@pi-in-go/pigpen-a2a 0.1.0

package/port/golden/send-missing-message.jsonl

@@ -0,0 +1,18 @@
+{"kind":"header","scenario":"send-missing-message","lane":"pig-go-self","host":"pig 0.3.1+1.0.1","extension":"sha256:766f7013020ffc915c35c324d2997a21f7274842e4e3a5c598801682e171d7fd","normalizer":"v3"}
+{"step":"01-prompt","ch":"response","data":{"command":"prompt","data":{"disposition":"started"},"success":true}}
+{"step":"01-prompt","ch":"host","data":{"type":"agent_start"}}
+{"step":"01-prompt","ch":"host","data":{"type":"turn_start"}}
+{"step":"01-prompt","ch":"host","data":{"message":{"content":"","role":"system"},"type":"message_end"}}
+{"step":"01-prompt","ch":"host","data":{"message":{"content":[{"text":"ask the peer","type":"text"}],"role":"user"},"type":"message_end"}}
+{"step":"01-prompt","ch":"llm","data":{"messages":[{"role":"user","text":"ask the peer"}],"system":{"inserted":"Use a2a_agents to discover which remote agents exist before calling a2a_send.\n- The remote agent is another agent, not a tool: send it a self-contained request. Data you send leaves this machine.\n- ","removed":""},"tools":[{"description":"Read the contents of a file. Supports text files and images (jpg, png, gif, webp, bmp). Images are sent as attachments. For text files, output is truncated to 2000 lines or 50KB (whichever is hit first). Use offset/limit for large files. When you need the full file, continue with offset until complete.","name":"read","parameters":{"properties":{"limit":{"description":"Maximum number of lines to read","type":"number"},"offset":{"description":"Line number to start reading from (1-indexed)","type":"number"},"path":{"description":"Path to the file to read (relative or absolute)","type":"string"}},"required":["path"],"type":"object"}},{"description":"Execute a bash command in the current working directory. Returns stdout and stderr. Output is truncated to last 2000 lines or 50KB (whichever is hit first). If truncated, full output is saved to a temp file. Optionally provide a timeout in seconds.","name":"bash","parameters":{"properties":{"command":{"description":"Shell command to execute","type":"string"},"timeout":{"description":"Timeout in seconds (optional, no default timeout)","type":"number"}},"required":["command"],"type":"object"}},{"description":"Edit a single file using exact text replacement. Every edits[].oldText must match a unique, non-overlapping region of the original file. If two changes affect the same block or nearby lines, merge them into one edit instead of emitting overlapping edits. Do not include large unchanged regions just to connect distant changes.","name":"edit","parameters":{"properties":{"edits":{"description":"One or more targeted replacements. Each edit is matched against the original file, not incrementally. Do not include overlapping or nested edits. If two changes touch the same block or nearby lines, merge them into one edit instead.","items":{"properties":{"newText":{"description":"Replacement text for this targeted edit.","type":"string"},"oldText":{"description":"Exact text for one targeted replacement. It must be unique in the original file and must not overlap with any other edits[].oldText in the same call.","type":"string"}},"required":["oldText","newText"],"type":"object"},"type":"array"},"path":{"description":"Path to the file to edit (relative or absolute)","type":"string"}},"required":["path","edits"],"type":"object"}},{"description":"Write content to a file. Creates the file if it doesn't exist, overwrites if it does. Automatically creates parent directories.","name":"write","parameters":{"properties":{"content":{"description":"Content to write to the file","type":"string"},"path":{"description":"Path to the file to write (relative or absolute)","type":"string"}},"required":["path","content"],"type":"object"}},{"description":"List the remote A2A (Agent2Agent) agents configured for this PiG, with each agent's card: name, description and skills.","name":"a2a_agents","parameters":{"additionalProperties":false,"properties":{},"type":"object"}},{"description":"Send a task to a remote A2A agent and wait for its answer. Returns the task state, ids and the agent's reply. Reuse contextId to continue the same conversation.","name":"a2a_send","parameters":{"additionalProperties":false,"properties":{"agent":{"description":"Name of a configured remote (see a2a_agents).","type":"string"},"contextId":{"description":"Continue this conversation (from an earlier a2a_send).","type":"string"},"message":{"description":"The task or question, as plain text.","type":"string"},"taskId":{"description":"Continue this task, when it is waiting for input.","type":"string"}},"required":["agent","message"],"type":"object"}},{"description":"Get, list or cancel tasks on a remote A2A agent.","name":"a2a_task","parameters":{"additionalProperties":false,"properties":{"action":{"enum":["get","cancel","list"],"type":"string"},"agent":{"description":"Name of a configured remote.","type":"string"},"taskId":{"description":"Required for get and cancel.","type":"string"}},"required":["agent","action"],"type":"object"}}]}}
+{"step":"01-prompt","ch":"host","data":{"message":{"content":[{"arguments":{"agent":"peer"},"name":"a2a_send","type":"toolCall"}],"role":"assistant","stopReason":"toolUse"},"type":"message_end"}}
+{"step":"01-prompt","ch":"host","data":{"args":{"agent":"peer"},"toolName":"a2a_send","type":"tool_execution_start"}}
+{"step":"01-prompt","ch":"host","data":{"isError":true,"result":{"content":[{"text":"Validation failed for tool \"a2a_send\":\n  - message: must have required properties message\n\nReceived arguments:\n{\n  \"agent\": \"peer\"\n}","type":"text"}],"details":{}},"toolName":"a2a_send","type":"tool_execution_end"}}
+{"step":"01-prompt","ch":"host","data":{"message":{"content":[{"text":"Validation failed for tool \"a2a_send\":\n  - message: must have required properties message\n\nReceived arguments:\n{\n  \"agent\": \"peer\"\n}","type":"text"}],"details":{},"isError":true,"role":"toolResult","toolName":"a2a_send"},"type":"message_end"}}
+{"step":"01-prompt","ch":"host","data":{"type":"turn_end"}}
+{"step":"01-prompt","ch":"host","data":{"type":"turn_start"}}
