feat(billing): agent-side spend records who was paid

Judge spend gained provider, model and mission on 2026-09-14; agent spend —
the larger half — did not. The runtime's `done` frame has always carried
`model` and `provider` beside the two token counts, and `topology_exec` read
only the counts, summed them, and charged the sum as output with no record of
which provider served the turn.

`TurnOutcome` and `StepRecord` carry a `Spend` now (input/output split,
provider, model), the worker passes it through `cm_billing::charge` along with
the mission id, and the chat runtime records the model it requested — that
loop drives one provider with no chain, so requested is answered. A bare
model name is recorded without a guessed family. `StepRecord.spend` is
`serde(default)` so journaled checkpoints from before this field still load,
and `tokens` stays as the total every reader keys on.

`charge` moved from `query!` to `query`: the macro pins the statement to
offline metadata that a schema change then has to regenerate against a live
database, for columns that are nullable text and uuid.

The done-frame test now asserts the split and the provider survive, not just
the sum.

Co-Authored-By: Claude Opus 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01WZb5A2kfVfjpdwSochkuHz

crates/cm-api/src/microvm_turn_executor.rs

@@ -295,6 +295,7 @@ impl<V: PhaseVm> TurnExecutor for MicroVmTurnExecutor<V> {
             // the honest value for "not measured on this path".
             tokens: 0,
             gated: Vec::new(),
+            spend: Default::default(),
         })
     }
 }

crates/cm-api/src/recursive_exec.rs

@@ -173,6 +173,7 @@ impl TurnExecutor for SubTopologyExecutor {
             output: record.final_output,
             tokens: record.totals.tokens,
             gated,
+            spend: Default::default(),
         })
     }
 }

crates/cm-api/src/swarm.rs

@@ -86,6 +86,7 @@ fn step(
         output: output.into(),
         gated: Vec::new(),
         tokens: 0,
+        spend: Default::default(),
     }
 }
 

crates/cm-api/src/topology_exec.rs

@@ -683,6 +683,7 @@ impl ZeroClawDriveExecutor {
     {
         let mut output = String::new();
         let mut tokens: u64 = 0;
+        let mut spend = cm_orchestrator::Spend::default();
         let mut gated: Vec<GatedAction> = Vec::new();
         let mut trace = ToolTrace::default();
 
@@ -720,6 +721,23 @@ impl ZeroClawDriveExecutor {
                             let input = v.get("input_tokens").and_then(|n| n.as_u64()).unwrap_or(0);
                             let out = v.get("output_tokens").and_then(|n| n.as_u64()).unwrap_or(0);
                             tokens = input + out;
+                            // The frame has always carried these; only
+                            // `tokens` was read, so every agent turn was
+                            // charged with no record of who was paid.
+                            spend = cm_orchestrator::Spend {
+                                input_tokens: input,
+                                output_tokens: out,
+                                provider: v
+                                    .get("provider")
+                                    .and_then(|p| p.as_str())
+                                    .filter(|p| !p.is_empty())
+                                    .map(str::to_string),
+                                model: v
+                                    .get("model")
+                                    .and_then(|m| m.as_str())
+                                    .filter(|m| !m.is_empty())
+                                    .map(str::to_string),
+                            };
                             break;
                         }
                         "approval_request" => {
@@ -807,6 +825,7 @@ impl ZeroClawDriveExecutor {
                 output: output.trim().to_string(),
                 tokens,
                 gated,
+                spend,
             },
             trace,
         ))
@@ -968,7 +987,10 @@ mod tests {
             json!({"type": "session_start", "session_id": "s1", "resumed": false}),
             json!({"type": "chunk", "content": "hel"}),
             json!({"type": "chunk", "content": "lo"}),
-            json!({"type": "done", "input_tokens": 5, "output_tokens": 7}),
+            // The real frame carries model and provider; the executor read
+            // only the two token counts until 2026-09-14.
+            json!({"type": "done", "input_tokens": 5, "output_tokens": 7,
+                   "model": "claude-sonnet-5", "provider": "anthropic"}),
         ]
     }
 
