coding-agent-cost 0.2.2__tar.gz → 0.3.0__tar.gz

{coding_agent_cost-0.2.2/coding_agent_cost.egg-info → coding_agent_cost-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: coding-agent-cost
-Version: 0.2.2
+Version: 0.3.0
 Summary: Estimate AI coding agent (Claude Code / Codex CLI) token usage and cost from local logs
 Author: shiki-yusuke
 License: MIT
@@ -232,6 +232,14 @@ network, never calls `gh`, and never resolves branches or PRs.
   flagged, since the reader's own cross-check of real transcripts found
   exactly that pattern in every observed duplicated group. See
   `CHANGELOG.md`'s 0.2.0 entry.
+  If the row a group adopts has no `stop_reason` (common in subagent
+  transcripts, where a message ending in `tool_use` may never get its final
+  line), its `output_tokens` is only the streaming head's value: the
+  group's `output` fact is flagged `source_quality: "output_lower_bound"`
+  -- the observed lower bound of that message's output tokens, not
+  guaranteed to be >= the true count. The group's input-side facts stay
+  `"ok"`, and the token amount itself is unchanged (still priced and
+  included in rows/totals); the flag is a warning only.
   When Anthropic's prompt-cache TTL breakdown (5-minute vs 1-hour writes) is
   present in the log, it's used; otherwise the cache-write tokens are priced
   at the 5-minute rate as an explicit **lower bound** and flagged
@@ -342,7 +350,7 @@ agent-cost measure --session-id <id> [--session-id <id> ...] \
 ```json
 {
   "protocol_version": "measure/v1",
-  "producer_version": "0.2.2",
+  "producer_version": "0.3.0",
   "accounting_basis": "agent-cost-raw-total/v2",
   "generated_at": "...",
   "window": { "since": "...", "until": null },
@@ -363,7 +371,7 @@ agent-cost measure --session-id <id> [--session-id <id> ...] \
     "duplicate_rows_skipped": 0,
     "conflicting_duplicate_groups": 0,
     "missing_dedup_identity_rows": 0,
-    "source_quality": { "ok": 41, "first_event_delta": 2, "identity_missing": 0 }
+    "source_quality": { "ok": 41, "first_event_delta": 2, "identity_missing": 0, "output_lower_bound": 1 }
   }
 }
 ```
@@ -395,8 +403,9 @@ includes absolute file paths, rollout paths, prompt/message content, or git
 branch names -- only the fields needed to reproduce a cost estimate:
 `occurred_at_utc`, `agent`, `session_id`, `model_raw`, `model_key`,
 `token_kind`, `tokens`, `mode`, and `source_quality` (a fixed-vocabulary
-caveat about how that one fact was derived, e.g. `"ok"` or Codex's
-`"first_event_delta"` -- never null).
+caveat about how that one fact was derived: `"ok"`, Codex's
+`"first_event_delta"`, or Claude's `"identity_missing"` /
+`"output_lower_bound"` -- never null).
 
 ## License
 

{coding_agent_cost-0.2.2 → coding_agent_cost-0.3.0}/README.md

@@ -206,6 +206,14 @@ network, never calls `gh`, and never resolves branches or PRs.
   flagged, since the reader's own cross-check of real transcripts found
   exactly that pattern in every observed duplicated group. See
   `CHANGELOG.md`'s 0.2.0 entry.
+  If the row a group adopts has no `stop_reason` (common in subagent
+  transcripts, where a message ending in `tool_use` may never get its final
+  line), its `output_tokens` is only the streaming head's value: the
+  group's `output` fact is flagged `source_quality: "output_lower_bound"`
+  -- the observed lower bound of that message's output tokens, not
+  guaranteed to be >= the true count. The group's input-side facts stay
+  `"ok"`, and the token amount itself is unchanged (still priced and
+  included in rows/totals); the flag is a warning only.
   When Anthropic's prompt-cache TTL breakdown (5-minute vs 1-hour writes) is
   present in the log, it's used; otherwise the cache-write tokens are priced
   at the 5-minute rate as an explicit **lower bound** and flagged
@@ -316,7 +324,7 @@ agent-cost measure --session-id <id> [--session-id <id> ...] \
 ```json
 {
   "protocol_version": "measure/v1",
-  "producer_version": "0.2.2",
+  "producer_version": "0.3.0",
   "accounting_basis": "agent-cost-raw-total/v2",
   "generated_at": "...",
   "window": { "since": "...", "until": null },
@@ -337,7 +345,7 @@ agent-cost measure --session-id <id> [--session-id <id> ...] \
     "duplicate_rows_skipped": 0,
     "conflicting_duplicate_groups": 0,
     "missing_dedup_identity_rows": 0,
-    "source_quality": { "ok": 41, "first_event_delta": 2, "identity_missing": 0 }
+    "source_quality": { "ok": 41, "first_event_delta": 2, "identity_missing": 0, "output_lower_bound": 1 }
   }
 }
 ```
@@ -369,8 +377,9 @@ includes absolute file paths, rollout paths, prompt/message content, or git
 branch names -- only the fields needed to reproduce a cost estimate:
 `occurred_at_utc`, `agent`, `session_id`, `model_raw`, `model_key`,
 `token_kind`, `tokens`, `mode`, and `source_quality` (a fixed-vocabulary
-caveat about how that one fact was derived, e.g. `"ok"` or Codex's
-`"first_event_delta"` -- never null).
+caveat about how that one fact was derived: `"ok"`, Codex's
+`"first_event_delta"`, or Claude's `"identity_missing"` /
+`"output_lower_bound"` -- never null).
 