+{"step":"01-prompt","ch":"llm","data":{"messages":[{"role":"user","text":"ask the peer"},{"role":"assistant","text":"","toolCalls":[{"arguments":"{\"agent\":\"peer\"}","name":"a2a_send"}]},{"role":"tool","text":"Validation failed for tool \"a2a_send\":\n  - message: must have required properties message\n\nReceived arguments:\n{\n  \"agent\": \"peer\"\n}"}],"system":{"inserted":"Use a2a_agents to discover which remote agents exist before calling a2a_send.\n- The remote agent is another agent, not a tool: send it a self-contained request. Data you send leaves this machine.\n- ","removed":""},"tools":[{"description":"Read the contents of a file. Supports text files and images (jpg, png, gif, webp, bmp). Images are sent as attachments. For text files, output is truncated to 2000 lines or 50KB (whichever is hit first). Use offset/limit for large files. When you need the full file, continue with offset until complete.","name":"read","parameters":{"properties":{"limit":{"description":"Maximum number of lines to read","type":"number"},"offset":{"description":"Line number to start reading from (1-indexed)","type":"number"},"path":{"description":"Path to the file to read (relative or absolute)","type":"string"}},"required":["path"],"type":"object"}},{"description":"Execute a bash command in the current working directory. Returns stdout and stderr. Output is truncated to last 2000 lines or 50KB (whichever is hit first). If truncated, full output is saved to a temp file. Optionally provide a timeout in seconds.","name":"bash","parameters":{"properties":{"command":{"description":"Shell command to execute","type":"string"},"timeout":{"description":"Timeout in seconds (optional, no default timeout)","type":"number"}},"required":["command"],"type":"object"}},{"description":"Edit a single file using exact text replacement. Every edits[].oldText must match a unique, non-overlapping region of the original file. If two changes affect the same block or nearby lines, merge them into one edit instead of emitting overlapping edits. Do not include large unchanged regions just to connect distant changes.","name":"edit","parameters":{"properties":{"edits":{"description":"One or more targeted replacements. Each edit is matched against the original file, not incrementally. Do not include overlapping or nested edits. If two changes touch the same block or nearby lines, merge them into one edit instead.","items":{"properties":{"newText":{"description":"Replacement text for this targeted edit.","type":"string"},"oldText":{"description":"Exact text for one targeted replacement. It must be unique in the original file and must not overlap with any other edits[].oldText in the same call.","type":"string"}},"required":["oldText","newText"],"type":"object"},"type":"array"},"path":{"description":"Path to the file to edit (relative or absolute)","type":"string"}},"required":["path","edits"],"type":"object"}},{"description":"Write content to a file. Creates the file if it doesn't exist, overwrites if it does. Automatically creates parent directories.","name":"write","parameters":{"properties":{"content":{"description":"Content to write to the file","type":"string"},"path":{"description":"Path to the file to write (relative or absolute)","type":"string"}},"required":["path","content"],"type":"object"}},{"description":"List the remote A2A (Agent2Agent) agents configured for this PiG, with each agent's card: name, description and skills.","name":"a2a_agents","parameters":{"additionalProperties":false,"properties":{},"type":"object"}},{"description":"Send a task to a remote A2A agent and wait for its answer. Returns the task state, ids and the agent's reply. Reuse contextId to continue the same conversation.","name":"a2a_send","parameters":{"additionalProperties":false,"properties":{"agent":{"description":"Name of a configured remote (see a2a_agents).","type":"string"},"contextId":{"description":"Continue this conversation (from an earlier a2a_send).","type":"string"},"message":{"description":"The task or question, as plain text.","type":"string"},"taskId":{"description":"Continue this task, when it is waiting for input.","type":"string"}},"required":["agent","message"],"type":"object"}},{"description":"Get, list or cancel tasks on a remote A2A agent.","name":"a2a_task","parameters":{"additionalProperties":false,"properties":{"action":{"enum":["get","cancel","list"],"type":"string"},"agent":{"description":"Name of a configured remote.","type":"string"},"taskId":{"description":"Required for get and cancel.","type":"string"}},"required":["agent","action"],"type":"object"}}]}}
+{"step":"01-prompt","ch":"host","data":{"message":{"content":[{"text":"done","type":"text"}],"role":"assistant","stopReason":"stop"},"type":"message_end"}}
+{"step":"01-prompt","ch":"host","data":{"type":"turn_end"}}
+{"step":"01-prompt","ch":"host","data":{"type":"agent_end"}}
+{"step":"99-shutdown","ch":"exit","data":{"code":0}}

package/port/golden/send-without-remotes.jsonl

@@ -0,0 +1,18 @@
+{"kind":"header","scenario":"send-without-remotes","lane":"pig-go-self","host":"pig 0.3.1+1.0.1","extension":"sha256:766f7013020ffc915c35c324d2997a21f7274842e4e3a5c598801682e171d7fd","normalizer":"v3"}
+{"step":"01-prompt","ch":"response","data":{"command":"prompt","data":{"disposition":"started"},"success":true}}
+{"step":"01-prompt","ch":"host","data":{"type":"agent_start"}}
+{"step":"01-prompt","ch":"host","data":{"type":"turn_start"}}
+{"step":"01-prompt","ch":"host","data":{"message":{"content":"","role":"system"},"type":"message_end"}}
+{"step":"01-prompt","ch":"host","data":{"message":{"content":[{"text":"ask the peer","type":"text"}],"role":"user"},"type":"message_end"}}
+{"step":"01-prompt","ch":"llm","data":{"messages":[{"role":"user","text":"ask the peer"}],"system":{"inserted":"Use a2a_agents to discover which remote agents exist before calling a2a_send.\n- The remote agent is another agent, not a tool: send it a self-contained request. Data you send leaves this machine.\n- ","removed":""},"tools":[{"description":"Read the contents of a file. Supports text files and images (jpg, png, gif, webp, bmp). Images are sent as attachments. For text files, output is truncated to 2000 lines or 50KB (whichever is hit first). Use offset/limit for large files. When you need the full file, continue with offset until complete.","name":"read","parameters":{"properties":{"limit":{"description":"Maximum number of lines to read","type":"number"},"offset":{"description":"Line number to start reading from (1-indexed)","type":"number"},"path":{"description":"Path to the file to read (relative or absolute)","type":"string"}},"required":["path"],"type":"object"}},{"description":"Execute a bash command in the current working directory. Returns stdout and stderr. Output is truncated to last 2000 lines or 50KB (whichever is hit first). If truncated, full output is saved to a temp file. Optionally provide a timeout in seconds.","name":"bash","parameters":{"properties":{"command":{"description":"Shell command to execute","type":"string"},"timeout":{"description":"Timeout in seconds (optional, no default timeout)","type":"number"}},"required":["command"],"type":"object"}},{"description":"Edit a single file using exact text replacement. Every edits[].oldText must match a unique, non-overlapping region of the original file. If two changes affect the same block or nearby lines, merge them into one edit instead of emitting overlapping edits. Do not include large unchanged regions just to connect distant changes.","name":"edit","parameters":{"properties":{"edits":{"description":"One or more targeted replacements. Each edit is matched against the original file, not incrementally. Do not include overlapping or nested edits. If two changes touch the same block or nearby lines, merge them into one