feat: add review effort accounting and budget governor

pilot/README-langfuse.md

@@ -27,6 +27,11 @@ pair to rotate instead of two. Tags carry the finer cut:
 `provider:headroom`, `model:<bare>`, `engine:opencode`, `repo:<owner/name>`,
 `lens:<id>` per fan-out lens.
 
+Each trace metadata record also includes the completed iteration count, tool
+calls, per-iteration token details, and whether a configured budget stopped the
+run. A capped run is tagged in the review body and can be filtered in Langfuse
+with `cap_hit` / `cap_reason` metadata.
+
 To split into two *projects* later, point `LANGFUSE_PUBLIC_KEY` /
 `LANGFUSE_SECRET_KEY` at the second project on whichever deployment runs the
 Claude path. Nothing in the code needs to change.

pilot/README-webhook.md

@@ -272,6 +272,14 @@ Set `.pr-review.json: "reviewers": []` to opt out (single-primary fallback).
     { "id": "my-lens",  "agent_file": ".opencode/agents/my-lens.md", "model": "headroom/glm-5.2:cloud" }
   ],
   "triage": { "enabled": true, "max_lenses": 4 },
+  "budget": {
+    "max_steps": 20,
+    "max_total_tokens": 120000,
+    "max_output_tokens": 20000,
+    "max_duration_seconds": 480,
+    "max_lenses": 4,
+    "max_equivalent_cost_usd": 1.00
+  },
   "max_findings": 7
 }
 ```
@@ -285,9 +293,19 @@ files. Fail-open: if triage errors, all lenses run.
 | var | default | effect |
 |-----|---------|--------|
 | `PRAGENT_MAX_PARALLEL_LENSES` | 4 | cap concurrency |
+| `PRAGENT_MAX_REVIEW_STEPS` | 20 | maximum completed model iterations per review |
+| `PRAGENT_MAX_REVIEW_TOKENS` | 120000 | maximum cumulative tokens per review |
+| `PRAGENT_MAX_REVIEW_OUTPUT_TOKENS` | 20000 | maximum generated tokens per review |
+| `PRAGENT_REVIEW_TIMEOUT` | 480 | maximum review duration (s) |
 | `PRAGENT_LENS_TIMEOUT` | 540 | per-lens subprocess timeout (s) |
 | `PRAGENT_REVIEWERS` | unset | force multi-lens fan-out even without `reviewers[]` |
 
+Budget limits can also be set per repository in the trusted base-branch
+`.pr-review.json`. The process terminates after a completed iteration crosses a
+limit, preserves any output already emitted, and records the cap reason in the
+review body and Langfuse metadata. Environment variables provide deployment-wide
+defaults; repository budget values override them.
+
 **Cross-lens dedup:** synthesiser drops duplicates by
 `sha256[:16](path|line|severity|problem[:80])` (matches the feedback DB's
 `posthash`), then promotes multi-lens agreement by one severity step

pilot/README.md

@@ -74,6 +74,9 @@ security, and webhook registration details.
 | `PRAGENT_ENGINE` | `opencode` | `opencode` or legacy model path |
 | `DIFF_MAX_CHARS` | `150000` | Diff input cap |
 | `PRAGENT_MAX_CONCURRENT_REVIEWS` | `2` | Process concurrency bound |
+| `PRAGENT_MAX_REVIEW_STEPS` | `20` | Maximum completed model iterations per review |
+| `PRAGENT_MAX_REVIEW_TOKENS` | `120000` | Maximum cumulative tokens per review |
+| `PRAGENT_MAX_REVIEW_OUTPUT_TOKENS` | `20000` | Maximum generated tokens per review |
 | `LANGFUSE_HOST` + keys | unset | Enables telemetry; unset is a no-op |
 
 ## Tests

pilot/observability/langfuse.py

@@ -249,6 +249,11 @@ def build_batch(
         tags.append(f"tier:{tier}")
     for lens in lenses or []:
         tags.append(f"lens:{lens}")
+    if usage.get("budget_cap_hit"):
+        tags.extend([
+            "budget:capped",
+            f"budget:{usage.get('budget_cap_reason', 'unknown')}",
+        ])
 
     costs, cost_basis = _cost_details(usage, model, price_target) if usage else ({}, "")
     if cost_basis:
@@ -267,7 +272,19 @@ def build_batch(
         "severities": _severity_counts(findings),
         "provider_cost_usd": usage.get("cost"),
         "cost_basis": cost_basis or None,
+        "iterations": usage.get("steps"),
+        "tool_calls": usage.get("tool_calls"),
+        "cap_hit": usage.get("budget_cap_hit"),
+        "cap_reason": usage.get("budget_cap_reason"),
+        "tokens_per_finding": round(
+            float(usage.get("total") or 0) / max(1, len(findings or [])), 2
+        ),
+        "steps_per_finding": round(
+            float(usage.get("steps") or 0) / max(1, len(findings or [])), 2
+        ),
     }
+    if usage.get("iterations"):
+        metadata["iteration_usage"] = usage["iterations"][:50]
     if lenses:
         metadata["lenses"] = lenses
     if tier:

pilot/review/budget.py

@@ -0,0 +1,142 @@
+"""Trusted review budget policy and thread-safe accounting."""
