qaas-python 0.2.2__tar.gz → 0.2.3__tar.gz

{qaas_python-0.2.2 → qaas_python-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: qaas-python
-Version: 0.2.2
+Version: 0.2.3
 Summary: A multi-agent QA system: finds real defects, reproduces them, files tickets, fixes them, and proves the fix
 Project-URL: Homepage, https://github.com/allaabdella2-us/qa-multi-agent-system
 Project-URL: Repository, https://github.com/allaabdella2-us/qa-multi-agent-system

{qaas_python-0.2.2 → qaas_python-0.2.3}/pyproject.toml

@@ -2,7 +2,7 @@
 # Distribution name is `qaas-python` (`qaas` was taken); the import package and
 # the CLI are both `qaas`.
 name = "qaas-python"
-version = "0.2.2"
+version = "0.2.3"
 description = "A multi-agent QA system: finds real defects, reproduces them, files tickets, fixes them, and proves the fix"
 readme = "README.md"
 license = "MIT"

{qaas_python-0.2.2 → qaas_python-0.2.3}/src/qaas/cli.py

@@ -500,14 +500,18 @@ def validate(config_dir: Path | None = ConfigDir) -> None:
     # never dispatched. The mode meant for every pull request could not file a
     # ticket. It took a live run to notice; this check makes it free.
     for mode_name, mode in sorted(cfg.run_modes.items()):
-        needed = sum(
-            cfg.agents[a].max_budget_usd for a in mode.agents if a in cfg.agents
-        )
-        if needed > mode.max_budget_usd:
+        # Only meaningful when both sides declare a cap. The shipped config
+        # declares none, so this check simply does not fire there.
+        agent_caps = [
+            cfg.agents[a].max_budget_usd for a in mode.agents
+            if a in cfg.agents and cfg.agents[a].max_budget_usd is not None
+        ]
+        needed = sum(agent_caps)
+        if mode.max_budget_usd is not None and agent_caps and needed > mode.max_budget_usd:
             missing = [a for a in mode.agents if a in cfg.agents][-1]
             problems.append(
-                f"mode '{mode_name}': agents can spend ${needed:.2f} but the cap is "
-                f"${mode.max_budget_usd:.2f}, so the run stops before it reaches "
+                f"mode '{mode_name}': the agents' caps exceed the mode's cap, so "
+                f"its cap, so the run stops before it reaches "
                 f"{missing} and files nothing. Raise max_budget_usd or drop an agent"
             )
 
@@ -567,7 +571,7 @@ def validate(config_dir: Path | None = ConfigDir) -> None:
         filing = "" if rm.files_tickets else "  [dim](no filing)[/dim]"
         console.print(
             f"[bold]{mode}[/bold]: {', '.join(rm.agents)}  "
-            f"[dim]budget ${rm.max_budget_usd:.2f}, {rm.max_wall_clock_s}s[/dim]{filing}"
+            f"[dim]{rm.max_wall_clock_s}s[/dim]{filing}"
         )
 
     if notes:
@@ -834,7 +838,7 @@ def runs(root: Path = Root, limit: int = 10) -> None:
         console.print("[dim]no runs yet[/dim]")
         return
     table = Table(header_style="bold")
-    for col in ("run", "envelopes", "agents", "cost"):
+    for col in ("run", "envelopes", "agents"):
         table.add_column(col)
     for run_id in ids:
         store = RunStore(run_id, root)
@@ -843,7 +847,6 @@ def runs(root: Path = Root, limit: int = 10) -> None:
             run_id,
             str(len(store.envelopes())),
             str(len(results)),
-            f"${store.total_cost_usd():.2f}",
         )
     console.print(table)
 