edit instead.","items":{"properties":{"newText":{"description":"Replacement text for this targeted edit.","type":"string"},"oldText":{"description":"Exact text for one targeted replacement. It must be unique in the original file and must not overlap with any other edits[].oldText in the same call.","type":"string"}},"required":["oldText","newText"],"type":"object"},"type":"array"},"path":{"description":"Path to the file to edit (relative or absolute)","type":"string"}},"required":["path","edits"],"type":"object"}},{"description":"Write content to a file. Creates the file if it doesn't exist, overwrites if it does. Automatically creates parent directories.","name":"write","parameters":{"properties":{"content":{"description":"Content to write to the file","type":"string"},"path":{"description":"Path to the file to write (relative or absolute)","type":"string"}},"required":["path","content"],"type":"object"}},{"description":"List the remote A2A (Agent2Agent) agents configured for this PiG, with each agent's card: name, description and skills.","name":"a2a_agents","parameters":{"additionalProperties":false,"properties":{},"type":"object"}},{"description":"Send a task to a remote A2A agent and wait for its answer. Returns the task state, ids and the agent's reply. Reuse contextId to continue the same conversation.","name":"a2a_send","parameters":{"additionalProperties":false,"properties":{"agent":{"description":"Name of a configured remote (see a2a_agents).","type":"string"},"contextId":{"description":"Continue this conversation (from an earlier a2a_send).","type":"string"},"message":{"description":"The task or question, as plain text.","type":"string"},"taskId":{"description":"Continue this task, when it is waiting for input.","type":"string"}},"required":["agent","message"],"type":"object"}},{"description":"Get, list or cancel tasks on a remote A2A agent.","name":"a2a_task","parameters":{"additionalProperties":false,"properties":{"action":{"enum":["get","cancel","list"],"type":"string"},"agent":{"description":"Name of a configured remote.","type":"string"},"taskId":{"description":"Required for get and cancel.","type":"string"}},"required":["agent","action"],"type":"object"}}]}}
+{"step":"01-prompt","ch":"host","data":{"message":{"content":[{"arguments":{"agent":"peer","message":"hello peer"},"name":"a2a_send","type":"toolCall"}],"role":"assistant","stopReason":"toolUse"},"type":"message_end"}}
+{"step":"01-prompt","ch":"host","data":{"args":{"agent":"peer","message":"hello peer"},"toolName":"a2a_send","type":"tool_execution_start"}}
+{"step":"01-prompt","ch":"host","data":{"isError":true,"result":{"content":[{"text":"a2a: no remotes are configured; add a \"remotes\" object to a2a.json","type":"text"}],"details":{}},"toolName":"a2a_send","type":"tool_execution_end"}}
+{"step":"01-prompt","ch":"host","data":{"message":{"content":[{"text":"a2a: no remotes are configured; add a \"remotes\" object to a2a.json","type":"text"}],"details":{},"isError":true,"role":"toolResult","toolName":"a2a_send"},"type":"message_end"}}
+{"step":"01-prompt","ch":"host","data":{"type":"turn_end"}}
+{"step":"01-prompt","ch":"host","data":{"type":"turn_start"}}
+{"step":"01-prompt","ch":"llm","data":{"messages":[{"role":"user","text":"ask the peer"},{"role":"assistant","text":"","toolCalls":[{"arguments":"{\"agent\":\"peer\",\"message\":\"hello peer\"}","name":"a2a_send"}]},{"role":"tool","text":"a2a: no remotes are configured; add a \"remotes\" object to a2a.json"}],"system":{"inserted":"Use a2a_agents to discover which remote agents exist before calling a2a_send.\n- The remote agent is another agent, not a tool: send it a self-contained request. Data you send leaves this machine.\n- ","removed":""},"tools":[{"description":"Read the contents of a file. Supports text files and images (jpg, png, gif, webp, bmp). Images are sent as attachments. For text files, output is truncated to 2000 lines or 50KB (whichever is hit first). Use offset/limit for large files. When you need the full file, continue with offset until complete.","name":"read","parameters":{"properties":{"limit":{"description":"Maximum number of lines to read","type":"number"},"offset":{"description":"Line number to start reading from (1-indexed)","type":"number"},"path":{"description":"Path to the file to read (relative or absolute)","type":"string"}},"required":["path"],"type":"object"}},{"description":"Execute a bash command in the current working directory. Returns stdout and stderr. Output is truncated to last 2000 lines or 50KB (whichever is hit first). If truncated, full output is saved to a temp file. Optionally provide a timeout in seconds.","name":"bash","parameters":{"properties":{"command":{"description":"Shell command to execute","type":"string"},"timeout":{"description":"Timeout in seconds (optional, no default timeout)","type":"number"}},"required":["command"],"type":"object"}},{"description":"Edit a single file using exact text replacement. Every edits[].oldText must match a unique, non-overlapping region of the original file. If two changes affect the same block or nearby lines, merge them into one edit instead of emitting overlapping edits. Do not include large unchanged regions just to connect distant changes.","name":"edit","parameters":{"properties":{"edits":{"description":"One or more targeted replacements. Each edit is matched against the original file, not incrementally. Do not include overlapping or nested edits. If two changes touch the same block or nearby lines, merge them into one edit instead.","items":{"properties":{"newText":{"description":"Replacement text for this targeted edit.","type":"string"},"oldText":{"description":"Exact text for one targeted replacement. It must be unique in the original file and must not overlap with any other edits[].oldText in the same call.","type":"string"}},"required":["oldText","newText"],"type":"object"},"type":"array"},"path":{"description":"Path to the file to edit (relative or absolute)","type":"string"}},"required":["path","edits"],"type":"object"}},{"description":"Write content to a file. Creates the file if it doesn't exist, overwrites if it does. Automatically creates parent directories.","name":"write","parameters":{"properties":{"content":{"description":"Content to write to the file","type":"string"},"path":{"description":"Path to the file to write (relative or absolute)","type":"string"}},"required":["path","content"],"type":"object"}},{"description":"List the remote A2A (Agent2Agent) agents configured for this PiG, with each agent's card: name, description and skills.","name":"a2a_agents","parameters":{"additionalProperties":false,"properties":{},"type":"object"}},{"description":"Send a task to a remote A2A agent and wait for its answer. Returns the task state, ids and the agent's reply. Reuse contextId to continue the same conversation.","name":"a2a_send","parameters":{"additionalProperties":false,"properties":{"agent":{"description":"Name of a configured remote (see a2a_agents).","type":"string"},"contextId":{"description":"Continue this conversation (from an earlier a2a_send).","type":"string"},"message":{"description":"The task or question, as plain text.","type":"string"},"taskId":{"description":"Continue this task, when it is waiting for input.","type":"string"}},"required":["agent","message"],"type":"object"}},{"description":"Get, list or cancel tasks on a remote A2A agent.","name":"a2a_task","parameters":{"additionalProperties":false,"properties":{"action":{"enum":["get","cancel","list"],"type":"string"},"agent":{"description":"Name of a configured remote.","type":"string"},"taskId":{"description":"Required for get and cancel.","type":"string"}},"required":["agent","action"],"type":"object"}}]}}