 ## License
 

{coding_agent_cost-0.2.2 → coding_agent_cost-0.3.0}/agent_cost/__init__.py

@@ -6,4 +6,4 @@ against a versioned rate catalog. Everything happens locally; there are no
 network calls.
 """
 
-__version__ = "0.2.2"
+__version__ = "0.3.0"

{coding_agent_cost-0.2.2 → coding_agent_cost-0.3.0}/agent_cost/facts.py

@@ -32,10 +32,14 @@ MODES = ("fast", "normal", "unknown")
 # (e.g. Codex's first delta in a rollout is measured against an assumed
 # zero baseline; Claude's reader can't dedup a row that lacks a full
 # (message.id, requestId) pair, so it emits that row individually and
-# flags it "identity_missing" rather than silently treating it as "ok").
+# flags it "identity_missing" rather than silently treating it as "ok";
+# "output_lower_bound" marks a Claude output fact whose tokens are only the
+# observed lower bound of that message's output_tokens -- the reader's
+# adopted row had no stop_reason, so the value is not guaranteed to be
+# >= the true count).
 # This is never left unset -- every Fact defaults to "ok" so export never
 # emits a null source_quality.
-SOURCE_QUALITY_VALUES = ("ok", "first_event_delta", "identity_missing")
+SOURCE_QUALITY_VALUES = ("ok", "first_event_delta", "identity_missing", "output_lower_bound")
 
 _BRACKET_SUFFIX = re.compile(r"\[[^\]]*\]$")
 _DATE_SUFFIX = re.compile(r"@\d{6,8}$")

{coding_agent_cost-0.2.2 → coding_agent_cost-0.3.0}/agent_cost/readers/claude.py

@@ -278,6 +278,14 @@ def _resolve_mode(rows: list, adopted: dict) -> str:
     return adopted["mode"]
 
 
+def _is_final(row: dict) -> bool:
+    """Whether a row carries a real ``message.stop_reason`` -- a non-empty
+    ``str``. Null, missing, ``False``, ``""`` and non-string values all
+    fail to qualify."""
+    stop_reason = row["stop_reason"]
+    return isinstance(stop_reason, str) and bool(stop_reason)
+
+
 def _select_adopted_row(rows: list) -> dict:
     """Pick the row within one dedup group whose usage gets emitted.
 
@@ -302,8 +310,7 @@ def _select_adopted_row(rows: list) -> dict:
     """
     adopted_idx = None
     for idx in range(len(rows) - 1, -1, -1):
-        stop_reason = rows[idx]["stop_reason"]
-        if isinstance(stop_reason, str) and stop_reason:
+        if _is_final(rows[idx]):
             adopted_idx = idx
             break
 
@@ -366,6 +373,19 @@ def parse_session_detailed(jsonl_path: Path) -> ClaudeParseResult:
     the group has exactly one concrete mode elsewhere, that concrete mode
     is emitted instead (see its docstring).
 