@@ -872,9 +875,6 @@ def show(run_id: str, root: Path = Root) -> None:
         header.append(f"started {summary.started:%Y-%m-%d %H:%M:%S}Z")
     if summary.duration_s is not None:
         header.append(f"duration {summary.duration_s:.0f}s")
-    header.append(f"cost ${summary.cost_usd:.2f}")
-    if summary.budget_usd:
-        header.append(f"of ${summary.budget_usd:.2f} budget")
     console.print("  " + "  ".join(header))
     if summary.target_sha:
         dirty = " [yellow](dirty tree)[/yellow]" if summary.target_dirty else ""
@@ -960,7 +960,6 @@ def trace(
     table.add_column("agent", style="cyan")
     table.add_column("kind")
     table.add_column("detail", overflow="fold")
-    table.add_column("cost", justify="right", style="dim")
     for row in trace_mod.timeline(entries):
         label = f"{row.kind} ×{row.count}" if row.count > 1 else row.kind
         table.add_row(
@@ -968,7 +967,6 @@ def trace(
             row.agent,
             f"[{KIND_STYLE.get(row.kind, 'white')}]{label}[/]",
             row.detail,
-            f"${row.cost_usd:.2f}" if row.cost_usd is not None else "",
         )
     console.print(table)
     console.print(f"\n[dim]{len(entries)} entries[/dim]")
@@ -1082,7 +1080,7 @@ def run(
     rm = cfg.run_modes[mode]
     console.print(
         f"[bold]{mode}[/bold] — {len(specs)} agents, "
-        f"budget ${rm.max_budget_usd:.2f}, concurrency {rm.max_concurrency}"
+        f"concurrency {rm.max_concurrency}"
     )
 
     if dry_run:
@@ -1093,7 +1091,7 @@ def run(
             d = describe(spec, prompt_dirs)
             console.print(
                 f"  [bold]{spec.name:14s}[/bold] {spec.model:18s} effort={spec.effort:7s} "
-                f"turns<={spec.max_turns:<3d} ${spec.max_budget_usd:.2f}"
+                f"turns<={spec.max_turns}"
             )
             console.print(f"    tools: {', '.join(d['allowed_tools'])}")
             console.print(f"    prompt: {d['prompt_chars']} chars")
@@ -1101,11 +1099,11 @@ def run(
 
     def on_event(kind: str, detail: dict) -> None:
         if kind == "agent_started":
-            console.print(f"[dim]->[/dim] {detail.get('agent')} [dim](${detail.get('budget', 0):.2f})[/dim]")
+            console.print(f"[dim]->[/dim] {detail.get('agent')}")
         elif kind == "finished":
             console.print(
                 f"[dim]<-[/dim] {detail.get('agent')} "
-                f"[dim]${detail.get('cost', 0):.3f}, {detail.get('envelopes', 0)} findings[/dim]"
+                f"[dim]{detail.get('envelopes', 0)} findings[/dim]"
             )
         elif kind == "stopped":
             console.print(f"[yellow]stopped: {detail.get('reason')}[/yellow]")
@@ -1172,11 +1170,6 @@ def score(
     table.add_row("false positives", f"{s['false_positives']} ({s['false_positive_rate']:.0%})")
     table.add_row("duplicates", f"{s['duplicates']} ({s['duplicate_rate']:.0%})")
     table.add_row("severity agreement", f"{s['severity_agreement']:.0%}")
-    table.add_row("cost", f"${s['cost_usd']:.2f}")
-    table.add_row(
-        "cost per accepted",
-        f"${s['cost_per_accepted']:.2f}" if s["cost_per_accepted"] is not None else "-",
-    )
     console.print(table)
 
     if card.matches:

{qaas_python-0.2.2 → qaas_python-0.2.3}/src/qaas/conductor.py

@@ -110,7 +110,7 @@ class RunReport:
 class Budget:
     """The spend and wall-clock governor. Checked before every dispatch."""
 
