@openhands/extensions 0.27.0 → 0.29.0

package/skills/github/scripts/agent_conversation.py

@@ -32,6 +32,11 @@ _CLOUD_START_GRACE_SECONDS = 10 * 60
 # How long to wait for a paused conversation's sandbox to come back up.
 _CLOUD_RESUME_TIMEOUT_SECONDS = 120
 _CLOUD_POLL_SECONDS = 3
+# How many times a matched delivery whose conversation ended in ERROR is sent
+# again. The delivery key never changes for a stable subject, so without a
+# retry its work is stranded; without a bound, a conversation that fails the
+# same way every time would be re-run on every scan.
+_MAX_ERROR_RETRIES = 2
 
 
 def _register_tools() -> None:
@@ -204,14 +209,23 @@ class AgentConversationDispatcher:
 
         same_delivery = record.get("delivery") == delivery
         same_head = bool(head) and record.get("head") == head
+        # Error retries count against one delivery; a new delivery starts over.
+        error_retries = int(record.get("error_retries") or 0) if same_delivery else 0
+        can_retry = error_retries < _MAX_ERROR_RETRIES
 
         if self._cloud:
             disposition, conversation_id = self._deliver_cloud(
-                record, conversation_id, subject, prompt, same_delivery, same_head
+                record,
+                conversation_id,
+                subject,
+                prompt,
+                same_delivery,
+                same_head,
+                can_retry,
             )
         else:
             disposition = self._deliver_local(
-                conversation_id, prompt, same_delivery, same_head
+                conversation_id, prompt, same_delivery, same_head, can_retry
             )
 
         if disposition in ("deduplicated", "in_progress"):
@@ -228,6 +242,10 @@ class AgentConversationDispatcher:
         }
         if disposition == "created" and self._cloud:
             new_record["started_at"] = time.time()
+        if disposition == "retried":
+            error_retries += 1
+        if error_retries:
+            new_record["error_retries"] = error_retries
         _kv_request(state_key, "PUT", new_record)
         return {
             "disposition": disposition,
@@ -235,7 +253,14 @@ class AgentConversationDispatcher:
         }
 
     def _deliver_cloud(
-        self, record, conversation_id, subject, prompt, same_delivery, same_head
+        self,
+        record,
+        conversation_id,
+        subject,
+        prompt,
+        same_delivery,
+        same_head,
+        can_retry,
     ):
         """Deliver through the OpenHands API; return the disposition and the id.
 
@@ -272,11 +297,21 @@ class AgentConversationDispatcher:
             if status in ("idle", "paused"):
                 self._cloud.run(conversation)
                 return "resumed", current_id
+            if status == "error" and can_retry:
+                # The delivery matched but its conversation died before the work
+                # finished, so send the revision again rather than strand it.
+                # The API reports an execution status only while the sandbox
+                # runs, so an errored conversation whose sandbox was already
+                # paused is not seen here and keeps reporting deduplicated.
+                self._cloud.send(conversation, prompt)
+                return "retried", current_id
             return "deduplicated", current_id
         self._cloud.send(conversation, prompt)
         return "resumed", current_id
 
-    def _deliver_local(self, conversation_id, prompt, same_delivery, same_head) -> str:
+    def _deliver_local(
+        self, conversation_id, prompt, same_delivery, same_head, can_retry
+    ) -> str:
         if self._workspace is None:
             raise RuntimeError("AgentConversationDispatcher must be used as a context")
 
@@ -321,6 +356,18 @@ class AgentConversationDispatcher:
                     ):
                         conversation.update_secrets(self._secrets)
                         conversation.run(blocking=False)
+                    elif (
+                        conversation.state.execution_status
+                        == ConversationExecutionStatus.ERROR
+                        and can_retry
+                    ):
+                        # The delivery matched but its conversation died before
+                        # the work finished, so send the revision again rather
+                        # than strand it.
+                        conversation.update_secrets(self._secrets)
+                        conversation.send_message(prompt)
+                        conversation.run(blocking=False)
+                        disposition = "retried"
                     else:
                         disposition = "deduplicated"
                 else:

package/skills/github-issue-to-pr/scripts/agent_conversation.py

@@ -32,6 +32,11 @@ _CLOUD_START_GRACE_SECONDS = 10 * 60
 # How long to wait for a paused conversation's sandbox to come back up.
 _CLOUD_RESUME_TIMEOUT_SECONDS = 120
 _CLOUD_POLL_SECONDS = 3
+# How many times a matched delivery whose conversation ended in ERROR is sent
+# again. The delivery key never changes for a stable subject, so without a
+# retry its work is stranded; without a bound, a conversation that fails the
+# same way every time would be re-run on every scan.
+_MAX_ERROR_RETRIES = 2
 
 
 def _register_tools() -> None:
@@ -204,14 +209,23 @@ class AgentConversationDispatcher:
 
         same_delivery = record.get("delivery") == delivery
         same_head = bool(head) and record.get("head") == head
+        # Error retries count against one delivery; a new delivery starts over.
+        error_retries = int(record.get("error_retries") or 0) if same_delivery else 0
+        can_retry = error_retries < _MAX_ERROR_RETRIES
 
         if self._cloud:
             disposition, conversation_id = self._deliver_cloud(
-                record, conversation_id, subject, prompt, same_delivery, same_head
+                record,
+                conversation_id,
+                subject,
+                prompt,
+                same_delivery,
+                same_head,
+                can_retry,
             )
         else:
             disposition = self._deliver_local(
-                conversation_id, prompt, same_delivery, same_head
+                conversation_id, prompt, same_delivery, same_head, can_retry
             )
 
         if disposition in ("deduplicated", "in_progress"):
@@ -228,6 +242,10 @@ class AgentConversationDispatcher:
         }
         if disposition == "created" and self._cloud:
             new_record["started_at"] = time.time()
+        if disposition == "retried":
+            error_retries += 1
+        if error_retries:
+            new_record["error_retries"] = error_retries
         _kv_request(state_key, "PUT", new_record)
         return {
             "disposition": disposition,
@@ -235,7 +253,14 @@ class AgentConversationDispatcher:
         }
 
     def _deliver_cloud(
-        self, record, conversation_id, subject, prompt, same_delivery, same_head
+        self,
+        record,
+        conversation_id,
+        subject,
+        prompt,
+        same_delivery,
+        same_head,
+        can_retry,
     ):
         """Deliver through the OpenHands API; return the disposition and the id.
 
@@ -272,11 +297,21 @@ class AgentConversationDispatcher:
             if status in ("idle", "paused"):
                 self._cloud.run(conversation)
                 return "resumed", current_id
+            if status == "error" and can_retry:
+                # The delivery matched but its conversation died before the work
+                # finished, so send the revision again rather than strand it.
+                # The API reports an execution status only while the sandbox
+                # runs, so an errored conversation whose sandbox was already
+                # paused is not seen here and keeps reporting deduplicated.
+                self._cloud.send(conversation, prompt)
+                return "retried", current_id
             return "deduplicated", current_id
         self._cloud.send(conversation, prompt)
         return "resumed", current_id
 
-    def _deliver_local(self, conversation_id, prompt, same_delivery, same_head) -> str:
+    def _deliver_local(
+        self, conversation_id, prompt, same_delivery, same_head, can_retry
+    ) -> str:
         if self._workspace is None:
             raise RuntimeError("AgentConversationDispatcher must be used as a context")
 
@@ -321,6 +356,18 @@ class AgentConversationDispatcher:
                     ):
                         conversation.update_secrets(self._secrets)
                         conversation.run(blocking=False)
+                    elif (
+                        conversation.state.execution_status
+                        == ConversationExecutionStatus.ERROR
+                        and can_retry
+                    ):
+                        # The delivery matched but its conversation died before
+                        # the work finished, so send the revision again rather
+                        # than strand it.
+                        conversation.update_secrets(self._secrets)
+                        conversation.send_message(prompt)
+                        conversation.run(blocking=False)
+                        disposition = "retried"
                     else:
                         disposition = "deduplicated"
                 else:

package/skills/github-issue-triage/scripts/agent_conversation.py

@@ -32,6 +32,11 @@ _CLOUD_START_GRACE_SECONDS = 10 * 60
 # How long to wait for a paused conversation's sandbox to come back up.
 _CLOUD_RESUME_TIMEOUT_SECONDS = 120
 _CLOUD_POLL_SECONDS = 3
+# How many times a matched delivery whose conversation ended in ERROR is sent
+# again. The delivery key never changes for a stable subject, so without a
+# retry its work is stranded; without a bound, a conversation that fails the
+# same way every time would be re-run on every scan.
+_MAX_ERROR_RETRIES = 2
 
