cc-transcript 12.1.0__tar.gz → 13.0.0__tar.gz

{cc_transcript-12.1.0 → cc_transcript-13.0.0}/Cargo.lock

@@ -2,6 +2,12 @@
 # It is not intended for manual editing.
 version = 4
 
+[[package]]
+name = "adler2"
+version = "2.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "320119579fcad9c21884f5c4861d16174d0e06250625266f50fe6898340abefa"
+
 [[package]]
 name = "ahash"
 version = "0.8.12"
@@ -9,7 +15,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5a15f179cd60c4584b8a8c596927aadc462e27f2ca70c04e0071964a73ba7a75"
 dependencies = [
  "cfg-if",
- "getrandom",
+ "getrandom 0.3.4",
  "once_cell",
  "version_check",
  "zerocopy",
@@ -30,6 +36,12 @@ version = "1.5.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f2032f911046de80f0a198e0901378627c33f59ea0ac00e363d481118bd70a53"
 
+[[package]]
+name = "base64"
+version = "0.22.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
+
 [[package]]
 name = "bitflags"
 version = "2.13.0"
@@ -74,6 +86,7 @@ dependencies = [
  "sonic-rs",
  "tree-sitter",
  "tree-sitter-bash",
+ "udpipe-rs",
 ]
 
 [[package]]
@@ -100,6 +113,15 @@ dependencies = [
  "num-traits",
 ]
 
+[[package]]
+name = "crc32fast"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9481c1c90cbf2ac953f07c8d4a58aa3945c425b7185c9154d67a65e4230da511"
+dependencies = [
+ "cfg-if",
+]
+
 [[package]]
 name = "crossbeam-channel"
 version = "0.5.15"
@@ -180,6 +202,16 @@ version = "0.1.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5baebc0774151f905a1a2cc41989300b1e6fbb29aff0ceffa1064fdd3088d582"
 
+[[package]]
+name = "flate2"
+version = "1.1.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "843fba2746e448b37e26a819579957415c8cef339bf08564fe8b7ddbd959573c"
+dependencies = [
+ "crc32fast",
+ "miniz_oxide",
+]
+
 [[package]]
 name = "futures-core"
 version = "0.3.32"
@@ -204,6 +236,17 @@ dependencies = [
  "slab",
 ]
 
+[[package]]
+name = "getrandom"
+version = "0.2.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ff2abc00be7fca6ebc474524697ae276ad847ad0a6b3faa4bcb027e9a4614ad0"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "wasi",
+]
+
 [[package]]
 name = "getrandom"
 version = "0.3.4"
@@ -234,6 +277,22 @@ version = "0.5.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "fc0fef456e4baa96da950455cd02c081ca953b141298e41db3fc7e36b1da849c"
 
+[[package]]
+name = "http"
+version = "1.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6970f50e31d6fc17d3fa27329444bfa74e196cf62e95052a3f6fee181dba6425"
+dependencies = [
+ "bytes",
+ "itoa",
+]
+
+[[package]]
+name = "httparse"
+version = "1.10.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6dbf3de79e51f3d586ab4cb9d5c3e2c14aa28ed23d180cf89b4df0454a69cc87"
+
 [[package]]
 name = "indexmap"
 version = "2.14.0"
@@ -274,12 +333,28 @@ version = "0.12.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "32a66949e030da00e8c7d4434b251670a91556f4144941d37452769c25d58a53"
 
+[[package]]
+name = "log"
+version = "0.4.33"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0ceec5bc11778974d1bcb055b18002eba7f4b3518b6a0081b3af5f21666da9ad"
+
 [[package]]
 name = "memchr"
 version = "2.8.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6b947ae49db0d222b1dbc6b113ce7248a3fc3a6ca21b696717bfc000ba4484d8"
 
+[[package]]
+name = "miniz_oxide"
+version = "0.8.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1fa76a2c86f704bdb222d66965fb3d63269ce38518b83cb0575fca855ebb6316"
+dependencies = [
+ "adler2",
+ "simd-adler32",
+]
+
 [[package]]
 name = "munge"
 version = "0.4.7"
@@ -325,6 +400,12 @@ version = "1.21.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9f7c3e4beb33f85d45ae3e3a1792185706c8e16d043238c593331cc7cd313b50"
 
