feat: add Pi Coding Agent rollout seed source

docs/concepts/agent-rollout-ingestion.md

@@ -42,6 +42,18 @@ Use `AgentRolloutSeedSource` when you want to work from existing agent traces in
     )
     ```
 
+=== "Pi Coding Agent"
+
+    Uses `~/.pi/agent/sessions` and `*.jsonl` by default. Sessions are tree-structured JSONL files; the active conversation path is resolved automatically.
+
+    ```python
+    import data_designer.config as dd
+
+    seed_source = dd.AgentRolloutSeedSource(
+        format=dd.AgentRolloutFormat.PI_CODING_AGENT,
+    )
+    ```
+
 === "ATIF"
 
     ATIF requires an explicit `path`. See Harbor's [ATIF documentation](https://harborframework.com/docs/trajectory-format) for the format specification.
@@ -63,31 +75,31 @@ You can override `path` and `file_pattern` for any format when your rollout arti
 
 All supported rollout formats map into the same seeded row schema. In the table below, `None` means the source artifact does not expose that field directly, and `derived` means Data Designer computes it from normalized `messages`.
 
-| Normalized field | ATIF | Claude Code | Codex | Hermes Agent |
-|---|---|---|---|---|
-| `trace_id` | `session_id` | `sessionId[:agentId]` | `session_meta.id` or file stem | CLI `session_id` or file stem; gateway file stem |
-| `source_kind` | `"atif"` | `"claude_code"` | `"codex"` | `"hermes_agent"` |
-| `source_path` | Parsed `.json` path | Parsed `.jsonl` trace path | Parsed `rollout-*.jsonl` path | Parsed CLI `.json` or gateway `.jsonl` path |
-| `root_session_id` | `session_id` | `sessionId` or file stem | `trace_id` | `trace_id` |
-| `agent_id` | `None` | `agentId` | `None` | `None` |
-| `is_sidechain` | `False` | `isSidechain` | `False` | `False` |
-| `cwd` | `agent.extra.cwd` | First non-null record `cwd` | `session_meta.cwd` | `None` |
-| `project_path` | `extra.project_path` or `cwd` | `projectPath` or `cwd` | `cwd` | `None` |
-| `git_branch` | `agent.extra.git_branch` | First non-null record `gitBranch` | `session_meta.git_branch` | `None` |
-| `started_at` | Earliest step timestamp | Earliest row timestamp | `session_meta.timestamp` or earliest record timestamp | CLI `session_start`; gateway `created_at` |
-| `ended_at` | Latest step timestamp | Latest row timestamp | Latest record timestamp | CLI `last_updated`; gateway `updated_at` |
-| `messages` | Normalized steps | Normalized trace rows | Normalized response items | Normalized CLI or gateway rows |
-| `source_meta` | ATIF metadata | Claude metadata | Codex metadata | Hermes metadata |
-| `message_count` | `derived` | `derived` | `derived` | `derived` |
-| `tool_call_count` | `derived` | `derived` | `derived` | `derived` |
-| `final_assistant_message` | `derived` | `derived` | `derived` | `derived` |
+| Normalized field | ATIF | Claude Code | Codex | Hermes Agent | Pi Coding Agent |
+|---|---|---|---|---|---|
+| `trace_id` | `session_id` | `sessionId[:agentId]` | `session_meta.id` or file stem | CLI `session_id` or file stem; gateway file stem | Session header `id` |
+| `source_kind` | `"atif"` | `"claude_code"` | `"codex"` | `"hermes_agent"` | `"pi_coding_agent"` |
+| `source_path` | Parsed `.json` path | Parsed `.jsonl` trace path | Parsed `rollout-*.jsonl` path | Parsed CLI `.json` or gateway `.jsonl` path | Parsed `.jsonl` session path |
+| `root_session_id` | `session_id` | `sessionId` or file stem | `trace_id` | `trace_id` | Session header `id` |
+| `agent_id` | `None` | `agentId` | `None` | `None` | `None` |
+| `is_sidechain` | `False` | `isSidechain` | `False` | `False` | `False` |
+| `cwd` | `agent.extra.cwd` | First non-null record `cwd` | `session_meta.cwd` | `None` | Session header `cwd` |
+| `project_path` | `extra.project_path` or `cwd` | `projectPath` or `cwd` | `cwd` | `None` | Session header `cwd` |
+| `git_branch` | `agent.extra.git_branch` | First non-null record `gitBranch` | `session_meta.git_branch` | `None` | `None` |
+| `started_at` | Earliest step timestamp | Earliest row timestamp | `session_meta.timestamp` or earliest record timestamp | CLI `session_start`; gateway `created_at` | Earliest entry timestamp |
+| `ended_at` | Latest step timestamp | Latest row timestamp | Latest record timestamp | CLI `last_updated`; gateway `updated_at` | Latest entry timestamp |
+| `messages` | Normalized steps | Normalized trace rows | Normalized response items | Normalized CLI or gateway rows | Normalized active-path messages |
+| `source_meta` | ATIF metadata | Claude metadata | Codex metadata | Hermes metadata | Pi session metadata |
+| `message_count` | `derived` | `derived` | `derived` | `derived` | `derived` |
+| `tool_call_count` | `derived` | `derived` | `derived` | `derived` | `derived` |
+| `final_assistant_message` | `derived` | `derived` | `derived` | `derived` | `derived` |
 