+{"step":"01-prompt","ch":"host","data":{"message":{"content":[{"text":"done","type":"text"}],"role":"assistant","stopReason":"stop"},"type":"message_end"}}
+{"step":"01-prompt","ch":"host","data":{"type":"turn_end"}}
+{"step":"01-prompt","ch":"host","data":{"type":"agent_end"}}
+{"step":"99-shutdown","ch":"exit","data":{"code":0}}

package/port/golden/task-unknown-action.jsonl

@@ -0,0 +1,18 @@
+{"kind":"header","scenario":"task-unknown-action","lane":"pig-go-self","host":"pig 0.3.1+1.0.1","extension":"sha256:766f7013020ffc915c35c324d2997a21f7274842e4e3a5c598801682e171d7fd","normalizer":"v3"}
+{"step":"01-prompt","ch":"response","data":{"command":"prompt","data":{"disposition":"started"},"success":true}}
+{"step":"01-prompt","ch":"host","data":{"type":"agent_start"}}
+{"step":"01-prompt","ch":"host","data":{"type":"turn_start"}}
+{"step":"01-prompt","ch":"host","data":{"message":{"content":"","role":"system"},"type":"message_end"}}
+{"step":"01-prompt","ch":"host","data":{"message":{"content":[{"text":"poke the peer","type":"text"}],"role":"user"},"type":"message_end"}}
+{"step":"01-prompt","ch":"llm","data":{"messages":[{"role":"user","text":"poke the peer"}],"system":{"inserted":"Use a2a_agents to discover which remote agents exist before calling a2a_send.\n- The remote agent is another agent, not a tool: send it a self-contained request. Data you send leaves this machine.\n- ","removed":""},"tools":[{"description":"Read the contents of a file. Supports text files and images (jpg, png, gif, webp, bmp). Images are sent as attachments. For text files, output is truncated to 2000 lines or 50KB (whichever is hit first). Use offset/limit for large files. When you need the full file, continue with offset until complete.","name":"read","parameters":{"properties":{"limit":{"description":"Maximum number of lines to read","type":"number"},"offset":{"description":"Line number to start reading from (1-indexed)","type":"number"},"path":{"description":"Path to the file to read (relative or absolute)","type":"string"}},"required":["path"],"type":"object"}},{"description":"Execute a bash command in the current working directory. Returns stdout and stderr. Output is truncated to last 2000 lines or 50KB (whichever is hit first). If truncated, full output is saved to a temp file. Optionally provide a timeout in seconds.","name":"bash","parameters":{"properties":{"command":{"description":"Shell command to execute","type":"string"},"timeout":{"description":"Timeout in seconds (optional, no default timeout)","type":"number"}},"required":["command"],"type":"object"}},{"description":"Edit a single file using exact text replacement. Every edits[].oldText must match a unique, non-overlapping region of the original file. If two changes affect the same block or nearby lines, merge them into one edit instead of emitting overlapping edits. Do not include large unchanged regions just to connect distant changes.","name":"edit","parameters":{"properties":{"edits":{"description":"One or more targeted replacements. Each edit is matched against the original file, not incrementally. Do not include overlapping or nested edits. If two changes touch the same block or nearby lines, merge them into one edit instead.","items":{"properties":{"newText":{"description":"Replacement text for this targeted edit.","type":"string"},"oldText":{"description":"Exact text for one targeted replacement. It must be unique in the original file and must not overlap with any other edits[].oldText in the same call.","type":"string"}},"required":["oldText","newText"],"type":"object"},"type":"array"},"path":{"description":"Path to the file to edit (relative or absolute)","type":"string"}},"required":["path","edits"],"type":"object"}},{"description":"Write content to a file. Creates the file if it doesn't exist, overwrites if it does. Automatically creates parent directories.","name":"write","parameters":{"properties":{"content":{"description":"Content to write to the file","type":"string"},"path":{"description":"Path to the file to write (relative or absolute)","type":"string"}},"required":["path","content"],"type":"object"}},{"description":"List the remote A2A (Agent2Agent) agents configured for this PiG, with each agent's card: name, description and skills.","name":"a2a_agents","parameters":{"additionalProperties":false,"properties":{},"type":"object"}},{"description":"Send a task to a remote A2A agent and wait for its answer. Returns the task state, ids and the agent's reply. Reuse contextId to continue the same conversation.","name":"a2a_send","parameters":{"additionalProperties":false,"properties":{"agent":{"description":"Name of a configured remote (see a2a_agents).","type":"string"},"contextId":{"description":"Continue this conversation (from an earlier a2a_send).","type":"string"},"message":{"description":"The task or question, as plain text.","type":"string"},"taskId":{"description":"Continue this task, when it is waiting for input.","type":"string"}},"required":["agent","message"],"type":"object"}},{"description":"Get, list or cancel tasks on a remote A2A agent.","name":"a2a_task","parameters":{"additionalProperties":false,"properties":{"action":{"enum":["get","cancel","list"],"type":"string"},"agent":{"description":"Name of a configured remote.","type":"string"},"taskId":{"description":"Required for get and cancel.","type":"string"}},"required":["agent","action"],"type":"object"}}]}}
+{"step":"01-prompt","ch":"host","data":{"message":{"content":[{"arguments":{"action":"explode","agent":"peer","taskId":"t"},"name":"a2a_task","type":"toolCall"}],"role":"assistant","stopReason":"toolUse"},"type":"message_end"}}
+{"step":"01-prompt","ch":"host","data":{"args":{"action":"explode","agent":"peer","taskId":"t"},"toolName":"a2a_task","type":"tool_execution_start"}}
+{"step":"01-prompt","ch":"host","data":{"isError":true,"result":{"content":[{"text":"Validation failed for tool \"a2a_task\":\n  - action: must be equal to one of the allowed values\n\nReceived arguments:\n{\n  \"action\": \"explode\",\n  \"agent\": \"peer\",\n  \"taskId\": \"t\"\n}","type":"text"}],"details":{}},"toolName":"a2a_task","type":"tool_execution_end"}}