+[[package]]
+name = "percent-encoding"
+version = "2.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9b4f627cb1b25917193a259e49bdad08f671f8d9708acfd5fe0a8c1455d87220"
+
 [[package]]
 name = "pin-project-lite"
 version = "0.2.17"
@@ -524,6 +605,20 @@ version = "0.5.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cadadef317c2f20755a64d7fdc48f9e7178ee6b0e1f7fce33fa60f1d68a276e6"
 
+[[package]]
+name = "ring"
+version = "0.17.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a4689e6c2294d81e88dc6261c768b63bc4fcdb852be6d1352498b114f61383b7"
+dependencies = [
+ "cc",
+ "cfg-if",
+ "getrandom 0.2.17",
+ "libc",
+ "untrusted",
+ "windows-sys",
+]
+
 [[package]]
 name = "rkyv"
 version = "0.8.16"
@@ -566,6 +661,41 @@ dependencies = [
  "windows-sys",
 ]
 
+[[package]]
+name = "rustls"
+version = "0.23.41"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6b92b125634d9b795e7beca796cc790df15a7fb38323bf3196fda83292d06b1f"
+dependencies = [
+ "log",
+ "once_cell",
+ "ring",
+ "rustls-pki-types",
+ "rustls-webpki",
+ "subtle",
+ "zeroize",
+]
+
+[[package]]
+name = "rustls-pki-types"
+version = "1.15.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "764899a24af3980067ee14bc143654f297b22eaebfe3c7b6b211920a5a59b046"
+dependencies = [
+ "zeroize",
+]
+
+[[package]]
+name = "rustls-webpki"
+version = "0.103.13"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "61c429a8649f110dddef65e2a5ad240f747e85f7758a6bccc7e5777bd33f756e"
+dependencies = [
+ "ring",
+ "rustls-pki-types",
+ "untrusted",
+]
+
 [[package]]
 name = "rustversion"
 version = "1.0.22"
@@ -622,6 +752,12 @@ version = "2.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f8fadd59c855ef2080decdef8ff161eb6661b86933c9d82e5ba29dc602a55aba"
 
+[[package]]
+name = "simd-adler32"
+version = "0.3.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "703d5c7ef118737c72f1af64ad2f6f8c5e1921f818cdcb97b8fe6fc69bf66214"
+
 [[package]]
 name = "simdutf8"
 version = "0.1.5"
@@ -679,6 +815,12 @@ version = "0.1.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2b2231b7c3057d5e4ad0156fb3dc807d900806020c5ffa3ee6ff2c8c76fb8520"
 
+[[package]]
+name = "subtle"
+version = "2.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "13c2bddecc57b384dee18652358fb23172facb8a2c51ccc10d74c157bdea3292"
+
 [[package]]
 name = "swift-bridge"
 version = "0.1.59"
@@ -759,7 +901,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "32497e9a4c7b38532efcdebeef879707aa9f794296a4f0244f6f69e9bc8574bd"
 dependencies = [
  "fastrand",
- "getrandom",
+ "getrandom 0.3.4",
  "once_cell",
  "rustix",
  "windows-sys",
@@ -830,12 +972,63 @@ version = "0.1.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "009994f150cc0cd50ff54917d5bc8bffe8cad10ca10d81c34da2ec421ae61782"
 
+[[package]]
+name = "udpipe-rs"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9a8f34a036b145a2d253613c2742c836f79c9d5f9c2220f03931762224d23452"
+dependencies = [
+ "cc",
+ "ureq",
+]
+
 [[package]]
 name = "unicode-ident"
 version = "1.0.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
 
+[[package]]
+name = "untrusted"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8ecb6da28b8a351d773b68d5825ac39017e680750f980f3a1a85cd8dd28a47c1"
+
+[[package]]
+name = "ureq"
+version = "3.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dea7109cdcd5864d4eeb1b58a1648dc9bf520360d7af16ec26d0a9354bafcfc0"
+dependencies = [
+ "base64",
+ "flate2",
+ "log",
+ "percent-encoding",
+ "rustls",
+ "rustls-pki-types",
+ "ureq-proto",
+ "utf8-zero",
+ "webpki-roots",
+]
+
+[[package]]
+name = "ureq-proto"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e994ba84b0bd1b1b0cf92878b7ef898a5c1760108fe7b6010327e274917a808c"
+dependencies = [
+ "base64",
+ "http",
+ "httparse",
+ "log",
+]
+
+[[package]]
+name = "utf8-zero"
+version = "0.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b8c0a043c9540bae7c578c88f91dda8bd82e59ae27c21baca69c8b191aaf5a6e"
+
 [[package]]
 name = "uuid"
 version = "1.23.2"
@@ -852,6 +1045,12 @@ version = "0.9.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
 