+
+from __future__ import annotations
+
+import os
+import threading
+import time
+from dataclasses import dataclass
+
+
+DEFAULTS = {
+    "max_steps": 20,
+    "max_total_tokens": 120_000,
+    "max_output_tokens": 20_000,
+    "max_duration_seconds": 480,
+}
+
+
+@dataclass(frozen=True)
+class Budget:
+    max_steps: int = DEFAULTS["max_steps"]
+    max_total_tokens: int = DEFAULTS["max_total_tokens"]
+    max_output_tokens: int = DEFAULTS["max_output_tokens"]
+    max_duration_seconds: int = DEFAULTS["max_duration_seconds"]
+    max_lenses: int = 4
+    max_equivalent_cost_usd: float | None = None
+    price_target: str = "claude-sonnet-5"
+
+    @classmethod
+    def from_config(cls, config: dict | None) -> "Budget":
+        values = dict(DEFAULTS)
+        values["max_lenses"] = _env_int("PRAGENT_MAX_PARALLEL_LENSES", 4)
+        env_map = {
+            "max_steps": "PRAGENT_MAX_REVIEW_STEPS",
+            "max_total_tokens": "PRAGENT_MAX_REVIEW_TOKENS",
+            "max_output_tokens": "PRAGENT_MAX_REVIEW_OUTPUT_TOKENS",
+            "max_duration_seconds": "PRAGENT_REVIEW_TIMEOUT",
+            "max_lenses": "PRAGENT_MAX_PARALLEL_LENSES",
+        }
+        for key, env_key in env_map.items():
+            if env_key in os.environ:
+                value = _env_int(env_key, values[key])
+                if value > 0:
+                    values[key] = value
+        raw = (config or {}).get("budget")
+        if isinstance(raw, dict):
+            for key in set(DEFAULTS) | {"max_lenses", "max_equivalent_cost_usd"}:
+                if key in raw:
+                    values[key] = raw[key]
+        cost = values.get("max_equivalent_cost_usd")
+        price_target = str(
+            (config or {}).get("cost_target")
+            or os.environ.get("PRAGENT_PRICE_TARGET")
+            or "claude-sonnet-5"
+        )
+        return cls(
+            max_steps=int(values["max_steps"]),
+            max_total_tokens=int(values["max_total_tokens"]),
+            max_output_tokens=int(values["max_output_tokens"]),
+            max_duration_seconds=int(values["max_duration_seconds"]),
+            max_lenses=int(values["max_lenses"]),
+            max_equivalent_cost_usd=float(cost) if cost is not None else None,
+            price_target=price_target,
+        )
+
+
+def _env_int(name: str, default: int) -> int:
+    try:
+        return int(os.environ.get(name, default))
+    except (TypeError, ValueError):
+        return default
+
+
+class BudgetState:
+    """Cumulative accounting shared by all subprocesses in one review."""
