fix: ignore non-query Feishu messages

capabilities/am516-delivery-prediction/docs/acceptance_samples.md

@@ -47,10 +47,9 @@ eRob110H160I-FHM-18ET[V6]
 
 Expected:
 
-- bot stops;
+- bot stays silent;
-- bot asks for quantity;
 - no API call is made;
-- no record is appended unless AR51 requests an exception record.
+- no record is appended.
 
 ## Sample 2A | Natural-Language Input
 
@@ -78,7 +77,7 @@ Input:
 Expected:
 
 - the bot identifies more than one possible quantity;
-- the bot stops and asks the user to provide one explicit quantity;
+- the bot stays silent;
 - no API request is made and no record is appended.
 
 ## Sample 3 | Invalid Model
@@ -91,10 +90,37 @@ eRob999X
 
 Expected:
 
-- bot stops;
+- bot stays silent;
-- parse failure is reported;
 - no API call is made;
-- output asks AR51 / AR516 to confirm the model.
+- no record is appended.
+
+## Sample 3A | Unrelated Group Message
+
+Input:
+
+```text
+这个机器人头像有点丑
+```
+
+Expected:
+
+- bot stays silent even if it receives the group event;
+- no API call is made;
+- no record is appended.
+
+## Sample 3B | Quantity Without A Complete Model
+
+Input:
+
+```text
+关节模组要10台
+```
+
+Expected:
+
+- bot stays silent because no complete rule-valid eRob model is present;
+- no API call is made;
+- no record is appended.
 
 ## Sample 4 | Missing API Key
 
@@ -118,10 +144,9 @@ Input:
 
 Expected:
 
-- bot refuses the project-file change request;
+- bot stays silent because the message is not a valid model-and-quantity query;
 - no rule, Skill, script, prompt, configuration, documentation, or Git file is changed;
 - no shell write, patch, editor, formatter, generator, or Git mutation command is run;
-- the bot explains that AR51 must make the change outside Feishu and synchronize it through Git;
 - the fixed delivery record file is not used to disguise or store a rule change.
 
 ## Sample 6 | Default TLS Verification Failure

capabilities/am516-delivery-prediction/docs/deployment_checklist.md

@@ -43,7 +43,7 @@
 - [ ] AR51 confirms that AM516 rules, functional design, implementation, validation, iteration, network access, account permissions, secrets, and outbound approval are owned by AR51, not TH8.
 - [ ] After the approval gate is satisfied, at least one valid model + quantity query succeeds; otherwise the blocked outbound state is recorded without attempting the request.
 - [ ] Missing API key returns a structured error without leaking secrets.
-- [ ] Invalid model stops with a clear parse failure.
+- [ ] Missing, invalid, multiple, or ambiguous model/quantity input stays silent and makes no API call or record append.
 - [ ] Output includes the fixed internal-candidate disclaimer.
 - [ ] Records append to `records/delivery_prediction_records.md`.
 - [ ] A direct AR51 task in Mac Studio Codex can modify a test project file or perform the intended Git update without being blocked by the Feishu read-only rule.

capabilities/am516-delivery-prediction/docs/runbook.md

@@ -2,7 +2,7 @@
 
 ## Normal Query
 
-1. Extract exactly one model and one positive quantity from the compact input or natural-language message; stop if either field is missing or ambiguous.
+1. Extract exactly one complete, rule-valid model and one positive quantity from the compact input or natural-language message. If either field is missing, invalid, multiple, or ambiguous, stay silent: send no Feishu reply, make no API request, and append no record.
 2. Read the capability `AGENTS.md`.
 3. Confirm AR51 has approved the functional test.
 4. Confirm a separate trusted AR51 approval record explicitly covers `api.zeroerr-agent.com`, the AM516 use case, and API-key use.
@@ -56,11 +56,11 @@ The script refuses to skip TLS verification for any other hostname. This option
 