+[[package]]
+name = "wasi"
+version = "0.11.1+wasi-snapshot-preview1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ccf3ec651a847eb01de73ccad15eb7d99f80485de043efb2f370cd654f4ea44b"
+
 [[package]]
 name = "wasip2"
 version = "1.0.3+wasi-0.2.9"
@@ -906,6 +1105,15 @@ dependencies = [
  "unicode-ident",
 ]
 
+[[package]]
+name = "webpki-roots"
+version = "1.0.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bf85cb06032201fa7c6f829d7db5a7e5aa45bcc0655327713065f6f0576731bf"
+dependencies = [
+ "rustls-pki-types",
+]
+
 [[package]]
 name = "windows-sys"
 version = "0.52.0"
@@ -1005,6 +1213,12 @@ dependencies = [
  "syn 2.0.117",
 ]
 
+[[package]]
+name = "zeroize"
+version = "1.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e13c156562582aa81c60cb29407084cdb54c4164760106ab78e6c5b0858cf64e"
+
 [[package]]
 name = "zmij"
 version = "1.0.21"

{cc_transcript-12.1.0 → cc_transcript-13.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cc-transcript
-Version: 12.1.0
+Version: 13.0.0
 Classifier: Development Status :: 3 - Alpha
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
@@ -117,7 +117,7 @@ Each block reports text, thinking, and tool-io bytes plus per-tool call counts;
 - [Filtering events](https://yasyf.github.io/cc-transcript/docs/guide/filtering-events.html) covers composable clauses, specs, and the ready-made `NOISE_SPEC`.
 - [Sentiment scoring](https://yasyf.github.io/cc-transcript/docs/guide/scoring-sentiment.html) buckets conversations and scores them around any inference engine.
 - [Feedback mining](https://yasyf.github.io/cc-transcript/docs/guide/mining-feedback.html) runs detectors, confidence calibration, and LLM verdict passes over your corpus.
-- [Two backends, one protocol](https://yasyf.github.io/cc-transcript/docs/guide/backends-and-parity.html) pairs a Rust fast path with a Python reference, parity-asserted against each other.
+- [The Rust engine](https://yasyf.github.io/cc-transcript/docs/guide/rust-engine.html) executes parsing, filtering, scoring, and mining, its correctness pinned by generated literals and golden fixtures.
 - [API reference](https://yasyf.github.io/cc-transcript/reference/index.html) documents the complete typed surface, from `TranscriptEvent` to `SessionActivity`.
 
 Read the [docs](https://yasyf.github.io/cc-transcript/) for the full guide. Licensed under [PolyForm Noncommercial 1.0.0](https://github.com/yasyf/cc-transcript/blob/main/LICENSE).

{cc_transcript-12.1.0 → cc_transcript-13.0.0}/README.md

@@ -77,7 +77,7 @@ Each block reports text, thinking, and tool-io bytes plus per-tool call counts;
 - [Filtering events](https://yasyf.github.io/cc-transcript/docs/guide/filtering-events.html) covers composable clauses, specs, and the ready-made `NOISE_SPEC`.
 - [Sentiment scoring](https://yasyf.github.io/cc-transcript/docs/guide/scoring-sentiment.html) buckets conversations and scores them around any inference engine.
 - [Feedback mining](https://yasyf.github.io/cc-transcript/docs/guide/mining-feedback.html) runs detectors, confidence calibration, and LLM verdict passes over your corpus.
-- [Two backends, one protocol](https://yasyf.github.io/cc-transcript/docs/guide/backends-and-parity.html) pairs a Rust fast path with a Python reference, parity-asserted against each other.
+- [The Rust engine](https://yasyf.github.io/cc-transcript/docs/guide/rust-engine.html) executes parsing, filtering, scoring, and mining, its correctness pinned by generated literals and golden fixtures.
 - [API reference](https://yasyf.github.io/cc-transcript/reference/index.html) documents the complete typed surface, from `TranscriptEvent` to `SessionActivity`.
 
 Read the [docs](https://yasyf.github.io/cc-transcript/) for the full guide. Licensed under [PolyForm Noncommercial 1.0.0](https://github.com/yasyf/cc-transcript/blob/main/LICENSE).