+
+    def __init__(self, budget: Budget):
+        self.budget = budget
+        self.started = time.monotonic()
+        self.steps = 0
+        self.total_tokens = 0
+        self.output_tokens = 0
+        self.equivalent_cost_usd = 0.0
+        self.cap_reason = ""
+        self._lock = threading.RLock()
+
+    def record(self, usage: dict, equivalent_cost_usd: float = 0.0) -> str:
+        with self._lock:
+            self.steps += int(usage.get("steps") or 0)
+            self.total_tokens += int(usage.get("total") or 0)
+            self.output_tokens += int(usage.get("output") or 0)
+            self.equivalent_cost_usd += equivalent_cost_usd
+            reason = self.reason()
+            if reason:
+                self.cap_reason = reason
+            return reason
+
+    def reason(self) -> str:
+        with self._lock:
+            if self.steps >= self.budget.max_steps:
+                return "max_steps"
+            if self.total_tokens >= self.budget.max_total_tokens:
+                return "max_total_tokens"
+            if self.output_tokens >= self.budget.max_output_tokens:
+                return "max_output_tokens"
+            if time.monotonic() - self.started >= self.budget.max_duration_seconds:
+                return "max_duration_seconds"
+            if (
+                self.budget.max_equivalent_cost_usd is not None
+                and self.equivalent_cost_usd >= self.budget.max_equivalent_cost_usd
+            ):
+                return "max_equivalent_cost_usd"
+            return ""
+
+    def snapshot(self) -> dict:
+        with self._lock:
+            return {
+                "steps": self.steps,
+                "total_tokens": self.total_tokens,
+                "output_tokens": self.output_tokens,
+                "equivalent_cost_usd": round(self.equivalent_cost_usd, 6),
+                "cap_hit": bool(self.cap_reason),
+                "cap_reason": self.cap_reason or None,
+            }
+
+
+def equivalent_cost(usage: dict, model: str, price_target: str = "") -> float:
+    """Estimate comparison cost for one completed iteration."""
+    try:
+        from cost_model import PRICES, Usage, cost
+        target = price_target or os.environ.get("PRAGENT_PRICE_TARGET", "claude-sonnet-5")
+        price = PRICES.get(target)
+        if price is None:
+            return 0.0
+        return cost(Usage(
+            uncached_input=max(0, int(usage.get("input") or 0) - int(usage.get("cache_read") or 0)),
+            cached_input=int(usage.get("cache_read") or 0),
+            cache_writes=int(usage.get("cache_write") or 0),
+            output=int(usage.get("output") or 0),
+        ), price)
+    except Exception:
+        return 0.0

pilot/review/configuration.py

@@ -25,6 +25,11 @@ CONFIG_MAX_INSTRUCTIONS_CHARS = 4000
 CONFIG_MAX_PATTERNS_ITEMS = 16  # allow + deny separately, total 32 entries
 CONFIG_MAX_FINDINGS = 30
 CONFIG_MAX_STATIC_MESSAGE_CHARS = 400  # free-text banner, mirror of instructions
+MAX_BUDGET_STEPS = 100
+MAX_BUDGET_TOKENS = 2_000_000
+MAX_BUDGET_SECONDS = 3_600
+MAX_BUDGET_LENSES = 8
+MAX_BUDGET_COST_USD = 100.0
 
 STYLES = frozenset(STYLE_DEFAULTS)
 SEVERITY_VALUES = frozenset(SEVERITIES)
@@ -49,6 +54,8 @@ def parse_repo_config(raw: str) -> dict:
       patterns       {allow:[…], deny:[…]}              — post-filter globs
       model          <key of cost_model.PRICES>          — per-repo override
       cost_target    <key of cost_model.PRICES>          — see equivalent_cost
+      budget         {max_steps, max_total_tokens, max_output_tokens,
+                      max_duration_seconds, max_lenses, max_equivalent_cost_usd}
       additional_context_urls   list[str] (≤ 8)          — see fetch_additional_context
     """
     if not raw:
@@ -193,6 +200,45 @@ def parse_repo_config(raw: str) -> dict:
         if cleaned:
             out["compare_against"] = cleaned[:12]
 
+    budget = _parse_budget(data.get("budget"))
+    if budget:
+        out["budget"] = budget
+
+    return out
+
+
+def _parse_budget(raw) -> dict:
+    """Sanitize optional per-review resource limits from trusted config."""