+    If the adopted row itself is not final (no non-empty-string
+    ``stop_reason`` -- see ``_is_final``), the group's ``output`` fact gets
+    ``source_quality="output_lower_bound"``: that row's ``output_tokens``
+    is a streaming head's value, observed to be a lower bound on the
+    message's real output count (subagent transcripts often end a
+    tool_use message without ever writing its final row). This keys off
+    the *adopted* row, not "does the group contain a final row", so a
+    final row overridden by a later, differing non-final row is flagged
+    too. The group's input-side facts stay ``"ok"`` (those fields don't
+    grow while streaming), and token amounts are emitted unchanged --
+    this only marks the caveat. Identity-missing rows never form a group
+    and keep ``"identity_missing"``.
+
     ``occurred_at_utc`` on the emitted fact is the *adopted* row's own
     timestamp (not the group's first-seen timestamp): the adopted row is
     what determines the actual token counts, and pricing/month-bucketing
@@ -493,6 +513,7 @@ def parse_session_detailed(jsonl_path: Path) -> ClaudeParseResult:
         if marker in standalone_rows:
             row = standalone_rows[marker]
             source_quality = "identity_missing"
+            output_source_quality = source_quality
             dedup_units.append(
                 ClaudeDedupUnit(
                     session_id=row["sid"],
@@ -544,6 +565,7 @@ def parse_session_detailed(jsonl_path: Path) -> ClaudeParseResult:
                 "tokens": adopted["tokens"],
             }
             source_quality = "ok"
+            output_source_quality = "ok" if _is_final(adopted) else "output_lower_bound"
 
         model_key = normalize_model_key(row["model_raw"])
         for kind, amount in row["tokens"].items():
@@ -557,7 +579,7 @@ def parse_session_detailed(jsonl_path: Path) -> ClaudeParseResult:
                     token_kind=kind,
                     tokens=amount,
                     mode=row["mode"],
-                    source_quality=source_quality,
+                    source_quality=output_source_quality if kind == "output" else source_quality,
                 )
             )
 

{coding_agent_cost-0.2.2 → coding_agent_cost-0.3.0/coding_agent_cost.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: coding-agent-cost
-Version: 0.2.2
+Version: 0.3.0
 Summary: Estimate AI coding agent (Claude Code / Codex CLI) token usage and cost from local logs
 Author: shiki-yusuke
 License: MIT
@@ -232,6 +232,14 @@ network, never calls `gh`, and never resolves branches or PRs.
   flagged, since the reader's own cross-check of real transcripts found
   exactly that pattern in every observed duplicated group. See
   `CHANGELOG.md`'s 0.2.0 entry.
+  If the row a group adopts has no `stop_reason` (common in subagent
+  transcripts, where a message ending in `tool_use` may never get its final
+  line), its `output_tokens` is only the streaming head's value: the
+  group's `output` fact is flagged `source_quality: "output_lower_bound"`
+  -- the observed lower bound of that message's output tokens, not
+  guaranteed to be >= the true count. The group's input-side facts stay
+  `"ok"`, and the token amount itself is unchanged (still priced and
+  included in rows/totals); the flag is a warning only.
   When Anthropic's prompt-cache TTL breakdown (5-minute vs 1-hour writes) is
   present in the log, it's used; otherwise the cache-write tokens are priced
   at the 5-minute rate as an explicit **lower bound** and flagged
@@ -342,7 +350,7 @@ agent-cost measure --session-id <id> [--session-id <id> ...] \
 ```json
 {
   "protocol_version": "measure/v1",
-  "producer_version": "0.2.2",
+  "producer_version": "0.3.0",
   "accounting_basis": "agent-cost-raw-total/v2",
   "generated_at": "...",
   "window": { "since": "...", "until": null },
@@ -363,7 +371,7 @@ agent-cost measure --session-id <id> [--session-id <id> ...] \
     "duplicate_rows_skipped": 0,
     "conflicting_duplicate_groups": 0,
     "missing_dedup_identity_rows": 0,
-    "source_quality": { "ok": 41, "first_event_delta": 2, "identity_missing": 0 }
+    "source_quality": { "ok": 41, "first_event_delta": 2, "identity_missing": 0, "output_lower_bound": 1 }
   }
 }
 ```
@@ -395,8 +403,9 @@ includes absolute file paths, rollout paths, prompt/message content, or git
 branch names -- only the fields needed to reproduce a cost estimate:
 `occurred_at_utc`, `agent`, `session_id`, `model_raw`, `model_key`,
 `token_kind`, `tokens`, `mode`, and `source_quality` (a fixed-vocabulary
-caveat about how that one fact was derived, e.g. `"ok"` or Codex's
-`"first_event_delta"` -- never null).
+caveat about how that one fact was derived: `"ok"`, Codex's
+`"first_event_delta"`, or Claude's `"identity_missing"` /
+`"output_lower_bound"` -- never null).
 