+{"step":"01-prompt","ch":"host","data":{"message":{"content":[{"text":"Validation failed for tool \"a2a_task\":\n  - action: must be equal to one of the allowed values\n\nReceived arguments:\n{\n  \"action\": \"explode\",\n  \"agent\": \"peer\",\n  \"taskId\": \"t\"\n}","type":"text"}],"details":{},"isError":true,"role":"toolResult","toolName":"a2a_task"},"type":"message_end"}}
+{"step":"01-prompt","ch":"host","data":{"type":"turn_end"}}
+{"step":"01-prompt","ch":"host","data":{"type":"turn_start"}}
+{"step":"01-prompt","ch":"llm","data":{"messages":[{"role":"user","text":"poke the peer"},{"role":"assistant","text":"","toolCalls":[{"arguments":"{\"action\":\"explode\",\"agent\":\"peer\",\"taskId\":\"t\"}","name":"a2a_task"}]},{"role":"tool","text":"Validation failed for tool \"a2a_task\":\n  - action: must be equal to one of the allowed values\n\nReceived arguments:\n{\n  \"action\": \"explode\",\n  \"agent\": \"peer\",\n  \"taskId\": \"t\"\n}"}],"system":{"inserted":"Use a2a_agents to discover which remote agents exist before calling a2a_send.\n- The remote agent is another agent, not a tool: send it a self-contained request. Data you send leaves this machine.\n- ","removed":""},"tools":[{"description":"Read the contents of a file. Supports text files and images (jpg, png, gif, webp, bmp). Images are sent as attachments. For text files, output is truncated to 2000 lines or 50KB (whichever is hit first). Use offset/limit for large files. When you need the full file, continue with offset until complete.","name":"read","parameters":{"properties":{"limit":{"description":"Maximum number of lines to read","type":"number"},"offset":{"description":"Line number to start reading from (1-indexed)","type":"number"},"path":{"description":"Path to the file to read (relative or absolute)","type":"string"}},"required":["path"],"type":"object"}},{"description":"Execute a bash command in the current working directory. Returns stdout and stderr. Output is truncated to last 2000 lines or 50KB (whichever is hit first). If truncated, full output is saved to a temp file. Optionally provide a timeout in seconds.","name":"bash","parameters":{"properties":{"command":{"description":"Shell command to execute","type":"string"},"timeout":{"description":"Timeout in seconds (optional, no default timeout)","type":"number"}},"required":["command"],"type":"object"}},{"description":"Edit a single file using exact text replacement. Every edits[].oldText must match a unique, non-overlapping region of the original file. If two changes affect the same block or nearby lines, merge them into one edit instead of emitting overlapping edits. Do not include large unchanged regions just to connect distant changes.","name":"edit","parameters":{"properties":{"edits":{"description":"One or more targeted replacements. Each edit is matched against the original file, not incrementally. Do not include overlapping or nested edits. If two changes touch the same block or nearby lines, merge them into one edit instead.","items":{"properties":{"newText":{"description":"Replacement text for this targeted edit.","type":"string"},"oldText":{"description":"Exact text for one targeted replacement. It must be unique in the original file and must not overlap with any other edits[].oldText in the same call.","type":"string"}},"required":["oldText","newText"],"type":"object"},"type":"array"},"path":{"description":"Path to the file to edit (relative or absolute)","type":"string"}},"required":["path","edits"],"type":"object"}},{"description":"Write content to a file. Creates the file if it doesn't exist, overwrites if it does. Automatically creates parent directories.","name":"write","parameters":{"properties":{"content":{"description":"Content to write to the file","type":"string"},"path":{"description":"Path to the file to write (relative or absolute)","type":"string"}},"required":["path","content"],"type":"object"}},{"description":"List the remote A2A (Agent2Agent) agents configured for this PiG, with each agent's card: name, description and skills.","name":"a2a_agents","parameters":{"additionalProperties":false,"properties":{},"type":"object"}},{"description":"Send a task to a remote A2A agent and wait for its answer. Returns the task state, ids and the agent's reply. Reuse contextId to continue the same conversation.","name":"a2a_send","parameters":{"additionalProperties":false,"properties":{"agent":{"description":"Name of a configured remote (see a2a_agents).","type":"string"},"contextId":{"description":"Continue this conversation (from an earlier a2a_send).","type":"string"},"message":{"description":"The task or question, as plain text.","type":"string"},"taskId":{"description":"Continue this task, when it is waiting for input.","type":"string"}},"required":["agent","message"],"type":"object"}},{"description":"Get, list or cancel tasks on a remote A2A agent.","name":"a2a_task","parameters":{"additionalProperties":false,"properties":{"action":{"enum":["get","cancel","list"],"type":"string"},"agent":{"description":"Name of a configured remote.","type":"string"},"taskId":{"description":"Required for get and cancel.","type":"string"}},"required":["agent","action"],"type":"object"}}]}}
+{"step":"01-prompt","ch":"host","data":{"message":{"content":[{"text":"done","type":"text"}],"role":"assistant","stopReason":"stop"},"type":"message_end"}}
+{"step":"01-prompt","ch":"host","data":{"type":"turn_end"}}
+{"step":"01-prompt","ch":"host","data":{"type":"agent_end"}}
+{"step":"99-shutdown","ch":"exit","data":{"code":0}}

package/port/golden/tools-visible-to-model.jsonl

@@ -0,0 +1,11 @@
+{"kind":"header","scenario":"tools-visible-to-model","lane":"pig-go-self","host":"pig 0.3.1+1.0.1","extension":"sha256:766f7013020ffc915c35c324d2997a21f7274842e4e3a5c598801682e171d7fd","normalizer":"v3"}
+{"step":"01-prompt","ch":"response","data":{"command":"prompt","data":{"disposition":"started"},"success":true}}
+{"step":"01-prompt","ch":"host","data":{"type":"agent_start"}}
+{"step":"01-prompt","ch":"host","data":{"type":"turn_start"}}
+{"step":"01-prompt","ch":"host","data":{"message":{"content":"","role":"system"},"type":"message_end"}}
+{"step":"01-prompt","ch":"host","data":{"message":{"content":[{"text":"hello","type":"text"}],"role":"user"},"type":"message_end"}}