+    if not isinstance(raw, dict):
+        return {}
+    out: dict = {}
+    integer_limits = {
+        "max_steps": (1, MAX_BUDGET_STEPS),
+        "max_total_tokens": (1, MAX_BUDGET_TOKENS),
+        "max_output_tokens": (1, MAX_BUDGET_TOKENS),
+        "max_duration_seconds": (1, MAX_BUDGET_SECONDS),
+        "max_lenses": (1, MAX_BUDGET_LENSES),
+    }
+    for key, (lo, hi) in integer_limits.items():
+        value = raw.get(key)
+        if isinstance(value, int) and not isinstance(value, bool):
+            if lo <= value <= hi:
+                out[key] = value
+        elif isinstance(value, str) and value.strip().isdigit():
+            number = int(value.strip())
+            if lo <= number <= hi:
+                out[key] = number
+    cost = raw.get("max_equivalent_cost_usd")
+    if isinstance(cost, (int, float)) and not isinstance(cost, bool):
+        if 0 < float(cost) <= MAX_BUDGET_COST_USD:
+            out["max_equivalent_cost_usd"] = float(cost)
+    elif isinstance(cost, str):
+        try:
+            number = float(cost.strip())
+        except ValueError:
+            number = 0
+        if 0 < number <= MAX_BUDGET_COST_USD:
+            out["max_equivalent_cost_usd"] = number
     return out
 
 

pilot/review/opencode.py

@@ -73,6 +73,7 @@ from .opencode_lenses import (
     filter_by_skip_if, intersect_with_triage, merge_usage, run_lenses,
 )
 from . import opencode_runtime as _runtime
+from .budget import Budget, BudgetState
 _filter_by_skip_if = filter_by_skip_if
 _intersect_with_triage = intersect_with_triage
 
@@ -112,7 +113,7 @@ def _new_usage() -> dict:
     return {
         "input": 0, "output": 0, "reasoning": 0,
         "cache_read": 0, "cache_write": 0, "total": 0,
-        "cost": 0.0, "steps": 0,
+        "cost": 0.0, "steps": 0, "tool_calls": 0, "iterations": [],
     }
 
 
@@ -146,6 +147,8 @@ def parse_opencode_events(stdout: str) -> tuple[str, dict | None]:
             continue
         etype = ev.get("type")
         part = ev.get("part") or {}
+        if etype in ("tool_use", "tool_result", "tool_call"):
+            usage["tool_calls"] += 1
         if etype == "text" and isinstance(part, dict):
             t = part.get("text")
             if isinstance(t, str):
@@ -166,6 +169,18 @@ def parse_opencode_events(stdout: str) -> tuple[str, dict | None]:
                 cost = part.get("cost")
                 if isinstance(cost, (int, float)):
                     usage["cost"] += float(cost)
+                usage["iterations"].append({
+                    "step": usage["steps"],
+                    "input": int(tok.get("input") or 0),
+                    "output": int(tok.get("output") or 0),
+                    "reasoning": int(tok.get("reasoning") or 0),
+                    "cache_read": int((cache or {}).get("read") or 0)
+                    if isinstance(cache, dict) else 0,
+                    "cache_write": int((cache or {}).get("write") or 0)
+                    if isinstance(cache, dict) else 0,
+                    "total": int(tok.get("total") or 0),
+                    "cost": float(cost) if isinstance(cost, (int, float)) else 0.0,
+                })
     return "".join(text_parts), (usage if saw_step else None)
 
 _PROMPT = (
@@ -299,6 +314,17 @@ def _balanced_jsons(text: str):
                     start = None
 
 
+def _run_process(
+    cmd, *, cwd, env, timeout, parse_events, budget=None, budget_state=None,
+    model="",
+):
+    return _runtime._run_process(
+        cmd, cwd=cwd, env=env, timeout=timeout, parse_events=parse_events,
+        budget=budget, budget_state=budget_state, model=model,
+        runner=subprocess.run,
+    )
+
+
 
 
 def triage(
@@ -307,6 +333,8 @@ def triage(
     reviewers: list[ReviewerSpec],
     default_model: str,
     factory_root: str,
+    budget: Budget | None = None,
+    budget_state: BudgetState | None = None,
 ) -> list[str] | None:
     """Run the triage agent. Returns the lens subset with surface.
 
@@ -344,9 +372,10 @@ def triage(
         prompt,
     ]
     try:
-        proc = subprocess.run(
-            cmd, cwd=workdir, env=env, capture_output=True, text=True,
-            stdin=subprocess.DEVNULL, timeout=120,
+        proc = _run_process(
+            cmd, cwd=workdir, env=env, timeout=min(120, budget.max_duration_seconds)
+            if budget else 120, parse_events=parse_opencode_events,
+            budget=budget, budget_state=budget_state, model=default_model,
         )
     except (subprocess.TimeoutExpired, Exception) as e:
         print(f"pragent: triage crashed: {e}; falling back to all lenses", flush=True)
@@ -401,6 +430,8 @@ def run_lenses_review(
     model: str,
     compression_note: str = "",
     additional_context: str = "",
+    budget: Budget | None = None,
+    budget_state: BudgetState | None = None,
 ) -> tuple[str, dict | None]:
     """Fan-out + synthesize path. Returns (merged-text, merged-usage).
