[codex-analytics] rework thread_source for thread analytics (#20949)

## Summary
- make `thread_source` an explicit optional thread-level field on
`thread/start`, `thread/fork`, and returned thread payloads
- persist `thread_source` in rollout/session metadata so resumed live
threads retain the original value
- replace the old best-effort `session_source` -> `thread_source`
mapping with an explicit caller-supplied analytics classification

## Why
Before this change, analytics `thread_source` was populated by a
best-effort mapping from `session_source`. `session_source` describes
the runtime/client surface, not the actual thread-level origin, so that
projection was not accurate enough to distinguish cases such as `user`,
`subagent`, `memory_consolidation`, and future thread origins reliably.

Making `thread_source` explicit keeps one thread-level analytics field
while letting callers provide the real classification directly instead
of recovering it indirectly from `session_source`.

## Impact
For new analytics events, `thread_source` now reflects the explicit
thread-level classification supplied by the caller rather than an
inferred value derived from `session_source`. Existing protocol fields
remain optional; callers that omit `threadSource` now produce `null`
instead of a best-effort inferred value.

## Validation
- `just write-app-server-schema`
- `cargo test -p codex-analytics -p codex-core -p
codex-app-server-protocol --no-run`
- `cargo test -p codex-app-server-protocol
generated_ts_optional_nullable_fields_only_in_params`
- `cargo test -p codex-analytics
thread_initialized_event_serializes_expected_shape`
- `cargo test -p codex-core
resume_stopped_thread_from_rollout_preserves_thread_source`

codex-rs/app-server-protocol/src/protocol/common.rs

@@ -2184,6 +2184,7 @@ mod tests {
                     cwd: cwd.clone(),
                     cli_version: "0.0.0".to_string(),
                     source: v2::SessionSource::Exec,
+                    thread_source: None,
                     agent_nickname: None,
                     agent_role: None,
                     git_info: None,
@@ -2226,6 +2227,7 @@ mod tests {
                         "cwd": absolute_path_string("tmp"),
                         "cliVersion": "0.0.0",
                         "source": "exec",
+                        "threadSource": null,
                         "agentNickname": null,
                         "agentRole": null,
                         "gitInfo": null,

codex-rs/app-server-protocol/src/protocol/v2/thread.rs

@@ -6,6 +6,7 @@ use super::PermissionProfileSelectionParams;
 use super::SandboxMode;
 use super::SandboxPolicy;
 use super::Thread;
+use super::ThreadSource;
 use super::Turn;
 use super::TurnEnvironmentParams;
 use super::shared::v2_enum_from_core;
@@ -134,6 +135,9 @@ pub struct ThreadStartParams {
     pub ephemeral: Option<bool>,
     #[ts(optional = nullable)]
     pub session_start_source: Option<ThreadStartSource>,
+    /// Optional client-supplied analytics source classification for this thread.
+    #[ts(optional = nullable)]
+    pub thread_source: Option<ThreadSource>,
     /// Optional sticky environments for this thread.
     ///
     /// Omitted selects the default environment when environment access is
@@ -388,6 +392,9 @@ pub struct ThreadForkParams {
     pub developer_instructions: Option<String>,
     #[serde(default, skip_serializing_if = "std::ops::Not::not")]
     pub ephemeral: bool,
+    /// Optional client-supplied analytics source classification for this forked thread.
+    #[ts(optional = nullable)]
+    pub thread_source: Option<ThreadSource>,
     /// When true, return only thread metadata and live fork state without
     /// populating `thread.turns`. This is useful when the client plans to call
     /// `thread/turns/list` immediately after forking.

codex-rs/app-server-protocol/src/protocol/v2/thread_data.rs

@@ -4,6 +4,7 @@ use super::ThreadStatus;
 use super::TurnStatus;
 use codex_protocol::protocol::SessionSource as CoreSessionSource;
 use codex_protocol::protocol::SubAgentSource as CoreSubAgentSource;
+use codex_protocol::protocol::ThreadSource as CoreThreadSource;
 use codex_utils_absolute_path::AbsolutePathBuf;
 use schemars::JsonSchema;
 use serde::Deserialize;
@@ -60,6 +61,35 @@ impl From<SessionSource> for CoreSessionSource {
     }
 }
 
+#[derive(Serialize, Deserialize, Debug, Clone, Copy, PartialEq, Eq, JsonSchema, TS)]
+#[serde(rename_all = "snake_case")]
+#[ts(rename_all = "snake_case", export_to = "v2/")]
+pub enum ThreadSource {
+    User,
+    Subagent,
+    MemoryConsolidation,
+}
+
+impl From<CoreThreadSource> for ThreadSource {
+    fn from(value: CoreThreadSource) -> Self {
+        match value {
+            CoreThreadSource::User => ThreadSource::User,
+            CoreThreadSource::Subagent => ThreadSource::Subagent,
+            CoreThreadSource::MemoryConsolidation => ThreadSource::MemoryConsolidation,
+        }
+    }
+}
+
+impl From<ThreadSource> for CoreThreadSource {
+    fn from(value: ThreadSource) -> Self {
+        match value {
+            ThreadSource::User => CoreThreadSource::User,
+            ThreadSource::Subagent => CoreThreadSource::Subagent,
+            ThreadSource::MemoryConsolidation => CoreThreadSource::MemoryConsolidation,
+        }
+    }
+}
+
 #[derive(Serialize, Deserialize, Debug, Clone, PartialEq, Eq, JsonSchema, TS)]
 #[serde(rename_all = "camelCase")]
 #[ts(export_to = "v2/")]
@@ -98,6 +128,8 @@ pub struct Thread {
     pub cli_version: String,
     /// Origin of the thread (CLI, VSCode, codex exec, codex app-server, etc.).
     pub source: SessionSource,
+    /// Optional analytics source classification for this thread.
+    pub thread_source: Option<ThreadSource>,
     /// Optional random unique nickname assigned to an AgentControl-spawned sub-agent.
     pub agent_nickname: Option<String>,
     /// Optional role (agent_role) assigned to an AgentControl-spawned sub-agent.