{cc_transcript-12.1.0 → cc_transcript-13.0.0}/cc_transcript/__init__.py

@@ -147,7 +147,7 @@ EXPORTS: dict[str, str] = {
             "cost_of_assistant",
             "resolve_pricing",
         ),
-        "cc_transcript.backend": ("Backend", "ParsedTranscript"),
+        "cc_transcript.backend": ("ParsedTranscript",),
         "cc_transcript.discovery": (
             "CLAUDE_PROJECTS_DIR",
             "TranscriptDiscovery",
@@ -275,7 +275,6 @@ if TYPE_CHECKING:
     from cc_transcript.activity import (
         result_index as result_index,
     )
-    from cc_transcript.backend import Backend as Backend
     from cc_transcript.backend import ParsedTranscript as ParsedTranscript
     from cc_transcript.builders import (
         NOISE_SPEC as NOISE_SPEC,

{cc_transcript-12.1.0 → cc_transcript-13.0.0}/cc_transcript/_parser_rs.pyi

@@ -30,11 +30,18 @@ def lexicon_polarity(token: str, /) -> int:
     """Polarity of a single token surface: domain override, else AFINN floored at MIN_MAGNITUDE."""
 
 def lexicon_has_hit(text: str, want_negative: bool, /) -> bool:
-    """Whether any token surface's polarity crosses the fixed ±3 floor (the negative side when ``want_negative``)."""
+    """Whether any content token's effective (negation-flipped) polarity crosses the fixed ±3 floor."""
 
 def lexicon_overrides() -> list[tuple[str, int]]:
     """The embedded domain-override entries (for the single-source drift guard)."""
 
+def nlp_analyze(text: str, /) -> list[tuple[str, str, str, str, int, int, int, bool]]:
+    """Analyze ``text`` with the embedded UDPipe model.
+
+    Per token: ``(form, lower, lemma, upos, char_start, char_end, polarity, negated)``,
+    where offsets are codepoint indices and polarity is the surface-keyed lexicon score.
+    """
+
 def embedded_literals() -> dict[str, str | float | list[str]]:
     """The generated protocol, mining, and command literals keyed ``module.NAME`` (for the single-source drift guard)."""
 
@@ -47,8 +54,10 @@ def score_post_process(spec_json: str, buckets: list[list[str]], raw: list[int],
 def command_prefixes(commands: list[str], /) -> list[list[str]]:
     """Permission-style prefixes per command line, parsed in parallel off the GIL."""
 
-def mine_signals(raw: bytes, spec_json: str, /) -> list[dict[str, Any]]:
-    """Parses raw transcript bytes and mines signal dicts per the portable mining spec."""
+def mine_events(
+    events: list[TranscriptEvent], spec_json: str, callable_formats: list[tuple[str, Any, Any]], /
+) -> list[dict[str, Any]]:
+    """Mines signal dicts from parsed transcript events per the portable mining spec."""
 
 def session_activity_probe(
     path: str, waiting_tools: list[str] | None = ..., human_facing_tools: list[str] | None = ..., /