 
@@ -409,6 +440,8 @@ def run_lenses_review(
     always has: prose + a final ```json fence with the legacy schema).
     """
     os.makedirs(WORK_ROOT, exist_ok=True)
+    budget = budget or Budget.from_config(config)
+    budget_state = budget_state or BudgetState(budget)
     workdir = tempfile.mkdtemp(prefix=f"{repo.replace('/', '_')}-{sha[:8]}-", dir=WORK_ROOT)
     keep = bool(os.environ.get("PRAGENT_KEEP_WORK"))
     t0 = time.monotonic()
@@ -429,14 +462,16 @@ def run_lenses_review(
             # Edge case: reviewers[] present but every entry had activation:off.
             # Fall back to single-primary.
             return _fallback_single_primary(
-                workdir=workdir, model=model,
+                workdir=workdir, model=model, budget=budget,
+                budget_state=budget_state,
             )
 
         triage_cfg = parse_triage_config((config or {}).get("triage"))
         changed_paths = changed_files(diff)
-        reviewers = _filter_by_skip_if(reviewers, changed_paths)
+        reviewers = _filter_by_skip_if(reviewers, changed_paths)[:budget.max_lenses]
         selected = triage(
             workdir, triage_cfg, reviewers, model, _factory_dir(),
+            budget=budget, budget_state=budget_state,
         )
         if selected is not None:
             if not selected:
@@ -453,12 +488,15 @@ def run_lenses_review(
             return _no_surface_response(repo, index, sha, 0)
 
         factory_root = _factory_dir()
-        results = run_lenses(workdir, reviewers, model, factory_root)
+        results = run_lenses(
+            workdir, reviewers, model, factory_root, budget, budget_state,
+        )
 
         # Merge findings + usage across lenses
         findings_per_lens = {lid: r[0] for lid, r in results.items()}
         merged = synthesize(findings_per_lens, reviewers)
         merged_usage = merge_usage([r[1] for r in results.values()])
+        merged_usage.update({f"budget_{k}": v for k, v in budget_state.snapshot().items()})
 
         # Build a synthetic text response that ai_review.parse_review_output
         # can consume (prose summary + final ```json fence with legacy schema).
@@ -543,10 +581,15 @@ def _no_surface_response(
     return text, None
 
 
-def _fallback_single_primary(workdir: str, model: str) -> tuple[str, dict | None]:
+def _fallback_single_primary(
+    workdir: str, model: str, budget: Budget | None = None,
+    budget_state: BudgetState | None = None,
+) -> tuple[str, dict | None]:
     """Used when reviewers[] resolves to empty (all activation:off)."""
     try:
-        text, usage = run_opencode(workdir, model)
+        text, usage = run_opencode(
+            workdir, model, budget=budget, budget_state=budget_state,
+        )
         return text, usage
     except Exception as e:
         print(f"pragent: fallback single-primary failed: {e}", flush=True)
@@ -576,12 +619,14 @@ def _warm_opencode(home: str, model: str) -> None:
 
 def run_opencode(
     workdir: str, model: str, timeout: int | None = None,
+    budget: Budget | None = None, budget_state: BudgetState | None = None,
 ) -> tuple[str, dict | None]:
     return _runtime.run_opencode(
         workdir, model, opencode_bin=_opencode_bin(),
         shared_home_fn=_shared_home, warm_fn=_warm_opencode,
         build_environment=_build_env, parse_events=parse_opencode_events,
-        prompt=_PROMPT, timeout=timeout or TIMEOUT, runner=subprocess.run,
+        prompt=_PROMPT, timeout=timeout or TIMEOUT, budget=budget,
+        budget_state=budget_state, runner=subprocess.run,
     )
 
 
@@ -642,6 +687,8 @@ def run(
             additional_context=additional_context,
         )
 
+    budget = Budget.from_config(config)
+    budget_state = BudgetState(budget)
     os.makedirs(WORK_ROOT, exist_ok=True)
     workdir = tempfile.mkdtemp(prefix=f"{repo.replace('/', '_')}-{sha[:8]}-", dir=WORK_ROOT)
     keep = bool(os.environ.get("PRAGENT_KEEP_WORK"))
@@ -663,7 +710,9 @@ def run(
             additional_context=additional_context,
         )
         drop_factory(workdir)
-        text, usage = run_opencode(workdir, model)
+        text, usage = run_opencode(
+            workdir, model, budget=budget, budget_state=budget_state,
+        )
         if not text.strip():
             raise RuntimeError("opencode produced no output")
         if usage is not None:

pilot/review/opencode_lenses.py

@@ -7,7 +7,7 @@ from .opencode_synthesis import _normalize_lens_finding
 LENS_TIMEOUT_S = 540
 
 
-def _run_one_lens(workdir, spec, model, factory_root):
+def _run_one_lens(workdir, spec, model, factory_root, budget=None, budget_state=None):
     """Run one lens through the compatibility module's runtime seam."""