 
 def _register_tools() -> None:
@@ -204,14 +209,23 @@ class AgentConversationDispatcher:
 
         same_delivery = record.get("delivery") == delivery
         same_head = bool(head) and record.get("head") == head
+        # Error retries count against one delivery; a new delivery starts over.
+        error_retries = int(record.get("error_retries") or 0) if same_delivery else 0
+        can_retry = error_retries < _MAX_ERROR_RETRIES
 
         if self._cloud:
             disposition, conversation_id = self._deliver_cloud(
-                record, conversation_id, subject, prompt, same_delivery, same_head
+                record,
+                conversation_id,
+                subject,
+                prompt,
+                same_delivery,
+                same_head,
+                can_retry,
             )
         else:
             disposition = self._deliver_local(
-                conversation_id, prompt, same_delivery, same_head
+                conversation_id, prompt, same_delivery, same_head, can_retry
             )
 
         if disposition in ("deduplicated", "in_progress"):
@@ -228,6 +242,10 @@ class AgentConversationDispatcher:
         }
         if disposition == "created" and self._cloud:
             new_record["started_at"] = time.time()
+        if disposition == "retried":
+            error_retries += 1
+        if error_retries:
+            new_record["error_retries"] = error_retries
         _kv_request(state_key, "PUT", new_record)
         return {
             "disposition": disposition,
@@ -235,7 +253,14 @@ class AgentConversationDispatcher:
         }
 
     def _deliver_cloud(
-        self, record, conversation_id, subject, prompt, same_delivery, same_head
+        self,
+        record,
+        conversation_id,
+        subject,
+        prompt,
+        same_delivery,
+        same_head,
+        can_retry,
     ):
         """Deliver through the OpenHands API; return the disposition and the id.
 
@@ -272,11 +297,21 @@ class AgentConversationDispatcher:
             if status in ("idle", "paused"):
                 self._cloud.run(conversation)
                 return "resumed", current_id
+            if status == "error" and can_retry:
+                # The delivery matched but its conversation died before the work
+                # finished, so send the revision again rather than strand it.
+                # The API reports an execution status only while the sandbox
+                # runs, so an errored conversation whose sandbox was already
+                # paused is not seen here and keeps reporting deduplicated.
+                self._cloud.send(conversation, prompt)
+                return "retried", current_id
             return "deduplicated", current_id
         self._cloud.send(conversation, prompt)
         return "resumed", current_id
 
-    def _deliver_local(self, conversation_id, prompt, same_delivery, same_head) -> str:
+    def _deliver_local(
+        self, conversation_id, prompt, same_delivery, same_head, can_retry
+    ) -> str:
         if self._workspace is None:
             raise RuntimeError("AgentConversationDispatcher must be used as a context")
 
@@ -321,6 +356,18 @@ class AgentConversationDispatcher:
                     ):
                         conversation.update_secrets(self._secrets)
                         conversation.run(blocking=False)
+                    elif (
+                        conversation.state.execution_status
+                        == ConversationExecutionStatus.ERROR
+                        and can_retry
+                    ):
+                        # The delivery matched but its conversation died before
+                        # the work finished, so send the revision again rather
+                        # than strand it.
+                        conversation.update_secrets(self._secrets)
+                        conversation.send_message(prompt)
+                        conversation.run(blocking=False)
+                        disposition = "retried"
                     else:
                         disposition = "deduplicated"
                 else:

package/skills/github-pr-reviewer/README.md

@@ -61,6 +61,11 @@ This skill is activated by:
   checkout when the review ends, so nothing accumulates between runs
 - Publishes a real pull request review, with inline comments where a finding
   maps to a changed line, and verifies on GitHub that it landed
+- Requires live evidence from the real app before approving a user-visible UI
+  change when the repository's guidance demands it: unit tests, CSS-token
+  assertions, generated mockups, and reconstructed captures cannot substitute.
+  Missing evidence yields a COMMENT review that names the gap, so no approval
+  and no maintainer handoff
 - Posts acknowledgement comments with AI disclosure
 - Configurable review tone and polling schedule
 - Optional human handoff after an exact-head approval. The scanner ranks the

package/skills/github-pr-reviewer/SKILL.md

@@ -189,6 +189,18 @@ handler recognizes the verdict and requests one configured maintainer through th
 same handoff used after an approval. An in-scope change continues the existing
 review unchanged.
 