cc_transcript-13.0.0/cc_transcript/activity_probe.py

@@ -0,0 +1,98 @@
+"""Session-activity probe — captain-hook's ``is_waiting`` oracle over one transcript.
+
+:func:`session_activity_probe` is the public entry: it hands a ``.jsonl`` transcript to the
+Rust extension, which reads and parses the file and runs the oracle in one pass, returning a
+:class:`SessionActivityProbe`. The verdict spans undelivered task notifications (the
+:class:`~cc_transcript.notifications.Notifications` queue replay), ephemeral waits (waiting
+tools, backgrounded Agent/Task/Bash, subagentless Agent/Task) over the current turn, and
+pending async launches (async Agent/Task, live Workflow) session-wide — a launch counts as
+completed only once its notification was delivered or drained, never when merely enqueued —
+and flags unanswered non-human-facing tool calls in the current turn as mid-tool.
+Compact-summary user lines do not open turns, matching captain-hook, which consumes this
+probe since the 10.2.0 shared-classifier fix.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import TYPE_CHECKING, Literal
+
+from cc_transcript.tools import expand_tool_names
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+DEFAULT_WAITING_TOOLS = frozenset({"Monitor", "ScheduleWakeup", "SendMessage", "TeamCreate"})
+DEFAULT_HUMAN_FACING_TOOLS = expand_tool_names("AskUserQuestion|ExitPlanMode")
+
+PendingKind = Literal[
+    "waiting_tool",
+    "background",
+    "subagentless_task",
+    "pending_async_task",
+    "pending_async_workflow",
+    "mid_tool",
+]
+"""How a tool call contributes to the session-activity verdict."""
+
+
+@dataclass(frozen=True, slots=True)
+class PendingItem:
+    """One tool call contributing to the session-activity verdict.
+
+    Attributes:
+        tool_use_id: The contributing call's tool-use id.
+        name: The tool's name exactly as invoked.
+        kind: How the call contributes to the verdict.
+    """
+
+    tool_use_id: str | None
+    name: str
+    kind: PendingKind
+
+
+@dataclass(frozen=True, slots=True)
+class SessionActivityProbe:
+    """The session-activity verdict over one transcript.
+
+    Attributes:
+        is_waiting: Whether the session waits on ephemeral or pending async work.
+        mid_tool: Whether the current turn has an unanswered non-human-facing call.
+        pending: The contributing calls, in document order, deduped by tool-use id.
+        last_event_epoch: The latest envelope timestamp as epoch seconds, or None.
+    """
+
+    is_waiting: bool
+    mid_tool: bool
+    pending: tuple[PendingItem, ...]
+    last_event_epoch: int | None
+
+
+def session_activity_probe(
+    path: Path,
+    *,
+    waiting_tools: frozenset[str] = DEFAULT_WAITING_TOOLS,
+    human_facing_tools: frozenset[str] = DEFAULT_HUMAN_FACING_TOOLS,
+) -> SessionActivityProbe:
+    """Probes the transcript at ``path`` for session activity.
+
+    The Rust extension reads and parses the file and runs the oracle in one pass,
+    returning the session-activity verdict.
+
+    Args:
+        path: The ``.jsonl`` transcript to probe.
+        waiting_tools: Tool names whose calls in the current turn mark the session waiting.
+        human_facing_tools: Tool names whose unanswered calls are the user's move, never mid-tool.
+
+    Returns:
+        The session-activity verdict.
+    """
+    from cc_transcript import _parser_rs
+
+    payload = _parser_rs.session_activity_probe(str(path), sorted(waiting_tools), sorted(human_facing_tools))
+    return SessionActivityProbe(
+        is_waiting=payload["is_waiting"],
+        mid_tool=payload["mid_tool"],
+        pending=tuple(PendingItem(**item) for item in payload["pending"]),
+        last_event_epoch=payload["last_event_epoch"],
+    )

cc_transcript-13.0.0/cc_transcript/backend.py

@@ -0,0 +1,24 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+    from cc_transcript.models import TranscriptEvent
+
+
+@dataclass(frozen=True, slots=True)
+class ParsedTranscript:
+    """The parsed events of a single transcript file.
+
+    Attributes:
+        path: The transcript's path on disk.
+        mtime: The transcript's modification time when parsed.
+        events: The parsed events, in file order.
+    """
+
+    path: Path
+    mtime: float
+    events: tuple[TranscriptEvent, ...]

{cc_transcript-12.1.0 → cc_transcript-13.0.0}/cc_transcript/command.py

@@ -495,22 +495,8 @@ def command_prefixes(command: str) -> tuple[str, ...]:
     return parse_command_line(command).prefixes
 
 
-def load_rust_prefixes() -> Callable[[list[str]], list[list[str]]] | None:
-    # Stale-extension guard (mirrors parser.load_rust_backend): the compiled
-    # extension may be absent or predate the command_prefixes symbol.
-    try:
-        from cc_transcript import _parser_rs
-    except ImportError:
-        return None
-    return _parser_rs.command_prefixes if hasattr(_parser_rs, "command_prefixes") else None
-
-
 def bulk_command_prefixes(commands: Sequence[str]) -> list[tuple[str, ...]]:
-    """``command_prefixes`` over many commands at once, on the Rust fast path when available.
+    """``command_prefixes`` over many commands at once, on the Rust fast path."""
+    from cc_transcript import _parser_rs
 
-    Falls back to the Python parser when the compiled extension is missing or
-    predates the ``command_prefixes`` symbol.
-    """
-    if rust := load_rust_prefixes():
-        return [tuple(prefixes) for prefixes in rust(list(commands))]
-    return [command_prefixes(command) for command in commands]
+    return [tuple(prefixes) for prefixes in _parser_rs.command_prefixes(list(commands))]

{cc_transcript-12.1.0 → cc_transcript-13.0.0}/cc_transcript/facts.py

@@ -95,6 +95,7 @@ def fact_of(use: ToolUse, session_id: SessionId, path: Path, prefixes: tuple[str
     call = use.call
     server, tool, access = mcp_split(call.name)
     denied, user_said = denial_fields(use.result)
+    assert use.ref.tool_use_id is not None, "ToolUse refs always carry the tool-use id"
     return ToolFact(
         ts=use.ts,
         session_id=session_id,

{cc_transcript-12.1.0 → cc_transcript-13.0.0}/cc_transcript/filterspec.py

@@ -1,9 +1,12 @@
-"""Declarative, both-backend filtering of a transcript event stream.
+"""Declarative filtering of a transcript event stream.
 