     from . import opencode as oc
 
@@ -28,9 +28,12 @@ def _run_one_lens(workdir, spec, model, factory_root):
         "--agent", spec.id, "--dir", workdir, "--model", model, prompt,
     ]
     try:
-        proc = oc.subprocess.run(
-            cmd, cwd=workdir, env=env, capture_output=True, text=True,
-            stdin=oc.subprocess.DEVNULL, timeout=LENS_TIMEOUT_S,
+        proc = oc._run_process(
+            cmd, cwd=workdir, env=env,
+            timeout=min(LENS_TIMEOUT_S, budget.max_duration_seconds)
+            if budget else LENS_TIMEOUT_S,
+            parse_events=oc.parse_opencode_events, budget=budget,
+            budget_state=budget_state, model=model,
         )
     except oc.subprocess.TimeoutExpired:
         print(f"pragent: lens {spec.id} timed out after {LENS_TIMEOUT_S}s", flush=True)
@@ -69,7 +72,7 @@ def _run_one_lens(workdir, spec, model, factory_root):
     return normalized, usage, spec.id
 
 
-def run_lenses(workdir, reviewers, default_model, factory_root):
+def run_lenses(workdir, reviewers, default_model, factory_root, budget=None, budget_state=None):
     """Run configured lenses in parallel and return results by lens id."""
     if not reviewers:
         return {}
@@ -81,7 +84,7 @@ def run_lenses(workdir, reviewers, default_model, factory_root):
         futures = {
             ex.submit(
                 _run_one_lens, workdir, spec,
-                spec.model or default_model, factory_root,
+                spec.model or default_model, factory_root, budget, budget_state,
             ): spec
             for spec in reviewers
         }
@@ -131,5 +134,5 @@ def merge_usage(parts):
         for key in base:
             if isinstance(base[key], (int, float)):
                 base[key] += usage.get(key, 0) or 0
+        base["iterations"].extend(usage.get("iterations", []) or [])
     return base
-

pilot/review/opencode_runtime.py

@@ -2,6 +2,9 @@
 
 import os
 import subprocess
+import time
+
+from .budget import Budget, BudgetState, equivalent_cost
 
 
 _ENV_ALLOW = frozenset({
@@ -66,6 +69,7 @@ def warm_opencode(
 def run_opencode(
     workdir, model, *, opencode_bin, shared_home_fn, warm_fn,
     build_environment, parse_events, prompt, timeout,
+    budget: Budget | None = None, budget_state: BudgetState | None = None,
     runner=subprocess.run,
 ):
     home = shared_home_fn()
@@ -78,19 +82,107 @@ def run_opencode(
     last_err = ""
     for _ in range(2):
         try:
-            proc = runner(
-                cmd, cwd=workdir, env=env, capture_output=True, text=True,
-                stdin=subprocess.DEVNULL, timeout=timeout,
+            proc = _run_process(
+                cmd, cwd=workdir, env=env, timeout=timeout,
+                parse_events=parse_events, budget=budget,
+                budget_state=budget_state, model=model, runner=runner,
             )
         except subprocess.TimeoutExpired as exc:
             last_err = f"opencode timed out after {exc.timeout}s"
             continue
         text, usage = parse_events(proc.stdout or "")
+        if usage and budget_state:
+            usage.update({f"budget_{k}": v for k, v in budget_state.snapshot().items()})
         if text.strip():
             return text, usage
+        if budget_state and budget_state.cap_reason:
+            reason = budget_state.cap_reason
+            empty_usage = usage or {
+                "input": 0, "output": 0, "reasoning": 0,
+                "cache_read": 0, "cache_write": 0, "total": 0,
+                "cost": 0.0, "steps": 0, "tool_calls": 0, "iterations": [],
+            }
+            empty_usage.update({
+                f"budget_{k}": v for k, v in budget_state.snapshot().items()
+            })
+            return (
+                "Review stopped before a complete response was produced "
+                f"because the budget reached {reason}.\n\n"
+                "```json\n{\"summary\": \"Review budget reached\", "
+                "\"findings\": []}\n```\n",
+                empty_usage,
+            )
+        if usage and usage.get("budget_cap_hit"):
+            return text, usage
         last_err = (
             f"opencode empty text (rc={proc.returncode}); "
             f"stderr: {(proc.stderr or '')[-1500:]}"
         )
     raise RuntimeError(last_err or "opencode produced no output")
 
+
+def _run_process(
+    cmd, *, cwd, env, timeout, parse_events, budget, budget_state, model, runner,
+):
+    """Run a process, terminating it after a completed event exceeds budget."""