 ## License
 

{coding_agent_cost-0.2.2 → coding_agent_cost-0.3.0}/coding_agent_cost.egg-info/SOURCES.txt

@@ -29,5 +29,6 @@ tests/test_rates.py
 tests/test_reader_claude.py
 tests/test_reader_codex.py
 tests/test_reader_dedup.py
+tests/test_reader_output_lower_bound.py
 tests/test_sonnet_5_5_rates.py
 tests/test_version_consistency.py

{coding_agent_cost-0.2.2 → coding_agent_cost-0.3.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "coding-agent-cost"
-version = "0.2.2"
+version = "0.3.0"
 description = "Estimate AI coding agent (Claude Code / Codex CLI) token usage and cost from local logs"
 readme = "README.md"
 license = { text = "MIT" }

{coding_agent_cost-0.2.2 → coding_agent_cost-0.3.0}/tests/test_cli.py

@@ -471,6 +471,7 @@ def test_measure_unknown_session_id_exits_zero_with_empty_result(tmp_path, monke
         "ok": 0,
         "first_event_delta": 0,
         "identity_missing": 0,
+        "output_lower_bound": 0,
     }
 
 

coding_agent_cost-0.3.0/tests/test_reader_output_lower_bound.py

@@ -0,0 +1,265 @@
+"""Tests for ``source_quality="output_lower_bound"`` (E0-a4 S1).
+
+Spec: when the row a dedup group adopts (``_select_adopted_row``) has no
+valid ``message.stop_reason`` (a non-empty ``str``), that group's
+``token_kind="output"`` fact is flagged ``"output_lower_bound"`` -- its
+``output_tokens`` is the streaming head's value, a lower bound on the true
+count. Input-side facts from the same group stay ``"ok"``. The decision is
+"is the *adopted* row final", not "does the group contain a final row", so
+a final row followed by a differing non-final row (adoption switches to
+the last row) is flagged too. Identity-missing standalone rows keep
+``"identity_missing"``. Token amounts, adoption and conflict counting are
+unchanged -- only the flag is added.
+
+All fixtures are synthetic and written to ``tmp_path``.
+"""
+
+import json
+
+import pytest
+
+from agent_cost import cli
+from agent_cost.facts import SOURCE_QUALITY_VALUES
+from agent_cost.readers.claude import parse_session_detailed
+
+_ABSENT = object()
+
+
+def _event(
+    ts,
+    output,
+    *,
+    stop_reason=_ABSENT,
+    msg_id="msg-1",
+    req_id="req-1",
+    session_id="s-olb",
+    input_tokens=10,
+    cache_read=20,
+    cache_write_5m=30,
+):
+    message = {
+        "id": msg_id,
+        "model": "claude-sonnet-5",
+        "usage": {
+            "input_tokens": input_tokens,
+            "cache_read_input_tokens": cache_read,
+            "cache_creation_input_tokens": cache_write_5m,
+            "cache_creation": {"ephemeral_5m_input_tokens": cache_write_5m, "ephemeral_1h_input_tokens": 0},
+            "output_tokens": output,
+        },
+    }
+    if msg_id is None:
+        del message["id"]
+    if stop_reason is not _ABSENT:
+        message["stop_reason"] = stop_reason
+    event = {
+        "type": "assistant",
+        "timestamp": ts,
+        "sessionId": session_id,
+        "requestId": req_id,
+        "message": message,
+    }
+    if req_id is None:
+        del event["requestId"]
+    return event
+
+
+def _write(path, events):
+    path.write_text("\n".join(json.dumps(e) for e in events) + "\n")
+    return path
+
+
+def _parse(tmp_path, events):
+    return parse_session_detailed(_write(tmp_path / "session.jsonl", events))
+
+
+def _quality_by_kind(facts):
+    return {f.token_kind: f.source_quality for f in facts}
+
+
+def _tokens_by_kind(facts):
+    return {f.token_kind: f.tokens for f in facts}
+
+
+INPUT_KINDS = ("input_nocache", "cache_read", "cache_write_5m")
+
+
+def test_output_lower_bound_is_last_source_quality_value():
+    assert SOURCE_QUALITY_VALUES[-1] == "output_lower_bound"
+    assert SOURCE_QUALITY_VALUES[:3] == ("ok", "first_event_delta", "identity_missing")
+
+
+def test_group_without_final_row_flags_only_output(tmp_path):
+    """AC1: no row in the group has a stop_reason -> adopted = last row,
+    its output fact is output_lower_bound, input-side facts stay ok."""
