mio-agent-runtime 0.2.4 → 0.2.5
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/adapters/opencode.js +2 -0
- package/adapters/workbuddy.js +2 -0
- package/package.json +1 -1
package/adapters/opencode.js
CHANGED
|
@@ -15,6 +15,8 @@ Mio MCP tools are available. Treat these as mandatory runtime rules for every wo
|
|
|
15
15
|
- After a decision affecting architecture, deployment, dependencies, or long-term behavior, call \`mio-intelligence_mio_memory_record\` with \`kind\`: \`decision\`, \`context\`, \`problem\`, or \`note\`.
|
|
16
16
|
- When a tool call fails, retries, or returns an error, call \`mio-intelligence_mio_observer_ingest\` with a stable \`trace_id\`, relevant \`event_type\`, \`payload\`, and \`outcome\`.
|
|
17
17
|
- Before a high-risk operation such as deletion, migration, credential change, or production change, call \`mio-intelligence_mio_policy_check\` and follow its suggestion when available.
|
|
18
|
+
- At the end of every task, before producing the final answer, call \`mio-intelligence_mio_observer_ingest\` with \`event_type\` = \`task_outcome\`, a stable \`trace_id\`, \`outcome\` = \`success\` / \`failure\` / \`aborted\`, and a brief non-sensitive \`payload\`. If Mio is unavailable, do not block the final answer.
|
|
19
|
+
- When you reuse a prior decision or experience returned by \`mio-intelligence_mio_memory_query\` and it changes your approach or outcome, call \`mio-intelligence_mio_experience_reuse\` with \`sourceAgent\`, \`targetAgent\`, \`experienceId\`, \`reuse\`, \`behaviorChanged\`, and \`outcomeImproved\`.
|
|
18
20
|
- If Mio MCP is unavailable, do not block the task. Continue normally and note the missed memory or observation.
|
|
19
21
|
- Do not store secrets, credentials, or raw sensitive content in Mio memory.
|
|
20
22
|
${INSTRUCTIONS_END}`
|
package/adapters/workbuddy.js
CHANGED
|
@@ -49,6 +49,8 @@ Mio MCP tools are available. Treat these as mandatory runtime rules for every wo
|
|
|
49
49
|
- After a decision affecting architecture, deployment, dependencies, or long-term behavior, call \`mio-intelligence_mio.memory.record\` with \`kind\`: \`decision\`, \`context\`, \`problem\`, or \`note\`.
|
|
50
50
|
- When a tool call fails, retries, or returns an error, call \`mio-intelligence_mio.observer.ingest\` with a stable \`trace_id\`, relevant \`event_type\`, \`payload\`, and \`outcome\`.
|
|
51
51
|
- Before a high-risk operation such as deletion, migration, credential change, or production change, call \`mio-intelligence_mio.policy.check\` and follow its suggestion when available.
|
|
52
|
+
- At the end of every task, before producing the final answer, call \`mio-intelligence_mio.observer.ingest\` with \`event_type\` = \`task_outcome\`, a stable \`trace_id\`, \`outcome\` = \`success\` / \`failure\` / \`aborted\`, and a brief non-sensitive \`payload\`. If Mio is unavailable, do not block the final answer.
|
|
53
|
+
- When you reuse a prior decision or experience returned by \`mio-intelligence_mio.memory.query\` and it changes your approach or outcome, call \`mio-intelligence_mio.experience.reuse\` with \`sourceAgent\`, \`targetAgent\`, \`experienceId\`, \`reuse\`, \`behaviorChanged\`, and \`outcomeImproved\`.
|
|
52
54
|
- If Mio MCP is unavailable, do not block the task. Continue normally and note the missed memory or observation.
|
|
53
55
|
- Do not store secrets, credentials, or raw sensitive content in Mio memory.
|
|
54
56
|
${MEMORY_END}`
|