+{"step":"01-prompt","ch":"llm","data":{"messages":[{"role":"user","text":"hello"}],"system":{"inserted":"Use a2a_agents to discover which remote agents exist before calling a2a_send.\n- The remote agent is another agent, not a tool: send it a self-contained request. Data you send leaves this machine.\n- ","removed":""},"tools":[{"description":"Read the contents of a file. Supports text files and images (jpg, png, gif, webp, bmp). Images are sent as attachments. For text files, output is truncated to 2000 lines or 50KB (whichever is hit first). Use offset/limit for large files. When you need the full file, continue with offset until complete.","name":"read","parameters":{"properties":{"limit":{"description":"Maximum number of lines to read","type":"number"},"offset":{"description":"Line number to start reading from (1-indexed)","type":"number"},"path":{"description":"Path to the file to read (relative or absolute)","type":"string"}},"required":["path"],"type":"object"}},{"description":"Execute a bash command in the current working directory. Returns stdout and stderr. Output is truncated to last 2000 lines or 50KB (whichever is hit first). If truncated, full output is saved to a temp file. Optionally provide a timeout in seconds.","name":"bash","parameters":{"properties":{"command":{"description":"Shell command to execute","type":"string"},"timeout":{"description":"Timeout in seconds (optional, no default timeout)","type":"number"}},"required":["command"],"type":"object"}},{"description":"Edit a single file using exact text replacement. Every edits[].oldText must match a unique, non-overlapping region of the original file. If two changes affect the same block or nearby lines, merge them into one edit instead of emitting overlapping edits. Do not include large unchanged regions just to connect distant changes.","name":"edit","parameters":{"properties":{"edits":{"description":"One or more targeted replacements. Each edit is matched against the original file, not incrementally. Do not include overlapping or nested edits. If two changes touch the same block or nearby lines, merge them into one edit instead.","items":{"properties":{"newText":{"description":"Replacement text for this targeted edit.","type":"string"},"oldText":{"description":"Exact text for one targeted replacement. It must be unique in the original file and must not overlap with any other edits[].oldText in the same call.","type":"string"}},"required":["oldText","newText"],"type":"object"},"type":"array"},"path":{"description":"Path to the file to edit (relative or absolute)","type":"string"}},"required":["path","edits"],"type":"object"}},{"description":"Write content to a file. Creates the file if it doesn't exist, overwrites if it does. Automatically creates parent directories.","name":"write","parameters":{"properties":{"content":{"description":"Content to write to the file","type":"string"},"path":{"description":"Path to the file to write (relative or absolute)","type":"string"}},"required":["path","content"],"type":"object"}},{"description":"List the remote A2A (Agent2Agent) agents configured for this PiG, with each agent's card: name, description and skills.","name":"a2a_agents","parameters":{"additionalProperties":false,"properties":{},"type":"object"}},{"description":"Send a task to a remote A2A agent and wait for its answer. Returns the task state, ids and the agent's reply. Reuse contextId to continue the same conversation.","name":"a2a_send","parameters":{"additionalProperties":false,"properties":{"agent":{"description":"Name of a configured remote (see a2a_agents).","type":"string"},"contextId":{"description":"Continue this conversation (from an earlier a2a_send).","type":"string"},"message":{"description":"The task or question, as plain text.","type":"string"},"taskId":{"description":"Continue this task, when it is waiting for input.","type":"string"}},"required":["agent","message"],"type":"object"}},{"description":"Get, list or cancel tasks on a remote A2A agent.","name":"a2a_task","parameters":{"additionalProperties":false,"properties":{"action":{"enum":["get","cancel","list"],"type":"string"},"agent":{"description":"Name of a configured remote.","type":"string"},"taskId":{"description":"Required for get and cancel.","type":"string"}},"required":["agent","action"],"type":"object"}}]}}
+{"step":"01-prompt","ch":"host","data":{"message":{"content":[{"text":"ok","type":"text"}],"role":"assistant","stopReason":"stop"},"type":"message_end"}}
+{"step":"01-prompt","ch":"host","data":{"type":"turn_end"}}
+{"step":"01-prompt","ch":"host","data":{"type":"agent_end"}}
+{"step":"99-shutdown","ch":"exit","data":{"code":0}}

package/port/interop/kagent/main.go

@@ -0,0 +1,73 @@
+// Command kagent-a2a-echo serves an A2A agent with kagent's own A2A server package
+// (github.com/kagent-dev/kagent/go/adk/pkg/a2a/server, Apache-2.0), the code kagent agents use to
+// speak A2A. scripts/interop-kagent.mjs copies that package from a kagent checkout and changes one
+// thing: its hard-coded readiness listener (":8081") binds an ephemeral port, so it can run next to
+// another service. Every A2A handler is unmodified. The executor echoes the message; the message "sleep" waits for cancellation.
+// It exists for the pigpen a2a interop test.
+package main
+
+import (
+	"context"
+	"flag"
+	"iter"
+	"log/slog"
+	"os"
+	"strings"
+
+	a2atype "github.com/a2aproject/a2a-go/v2/a2a"
+	"github.com/a2aproject/a2a-go/v2/a2asrv"
+	a2aserver "kagentinterop/server"
+)
+
+type echo struct{}
+
+func (echo) Execute(ctx context.Context, ec *a2asrv.ExecutorContext) iter.Seq2[a2atype.Event, error] {
+	return func(yield func(a2atype.Event, error) bool) {
+		var text strings.Builder
+		for _, p := range ec.Message.Parts {
+			text.WriteString(p.Text())
+		}
+		if ec.StoredTask == nil && !yield(a2atype.NewSubmittedTask(ec, ec.Message), nil) {
+			return
+		}
+		if !yield(a2atype.NewStatusUpdateEvent(ec, a2atype.TaskStateWorking, nil), nil) {
+			return
+		}
+		if text.String() == "sleep" {
+			<-ctx.Done()
+			return
+		}
+		if !yield(a2atype.NewArtifactEvent(ec, a2atype.NewTextPart("kagent echo: "+text.String())), nil) {
+			return
+		}
+		yield(a2atype.NewStatusUpdateEvent(ec, a2atype.TaskStateCompleted, nil), nil)
+	}
+}
+
+func (echo) Cancel(ctx context.Context, ec *a2asrv.ExecutorContext) iter.Seq2[a2atype.Event, error] {
+	return func(yield func(a2atype.Event, error) bool) {
+		yield(a2atype.NewStatusUpdateEvent(ec, a2atype.TaskStateCanceled, nil), nil)
+	}
+}
+
+func main() {
+	port := flag.String("port", "8083", "port")
+	flag.Parse()
+	logger := slog.New(slog.NewTextHandler(os.Stderr, nil))
+	card := a2atype.AgentCard{
+		Name: "kagent-echo", Description: "kagent A2A server package with an echo executor", Version: "1",
+		SupportedInterfaces: []*a2atype.AgentInterface{a2atype.NewAgentInterface("http://kagent-controller.kagent.svc.cluster.local:8083/api/a2a/kagent/echo", a2atype.TransportProtocolJSONRPC)},
+		Capabilities:        a2atype.AgentCapabilities{Streaming: true},
+		DefaultInputModes:   []string{"text"}, DefaultOutputModes: []string{"text"},
+		Skills: []a2atype.AgentSkill{{ID: "echo", Name: "Echo", Description: "echoes", Tags: []string{"echo"}}},
+	}
+	srv, err := a2aserver.NewA2AServer(card, echo{}, logger, a2aserver.ServerConfig{Host: "127.0.0.1", Port: *port})
+	if err != nil {
+		logger.Error("new server", "error", err)
+		os.Exit(1)
+	}
+	if err := srv.Run(); err != nil {
+		logger.Error("run", "error", err)
+		os.Exit(1)
+	}
+}

package/port/mutation-run.txt

@@ -0,0 +1,222 @@
+# review re-run (rev-pigpen-a2a): every mutant in mutations.json applied to a copy of extensions/a2a, go test -count=1 (unit and fake-host;
+# e2e, Binary and kagent tests skipped), 8 jobs, 109 mutants, 2026-09-30, pig 0.3.0+0.87.1. Runner: exact find/replace, one occurrence each.
+# result: 109 killed, 0 survived
+KILLED   listener-starts-without-config
+         first failing test: TestWorkerChildNeverListens
+KILLED   worker-child-may-listen
+         first failing test: TestWorkerProcessDoesNotOpenAListener
+KILLED   flag-not-highest-precedence
+         first failing test: TestPrecedenceFlagOverEnvOverFile
+KILLED   env-not-over-file
+         first failing test: TestPrecedenceFlagOverEnvOverFile
+KILLED   unknown-keys-and-inline-secrets-accepted
+         first failing test: TestInlineSecretsAreRejected
+KILLED   listener-without-tokens-allowed
+         first failing test: TestListenerNeedsAuthentication
+KILLED   insecure-no-auth-off-loopback
+         first failing test: TestInsecureNoAuthOnlyOnLoopback
+KILLED   insecure-and-tokens-both
+         first failing test: TestInsecureNoAuthWithTokensIsAmbiguous
+KILLED   short-tokens-allowed
+         first failing test: TestTokenConfigValidation
+KILLED   duplicate-token-values-allowed
+         first failing test: TestTwoVariablesWithOneValueAreRejected
+KILLED   duplicate-token-names-allowed
+         first failing test: TestTokenConfigValidation
+KILLED   tenant-not-validated
+         first failing test: TestTokenConfigValidation
+KILLED   missing-token-env-allowed
+         first failing test: TestTokenEnvNotSetIsSaidPlainly
+KILLED   listen-not-host-port
+         first failing test: TestMalformedListenAddressSaysHostPort
+KILLED   worker-gets-pig-default-tools
+         first failing test: TestReview_WorkerHasNoToolsUnlessConfigured
+KILLED   remote-url-scheme-unchecked
+         first failing test: TestRemoteDefaultsAndValidation
+KILLED   remote-name-unchecked
+         first failing test: TestRemoteDefaultsAndValidation
+KILLED   basic-scheme-accepted
+         first failing test: TestAuthenticateRejects
+KILLED   extra-fields-accepted
+         first failing test: TestAuthenticateRejects
+KILLED   token-comparison-inverted
+         first failing test: TestAuthenticateBearer
+KILLED   insecure-flag-ignored
+         first failing test: TestInsecureNoAuthGivesOneAnonymousPrincipal
+KILLED   tenant-key-uses-token-name
+         first failing test: TestPrincipalKeysIsolate
+KILLED   key-namespaces-collide
+         first failing test: TestPrincipalKeysIsolate
+KILLED   everything-public
+         first failing test: TestWrapRejectsWith401AndChallenge
+KILLED   no-bearer-challenge
+         first failing test: TestWrapRejectsWith401AndChallenge
+KILLED   empty-authenticator-allowed
+         first failing test: TestNoTokensNoInsecureFlagIsAnError
+KILLED   file-parts-dropped
+         first failing test: TestTextPlusFilePartIsRefusedNotTrimmed
+KILLED   empty-prompt-accepted
+         first failing test: TestEmptyMessageIsRejected
+KILLED   prompt-size-unbounded
+         first failing test: TestOversizedPromptIsRefusedBelowTheBodyLimit
+KILLED   timeout-never-fires
+         first failing test: TestTaskTimeoutFailsTheTask
+KILLED   worker-error-detail-leaks
+         first failing test: TestWorkerErrorDetailIsNotSentToThePeer
+KILLED   context-not-serialised
+         first failing test: TestCancelBeforeTheWorkerStartsBehindTheSameContext
+KILLED   concurrency-limit-ignored
+         first failing test: TestCancelBeforeTheWorkerStartsBehindTheConcurrencyLimit
+KILLED   cancel-does-not-stop-worker
+         first failing test: TestCancelBeforeTheWorkerStartsBehindTheConcurrencyLimit
+KILLED   failure-reason-dropped
+         first failing test: TestWorkerFailureBecomesAFailedTask
+KILLED   principal-not-checked
+         first failing test: TestExecutorRefusesAForgedUser
+KILLED   version-not-enforced
+         first failing test: TestProtocolVersionIsPinned
+KILLED   absent-version-accepted
+         first failing test: TestProtocolVersionIsPinned
+KILLED   minor-versions-accepted
+         first failing test: TestCardWithoutAProtocol10InterfaceIsRefused
+KILLED   mixed-version-values-accepted
+         first failing test: TestMixedVersionHeaderIsRefused
+KILLED   tenant-not-enforced
+         first failing test: TestRequestTenantMustMatchTheTokensTenant
+KILLED   user-not-attached
+         first failing test: TestCancelBeforeTheWorkerStartsBehindTheConcurrencyLimit
+KILLED   body-size-unbounded
+         first failing test: TestBodyLimitAppliesEvenWithASmallPrompt
+KILLED   card-requires-auth
+         first failing test: TestAgentCardIsPublicAndPinnedToProtocol10
+KILLED   card-drops-streaming
+         first failing test: TestAgentCardIsPublicAndPinnedToProtocol10
+KILLED   card-claims-push
+         first failing test: TestAgentCardIsPublicAndPinnedToProtocol10
+KILLED   card-ignores-external-url
+         first failing test: TestAgentCardAdvertisesExternalURL
+KILLED   card-without-security-requirement
+         first failing test: TestAgentCardIsPublicAndPinnedToProtocol10
+KILLED   plain-http-on-tls
+         first failing test: TestTLSListener
+KILLED   second-start-allowed
+         first failing test: TestSecondStartIsAnError
+KILLED   worker-keeps-extensions
+         first failing test: TestWorkerPassesFlagsSessionAndCwd
+KILLED   worker-not-marked
+         first failing test: TestWorkerEnvironmentIsAllowlisted
+KILLED   worker-inherits-secrets
+         first failing test: TestWorkerEnvironmentIsAllowlisted
+KILLED   passenv-ignored
+         first failing test: TestReview_WorkerKillsWhatATurnLeftBehind
+KILLED   session-id-ignores-principal
+         first failing test: TestSessionIDIsStableScopedAndSafe
+KILLED   session-id-ignores-context
+         first failing test: TestSessionIDIsStableScopedAndSafe