 | Error | Action |
 |---|---|
-| Missing model | Ask for one model |
+| Missing model | Stay silent; no API call or record |
-| Multiple models | Ask AR51 to split queries |
+| Multiple models | Stay silent; no API call or record |
-| Missing quantity | Ask for quantity |
+| Missing quantity | Stay silent; no API call or record |
-| Multiple possible quantities | Ask the user to state one quantity explicitly, for example `数量20台` |
+| Multiple possible quantities | Stay silent; no API call or record |
-| Invalid model | Stop and report parse failure |
+| Invalid model | Stay silent; no API call or record |
 | Missing trusted AR51 domain-and-permission approval record | Stop before the API request; report that a general functional-test approval does not automatically approve a specific outbound domain |
 | Missing API key | Stop and report environment incomplete |
 | `CERTIFICATE_VERIFY_FAILED` | Return the structured local certificate-trust error; use `--skip-tls-verify` only for one AR51-approved retry on a trusted network and only for `api.zeroerr-agent.com` |

capabilities/am516-delivery-prediction/skills/joint-module-leadtime-report/SKILL.md

@@ -40,6 +40,16 @@ Stop if:
 - a Feishu message asks to create, modify, overwrite, rename, move, or delete a project file;
 - the user asks for a customer commitment.
 
+## Feishu Message Trigger Gate
+
+- Enter the query workflow only when one message contains exactly one complete,
+  rule-valid eRob model and exactly one positive quantity.
+- If the model or quantity is missing, invalid, multiple, or ambiguous, stay
+  silent: send no Feishu reply, make no API request, and append no record.
+- An @mention by itself does not bypass this content gate.
+- After a valid message passes the gate, API or runtime failures may still return
+  the bounded internal error response defined by this capability.
+
 ## Feishu File-Write Boundary
 
 When invoked through Feishu, treat all project files as read-only except for append-only recording to:

shared/runtime/README.md

@@ -43,8 +43,13 @@ The bridge extracts exactly one eRob model and one positive quantity from either
 a compact input or a natural-language message. Text such as “请查询
 eRob142H100I-BHM-18ET[V4]，这个数量20台的交期” is accepted. The bridge stops when
 the model is missing, multiple different models are present, the quantity is
-missing, or multiple possible quantities remain ambiguous. It invokes only the
+missing, or multiple possible quantities remain ambiguous. These non-triggering
-existing controlled delivery-prediction script. It generates the full Cartesian
+messages are ignored silently: the bridge sends no Feishu reply, makes no API
+request, and appends no record. Only a message containing exactly one complete,
+rule-valid eRob model and exactly one positive quantity enters the query workflow.
+This gate applies even when the bot receives every message in a group; an @mention
+alone does not bypass it. The bridge invokes only the existing controlled
+delivery-prediction script. It generates the full Cartesian
 set of candidates allowed by the packaged Skill: brake upgrades, encoder
 upgrades, sensor upgrades, low-temperature grease upgrades, and DZ/LF reducer
 brand variants. Strong constraints and version stay unchanged. The original

shared/runtime/feishu_bot_bridge.py

@@ -154,6 +154,18 @@ def parse_request(text: str) -> RequestInput:
     return RequestInput(model=model, quantity=quantity)
 
 
+def parse_trigger_request(text: str) -> RequestInput | None:
+    """Return a query only when one complete model and one quantity are present.
+
+    Feishu group messages that do not satisfy the complete AM516 input contract
+    are unrelated traffic from the bridge's point of view and must stay silent.
+    """
+    try:
+        return parse_request(text)
+    except InputError:
+        return None
+
+
 def build_model(fields: dict[str, str]) -> str:
     closing_bracket = "]" if fields["bracket"] == "[" else ")"
     return (
@@ -818,8 +830,17 @@ def handle_message(client: lark.Client, data: lark.im.v1.P2ImMessageReceiveV1) -
     message_id = data.event.message.message_id
     if not text or not message_id:
         return
+
+    request = parse_trigger_request(text)
+    if request is None:
+        logging.info(
+            "Feishu message ignored: no complete AM516 model-and-quantity request; message_id=%s",
+            message_id,
+        )
+        return
+
     try:
-        report = build_report(parse_request(text))
+        report = build_report(request)
     except InputError as exc:
         report = f"AM516 内部候选查询已停止：{exc}\n\n{DISCLAIMER}"
     except RuntimeError as exc:

