Files
Gitea-Tools/webui/linkage_loader.py
T
sysadminandClaude Opus 4.8 211890f361 feat(webui): Gitea issue and PR linkage console (Closes #645)
Add a Phase 3 read-only console that resolves issue↔PR linkage with
evidence (closes keyword, branch marker, body mention), surfaces the
latest canonical handoff for a focused thread, and deep-links to Gitea
only under the admin reveal opt-in.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
2026-07-25 16:40:07 -04:00

772 lines
27 KiB
Python

"""Gitea issue↔PR linkage model for the console (#645, Phase 3).
Operators lose context between an issue and the PR that closes it: which PR
carries which issue, whether two PRs claim the same issue, and what the latest
canonical handoff on that thread said. The evidence exists in Gitea, but only
as free text scattered across PR titles, bodies, and branch names.
This module resolves that linkage into one read-only model:
* :func:`resolve_linkage` is a pure function from raw Gitea issue/PR payloads to
a :class:`LinkageIndex`. It records *how* each edge was found (a ``Closes #N``
keyword, the canonical ``feat/issue-N-…`` branch marker, or a bare ``#N``
body reference) and never collapses several candidates into one silent guess.
* :func:`load_linkage_snapshot` scopes that index to a registry project and
optionally attaches the latest Canonical Thread Handoff (CTH) summary for one
focused issue or PR.
Design rules, matching the rest of the console:
- **Read-only.** Gitea is read through the shared authenticated helpers. No
endpoint here mutates anything, and no write action is registered.
- **Qualified absence.** Linkage is a claim about a *loaded* window of Gitea.
When pagination did not complete, when credentials were unavailable, or when
only open items were fetched, the snapshot says so and every "no linked PR"
is marked non-authoritative. An empty edge list from a partial read is not
evidence that no link exists.
- **Handoff is loaded, never assumed.** CTH comments are thread-scoped, so they
are fetched only for an explicitly focused issue or PR. Every other row
reports ``not_loaded`` rather than rendering as "no handoff".
- **Redaction at the boundary.** Titles, labels, handoff fields, and error
reasons are free text from Gitea and cross :mod:`webui.console_redaction`
before they leave this module.
- **Deep links are opt-in.** A link to the Gitea web UI is emitted only under
the ``GITEA_MCP_REVEAL_ENDPOINTS`` admin opt-in, exactly as the MCP tools
gate their own URL exposure.
Non-goals (from the issue): no issue/PR editor, no browser review or merge, no
reimplementation of Gitea search.
"""
from __future__ import annotations
import os
import re
from dataclasses import dataclass
from typing import Any, Callable, Iterable, Sequence
from gitea_auth import api_fetch_page, get_auth_header, gitea_url, repo_api_url
from webui import console_redaction
from webui.project_registry import ProjectRecord, load_registry
from webui.queue_loader import (
PaginationMeta,
_fetch_issues,
_fetch_prs,
_host_from_url,
)
#: Version of the serialized linkage contract. Bump on any breaking change.
LINKAGE_SCHEMA_VERSION = 1
# --- Linkage evidence -------------------------------------------------------
# Ordered strongest to weakest. The strength ordering is what makes an
# ambiguous PR detectable: two candidates at the same strength are a genuine
# ambiguity, while a weaker candidate alongside a stronger one is not.
EVIDENCE_CLOSES = "closes_keyword"
EVIDENCE_BRANCH = "branch_marker"
EVIDENCE_REFERENCE = "body_reference"
EVIDENCE_ORDER: tuple[str, ...] = (
EVIDENCE_CLOSES,
EVIDENCE_BRANCH,
EVIDENCE_REFERENCE,
)
_EVIDENCE_RANK = {name: rank for rank, name in enumerate(EVIDENCE_ORDER)}
EVIDENCE_DESCRIPTIONS: dict[str, str] = {
EVIDENCE_CLOSES: (
"the PR title or body declares 'closes/fixes/resolves #N' — Gitea itself "
"acts on this keyword, so it is the strongest available evidence"
),
EVIDENCE_BRANCH: (
"the PR head branch carries the canonical issue marker "
"'(fix|feat|docs|chore)/issue-N-…' minted by the issue lock"
),
EVIDENCE_REFERENCE: (
"the PR body mentions '#N' without a closing keyword; a mention is not "
"a claim that the PR closes that issue"
),
}
_CLOSES_RE = re.compile(r"(?:closes|fixes|resolves)\s+#(\d+)", re.IGNORECASE)
_REFERENCE_RE = re.compile(r"#(\d+)")
_BRANCH_MARKER_RE = re.compile(
r"^(?:fix|feat|docs|chore)/issue-(\d+)(?:[-/]|$)", re.IGNORECASE
)