-    def __init__(self, max_usd: float, max_seconds: int, *, already_spent: float = 0.0):
+    def __init__(self, max_usd: float | None, max_seconds: int, *, already_spent: float = 0.0):
         self.max_usd = max_usd
         self.max_seconds = max_seconds
         #: What this run has already cost, including earlier invocations.
@@ -130,23 +130,28 @@ class Budget:
         return time.monotonic() - self.started
 
     @property
-    def remaining_usd(self) -> float:
-        return max(0.0, self.max_usd - self.spent)
+    def remaining_usd(self) -> float | None:
+        return None if self.max_usd is None else max(0.0, self.max_usd - self.spent)
 
     def spend(self, amount: float) -> None:
         self.spent += amount
 
     def check(self) -> None:
-        if self.spent >= self.max_usd:
+        # `max_usd is None` means no spend ceiling -- the shipped config sets
+        # none, because a dollar figure bakes one vendor's pricing into a tool
+        # meant to run against local models too. The wall-clock cap and each
+        # agent's `max_turns` still bound a run; those are model-agnostic.
+        if self.max_usd is not None and self.spent >= self.max_usd:
             raise BudgetExceeded(f"spend cap reached: ${self.spent:.2f} of ${self.max_usd:.2f}")
         if self.elapsed >= self.max_seconds:
             raise BudgetExceeded(
                 f"wall-clock cap reached: {self.elapsed:.0f}s of {self.max_seconds}s"
             )
 
-    def allowance(self, spec: AgentSpec) -> float:
-        """What this agent may spend: its own cap, or what the run has left."""
-        return max(0.01, min(spec.max_budget_usd, self.remaining_usd))
+    def allowance(self, spec: AgentSpec) -> float | None:
+        """What this agent may spend, or None when neither it nor the run caps it."""
+        caps = [c for c in (spec.max_budget_usd, self.remaining_usd) if c is not None]
+        return max(0.01, min(caps)) if caps else None
 
 
 class Conductor:

{qaas_python-0.2.2 → qaas_python-0.2.3}/src/qaas/config.py

@@ -74,7 +74,8 @@ class AgentSpec(BaseModel):
     model: str = "claude-opus-5"
     effort: Literal["low", "medium", "high", "xhigh", "max"] = "high"
     max_turns: int = 40
-    max_budget_usd: float = 2.0
+    max_budget_usd: float | None = None
+
 
     mcp_servers: list[str] = Field(default_factory=list)
     builtin_tools: list[str] = Field(default_factory=list)
@@ -165,7 +166,8 @@ class RunMode(BaseModel):
 
     trigger: str
     agents: list[str]
-    max_budget_usd: float = 10.0
+    max_budget_usd: float | None = None
+
     max_wall_clock_s: int = 3600
     max_concurrency: int = 3
     files_tickets: bool = True

{qaas_python-0.2.2 → qaas_python-0.2.3}/src/qaas/defaults/config/agents/arbiter.yaml

@@ -9,7 +9,6 @@ prompt: ARBITER.md
 model: claude-opus-5
 effort: high
 max_turns: 50
-max_budget_usd: 3.0
 mcp_servers: [envelope, vcs, contract_diff, test_runner]
 builtin_tools: [Read, Grep, Glob]
 skills: [adversarial-review, root-cause-vs-symptom, regression-risk-scoring, test-quality-audit]

{qaas_python-0.2.2 → qaas_python-0.2.3}/src/qaas/defaults/config/agents/cartographer.yaml

@@ -7,7 +7,6 @@ prompt: CARTOGRAPHER.md
 model: claude-sonnet-5      # extraction, not judgment
 effort: medium
 max_turns: 60
-max_budget_usd: 2.0
 mcp_servers: [envelope]
 builtin_tools: [Read, Grep, Glob]
 policy: {}                  # read-only

{qaas_python-0.2.2 → qaas_python-0.2.3}/src/qaas/defaults/config/agents/clerk.yaml

@@ -8,7 +8,6 @@ prompt: CLERK.md
 model: claude-sonnet-5      # composition against a fixed rubric and house format
 effort: high
 max_turns: 50
-max_budget_usd: 2.0
 mcp_servers: [envelope, tracker, defect_memory]
 builtin_tools: [Read]
 policy:

{qaas_python-0.2.2 → qaas_python-0.2.3}/src/qaas/defaults/config/agents/conduit.yaml

@@ -8,7 +8,6 @@ prompt: CONDUIT.md
 model: claude-opus-5
 effort: high
 max_turns: 60
-max_budget_usd: 3.0
 mcp_servers: [envelope, contract_diff, env_control, defect_memory]
 builtin_tools: [Read, Grep, Glob]
 policy: {}

{qaas_python-0.2.2 → qaas_python-0.2.3}/src/qaas/defaults/config/agents/forge.yaml

@@ -8,7 +8,6 @@ prompt: FORGE.md
 model: claude-opus-5
 effort: high
 max_turns: 80
-max_budget_usd: 4.0
 mcp_servers: [envelope, test_runner, env_control, vcs]
 builtin_tools: [Read, Grep, Glob, Write, Edit, Bash]
 policy:

{qaas_python-0.2.2 → qaas_python-0.2.3}/src/qaas/defaults/config/agents/mender.yaml

@@ -10,7 +10,6 @@ prompt: MENDER.md
 model: claude-opus-5
 effort: high
 max_turns: 80
-max_budget_usd: 5.0
 mcp_servers: [envelope, test_runner, env_control, vcs, tracker, contract_diff]
 builtin_tools: [Read, Grep, Glob, Write, Edit, Bash]
 skills: [test-first-fix, minimal-diff-discipline, root-cause-vs-symptom, rollback-plan-authoring]

{qaas_python-0.2.2 → qaas_python-0.2.3}/src/qaas/defaults/config/agents/proof.yaml

@@ -8,7 +8,6 @@ prompt: PROOF.md
 model: claude-opus-5
 effort: high
 max_turns: 60
-max_budget_usd: 4.0
 mcp_servers: [envelope, test_runner, env_control, tracker, vcs]
 builtin_tools: [Read, Grep, Glob, Bash]
 policy:

{qaas_python-0.2.2 → qaas_python-0.2.3}/src/qaas/defaults/config/agents/surface.yaml

@@ -8,7 +8,6 @@ prompt: SURFACE.md
 model: claude-opus-5
 effort: high
 max_turns: 80
-max_budget_usd: 4.0
 mcp_servers: [envelope, env_control, playwright]
 builtin_tools: [Read, Grep, Glob]
 policy: {}

{qaas_python-0.2.2 → qaas_python-0.2.3}/src/qaas/defaults/config/agents/vault.yaml

@@ -10,7 +10,6 @@ prompt: VAULT.md
 model: claude-opus-5
 effort: high
 max_turns: 60
-max_budget_usd: 3.0
 mcp_servers: [envelope, env_control, defect_memory]
 builtin_tools: [Read, Grep, Glob]
 policy: {}

{qaas_python-0.2.2 → qaas_python-0.2.3}/src/qaas/defaults/config/agents/warden.yaml

@@ -9,10 +9,6 @@ prompt: WARDEN.md
 model: claude-opus-5
 effort: high
 max_turns: 60
-# Measured: WARDEN exhausted $3.00 on its first real run against the demo app
-# and was killed mid-audit. Building the endpoint-by-role matrix and actually
-# impersonating each role costs more than reading a spec does.
-max_budget_usd: 5.0
 mcp_servers: [envelope, env_control, defect_memory]
 builtin_tools: [Read, Grep, Glob]
 policy: {}

{qaas_python-0.2.2 → qaas_python-0.2.3}/src/qaas/defaults/config/system.yaml

@@ -9,6 +9,11 @@ target:
 tracker: local      # local | jira   -- swap to file against real Jira
 vcs: local          # local | github
 