 ### Notes
 
-- `trace_id`: Claude Code appends `agentId` when present. Hermes uses either the CLI session ID or the gateway transcript file stem.
-- `is_sidechain`: ATIF and Hermes currently normalize this to `False`. Claude Code preserves `isSidechain` directly.
-- `messages`: All formats normalize into the same chat-style message schema. See [Message Traces](traces.md) for the shared block structure.
-- `source_meta`: This is where format-specific details live, such as ATIF copied-context metadata, Claude summaries, Codex response-item types, or Hermes tool/session metadata.
+- `trace_id`: Claude Code appends `agentId` when present. Hermes uses either the CLI session ID or the gateway transcript file stem. Pi uses the session header `id`.
+- `is_sidechain`: ATIF, Hermes, and Pi currently normalize this to `False`. Claude Code preserves `isSidechain` directly.
+- `messages`: All formats normalize into the same chat-style message schema. See [Message Traces](traces.md) for the shared block structure. Pi sessions are tree-structured; only the active conversation path (from the last entry back to root) is included.
+- `source_meta`: This is where format-specific details live, such as ATIF copied-context metadata, Claude summaries, Codex response-item types, Hermes tool/session metadata, or Pi session version and branch information.
 
 ## Example: Summarize a Random Turn
 

packages/data-designer-config/src/data_designer/config/seed_source.py

@@ -176,6 +176,10 @@ def get_hermes_agent_default_path() -> str:
     return str(Path("~/.hermes/sessions").expanduser())
 
 
+def get_pi_coding_agent_default_path() -> str:
+    return str(Path("~/.pi/agent/sessions").expanduser())
+
+
 def _validate_filesystem_seed_source_path(value: str | None) -> str | None:
     if value is None:
         return None
@@ -200,6 +204,7 @@ class AgentRolloutFormat(StrEnum):
     CLAUDE_CODE = "claude_code"
     CODEX = "codex"
     HERMES_AGENT = "hermes_agent"
+    PI_CODING_AGENT = "pi_coding_agent"
 
 
 def get_agent_rollout_format_defaults(fmt: AgentRolloutFormat) -> tuple[str | None, str]:
@@ -211,6 +216,8 @@ def get_agent_rollout_format_defaults(fmt: AgentRolloutFormat) -> tuple[str | No
         return (get_codex_default_path(), "*.jsonl")
     if fmt == AgentRolloutFormat.HERMES_AGENT:
         return (get_hermes_agent_default_path(), "*.json*")
+    if fmt == AgentRolloutFormat.PI_CODING_AGENT:
+        return (get_pi_coding_agent_default_path(), "*.jsonl")
     raise ValueError(f"🛑 Unknown agent rollout format: {fmt!r}")
 
 
@@ -228,7 +235,8 @@ class AgentRolloutSeedSource(FileSystemSeedSource):
             "Directory containing agent rollout artifacts. This field is required for ATIF trajectories. "
             "When omitted, built-in defaults are used for formats that define one. "
             "Claude Code defaults to ~/.claude/projects, Codex defaults to ~/.codex/sessions, "
-            "and Hermes Agent defaults to ~/.hermes/sessions. "
+            "Hermes Agent defaults to ~/.hermes/sessions, "
+            "and Pi Coding Agent defaults to ~/.pi/agent/sessions. "
             "Relative paths are resolved from the current working directory when the config is loaded, "
             "not from the config file location."
         ),
@@ -238,7 +246,7 @@ class AgentRolloutSeedSource(FileSystemSeedSource):
         None,
         description=(
             "Case-sensitive filename pattern used to match agent rollout files. When omitted, "
-            "ATIF defaults to '*.json', Claude Code and Codex default to '*.jsonl', "
+            "ATIF defaults to '*.json', Claude Code, Codex, and Pi Coding Agent default to '*.jsonl', "
             "and Hermes Agent defaults to '*.json*'."
         ),
     )

packages/data-designer-engine/src/data_designer/engine/resources/agent_rollout/hermes_agent.py

@@ -16,6 +16,7 @@
     coerce_optional_str,
     load_json_object,
     load_jsonl_rows,
+    normalize_message_content,
     normalize_message_role,
     require_string,
     stringify_json_value,
@@ -244,7 +245,7 @@ def normalize_hermes_messages(
             normalized_messages.append(
                 build_message(
                     role="tool",
-                    content=_normalize_message_content(raw_message.get("content")),
+                    content=normalize_message_content(raw_message.get("content")),
                     tool_call_id=require_string(
                         raw_message.get("tool_call_id"),
                         f"Hermes tool message tool_call_id #{message_index} in {file_path}",
@@ -253,7 +254,7 @@ def normalize_hermes_messages(
             )
             continue
 
-        content = _normalize_message_content(raw_message.get("content"))
+        content = normalize_message_content(raw_message.get("content"))
         reasoning_content = coerce_optional_str(raw_message.get("reasoning"))
         tool_calls = normalize_hermes_tool_calls(
             raw_message.get("tool_calls"),
@@ -413,22 +414,6 @@ def _require_message_list(raw_messages: Any, *, file_path: Path, context: str) -
     return raw_messages
 
 
-def _normalize_message_content(content: Any) -> Any:
-    """Coerce Hermes message content into the normalized content shape.
-
-    Args:
-        content: Raw Hermes message content.
-
-    Returns:
-        A string or content-block list compatible with ``build_message``.
-    """
-    if content is None:
-        return ""
-    if isinstance(content, (str, list)):
-        return content
-    return stringify_json_value(content)
-
-
 def _extract_finish_reasons(raw_messages: list[dict[str, Any]]) -> list[str]:
     """Collect distinct assistant finish reasons in first-seen order.