@@ -1068,6 +1090,16 @@ mod tests {
         let out = exec.run_turn(req()).await.unwrap();
         assert_eq!(out.output, "hello");
         assert_eq!(out.tokens, 12);
+        assert_eq!(
+            out.spend,
+            cm_orchestrator::Spend {
+                input_tokens: 5,
+                output_tokens: 7,
+                provider: Some("anthropic".into()),
+                model: Some("claude-sonnet-5".into()),
+            },
+            "the split and the provider must survive the done frame, not just the sum"
+        );
         assert!(out.gated.is_empty());
     }
 

crates/cm-api/src/topology_worker.rs

@@ -556,16 +556,35 @@ async fn drive<E: TurnExecutor>(
                 }
                 if let Some(agent_id) = agent_of.get(&last.node_id).copied() {
                     if last.tokens > 0 {
-                        // The executor reports ONE total, not an in/out split.
-                        // Credits price the sum, so cost is right; the columns
-                        // record it as output rather than inventing a split.
+                        // The split and the provider come from the runtime's
+                        // `done` frame via `StepRecord.spend`. An executor
+                        // that reports only a total leaves the split at 0/0
+                        // and the total goes on the output side, as before.
+                        let (tin, tout) = if last.spend.input_tokens + last.spend.output_tokens > 0
+                        {
+                            (last.spend.input_tokens, last.spend.output_tokens)
+                        } else {
+                            (0, last.tokens as u64)
+                        };
+                        let mission_id: Option<Uuid> = sqlx::query_scalar::<_, Option<Uuid>>(
+                            "SELECT mission_id FROM topology_runs WHERE id = $1",
+                        )
+                        .bind(id)
+                        .fetch_optional(&pool)
+                        .await
+                        .ok()
+                        .flatten()
+                        .flatten();
                         if let Err(e) = cm_billing::charge(
                             &pool,
                             cm_domain::WorkspaceId::from(workspace_id),
                             cm_domain::AgentId::from(agent_id),
                             None,
-                            0,
-                            last.tokens as u64,
+                            tin,
+                            tout,
+                            last.spend.provider.as_deref(),
+                            last.spend.model.as_deref(),
+                            mission_id,
                         )
                         .await
                         {

crates/cm-billing/src/lib.rs

@@ -36,21 +36,36 @@ pub async fn charge(
     run_id: Option<Uuid>,
     input_tokens: u64,
     output_tokens: u64,
+    // Who was paid, and for which mission. `None` where the executor did not
+    // say. Until 2026-09-14 no agent-side row carried these, so the larger
+    // half of the spend could not be asked per provider — the judge's half
+    // could, and that is how a plan emptying twice went unexplained.
+    provider: Option<&str>,
+    model: Option<&str>,
+    mission_id: Option<Uuid>,
 ) -> Result<i64, BillingError> {
     let owed = credits_for_tokens(input_tokens + output_tokens);
     let mut tx = pool.begin().await?;
 
-    sqlx::query!(
+    // `sqlx::query`, not `query!`: the macro pins this statement to offline
+    // metadata that a schema change then has to regenerate against a live
+    // database, and the columns added by migration 0085 are nullable text
+    // and uuid — nothing here that a compile-time check would catch.
+    sqlx::query(
         "INSERT INTO usage_events
-            (workspace_id, agent_id, run_id, kind, tokens_in, tokens_out, credits)
-         VALUES ($1, $2, $3, 'llm_tokens', $4, $5, $6)",
-        workspace_id.as_uuid(),
-        agent_id.as_uuid(),
-        run_id,
-        input_tokens as i64,
-        output_tokens as i64,
-        sqlx::types::BigDecimal::from(owed),
+            (workspace_id, agent_id, run_id, kind, tokens_in, tokens_out, credits,
+             provider, model, mission_id)
+         VALUES ($1, $2, $3, 'llm_tokens', $4, $5, $6, $7, $8, $9)",
     )
+    .bind(workspace_id.as_uuid())
+    .bind(agent_id.as_uuid())
+    .bind(run_id)
+    .bind(input_tokens as i64)
+    .bind(output_tokens as i64)
+    .bind(sqlx::types::BigDecimal::from(owed))
+    .bind(provider)
+    .bind(model)
+    .bind(mission_id)
     .execute(&mut *tx)
     .await?;
 

crates/cm-billing/tests/billing.rs

@@ -62,7 +62,7 @@ async fn charges_span_lots_oldest_first_and_record_usage() {
         .unwrap();
 
     // 2500 tokens → 3 credits: drains the first lot (2) then one more.
-    let deducted = charge(&pool, ws.id, agent.id, Some(run_id), 1500, 1000)
+    let deducted = charge(&pool, ws.id, agent.id, Some(run_id), 1500, 1000, None, None, None)
         .await
         .unwrap();
     assert_eq!(deducted, 3);
@@ -96,7 +96,7 @@ async fn an_empty_workspace_records_usage_but_clamps_at_zero() {
         .unwrap();
 