+# No spend cap by default. A dollar figure bakes one vendor's pricing into
+# the config, and this is meant to run against local models too. `max_turns`
+# is the model-agnostic bound. Set `max_budget_usd` here if you want a
+# ceiling; the governor enforces one whenever it is present.
+
 thresholds:
   min_confidence_to_file: 0.6      # §7 confidence gate
   max_findings_per_agent_run: 25   # §8.3 loop breaker: pause and escalate, don't file
@@ -21,30 +26,18 @@ run_modes:
   pr-check:
     trigger: pull_request
     agents: [CARTOGRAPHER, CONDUIT, SURFACE, FORGE, CLERK]
-    # Was 6.0, which this roster could not complete. Measured on a real run:
-    # CARTOGRAPHER $0.69 + CONDUIT $2.25 + SURFACE $3.16 = $6.09, so the governor
-    # stopped the run before FORGE or CLERK ever dispatched. The mode meant to
-    # run on every pull request could not file a ticket, and it failed silently:
-    # agents ran, findings landed in the ledger, nothing errored. `qaas validate`
-    # now refuses a mode whose agents cannot fit inside its cap.
-    max_budget_usd: 16.0
     max_wall_clock_s: 900
     max_concurrency: 2
 
   nightly:
     trigger: cron
     agents: [CARTOGRAPHER, CONDUIT, SURFACE, VAULT, WARDEN, FORGE, CLERK]
-    # FORGE runs once per finding, so the deep sweep's budget scales with how
-    # much discovery found, not with the number of agents. Measured: discovery
-    # ~$6, then roughly $1-2 per finding reproduced.
-    max_budget_usd: 50.0
     max_wall_clock_s: 7200
     max_concurrency: 3
 
   incident:
     trigger: alert
     agents: [CONDUIT]
-    max_budget_usd: 4.0
     max_wall_clock_s: 600
     max_concurrency: 2
     files_tickets: false          # §9: diagnostic only, read-only, no filing
@@ -55,7 +48,6 @@ run_modes:
   fix-cycle:
     trigger: agent_ready_ticket
     agents: [PROOF, MENDER, ARBITER]
-    max_budget_usd: 20.0
     max_wall_clock_s: 3600
     max_concurrency: 1
 
@@ -64,6 +56,5 @@ run_modes:
   full-loop:
     trigger: on_demand
     agents: [CARTOGRAPHER, CONDUIT, SURFACE, VAULT, WARDEN, FORGE, CLERK, MENDER, ARBITER, PROOF]
-    max_budget_usd: 70.0
     max_wall_clock_s: 10800
     max_concurrency: 3

{qaas_python-0.2.2 → qaas_python-0.2.3}/tests/test_conductor.py

@@ -168,10 +168,18 @@ async def test_each_forge_invocation_gets_its_own_finding(cfg, tmp_path, fake_ag
 
 
 async def test_a_spend_blowout_stops_the_run_and_escalates(cfg, tmp_path, fake_agents):
+    """The governor still works; it just no longer ships with a dollar figure.
+
+    Shipped config sets no `max_budget_usd` -- a price belongs to one vendor and
+    this runs against local models too -- so a test about spend has to declare
+    the cap it is testing.
+    """
     calls, behaviour = fake_agents
     behaviour["CARTOGRAPHER"] = {"publish_map": True, "cost": 99.0}
 
-    report = await make_conductor(cfg, tmp_path).run("pr-check")
+    mode = cfg.run_modes["pr-check"].model_copy(update={"max_budget_usd": 10.0})
+    capped = cfg.model_copy(update={"run_modes": {**cfg.run_modes, "pr-check": mode}})
+    report = await make_conductor(capped, tmp_path).run("pr-check")
     assert report.stopped_early and "spend cap" in report.stopped_early
     assert "CLERK" not in [n for n, _ in calls]
     assert report.escalations
@@ -533,13 +541,15 @@ async def test_a_resumed_run_keeps_the_budget_it_already_spent(cfg, tmp_path, fa
     store = RunStore.new(tmp_path)
 