+    if budget is None or budget_state is None:
+        return runner(
+            cmd, cwd=cwd, env=env, capture_output=True, text=True,
+            stdin=subprocess.DEVNULL, timeout=timeout,
+        )
+    existing_reason = budget_state.reason()
+    if existing_reason:
+        budget_state.cap_reason = existing_reason
+        return subprocess.CompletedProcess(cmd, 0, "", "")
+    proc = subprocess.Popen(
+        cmd, cwd=cwd, env=env, stdout=subprocess.PIPE, stderr=subprocess.PIPE,
+        stdin=subprocess.DEVNULL, text=True,
+    )
+    output: list[str] = []
+    previous = {"steps": 0, "total": 0, "output": 0, "cost": 0.0}
+    cap_reason = ""
+    started = time.monotonic()
+    try:
+        assert proc.stdout is not None
+        for line in proc.stdout:
+            output.append(line)
+            _, usage = parse_events("".join(output))
+            if usage:
+                delta = {
+                    "steps": usage.get("steps", 0) - previous["steps"],
+                    "input": usage.get("input", 0) - previous.get("input", 0),
+                    "cache_read": usage.get("cache_read", 0) - previous.get("cache_read", 0),
+                    "cache_write": usage.get("cache_write", 0) - previous.get("cache_write", 0),
+                    "total": usage.get("total", 0) - previous["total"],
+                    "output": usage.get("output", 0) - previous["output"],
+                }
+                cost = float(usage.get("cost", 0.0)) - previous["cost"]
+                previous.update({
+                    "steps": usage.get("steps", 0),
+                    "input": usage.get("input", 0),
+                    "cache_read": usage.get("cache_read", 0),
+                    "cache_write": usage.get("cache_write", 0),
+                    "total": usage.get("total", 0),
+                    "output": usage.get("output", 0),
+                    "cost": float(usage.get("cost", 0.0)),
+                })
+                cap_reason = budget_state.record(
+                    delta, equivalent_cost(delta, model, budget.price_target),
+                )
+            if cap_reason or time.monotonic() - started >= budget.max_duration_seconds:
+                cap_reason = cap_reason or "max_duration_seconds"
+                budget_state.cap_reason = cap_reason
+                proc.terminate()
+                break
+        try:
+            proc.wait(timeout=5)
+        except subprocess.TimeoutExpired:
+            proc.kill()
+            proc.wait()
+    finally:
+        if proc.stdout:
+            proc.stdout.close()
+    stderr = proc.stderr.read() if proc.stderr else ""
+    return subprocess.CompletedProcess(
+        cmd, proc.returncode, "".join(output), stderr,
+    )

pilot/review/output.py

@@ -741,6 +741,17 @@ def _render_collapsible_usage(usage: dict | None, model: str, config: dict | Non
         f"- **Actual**: {actual_s}{actual_note}",
         f"- **Scope**: {scope}",
     ]
+    if usage.get("budget_cap_hit"):
+        lines.append(
+            f"- **Budget**: capped at `{usage.get('budget_cap_reason', 'configured limit')}`"
+        )
+    budget = (config or {}).get("budget") or {}
+    if budget:
+        limits = ", ".join(
+            f"{key.removeprefix('max_')}={value}"
+            for key, value in budget.items()
+        )
+        lines.append(f"- **Budget limits**: {limits}")
     if eq_rows:
         lines.append("")
         lines.append("- **Equivalent cost on paid providers** (this run's tokens):")