 A :class:`FilterSpec` is an ordered list of :class:`Clause` rules — *filters as
-data*. The same spec is interpreted by the Python interpreter here and, when
-:func:`is_portable` holds, serialized via :func:`spec_to_json` and executed by
-the Rust backend, which drops events before ever materializing a Python object.
+data*. Parse-time filtering runs in Rust: :func:`spec_to_json` serializes the spec to
+the JSON contract the Rust backend executes, dropping events during parsing before
+they ever materialize (pass a spec to
+:meth:`~cc_transcript.TranscriptParser.stream_transcripts`). Already-materialized
+events — a list the caller already holds — are filtered with :func:`apply_spec` or
+:func:`keep`.
 
 Consumers compose specs from the builders in :mod:`cc_transcript.builders` over
 named building blocks: the junk regex is split into categories
@@ -168,20 +171,6 @@ HEDGE_GROUPS: tuple[tuple[str, str], ...] = (
     ("hedged", r"\b(?:maybe|perhaps|possibly|might|not sure|i think|i guess|if you (?:want|prefer)|up to you)\b"),
 )
 
-PORTABLE_GROUP_NAMES: frozenset[str] = frozenset(
-    name
-    for name, _ in (
-        *STRUCTURAL_NOISE_GROUPS,
-        *INTERRUPT_MARKER_GROUPS,
-        *STOP_HOOK_GROUPS,
-        *CONTINUATION_GROUPS,
-        *COMMAND_ECHO_GROUPS,
-        *FRUSTRATION_GROUPS,
-        *MILD_IMPATIENCE_GROUPS,
-        *HEDGE_GROUPS,
-    )
-)
-
 RESUME_PHRASE_SET: frozenset[str] = frozenset(
     {
         "continue",
@@ -491,7 +480,11 @@ def clause_matches(clause: Clause, event: TranscriptEvent, kind: EventKind) -> b
 
 
 def keep(event: TranscriptEvent, spec: FilterSpec) -> bool:
-    """Returns whether ``event`` survives every ``DROP`` clause of ``spec``."""
+    """Returns whether ``event`` survives every ``DROP`` clause of ``spec``.
+
+    Filters an already-materialized :class:`~cc_transcript.models.TranscriptEvent`;
+    parse-time filtering runs in Rust before materialization via :func:`spec_to_json`.
+    """
     kind = event_kind(event)
     return not any(clause.action is Action.DROP and clause_matches(clause, event, kind) for clause in spec.clauses)
 
@@ -509,7 +502,7 @@ def labels_for(event: TranscriptEvent, spec: FilterSpec) -> tuple[str, ...]:
 
 
 def apply_spec(events: Iterable[TranscriptEvent], spec: FilterSpec) -> Iterator[TranscriptEvent]:
-    """Yields the events that survive every ``DROP`` clause of ``spec``."""
+    """Yields the already-materialized events that survive every ``DROP`` clause of ``spec``."""
     return (event for event in events if keep(event, spec))
 
 
@@ -520,24 +513,6 @@ def annotate_spec(
     return ((event, labels_for(event, spec)) for event in events if keep(event, spec))
 
 
-def is_portable(spec: FilterSpec) -> bool:
-    """Returns whether every clause is executable by the Rust interpreter.
-
-    A spec is portable when each :class:`TextMatchesAny` uses only group names
-    proven to match identically under the Rust ``regex`` crate; non-portable
-    specs fall back to the Python interpreter.
-    """
-    return all(clause_portable(clause) for clause in spec.clauses)
-
-
-def clause_portable(clause: Clause) -> bool:
-    match clause.predicate:
-        case TextMatchesAny(groups=groups):
-            return all(name in PORTABLE_GROUP_NAMES for name, _ in groups)
-        case _:
-            return True
-
-
 def spec_to_json(spec: FilterSpec) -> str:
     """Serializes ``spec`` to the JSON contract consumed by the Rust backend."""
     return orjson.dumps({"clauses": [clause_to_dict(clause) for clause in spec.clauses]}).decode()