+Before approving a change to user-visible UI behavior, the prompt requires live
+evidence from a real running application when the repository's guidance demands
+it: a screenshot, screen recording, or equivalent capture of the running app
+that exercises the production-facing path. Unit tests, CSS-token or contract
+assertions, generated mockups, and reconstructed captures may support the review
+but cannot substitute for that evidence. When the required evidence is missing,
+the reviewer publishes one `event: COMMENT` review naming exactly what is
+missing and ends with `🔄 CHANGES REQUESTED`, so approval is withheld and the
+deterministic maintainer handoff does not fire. Non-UI changes keep the existing
+requirement of the real command and its observed output, with tests insufficient
+as sole proof.
+
 The script prepares each review's workspace before the agent starts: the pull
 request's head commit is downloaded as a tarball and extracted to a directory of
 its own, which becomes the conversation's working directory. The agent is told

package/skills/github-pr-reviewer/scripts/agent_conversation.py

@@ -32,6 +32,11 @@ _CLOUD_START_GRACE_SECONDS = 10 * 60
 # How long to wait for a paused conversation's sandbox to come back up.
 _CLOUD_RESUME_TIMEOUT_SECONDS = 120
 _CLOUD_POLL_SECONDS = 3
+# How many times a matched delivery whose conversation ended in ERROR is sent
+# again. The delivery key never changes for a stable subject, so without a
+# retry its work is stranded; without a bound, a conversation that fails the
+# same way every time would be re-run on every scan.
+_MAX_ERROR_RETRIES = 2
 
 
 def _register_tools() -> None:
@@ -204,14 +209,23 @@ class AgentConversationDispatcher:
 
         same_delivery = record.get("delivery") == delivery
         same_head = bool(head) and record.get("head") == head
+        # Error retries count against one delivery; a new delivery starts over.
+        error_retries = int(record.get("error_retries") or 0) if same_delivery else 0
+        can_retry = error_retries < _MAX_ERROR_RETRIES
 
         if self._cloud:
             disposition, conversation_id = self._deliver_cloud(
-                record, conversation_id, subject, prompt, same_delivery, same_head
+                record,
+                conversation_id,
+                subject,
+                prompt,
+                same_delivery,
+                same_head,
+                can_retry,
             )
         else:
             disposition = self._deliver_local(
-                conversation_id, prompt, same_delivery, same_head
+                conversation_id, prompt, same_delivery, same_head, can_retry
             )
 
         if disposition in ("deduplicated", "in_progress"):
@@ -228,6 +242,10 @@ class AgentConversationDispatcher:
         }
         if disposition == "created" and self._cloud:
             new_record["started_at"] = time.time()
+        if disposition == "retried":
+            error_retries += 1
+        if error_retries:
+            new_record["error_retries"] = error_retries
         _kv_request(state_key, "PUT", new_record)
         return {
             "disposition": disposition,
@@ -235,7 +253,14 @@ class AgentConversationDispatcher:
         }
 
     def _deliver_cloud(
-        self, record, conversation_id, subject, prompt, same_delivery, same_head
+        self,
+        record,
+        conversation_id,
+        subject,
+        prompt,
+        same_delivery,
+        same_head,
+        can_retry,
     ):
         """Deliver through the OpenHands API; return the disposition and the id.
 
@@ -272,11 +297,21 @@ class AgentConversationDispatcher:
             if status in ("idle", "paused"):
                 self._cloud.run(conversation)
                 return "resumed", current_id
+            if status == "error" and can_retry:
+                # The delivery matched but its conversation died before the work
+                # finished, so send the revision again rather than strand it.
+                # The API reports an execution status only while the sandbox
+                # runs, so an errored conversation whose sandbox was already
+                # paused is not seen here and keeps reporting deduplicated.
+                self._cloud.send(conversation, prompt)
+                return "retried", current_id
             return "deduplicated", current_id
         self._cloud.send(conversation, prompt)
         return "resumed", current_id
 