+    result = _parse(
+        tmp_path,
+        [
+            _event("2026-10-01T00:00:00Z", 1, stop_reason=None),
+            _event("2026-10-01T00:00:01Z", 1),
+        ],
+    )
+    quality = _quality_by_kind(result.facts)
+    assert quality["output"] == "output_lower_bound"
+    for kind in INPUT_KINDS:
+        assert quality[kind] == "ok"
+    assert _tokens_by_kind(result.facts) == {"input_nocache": 10, "cache_read": 20, "cache_write_5m": 30, "output": 1}
+    assert result.duplicate_rows_skipped == 1
+    assert result.conflicting_duplicate_groups == 0
+
+
+def test_single_row_group_without_final_flags_output(tmp_path):
+    result = _parse(tmp_path, [_event("2026-10-01T00:00:00Z", 4)])
+    quality = _quality_by_kind(result.facts)
+    assert quality["output"] == "output_lower_bound"
+    for kind in INPUT_KINDS:
+        assert quality[kind] == "ok"
+
+
+def test_group_ending_in_final_row_is_all_ok(tmp_path):
+    """AC2: the last row carries a stop_reason -> every fact is ok."""
+    result = _parse(
+        tmp_path,
+        [
+            _event("2026-10-01T00:00:00Z", 1),
+            _event("2026-10-01T00:00:01Z", 2),
+            _event("2026-10-01T00:00:02Z", 57, stop_reason="tool_use"),
+        ],
+    )
+    assert {f.source_quality for f in result.facts} == {"ok"}
+    assert _tokens_by_kind(result.facts)["output"] == 57
+
+
+def test_final_row_followed_by_differing_row_flags_output(tmp_path):
+    """AC2b: a final row followed by a different non-final row switches
+    adoption to the last row (no stop_reason) -> output_lower_bound."""
+    result = _parse(
+        tmp_path,
+        [
+            _event("2026-10-01T00:00:00Z", 5, stop_reason="end_turn"),
+            _event("2026-10-01T00:00:01Z", 8),
+        ],
+    )
+    quality = _quality_by_kind(result.facts)
+    assert quality["output"] == "output_lower_bound"
+    for kind in INPUT_KINDS:
+        assert quality[kind] == "ok"
+    assert _tokens_by_kind(result.facts)["output"] == 8
+
+
+def test_final_row_followed_by_identical_row_stays_ok(tmp_path):
+    """AC2c: a final row followed by an identical (non-final) row keeps the
+    final row adopted -> ok, even though the group's last row isn't final."""
+    result = _parse(
+        tmp_path,
+        [
+            _event("2026-10-01T00:00:00Z", 5, stop_reason="end_turn"),
+            _event("2026-10-01T00:00:01Z", 5),
+        ],
+    )
+    assert {f.source_quality for f in result.facts} == {"ok"}
+    assert _tokens_by_kind(result.facts)["output"] == 5
+
+
+@pytest.mark.parametrize("stop_reason", ["", None, 0, 1, 1.5, False, ["end_turn"], _ABSENT])
+def test_invalid_stop_reason_only_group_flags_output(tmp_path, stop_reason):
+    """AC2c: stop_reason "" / None / numbers / non-str only -> not final."""
+    result = _parse(
+        tmp_path,
+        [
+            _event("2026-10-01T00:00:00Z", 3, stop_reason=stop_reason),
+            _event("2026-10-01T00:00:01Z", 6, stop_reason=stop_reason),
+        ],
+    )
+    quality = _quality_by_kind(result.facts)
+    assert quality["output"] == "output_lower_bound"
+    for kind in INPUT_KINDS:
+        assert quality[kind] == "ok"
+    assert _tokens_by_kind(result.facts)["output"] == 6
+
+
+def test_final_row_with_zero_output_is_ok(tmp_path):
+    """AC2c: a final row with output 0 emits no output fact; the rest is ok."""
+    result = _parse(
+        tmp_path,
+        [
+            _event("2026-10-01T00:00:00Z", 0),
+            _event("2026-10-01T00:00:01Z", 0, stop_reason="end_turn"),
+        ],
+    )
+    assert "output" not in _tokens_by_kind(result.facts)
+    assert {f.source_quality for f in result.facts} == {"ok"}
+
+
+@pytest.mark.parametrize("missing", ["msg_id", "req_id"])
+def test_identity_missing_row_stays_identity_missing(tmp_path, missing):
+    """AC2d: a standalone row without a full id pair is not a group, so it
+    keeps identity_missing on every fact (including output)."""