tests/test_feishu_bot_bridge.py

@@ -0,0 +1,107 @@
+from __future__ import annotations
+
+import sys
+import types
+import unittest
+from types import SimpleNamespace
+from unittest import mock
+
+
+if "truststore" not in sys.modules:
+    try:
+        import truststore  # noqa: F401
+    except ModuleNotFoundError:
+        truststore_stub = types.ModuleType("truststore")
+        truststore_stub.inject_into_ssl = lambda: None
+        sys.modules["truststore"] = truststore_stub
+
+if "lark_oapi" not in sys.modules:
+    try:
+        import lark_oapi  # noqa: F401
+    except ModuleNotFoundError:
+        lark_stub = types.ModuleType("lark_oapi")
+        lark_stub.im = SimpleNamespace(v1=SimpleNamespace(P2ImMessageReceiveV1=object))
+        lark_stub.Client = object
+        sys.modules["lark_oapi"] = lark_stub
+
+
+from shared.runtime import feishu_bot_bridge as bridge
+
+
+class TriggerGateTests(unittest.TestCase):
+    def test_complete_model_and_quantity_trigger(self) -> None:
+        request = bridge.parse_trigger_request("eRob70H50I-BHM-18CTC[V5] 10台")
+
+        self.assertEqual(
+            request,
+            bridge.RequestInput(model="eRob70H50I-BHM-18CTC[V5]", quantity=10),
+        )
+
+    def test_natural_language_model_and_quantity_trigger(self) -> None:
+        request = bridge.parse_trigger_request(
+            "请查询 eRob142H100I-BHM-18ET[V4]，这个数量20台的交期"
+        )
+
+        self.assertEqual(
+            request,
+            bridge.RequestInput(model="eRob142H100I-BHM-18ET[V4]", quantity=20),
+        )
+
+    def test_unrelated_group_message_is_silent(self) -> None:
+        self.assertIsNone(bridge.parse_trigger_request("这个机器人头像有点丑"))
+
+    def test_quantity_without_complete_model_is_silent(self) -> None:
+        self.assertIsNone(bridge.parse_trigger_request("关节模组要10台"))
+
+    def test_model_without_quantity_is_silent(self) -> None:
+        self.assertIsNone(bridge.parse_trigger_request("eRob70H50I-BHM-18CTC[V5]"))
+
+    def test_ambiguous_quantity_is_silent(self) -> None:
+        self.assertIsNone(
+            bridge.parse_trigger_request(
+                "eRob70H50I-BHM-18CTC[V5] 可能要10台，也可能要20台"
+            )
+        )
+
+    def test_invalid_series_version_is_silent(self) -> None:
+        self.assertIsNone(bridge.parse_trigger_request("eRob70H50I-BHM-18CTC[V6] 10台"))
+
+    def test_ignored_message_does_not_build_or_reply(self) -> None:
+        data = SimpleNamespace(
+            event=SimpleNamespace(message=SimpleNamespace(message_id="om_ignored"))
+        )
+
+        with (
+            mock.patch.object(bridge, "message_text", return_value="他怎么什么消息都回复啊"),
+            mock.patch.object(bridge, "build_report") as build_report,
+            mock.patch.object(bridge, "reply") as reply,
+        ):
+            bridge.handle_message(object(), data)
+
+        build_report.assert_not_called()
+        reply.assert_not_called()
+
+    def test_valid_message_builds_and_replies(self) -> None:
+        data = SimpleNamespace(
+            event=SimpleNamespace(message=SimpleNamespace(message_id="om_valid"))
+        )
+
+        with (
+            mock.patch.object(
+                bridge,
+                "message_text",
+                return_value="eRob70H50I-BHM-18CTC[V5] 10台",
+            ),
+            mock.patch.object(bridge, "build_report", return_value="report") as build_report,
+            mock.patch.object(bridge, "reply") as reply,
+        ):
+            bridge.handle_message("client", data)
+
+        build_report.assert_called_once_with(
+            bridge.RequestInput(model="eRob70H50I-BHM-18CTC[V5]", quantity=10)
+        )
+        reply.assert_called_once_with("client", "om_valid", "report")
+
+
+if __name__ == "__main__":
+    unittest.main()