-    def _deliver_local(self, conversation_id, prompt, same_delivery, same_head) -> str:
+    def _deliver_local(
+        self, conversation_id, prompt, same_delivery, same_head, can_retry
+    ) -> str:
         if self._workspace is None:
             raise RuntimeError("AgentConversationDispatcher must be used as a context")
 
@@ -321,6 +356,18 @@ class AgentConversationDispatcher:
                     ):
                         conversation.update_secrets(self._secrets)
                         conversation.run(blocking=False)
+                    elif (
+                        conversation.state.execution_status
+                        == ConversationExecutionStatus.ERROR
+                        and can_retry
+                    ):
+                        # The delivery matched but its conversation died before
+                        # the work finished, so send the revision again rather
+                        # than strand it.
+                        conversation.update_secrets(self._secrets)
+                        conversation.send_message(prompt)
+                        conversation.run(blocking=False)
+                        disposition = "retried"
                     else:
                         disposition = "deduplicated"
                 else:

package/skills/github-pr-reviewer/scripts/main.py

@@ -847,7 +847,21 @@ def _build_review_prompt(
         "credential, configuration, or external state stayed unchanged. Do not add speculative or "
         "out-of-scope notes: every blocking or non-blocking observation must identify demonstrated "
         "behavior on the current head and explain why it matters to the merge decision.\n"
-        f"7. Publish one review with `POST /repos/{repo}/pulls/{number}/reviews`, using "
+        "7. LIVE EVIDENCE GATE - if the change alters user-visible UI behavior and the repository "
+        "guidance requires live evidence for it, you must not approve unless that evidence is from a "
+        "real running application and exercises the production-facing path. Live evidence means a "
+        "screenshot, screen recording, or equivalent capture of the running app, not the source, a "
+        "diff, or a description of what it should render. Unit tests, CSS-token or contract "
+        "assertions, generated mockups, and reconstructed or hand-built captures may support the "
+        "review but never substitute for the required live evidence. When the repository guidance "
+        "requires that evidence and only non-live evidence is available, do not approve: publish "
+        "exactly one review with `event: COMMENT` that names exactly which live evidence is missing, "
+        "and end its body with the verdict on its own line: `🔄 CHANGES REQUESTED`. State the gap as "
+        "a blocking finding, not a note, and never let a passing test suite stand in for the missing "
+        "capture. A UI change that does supply compliant live evidence, and any non-UI change "
+        "(backend, API, CLI, script) that follows the existing requirement of the real command and "
+        "its observed output, continues to step 8.\n"
+        f"8. Publish one review with `POST /repos/{repo}/pulls/{number}/reviews`, using "
         "`commit_id` equal to the Head SHA above. Use `event: APPROVE` when there are "
         "no material findings; otherwise use `event: COMMENT`. Never use "
         "`REQUEST_CHANGES`.\n"
@@ -858,19 +872,19 @@ def _build_review_prompt(
         "   Put the overall assessment in `body`, and each line-specific finding in the `comments` "
         "array with `path`, `line`, `side: RIGHT`, and `body`.\n"
         "   Only create inline comments for actionable findings; do not open praise or nitpick threads.\n"
-        "8. If a finding cannot be attached to a changed line, put it in the review body instead. "
+        "9. If a finding cannot be attached to a changed line, put it in the review body instead. "
         "If the API rejects the inline positions, retry with every finding in the body and no `comments` array. "
         "If GitHub forbids the configured bot from approving its own PR, retry the clean review with "
         "`event: COMMENT` and keep the approved verdict.\n"
-        "9. Begin the review body with this disclosure: "
+        "10. Begin the review body with this disclosure: "
         "`_This review was posted by an AI agent (OpenHands)._`\n"
-        "10. End the review body with a verdict on its own line: either `✅ APPROVED` "
+        "11. End the review body with a verdict on its own line: either `✅ APPROVED` "
         "or `🔄 CHANGES REQUESTED`.\n"
-        "11. If there are no material issues, still publish a review saying so, with the "
+        "12. If there are no material issues, still publish a review saying so, with the "
         "disclosure and the verdict.\n"
         f"\nReview instructions:\n{tone}{extra}{guide_section}\n\n"
         "After GitHub accepts the review, output exactly `GITHUB_REVIEW_POSTED`. "
-        "If publishing still fails after the fallback in step 8, output the complete review text "
+        "If publishing still fails after the fallback in step 9, output the complete review text "
         "so it can be posted as a comment instead."
     )