     # A first invocation that has already consumed most of the mode's cap.
-    mode = cfg.run_modes["pr-check"]
-    store.put_result(AgentResult(agent="CONDUIT", subtype="success",
-                                 cost_usd=mode.max_budget_usd - 0.05, num_turns=1))
-    assert store.total_cost_usd() == pytest.approx(mode.max_budget_usd - 0.05)
+    capped_mode = cfg.run_modes["pr-check"].model_copy(update={"max_budget_usd": 5.0})
+    capped = cfg.model_copy(update={"run_modes": {**cfg.run_modes, "pr-check": capped_mode}})
+    store.put_result(AgentResult(agent="CONDUIT", subtype="success", cost_usd=4.95, num_turns=1))
+    assert store.total_cost_usd() == pytest.approx(4.95)
 
     behaviour["CARTOGRAPHER"] = {"cost": 1.0, "publish_map": True}
-    report = await make_conductor(cfg, tmp_path).run("pr-check", run_id=store.run_id)
+    # The shipped config sets no cap, so this test supplies one -- the governor
+    # is still there, it just no longer bakes a dollar figure into defaults.
+    report = await make_conductor(capped, tmp_path).run("pr-check", run_id=store.run_id)
 
     assert report.stopped_early, "the resumed run ignored what the run had already spent"
     assert "spend cap" in report.stopped_early

{qaas_python-0.2.2 → qaas_python-0.2.3}/tests/test_config.py

@@ -121,12 +121,21 @@ def test_incident_mode_files_nothing(cfg):
     assert "CLERK" not in incident.agents
 
 
-def test_every_run_mode_is_budgeted(cfg):
+def test_every_run_mode_is_bounded(cfg):
+    """Every mode must have SOME bound. It used to be a dollar cap; the shipped
+    config sets none now, because a price belongs to one vendor and this is
+    meant to run against local models too. The wall clock is the bound that
+    survives that, and `max_turns` bounds each agent."""
     for name, mode in cfg.run_modes.items():
-        assert mode.max_budget_usd > 0, name
-        assert mode.max_wall_clock_s > 0, name
+        assert mode.max_wall_clock_s > 0, f"{name} has no wall-clock bound"
+        assert mode.max_concurrency > 0, f"{name} has no concurrency bound"
 
 
+def test_no_vendor_pricing_is_baked_into_the_shipped_config(cfg):
+    """A dollar figure in the defaults is a bet on one provider's price list."""
+    assert all(s.max_budget_usd is None for s in cfg.agents.values())
+    assert all(m.max_budget_usd is None for m in cfg.run_modes.values())
+
 def test_enabled_agents_resolves_a_mode(cfg):
     names = [s.name for s in cfg.enabled_agents("pr-check")]
     assert names == ["CARTOGRAPHER", "CONDUIT", "SURFACE", "FORGE", "CLERK"]
@@ -209,16 +218,12 @@ def test_a_nonsense_override_is_rejected_loudly(monkeypatch):
         load_config(search=CONFIG_SEARCH)
 
 
-def test_every_mode_can_afford_the_agents_it_names():
-    """A mode whose roster outspends its cap stops partway through and looks
-    like it worked. `pr-check` shipped with a $6 cap against a $15 roster:
-    discovery alone spent $6.09, so FORGE and CLERK never dispatched and the
-    mode meant for every pull request could not file a ticket. Nothing errored,
-    which is what made it survive."""
+def test_a_mode_that_cannot_afford_its_agents_is_rejected():
+    """Still enforced -- but only when someone actually sets caps, since the
+    shipped config sets none."""
     cfg = load_config(search=CONFIG_SEARCH)
     for name, mode in cfg.run_modes.items():
-        needed = sum(cfg.agents[a].max_budget_usd for a in mode.agents if a in cfg.agents)
-        assert needed <= mode.max_budget_usd, (
-            f"mode '{name}' names agents that can spend ${needed:.2f} against a "
-            f"${mode.max_budget_usd:.2f} cap; it will stop before the last agent runs"
-        )
+        caps = [cfg.agents[a].max_budget_usd for a in mode.agents
+                if a in cfg.agents and cfg.agents[a].max_budget_usd is not None]
+        if caps and mode.max_budget_usd is not None:
+            assert sum(caps) <= mode.max_budget_usd, f"mode '{name}' cannot finish"