+    kwargs = {missing: None}
+    result = _parse(tmp_path, [_event("2026-10-01T00:00:00Z", 9, **kwargs)])
+    assert result.missing_dedup_identity_rows == 1
+    assert "output" in _tokens_by_kind(result.facts)
+    assert {f.source_quality for f in result.facts} == {"identity_missing"}
+
+
+def test_flag_is_per_group(tmp_path):
+    """One group without a final row, one with: only the former's output is flagged."""
+    result = _parse(
+        tmp_path,
+        [
+            _event("2026-10-01T00:00:00Z", 2, msg_id="msg-a", req_id="req-a"),
+            _event("2026-10-01T00:00:01Z", 40, msg_id="msg-b", req_id="req-b", stop_reason="end_turn"),
+        ],
+    )
+    output_facts = [f for f in result.facts if f.token_kind == "output"]
+    assert [(f.tokens, f.source_quality) for f in output_facts] == [(2, "output_lower_bound"), (40, "ok")]
+    assert all(f.source_quality == "ok" for f in result.facts if f.token_kind != "output")
+
+
+# ---------------------------------------------------------------------------
+# CLI (AC3): measure's data_quality.source_quality always carries the key.
+# ---------------------------------------------------------------------------
+
+
+def _setup_claude_session(tmp_path, monkeypatch, events):
+    claude_home = tmp_path / "claude_home"
+    codex_home = tmp_path / "codex_home"
+    project_dir = claude_home / "projects" / "olb"
+    project_dir.mkdir(parents=True)
+    codex_home.mkdir()
+    monkeypatch.setenv("CLAUDE_HOME", str(claude_home))
+    monkeypatch.setenv("CODEX_HOME", str(codex_home))
+    monkeypatch.delenv("AGENT_COST_CONFIG", raising=False)
+    _write(project_dir / "session.jsonl", events)
+
+
+def _measure_source_quality(capsys):
+    rc = cli.main(["measure", "--session-id", "s-olb", "--since", "2026-09-01"])
+    assert rc == 0
+    return json.loads(capsys.readouterr().out)["data_quality"]["source_quality"]
+
+
+def test_measure_counts_output_lower_bound(tmp_path, monkeypatch, capsys):
+    _setup_claude_session(
+        tmp_path,
+        monkeypatch,
+        [
+            _event("2026-10-01T00:00:00Z", 1, msg_id="msg-a", req_id="req-a"),
+            _event("2026-10-01T00:00:01Z", 30, msg_id="msg-b", req_id="req-b", stop_reason="end_turn"),
+        ],
+    )
+    sq = _measure_source_quality(capsys)
+    assert set(sq.keys()) == set(SOURCE_QUALITY_VALUES)
+    assert sq["output_lower_bound"] == 1
+    assert sq["ok"] == 7
+    assert sq["identity_missing"] == 0
+
+
+def test_measure_reports_zero_output_lower_bound_when_absent(tmp_path, monkeypatch, capsys):
+    _setup_claude_session(
+        tmp_path,
+        monkeypatch,
+        [_event("2026-10-01T00:00:00Z", 30, stop_reason="end_turn")],
+    )
+    sq = _measure_source_quality(capsys)
+    assert sq == {"ok": 4, "first_event_delta": 0, "identity_missing": 0, "output_lower_bound": 0}

{coding_agent_cost-0.2.2 → coding_agent_cost-0.3.0}/tests/test_version_consistency.py

@@ -1,8 +1,8 @@
 """Spec: pyproject.toml's [project].version and agent_cost.__version__ must
-agree, and both must read "0.2.2" for this change (the Sonnet 5.5 catalog-only release bumps
-the package version, as the Opus 5.5 catalog release did for 0.2.1). A broken
-implementation would bump one file but not the other, or forget the bump
-entirely.
+agree, and both must read "0.3.0" for this change (the output_lower_bound
+source_quality value is an additive vocabulary change, so it bumps the minor
+version). A broken implementation would bump one file but not the other, or
+forget the bump entirely.
 
 Uses a plain regex instead of tomllib/tomli: this repo is dependency-free
 by design (pyproject.toml's own dependencies = []) and tomllib is
@@ -29,5 +29,5 @@ def test_pyproject_version_matches_package_version():
 
 
 def test_version_is_0_2_0():
-    assert agent_cost.__version__ == "0.2.2"
-    assert _pyproject_version() == "0.2.2"
+    assert agent_cost.__version__ == "0.3.0"
+    assert _pyproject_version() == "0.3.0"