     // Owes 5, only 1 available: deducts 1, balance hits zero, never negative.
-    let deducted = charge(&pool, ws.id, agent.id, Some(run_id), 4000, 500)
+    let deducted = charge(&pool, ws.id, agent.id, Some(run_id), 4000, 500, None, None, None)
         .await
         .unwrap();
     assert_eq!(deducted, 1);

crates/cm-orchestrator/src/evolve.rs

@@ -145,6 +145,7 @@ mod tests {
                 output: format!("{}<{}>", req.role, req.context.join("|")),
                 tokens: 10,
                 gated: vec![],
+                spend: Default::default(),
             })
         }
     }

crates/cm-orchestrator/src/harness.rs

@@ -147,6 +147,7 @@ mod tests {
                 output: format!("{}:{}", req.role, req.context.join(" ")),
                 tokens: 10,
                 gated,
+                spend: Default::default(),
             })
         }
     }

crates/cm-orchestrator/src/lib.rs

@@ -95,15 +95,35 @@ pub struct TurnRequest {
     pub context: Vec<String>,
 }
 
+/// What a turn cost and who was paid — the part of the runtime's `done` frame
+/// that `tokens` alone threw away.
+///
+/// `tokens` stayed as the one total every reader already keys on. This is
+/// the split beside it, plus the provider and model that answered, so the
+/// spend can be asked per provider BEFORE a plan limit asks it for you. Judge
+/// spend gained this on 2026-09-14 and agent spend did not, which left the
+/// larger of the two invisible.
+#[derive(Debug, Clone, Default, PartialEq, Eq, Serialize, Deserialize)]
+pub struct Spend {
+    pub input_tokens: u64,
+    pub output_tokens: u64,
+    /// Provider family that answered (`anthropic`, `glm`, …), when the
+    /// runtime said. `None` on executors that do not report one.
+    pub provider: Option<String>,
+    pub model: Option<String>,
+}
+
 /// The result of a single agent turn.
 #[derive(Debug, Clone)]
 pub struct TurnOutcome {
     /// The turn's textual output.
     pub output: String,
-    /// Model tokens spent (cost proxy).
+    /// Model tokens spent (cost proxy). Input + output.
     pub tokens: u64,
     /// Any sandbox-leaving actions attempted during the turn.
     pub gated: Vec<GatedAction>,
+    /// The split and the provider behind `tokens`.
+    pub spend: Spend,
 }
 
 /// Runs one safe agent turn. The real impl wraps `cm-runtime::Runtime`
@@ -143,6 +163,10 @@ pub struct StepRecord {
     pub gated: Vec<GatedAction>,
     /// Tokens it spent.
     pub tokens: u64,
+    /// The split and provider behind `tokens`. `default` so checkpoints
+    /// journaled before this field existed still load.
+    #[serde(default)]
+    pub spend: Spend,
 }
 
 /// The full record of a topology run (journal + final output + totals).
@@ -264,6 +288,7 @@ where
             output: outcome.output,
             gated: outcome.gated,
             tokens: outcome.tokens,
+            spend: outcome.spend,
         });
 
         // Hand the caller a durable snapshot to persist before the next turn.
@@ -309,6 +334,7 @@ mod tests {
                 output: format!("{}({})<{}>", req.role, req.node_id, req.context.join("|")),
                 tokens: 10,
                 gated,
+                spend: Default::default(),
             })
         }
     }
@@ -383,6 +409,7 @@ mod tests {
                     output: format!("{}({})<{}>", req.role, req.node_id, req.context.join("|")),
                     tokens: 10,
                     gated: vec![],
+                    spend: Default::default(),
                 })
             }
         }

crates/cm-orchestrator/src/provider_executor.rs

@@ -89,6 +89,7 @@ impl TurnExecutor for ProviderExecutor {
             tokens,
             // Tool-free reasoning turns leave the sandbox nowhere.
             gated: vec![],
+            spend: Default::default(),
         })
     }
 }

crates/cm-orchestrator/src/workflow.rs

@@ -74,6 +74,7 @@ mod tests {
                 output: format!("{}<{}>", req.node_id, req.context.join("|")),
                 tokens: 5,
                 gated: vec![],
+                spend: Default::default(),
             })
         }
     }

crates/cm-runtime/src/runtime.rs

@@ -875,6 +875,13 @@ impl Runtime {
         );
         // Meter the run (§8.4). Billing failures never fail the run — the
         // usage ledger is the recovery path.
+        // This loop drives ONE provider with no fallback chain, so the model
+        // the request named is the model that answered. The family is taken
+        // only from an explicit `provider:` prefix — a bare model name is
+        // recorded as-is with no family rather than guessed at, and a chat
+        // run is not a mission.
+        let model = state.request.model.as_str();
+        let provider = model.split_once(':').map(|(p, _)| p);
         if let Err(error) = cm_billing::charge(
             &self.inner.pool,
             state.workspace_id,
@@ -882,6 +889,9 @@ impl Runtime {
             Some(run_id),
             state.input_tokens,
             state.output_tokens,
+            provider,
+            Some(model),
+            None,
         )
         .await
         {