavior when env var unset - Allowlist policy still respected when require_mention=false Addresses Copilot PR NousResearch#4591 review comments. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>

Copilot

Pull request overview

Copilot reviewed 4 out of 4 changed files in this pull request and generated 2 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-04-02T13:34:41Z

+            require_mention=(
+                str(extra.get("require_mention") or os.getenv("FEISHU_REQUIRE_MENTION", "true")).strip().lower()
+                not in ("false", "0", "no")
+            ),


Bug: extra.get("require_mention") or os.getenv(...) treats False / 0 / empty values from extra as “not provided” and falls back to the env var/default. This makes it impossible to disable mention gating via PlatformConfig.extra (and via platforms.feishu.extra.require_mention config paths) unless an env var is also set. Use an explicit is not None / key-exists check (similar to telegram._telegram_require_mention) before falling back to the env var.

Copilot · 2026-04-02T13:34:41Z

+    def test_group_message_accepted_without_mention_when_require_mention_false(self):
+        """When require_mention=false, group messages are accepted without @mention."""
+        from gateway.config import PlatformConfig
+        from gateway.platforms.feishu import FeishuAdapter
+
+        adapter = FeishuAdapter(PlatformConfig())
+        message = SimpleNamespace(content='{"text":"hello"}', mentions=[])
+        sender_id = SimpleNamespace(open_id="ou_any", user_id=None)
+        self.assertTrue(adapter._should_accept_group_message(message, sender_id))


Test coverage gap: the new behavior is only tested via FEISHU_REQUIRE_MENTION env var. Since _load_settings() also reads config.extra["require_mention"], add a test that sets PlatformConfig(extra={"require_mention": False}) (with FEISHU_REQUIRE_MENTION unset) to ensure the adapter honors an explicit False value from config and doesn’t regress due to falsy or fallbacks.

Use explicit None check instead of 'or' fallback to correctly handle require_mention=False from PlatformConfig.extra. Previously the 'or' operator treated False/0/empty string as 'not provided' and fell back to env var, making it impossible to disable mention gating via config. - Add _resolve_require_mention() helper with explicit None check - Add tests for require_mention via PlatformConfig.extra (True/False) - Add test for extra precedence over env var when explicitly False Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>

Copilot

Pull request overview

Copilot reviewed 4 out of 4 changed files in this pull request and generated 2 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

Copilot

Pull request overview

Copilot reviewed 4 out of 4 changed files in this pull request and generated no new comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

- Allow require_mention from extra.get() (platforms.feishu.extra) with env var fallback - Add TestRequireMentionDisabled test class covering: - require_mention=false accepts messages without @mention - require_mention=true requires @mention (default) - Default behavior when env var unset - Allowlist policy still respected when require_mention=false Addresses Copilot PR NousResearch#4591 review comments. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>

alt-glitch · 2026-05-01T20:53:50Z

Likely duplicate of #12887 (and #15058, #5219, #7546) — same feature: require_mention config toggle for Feishu group chats.

alt-glitch · 2026-05-01T20:54:27Z

Likely duplicate of #12887 (and #15058, #5219, #7546) — same feature: require_mention config toggle for Feishu group chats.

teknium1 · 2026-07-12T08:03:55Z

Thanks for the Feishu configuration work. This is an automated hermes-sweeper review; current main already provides this behavior, including a more granular per-chat form.

plugins/platforms/feishu/adapter.py:1600 resolves require_mention from platform config or FEISHU_REQUIRE_MENTION (defaulting to true), and :4274 enforces it in the active group-admission path.
gateway/config.py:1182 bridges feishu.require_mention into the platform configuration consumed by that adapter.
tests/gateway/test_feishu_bot_admission.py:100 covers default/env/config resolution, and the admission matrix includes an unmentioned group message accepted when require_mention is false.
The fuller implementation landed in b94cb8e2c4e (feat(feishu): operator-configurable bot admission and mention policy) and shipped in v2026.5.7.
The member discussion also identified this as overlapping Feishu mention-toggle work.

Copilot AI review requested due to automatic review settings April 2, 2026 13:07

Copilot started reviewing on behalf of Leegenux April 2, 2026 13:08 View session

Copilot AI reviewed Apr 2, 2026

View reviewed changes

Leegenux requested a review from Copilot April 2, 2026 13:31

Copilot started reviewing on behalf of Leegenux April 2, 2026 13:31 View session

Copilot AI reviewed Apr 2, 2026

View reviewed changes

Leegenux requested a review from Copilot April 2, 2026 13:46

Copilot started reviewing on behalf of Leegenux April 2, 2026 13:47 View session

Copilot AI reviewed Apr 2, 2026

View reviewed changes

Comment thread gateway/platforms/feishu.py Outdated

Comment thread gateway/platforms/feishu.py Outdated

Leegenux and others added 2 commits April 2, 2026 21:51

Update gateway/platforms/feishu.py

dc5dac6

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

Update gateway/platforms/feishu.py

e6c31fd

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

Leegenux requested a review from Copilot April 2, 2026 13:52

Copilot started reviewing on behalf of Leegenux April 2, 2026 13:52 View session

Copilot AI reviewed Apr 2, 2026

View reviewed changes

This was referenced Apr 22, 2026

feat(feishu): add require_mention config option for group chats #12887

Closed

feat(feishu): add per-group require_mention toggle #12411

Closed

Feishu group messages ignore require_group_mention=false from config.yaml #15226

Closed

This was referenced Apr 28, 2026

feat(feishu): add default_require_mention for group messages #16864

Closed

feat(gateway): add FEISHU_REQUIRE_MENTION config to control group @mention gate #7546

Closed

feat(feishu): allow disabling group mention requirement #17406

Closed

alt-glitch added type/feature New feature or request P3 Low — cosmetic, nice to have comp/gateway Gateway runner, session dispatch, delivery platform/feishu Feishu / Lark adapter duplicate This issue or pull request already exists labels May 1, 2026

teknium1 closed this Jul 12, 2026

teknium1 added the sweeper:implemented-on-main Sweeper: behavior already present on current main label Jul 12, 2026

GottZ mentioned this pull request Aug 3, 2026

feat(feishu): reply_in_thread from config.yaml (no .env) #64332

Open

1 task

Navigation Menu

Uh oh!

feat(feishu): add require_mention config option for group chats - #4591

feat(feishu): add require_mention config option for group chats#4591
Leegenux wants to merge 5 commits into
NousResearch:mainfrom
Leegenux:feishu-require-mention

Leegenux commented Apr 2, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

Copilot AI Apr 2, 2026

Uh oh!

Copilot AI Apr 2, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

Copilot AI Apr 2, 2026

Uh oh!

Copilot AI Apr 2, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Uh oh!

alt-glitch commented May 1, 2026

Uh oh!

alt-glitch commented May 1, 2026

Uh oh!

teknium1 commented Jul 12, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

Uh oh!

Conversation

Leegenux commented Apr 2, 2026

Summary

Changes

Usage

Behavior

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI Apr 2, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 2, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI Apr 2, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 2, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

alt-glitch commented May 1, 2026

Uh oh!

alt-glitch commented May 1, 2026

Uh oh!

teknium1 commented Jul 12, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants