AI Intervention Agent

Previous value: -"Loop engineering: optional round label such as 'iter-3' or 'attempt-2'. Shown with the loop context so multiple rounds of the same loop are distinguishable at a glance. Length: clamped to 32 characters server-side."New value: +"Loop engineering: optional round label such as 'iter-3' or 'attempt-2'. Shown as a small badge on the task's tab so multiple rounds of the same loop are distinguishable at a glance. Length: clamped to 32 characters server-side."

Previous value: -"Loop engineering: optional stable identifier shared by every feedback round that belongs to the same goal / outer loop (agent-chosen, e.g. 'auth-refactor-2026-07'). Rounds that carry the same loop_id are grouped in the UI so the human reviewer can replay 'which rounds did this objective go through, and what was decided each time'. Length: clamped to 64 characters server-side. Omit for standalone one-shot questions (default behavior unchanged)."New value: +"Loop engineering: optional stable identifier shared by every feedback round that belongs to the same goal / outer loop (agent-chosen, e.g. 'auth-refactor-2026-07'). Rounds that carry the same loop_id are grouped in the server's loop ledger (GET /api/loops), which records 'which rounds did this objective go through, and what was decided each time'. The page itself does not display it. Length: clamped to 64 characters server-side. Omit for standalone one-shot questions (default behavior unchanged)."

Previous value: -"Loop engineering: optional one-sentence description of the loop's goal (e.g. 'Migrate auth/session.py to PyJWT 2.x with green integration tests'). Pass it on the first round of a loop_id; later rounds may omit it. Shown to the reviewer as loop context above the prompt. Length: clamped to 500 characters server-side."New value: +"Loop engineering: optional one-sentence description of the loop's goal (e.g. 'Migrate auth/session.py to PyJWT 2.x with green integration tests'). Pass it on the first round of a loop_id; later rounds may omit it. Stored with the task and the loop ledger, not displayed on the page. Length: clamped to 500 characters server-side."

Previous value: -"Loop engineering: optional free-form phase tag for this round, e.g. 'investigate' / 'implement' / 'verify' / 'review'. Helps the reviewer see where in the inner loop the agent currently is. Length: clamped to 32 characters server-side."New value: +"Loop engineering: optional free-form phase tag for this round, e.g. 'investigate' / 'implement' / 'verify' / 'review'. Stored with the task and the loop ledger, not displayed on the page. Length: clamped to 32 characters server-side."

Previous value: -"Loop engineering: optional verifiable completion criteria the human should judge the evidence against (e.g. 'pytest all green + no new ruff warnings + docs regenerated'). Rendered alongside the loop context so the verdict is made against an explicit baseline. Length: clamped to 500 characters server-side."New value: +"Loop engineering: optional verifiable completion criteria the human should judge the evidence against (e.g. 'pytest all green + no new ruff warnings + docs regenerated'). Stored with the task and the loop ledger but not displayed on the page, so put anything the human must read in `message`. Length: clamped to 500 characters server-side."

Previous value: -"Optional textarea placeholder hint shown to the user when waiting for free-text feedback. Per-task override of the global ``page.feedbackPlaceholder`` i18n string. Examples: 'Paste the error stack trace', 'Describe the visual glitch', 'Reply 'ok' to approve or 'no' + reason to reject'. Length: clamped to 200 characters server-side (single-line placeholders only; longer text is silently truncated; the response includes ``placeholder_truncated: true`` + ``placeholder_original_length`` + ``placeholder_max_length`` when clamping activates so callers can warn). If omitted or empty, the UI uses its default i18n placeholder. (mining-cycle-3 §2.1 — borrowed from gemini-cli ``ask_user`` schema.)"New value: +"Optional textarea placeholder hint shown to the user when waiting for free-text feedback. Per-task override of the global ``page.feedbackPlaceholder`` i18n string. Examples: 'Paste the error stack trace', 'Describe the visual glitch', 'Reply 'ok' to approve or 'no' + reason to reject'. Length: clamped to 200 characters server-side (single-line placeholders only; longer text is silently truncated and the tool result does not report it). If omitted or empty, the UI uses its default i18n placeholder."

Previous value: -"Optional short chip / tag rendered above the prompt in the task pane to give a one-word context cue (e.g. 'Auth', 'DB', 'Layout', 'CSS', 'i18n'). Length: clamped to 16 characters server-side; single-word recommendation, no spaces if avoidable. Especially useful in multi-task mode where the user juggles 3+ concurrent feedback requests — the chip lets them visually distinguish task domains at a glance. If omitted or empty, no chip is shown (default existing layout). (mining-cycle-3 §2.1 — borrowed from gemini-cli ``ask_user.header`` schema.)"New value: +"Optional short chip / tag rendered above the prompt in the task pane to give a one-word context cue (e.g. 'Auth', 'DB', 'Layout', 'CSS', 'i18n'). Length: clamped to 16 characters server-side; single-word recommendation, no spaces if avoidable. Especially useful in multi-task mode where the user juggles 3+ concurrent feedback requests — the chip lets them visually distinguish task domains at a glance. If omitted or empty, no chip is shown (default existing layout)."

Previous value: -"Question, summary, or proposal to display to the human user. MUST be a non-empty string. Supports CommonMark / GitHub-Flavored Markdown (headings, lists, tables, fenced code blocks, links, inline code). Recommended length: 1-2000 characters; soft cap 1,000,000 characters (~1 MB UTF-8, R166); inputs longer than the cap are truncated with a trailing ellipsis marker. Best practices: (1) state the question clearly in the first line; (2) include the recommended/default answer when proposing options; (3) escape special characters properly in JSON (use \\\" for quotes, \\n for newlines). If omitted, the server falls back to `summary` or `prompt` for cross-tool compatibility."New value: +"Question, summary, or proposal to display to the human user. MUST be a non-empty string. Supports CommonMark / GitHub-Flavored Markdown (headings, lists, tables, fenced code blocks, links, inline code). To show a screenshot or chart that lives on this machine, embed it as a Markdown image whose destination is the file path, e.g. `![chart](/abs/path/chart.png)` or a path relative to the workspace: png/jpg/gif/webp/bmp/avif files inside the workspace or the temp directory are displayed (max 8 per message, 8 MB each); any other local path is replaced by a short note and never read. Recommended length: 1-2000 characters; soft cap 1,000,000 characters (~1 MB UTF-8); inputs longer than the cap are truncated with a trailing ellipsis marker. Best practices: (1) state the question clearly in the first line; (2) include the recommended/default answer when proposing options; (3) escape special characters properly in JSON (use \\\" for quotes, \\n for newlines). If omitted, the server falls back to `summary` or `prompt` for cross-tool compatibility."

Previous value: -"Optional list of predefined choices the user can pick from (rendered as multi-select checkboxes alongside a free-text reply). Two canonical input shapes (v1.6.0+ — the legacy parallel-array shape `predefined_options_defaults` was removed in R167; use the dict form below to mark recommended options): (a) **RECOMMENDED** list[dict] of shape {\"label\": str, \"default\": bool} — mark the recommended option with `default: true` so the UI shows a pre-checked checkbox (field aliases accepted: \"label\"/\"text\"/\"value\", \"default\"/\"selected\"/\"checked\"); (b) list[str] — simple labels, all initially unchecked (use this when no recommendation is needed). Non-string and non-{label,...} items are silently dropped. Each option max length: 10000 characters (longer items truncated). Tips: (1) keep options short, action-oriented and mutually distinguishable; (2) PREFER the dict form for ANY recommended option — `{\"label\": \"Apply\", \"default\": true}`. The UI renders real pre-checked checkboxes, so do NOT use text-prefix hacks (adding marker words to the label) for marking recommendations; (3) the user may also ignore options and reply with free text. If omitted, the server falls back to `options` for cross-tool compatibility."New value: +"Optional list of predefined choices the user can pick from (rendered as multi-select checkboxes alongside a free-text reply). Two canonical input shapes (the older parallel-array shape `predefined_options_defaults` has been removed; use the dict form below to mark recommended options): (a) **RECOMMENDED** list[dict] of shape {\"label\": str, \"default\": bool} — mark the recommended option with `default: true` so the UI shows a pre-checked checkbox (field aliases accepted: \"label\"/\"text\"/\"value\", \"default\"/\"selected\"/\"checked\"); (b) list[str] — simple labels, all initially unchecked (use this when no recommendation is needed). Non-string and non-{label,...} items are silently dropped. Each option max length: 10000 characters (longer items truncated). Tips: (1) keep options short, action-oriented and mutually distinguishable; (2) PREFER the dict form for ANY recommended option — `{\"label\": \"Apply\", \"default\": true}`. The UI renders real pre-checked checkboxes, so do NOT use text-prefix hacks (adding marker words to the label) for marking recommendations; (3) the user may also ignore options and reply with free text. If omitted, the server falls back to `options` for cross-tool compatibility."

Previous value: -{
-  "properties": {
-    "result": {
-      "items": {},
-      "type": "array"
-    }
-  },
-  "required": [
-    "result"
-  ],
-  "type": "object",
-  "x-fastmcp-wrap-result": true
-}New value: +null

Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Optional UI mode hint: when ``'yesno'``, the frontend hides the free-text textarea and renders a single-row Yes/No button pair. User's click submits the literal string 'yes' or 'no' as the feedback result — saves typing + Submit-button click for binary decisions (approve/reject, proceed/abort, etc.). Allowed values: ``'yesno'`` (current) or ``None`` (default: keep textarea + optional ``predefined_options`` checkboxes). Unknown values silently treated as None (forward-compat for future types like ``'choice'`` / ``'rating'`` once the frontend supports them). (mining-cycle-3 §2.1 — borrowed from gemini-cli ``ask_user`` schema.)"
-}

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Loop engineering: optional round label such as 'iter-3' or 'attempt-2'. Shown with the loop context so multiple rounds of the same loop are distinguishable at a glance. Length: clamped to 32 characters server-side."
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Loop engineering: optional stable identifier shared by every feedback round that belongs to the same goal / outer loop (agent-chosen, e.g. 'auth-refactor-2026-07'). Rounds that carry the same loop_id are grouped in the UI so the human reviewer can replay 'which rounds did this objective go through, and what was decided each time'. Length: clamped to 64 characters server-side. Omit for standalone one-shot questions (default behavior unchanged)."
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Loop engineering: optional one-sentence description of the loop's goal (e.g. 'Migrate auth/session.py to PyJWT 2.x with green integration tests'). Pass it on the first round of a loop_id; later rounds may omit it. Shown to the reviewer as loop context above the prompt. Length: clamped to 500 characters server-side."
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Loop engineering: optional free-form phase tag for this round, e.g. 'investigate' / 'implement' / 'verify' / 'review'. Helps the reviewer see where in the inner loop the agent currently is. Length: clamped to 32 characters server-side."
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Loop engineering: optional verifiable completion criteria the human should judge the evidence against (e.g. 'pytest all green + no new ruff warnings + docs regenerated'). Rendered alongside the loop context so the verdict is made against an explicit baseline. Length: clamped to 500 characters server-side."
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional textarea placeholder hint shown to the user when waiting for free-text feedback. Per-task override of the global ``page.feedbackPlaceholder`` i18n string. Examples: 'Paste the error stack trace', 'Describe the visual glitch', 'Reply 'ok' to approve or 'no' + reason to reject'. Length: clamped to 200 characters server-side (single-line placeholders only; longer text is silently truncated; the response includes ``placeholder_truncated: true`` + ``placeholder_original_length`` + ``placeholder_max_length`` when clamping activates so callers can warn). If omitted or empty, the UI uses its default i18n placeholder. (mining-cycle-3 §2.1 — borrowed from gemini-cli ``ask_user`` schema.)"
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional short chip / tag rendered above the prompt in the task pane to give a one-word context cue (e.g. 'Auth', 'DB', 'Layout', 'CSS', 'i18n'). Length: clamped to 16 characters server-side; single-word recommendation, no spaces if avoidable. Especially useful in multi-task mode where the user juggles 3+ concurrent feedback requests — the chip lets them visually distinguish task domains at a glance. If omitted or empty, no chip is shown (default existing layout). (mining-cycle-3 §2.1 — borrowed from gemini-cli ``ask_user.header`` schema.)"
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional UI mode hint: when ``'yesno'``, the frontend hides the free-text textarea and renders a single-row Yes/No button pair. User's click submits the literal string 'yes' or 'no' as the feedback result — saves typing + Submit-button click for binary decisions (approve/reject, proceed/abort, etc.). Allowed values: ``'yesno'`` (current) or ``None`` (default: keep textarea + optional ``predefined_options`` checkboxes). Unknown values silently treated as None (forward-compat for future types like ``'choice'`` / ``'rating'`` once the frontend supports them). (mining-cycle-3 §2.1 — borrowed from gemini-cli ``ask_user`` schema.)"
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Accepted for compatibility; ignored by this server."
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Accepted for compatibility; UI language follows the user's saved settings."
+}

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

Added value: +null

Previous value: -"向用户展示的具体问题/提示（支持 Markdown）"New value: +"Question, summary, or proposal to display to the human user. MUST be a non-empty string. Supports CommonMark / GitHub-Flavored Markdown (headings, lists, tables, fenced code blocks, links, inline code). Recommended length: 1-2000 characters; hard limit 10000 (longer input is truncated). Best practices: (1) state the question clearly in the first line; (2) include the recommended/default answer when proposing options; (3) escape special characters properly in JSON (use \\\" for quotes, \\n for newlines). If omitted, the server falls back to `summary` or `prompt` for cross-tool compatibility."

Removed value: -"string"

Added value: +{
+  "anyOf": [
+    {
+      "items": {},
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Compatibility alias for `predefined_options`. Ignored when `predefined_options` is provided."
+}

Previous value: -"可选的预定义选项列表，供用户单选/多选"New value: +"Optional list of predefined choices the user can pick from (rendered as multi-select checkboxes alongside a free-text reply). Three input shapes are accepted (v1.5.20+): (a) list[str] — simple labels, all initially unchecked; (b) list[dict] of shape {\"label\": str, \"default\": bool} — let the recommended option start pre-checked without any extra param (aliases: \"label\"/\"text\"/\"value\", \"default\"/\"selected\"/\"checked\"); (c) list[str] paired with the sibling param `predefined_options_defaults` (parallel boolean array). Non-string and non-{label,...} items are silently dropped. Each option max length: 500 characters (longer items are truncated). Tips: (1) keep options short, action-oriented and mutually distinguishable; (2) prefer the dict form `{\"label\": \"Apply\", \"default\": true}` to mark the recommended/default answer — the UI now renders real pre-checked checkboxes, so do NOT rely on text-prefix hacks for marking recommended options; (3) the user may also ignore options and reply with free text. If omitted, the server falls back to `options` for cross-tool compatibility."

Added value: +{
+  "anyOf": [
+    {
+      "items": {},
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional sibling array (v1.5.20+) for the `list[str]` shape of `predefined_options`: each element decides whether the corresponding checkbox starts pre-checked. Truthy aliases (case-insensitive, trimmed): True / 1 / 1.0 / \"true\" / \"yes\" / \"on\" / \"selected\"; everything else (including None / 0 / lists / dicts) → False. Length is silently truncated when longer than `predefined_options` and padded with False when shorter. Ignored when `predefined_options` already uses the {\"label\", \"default\"} dict form (which takes precedence)."
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Accepted for compatibility; ignored by this server."
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Accepted for compatibility with other feedback MCP variants; this server ignores it (project context is taken from the running Web UI / config)."
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Compatibility alias for `message`. Ignored when `message` is provided."
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Accepted for compatibility; this server uses its own UI labels."
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Compatibility alias for `message` (used by noopstudios/Minidoracat interactive-feedback-mcp variants). Ignored when `message` is provided."
+}

Added value: +{
+  "anyOf": [
+    {
+      "items": {},
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Accepted for compatibility; ignored by this server."
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Accepted for compatibility (some agents pre-generate a trace ID and pass it through); this server always auto-generates an internal task ID and ignores the externally supplied value. Useful when the same `mcp.json` config also points at MCP variants that *do* honour an externally supplied task ID."
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Accepted for compatibility; this server uses its own configured backend timeout and auto-resubmit countdown."
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Compatibility alias for `timeout` (used by some MCP clients that explicitly suffix the unit). Both fields are accepted for compatibility — this server ignores them and uses its own configured backend timeout / auto-resubmit countdown. When both are provided, this server logs a debug line and discards both, since neither overrides server config."
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Accepted for compatibility; ignored by this server."
+}

Removed value: -[
-  "message"
-]