{qaas_python-0.2.2 → qaas_python-0.2.3}/tests/test_paths.py

@@ -114,12 +114,12 @@ def test_one_agent_file_can_be_shadowed_without_forking_the_rest(tmp_path):
     override = tmp_path / "config" / "agents"
     override.mkdir(parents=True)
     shipped = (PACKAGED_CONFIG / "agents" / "mender.yaml").read_text()
-    (override / "mender.yaml").write_text(shipped.replace("max_budget_usd: 5.0", "max_budget_usd: 9.0"))
+    (override / "mender.yaml").write_text(shipped.replace("max_turns: 80", "max_turns: 99"))
 
     cfg = load_config(search=(tmp_path / "config", *CONFIG_SEARCH))
-    assert cfg.agents["MENDER"].max_budget_usd == 9.0, "the override did not win"
+    assert cfg.agents["MENDER"].max_turns == 99, "the override did not win"
     assert len(cfg.agents) == len(PACKAGED_AGENTS), "shadowing one agent must not drop the others"
-    assert cfg.agents["CONDUIT"].max_budget_usd == 3.0, "an untouched agent changed"
+    assert cfg.agents["CONDUIT"].max_turns == 60, "an untouched agent changed"
 
 
 def test_system_yaml_is_taken_whole_from_the_first_layer(tmp_path):

{qaas_python-0.2.2 → qaas_python-0.2.3}/tests/test_trace.py

@@ -115,10 +115,24 @@ def test_the_timeline_carries_the_facts_not_just_the_kinds(runner, run):
     assert "CORVID-1" in output
 
 
-def test_cost_accumulates_through_the_run(runner, run):
+def test_cost_is_recorded_in_the_ledger_but_never_printed(runner, run):
+    """Cost is data, not display.
+
+    `qaas trace` used to carry a running-total column. The shipped config sets
+    no spend cap now -- a dollar figure is one vendor's price list, and this is
+    meant to run against local models too -- so printing money everywhere made
+    a Claude-specific assumption look like a property of the tool. The ledger
+    still records `cost_usd` on every `agent_finished`, so nothing is lost and
+    `--json` still carries it.
+    """
     output = _trace(runner, run)
-    assert "$1.25" in output, "CONDUIT's cost"
-    assert "$2.00" in output, "the running total after FORGE, not FORGE's $0.75"
+    assert "$" not in output, "a dollar figure reached the terminal"
+
+    entries = trace_mod.read_ledger(run)
+    finished = [e for e in entries if e.kind == "agent_finished"]
+    assert finished and any("cost_usd" in e.detail for e in finished), (
+        "cost stopped being recorded; it should only have stopped being printed"
+    )
 
 
 def test_consecutive_tool_calls_fold_into_one_row(run):
@@ -204,11 +218,11 @@ def test_json_output_survives_a_detail_longer_than_the_console(runner, tmp_path)
 # -- qaas show --------------------------------------------------------------
 
 
-def test_show_reports_cost_mode_duration_and_escalations(runner, run):
+def test_show_reports_mode_duration_and_escalations(runner, run):
     result = runner.invoke(cli.app, ["show", run.run_id, "--root", str(run.root)])
     assert result.exit_code == 0, result.output
     assert "fix-cycle" in result.output
-    assert "$2.00" in result.output, "cost, which show never printed"
+    assert "$" not in result.output, "no dollar figure should be printed"
     assert "duration" in result.output
     assert "escalations" in result.output and "CORVID-2 needs a human" in result.output