# Handoff-source states. ``not_loaded`` is deliberately distinct from "none
# found": a row whose comments were never fetched proves nothing about whether
# a handoff exists on that thread.
HANDOFF_NOT_LOADED = "not_loaded"
HANDOFF_LOADED = "loaded"
HANDOFF_UNAVAILABLE = "unavailable"
# Which item states were fetched. Linkage claims are scoped to this window.
STATE_OPEN = "open"
STATE_ALL = "all"
_SUPPORTED_STATES = (STATE_OPEN, STATE_ALL)
def _redact(value: Any) -> Any:
"""Redact one free-text field, failing closed to the placeholder."""
if value is None:
return None
return console_redaction.redact_text(str(value))
def deep_links_enabled(env: dict[str, str] | None = None) -> bool:
"""Whether Gitea web-UI deep links may be emitted (admin/debug opt-in)."""
source = env if env is not None else os.environ
return (source.get("GITEA_MCP_REVEAL_ENDPOINTS") or "").strip().lower() in {
"1",
"true",
"yes",
"on",
}
def _deep_link(host: str, org: str, repo: str, kind: str, number: int) -> str | None:
"""Build a Gitea web link for one item, or None when reveal is not enabled."""
if not deep_links_enabled() or not (host and org and repo):
return None
segment = "pulls" if kind == "pr" else "issues"
try:
return gitea_url(host, f"/{org}/{repo}/{segment}/{int(number)}")
except Exception:
return None
# --- Pure linkage resolution -------------------------------------------------
@dataclass(frozen=True)
class IssueLink:
"""One resolved edge from a PR to an issue, with the evidence that found it."""
issue_number: int
evidence: tuple[str, ...]
@property
def strength(self) -> int:
"""Rank of the strongest evidence backing this edge (lower is stronger)."""
return min(
(_EVIDENCE_RANK.get(name, len(EVIDENCE_ORDER)) for name in self.evidence),
default=len(EVIDENCE_ORDER),
)
@property
def closes(self) -> bool:
"""True only when the PR *declares* it closes the issue."""
return EVIDENCE_CLOSES in self.evidence
def to_dict(self) -> dict[str, Any]:
return {
"issue_number": self.issue_number,
"evidence": list(self.evidence),
"closes": self.closes,
}
def _sorted_links(links: Iterable[IssueLink]) -> tuple[IssueLink, ...]:
return tuple(sorted(links, key=lambda link: (link.strength, link.issue_number)))
def resolve_pr_links(pr: dict[str, Any]) -> tuple[IssueLink, ...]:
"""Resolve every issue a PR points at, strongest evidence first.
Every candidate is kept. Collapsing to a single "linked issue" is what makes
a mislinked or double-claimed PR invisible, so the caller decides what to do
with several candidates rather than being handed one guess.
"""
found: dict[int, set[str]] = {}
def _add(number: Any, evidence: str) -> None:
try:
issue_number = int(number)
except (TypeError, ValueError):
return
if issue_number <= 0:
return
found.setdefault(issue_number, set()).add(evidence)
title = str(pr.get("title") or "")
body = str(pr.get("body") or "")
for text in (title, body):
for match in _CLOSES_RE.finditer(text):
_add(match.group(1), EVIDENCE_CLOSES)
head_ref = str((pr.get("head") or {}).get("ref") or "")
branch_match = _BRANCH_MARKER_RE.match(head_ref.strip())
if branch_match:
_add(branch_match.group(1), EVIDENCE_BRANCH)
# The ``#N`` inside "Closes #N" is the *same* textual occurrence as the
# closing keyword, not a second, independent mention. Blanking the closing
# phrases first keeps "mention" meaning what the legend says it means: a
# reference the PR made without claiming to close anything.
for match in _REFERENCE_RE.finditer(_CLOSES_RE.sub(" ", body)):
_add(match.group(1), EVIDENCE_REFERENCE)
# A PR's own number appearing in its body is self-reference, not linkage.
try:
found.pop(int(pr.get("number")), None)
except (TypeError, ValueError):
pass
return _sorted_links(
IssueLink(
issue_number=number,
evidence=tuple(name for name in EVIDENCE_ORDER if name in evidence),
)
for number, evidence in found.items()
)
@dataclass(frozen=True)
class LinkageIndex:
"""Resolved linkage over one loaded window of issues and PRs."""
