nisse-review: read long files in parts; a retry starts afresh

From its failed review of #156: read_file stopped at 20,000 characters
with no way on, so the reviewer hunted each file's end a definition at a
time and ran out of turns; its retry carried every read before it, and a
model call timed out. Both drafts were lost.

- read_file takes a start line and says where the next part starts.
- Each run's view starts at its brief (Transcript.since); the log keeps
  the rest.
- A run out of turns with points drafted posts them as a partial review.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J5Utyfzw7gF7UhjRDEtjTk

nisse-review/src/nisse_review/reader.py

@@ -27,9 +27,11 @@ MAX_ISSUES = 20
 REF = "head (the PR's code) or base (the branch it merges into)."
 READ_FILE = tool(
     "read_file",
-    "Read a file in the repository. Its lines are numbered, for comment.",
+    "Read a file in the repository. Its lines are numbered, for comment. A "
+    "long file comes in parts: the end of each says where the next starts.",
     path="The file's path from the repository root.",
     ref=REF,
+    start="Optional: the line to start from (1, the default, is the top).",
 )
 LIST_FILES = tool(
     "list_files",
@@ -131,11 +133,27 @@ class Repository:
         lines = self.lines(path, ref)
         if lines is None:
             return ToolOutcome(f"{path}: no such file at {ref}", False)
-        text = "\n".join(f"{n:>5}  {line}" for n, line in enumerate(lines, 1))
-        if len(text) > MAX_FILE_CHARS:
-            more = len(text) - MAX_FILE_CHARS
-            text = text[:MAX_FILE_CHARS] + f"\n[{more} more characters not shown]"
-        return ToolOutcome(f"[{self.repo}@{ref}: {path}]\n{text}", True)
+        raw = str(arguments.get("start") or "1").strip()
+        if not raw.isdigit() or not 1 <= int(raw) <= max(len(lines), 1):
+            return ToolOutcome(f"start is a line number from 1 to {len(lines)}", False)
+        # A part of at most MAX_FILE_CHARS, in whole lines; the rest is a
+        # read away, never out of reach (#156: a long file's end was).
+        first = int(raw)
+        shown: list[str] = []
+        size = 0
+        for n in range(first, len(lines) + 1):
+            row = f"{n:>5}  {lines[n - 1]}"
+            if shown and size + len(row) + 1 > MAX_FILE_CHARS:
+                break
+            shown.append(row[:MAX_FILE_CHARS])
+            size += len(row) + 1
+        last = first + len(shown) - 1
+        where = f"lines {first}-{last} of {len(lines)}"
+        more = (
+            f"\n[{where}: read on with start={last + 1}]" if last < len(lines) else ""
+        )
+        text = "\n".join(shown)
+        return ToolOutcome(f"[{self.repo}@{ref}: {path}, {where}]\n{text}{more}", True)
 
     def _list(self, arguments: Mapping[str, Any]) -> ToolOutcome:
         folder = str(arguments.get("path", "")).strip().strip("/")

nisse-review/src/nisse_review/review.py

@@ -118,6 +118,10 @@ class Reviewer:
         """The review run: it ends waiting on post_review, or not."""
         transcript = self._store.transcript(item_id, "driver")
         start = transcript.read()[-1].id if transcript.read() else 0
+        # Each run starts afresh from its brief: a retry doesn't carry the
+        # failed run's reads (#156: they filled the context, and a call timed
+        # out). The log keeps them.
+        transcript = transcript.since(start)
         self._brief(transcript, repo.repo, pr)
         project = _project(repo.repo)
         index = self._knowledge.index(item_id, project)

nisse-review/src/nisse_review/scheduler.py

@@ -38,6 +38,12 @@ from nisse_review.state import (
     pr_of,
 )
 
+PARTIAL = (
+    "A partial review: I ran out of turns before finishing, so these are the "
+    "{n} point(s) I had drafted, without an overall view. A new push gets a "
+    "full look."
+)
+
 _WIP = re.compile(r"^\s*(\[wip\]|wip\b)", re.IGNORECASE)
 
 
@@ -238,10 +244,18 @@ class Scheduler:
                 outcome, draft = self._reviewer.run(item.id, pr, repo)
             finally:
                 repo.close()
-            if outcome.kind != "wait":
+            if outcome.kind == "capped" and draft.comments:
+                # Out of turns with points drafted: they're worth more posted
+                # than lost (#156), as a review that says it's partial.
+                self._oplog.emit(
+                    "review.partial", cause=outcome.note, work_item=item.id
+                )
+                summary = PARTIAL.format(n=len(draft.comments))
+            elif outcome.kind != "wait":
                 self._failed(item, known, pr, outcome.note or outcome.kind)
                 return
-            summary = str((outcome.arguments or {}).get("summary", ""))
+            else:
+                summary = str((outcome.arguments or {}).get("summary", ""))
             posted = self._reviewer.post(item.id, known.repo, pr, summary, draft)
         except GiteaError as exc:
             self._failed(item, known, None, f"Gitea: {exc}")