+KILLED   session-dir-shared
+         first failing test: TestWorkerPassesFlagsSessionAndCwd
+KILLED   worker-cwd-not-set
+         first failing test: TestWorkerPassesFlagsSessionAndCwd
+KILLED   tools-allowlist-dropped
+         first failing test: TestReview_WorkerHasNoToolsUnlessConfigured
+KILLED   session-not-kept
+         first failing test: TestWorkerPassesFlagsSessionAndCwd
+KILLED   abort-not-sent
+         first failing test: TestWorkerCancelAbortsThenReaps
+KILLED   no-kill-after-grace
+         first failing test: TestWorkerEscalatesToKillWhenTermIsIgnored
+KILLED   no-terminate
+         first failing test: TestWorkerAsksForTermBeforeKill
+KILLED   model-error-text-copied
+         first failing test: TestModelFailureMessageIsExactlyGeneric
+KILLED   model-error-not-a-failure
+         first failing test: TestModelFailureMessageIsExactlyGeneric
+KILLED   streamed-and-final-text-duplicated
+         first failing test: TestWorkerPassesFlagsSessionAndCwd
+KILLED   empty-prompt-sent
+         first failing test: TestWorkerRefusesEmptyPrompt
+KILLED   tool-updates-dropped
+         first failing test: TestWorkerStreamsUpdatesAndFinalText
+KILLED   ui-request-hangs
+         first failing test: TestWorkerFailsATurnThatNeedsInteractiveInput
+KILLED   rejected-prompt-ignored
+         first failing test: TestWorkerReportsARejectedPromptWithoutTheReason
+KILLED   any-protocol-version-accepted
+         first failing test: TestCardWithoutAProtocol10InterfaceIsRefused
+KILLED   credentials-follow-the-card
+         first failing test: TestCredentialsAreNotSentToAHostTheCardNamed
+KILLED   transport-host-not-checked
+         first failing test: TestCredentialTransportRefusesAnotherHost
+KILLED   redirects-followed-with-credentials
+         first failing test: TestRemoteRedirectsAreNotFollowed
+KILLED   bearer-not-sent
+         first failing test: TestBearerAndCustomHeadersComeFromEnvironment
+KILLED   missing-bearer-env-tolerated
+         first failing test: TestMissingTokenEnvironmentIsAnErrorBeforeAnyRequest
+KILLED   custom-headers-dropped
+         first failing test: TestBearerAndCustomHeadersComeFromEnvironment
+KILLED   remote-not-cancelled-on-abort
+         first failing test: TestCancellingTheCallCancelsTheRemoteTask
+KILLED   timeout-ignored
+         first failing test: undefined
+KILLED   unknown-agent-unnamed
+         first failing test: TestUnknownAgentNamesTheKnownOnes
+KILLED   names-unsorted
+         first failing test: TestRemotesNamesAreSorted
+KILLED   empty-message-sent
+         first failing test: TestSendRefusesAnEmptyMessageBeforeAnyRequest
+KILLED   input-required-called-terminal
+         first failing test: TestSummaryOfAnInputRequiredTaskIsNotTerminal
+KILLED   failure-text-hidden
+         first failing test: TestFailedAndInputRequiredStates
+KILLED   auth-error-shows-token-context
+         first failing test: TestAuthFailureIsExplainedWithoutTheToken
+KILLED   switch-drops-listener
+         first failing test: TestSessionSwitchKeepsTheListenerReloadRestartsIt
+KILLED   shutdown-keeps-listener
+         first failing test: TestConfiguredListenerServesAndShutdownStopsIt
+KILLED   config-error-silent
+         first failing test: TestInvalidConfigurationIsReportedNotFatal
+KILLED   start-failure-silent
+         first failing test: TestListenFailureIsReportedToTheUser
+KILLED   flag-not-read
+         first failing test: TestFlagOverridesTheConfigurationFile
+KILLED   agent-dir-ignored
+         first failing test: TestConfigIsReadFromTheAgentDirectory
+KILLED   stop-does-not-reload-config
+         first failing test: TestToolAfterShutdownUsesTheRewrittenConfiguration
+KILLED   status-hides-remotes
+         first failing test: TestReloadAppliesChangedConfiguration
+KILLED   tool-required-not-enforced
+         first failing test: TestToolsRejectBadArguments
+KILLED   tool-empty-message-allowed
+         first failing test: TestToolsRejectBadArguments
+KILLED   tool-errors-not-errors
+         first failing test: TestToolsWithoutRemotesSayWhy
+KILLED   unfinished-task-not-flagged
+         first failing test: TestSummaryOfAnInputRequiredTaskIsNotTerminal
+KILLED   task-action-unchecked
+         first failing test: TestToolsRejectBadArguments
+KILLED   send-drops-context
+         first failing test: TestSendToolPassesTheContextIDThrough
+KILLED   tls-load-failure-ignored
+         first failing test: TestUnreadableTLSKeyPairFailsStart
+KILLED   subscribe-ownership-unchecked
+         first failing test: TestSubscribeToALiveTaskDeliversTheRest
+KILLED   queued-cancel-ignored-at-slot
+         first failing test: TestCancelBeforeTheWorkerStartsBehindTheConcurrencyLimit
+KILLED   queued-cancel-ignored-at-context-lock
+         first failing test: TestCancelBeforeTheWorkerStartsBehindTheSameContext
+KILLED   shutdown-does-not-close-the-port
+         first failing test: TestShutdownClosesThePortEvenRightAfterStart
+KILLED   insecure-host-unchecked
+         first failing test: TestReview_InsecureLoopbackListenerRefusesAForeignHostHeader
+KILLED   transport-scheme-not-checked
+         first failing test: TestReview_CredentialsAreNotDowngradedToPlainHTTP
+KILLED   card-scheme-downgrade-accepted
+         first failing test: TestReview_CredentialsAreNotDowngradedToPlainHTTP
+KILLED   context-lock-shared-across-tenants
+         first failing test: TestReview_SameContextIDInTwoTenantsRunsConcurrently
+KILLED   left-behind-child-survives
+         first failing test: TestReview_WorkerKillsWhatATurnLeftBehind
+109 mutation(s), 0 not killed