pr_links: dict[int, tuple[IssueLink, ...]]
issue_prs: dict[int, tuple[int, ...]]
def primary_issue(self, pr_number: int) -> IssueLink | None:
"""The strongest edge for a PR, or None when it points at no issue."""
links = self.pr_links.get(int(pr_number)) or ()
return links[0] if links else None
def ambiguous(self, pr_number: int) -> bool:
"""True when two or more issues tie at the PR's strongest evidence."""
links = self.pr_links.get(int(pr_number)) or ()
if len(links) < 2:
return False
best = links[0].strength
return sum(1 for link in links if link.strength == best) > 1
def contested_issues(self) -> tuple[int, ...]:
"""Issues claimed by more than one PR in the loaded window."""
return tuple(
number for number, prs in sorted(self.issue_prs.items()) if len(prs) > 1
)
def resolve_linkage(prs: Sequence[dict[str, Any]]) -> LinkageIndex:
"""Build the bidirectional linkage index for a loaded window of PRs.
Only *closing* and *branch-marker* edges populate the issue→PR direction: a
bare ``#N`` mention is a reference, and treating it as "this PR is the work
for issue N" would invent contested issues out of ordinary cross-links. The
weaker edge stays visible on the PR→issue side, where it is labelled.
"""
pr_links: dict[int, tuple[IssueLink, ...]] = {}
issue_prs: dict[int, list[int]] = {}
for pr in prs or []:
try:
pr_number = int(pr["number"])
except (KeyError, TypeError, ValueError):
continue
links = resolve_pr_links(pr)
pr_links[pr_number] = links
for link in links:
if link.evidence == (EVIDENCE_REFERENCE,):
continue
bucket = issue_prs.setdefault(link.issue_number, [])
if pr_number not in bucket:
bucket.append(pr_number)
return LinkageIndex(
pr_links=pr_links,
issue_prs={number: tuple(sorted(items)) for number, items in issue_prs.items()},
)
# --- Canonical handoff summary ----------------------------------------------
@dataclass(frozen=True)
class HandoffSummary:
"""The latest CTH comment on one thread, redacted for display."""
comment_id: int | None
created_at: str | None
author: str | None
cth_type: str
cth_type_known: bool
status: str | None
next_owner: str | None
current_blocker: str | None
decision: str | None
next_action: str | None
def to_dict(self) -> dict[str, Any]:
return {
"comment_id": self.comment_id,
"created_at": self.created_at,
"author": self.author,
"cth_type": self.cth_type,
"cth_type_known": self.cth_type_known,
"status": self.status,
"next_owner": self.next_owner,
"current_blocker": self.current_blocker,
"decision": self.decision,
"next_action": self.next_action,
}
@dataclass(frozen=True)
class HandoffStatus:
"""Why a thread's handoff summary is present, absent, or unknown."""
state: str
reason: str | None = None
target: str | None = None
@property
def loaded(self) -> bool:
return self.state == HANDOFF_LOADED
def to_dict(self) -> dict[str, Any]:
return {"state": self.state, "reason": self.reason, "target": self.target}
def summarize_handoff(comments: Sequence[dict[str, Any]]) -> HandoffSummary | None:
"""Summarize the newest CTH comment in *comments*, or None when there is none.
Every field is redacted before it is returned: a handoff body is operator
free text that regularly quotes commands, and it is rendered verbatim on the
page this feeds.
"""
from canonical_thread_handoff import find_latest_cth, is_known_cth_type
try:
latest = find_latest_cth(list(comments or []))
except Exception:
return None
if not latest:
return None
fields = latest.get("fields") or {}
cth_type = str(latest.get("cth_type") or "").strip()
known = is_known_cth_type(cth_type)
try:
comment_id: int | None = int(latest.get("comment_id"))
except (TypeError, ValueError):
comment_id = None
return HandoffSummary(
comment_id=comment_id,
created_at=_redact(latest.get("created_at")),
author=_redact(latest.get("author")),
# An unrecognised heading is reported as such rather than republished:
# the heading is free text, and CTH_TYPES is the only authority for what
# a handoff type may be.
cth_type=cth_type if known else "unrecognized",
cth_type_known=known,
status=_redact(fields.get("status")),
next_owner=_redact(fields.get("next owner")),
current_blocker=_redact(fields.get("current blocker")),
decision=_redact(fields.get("decision")),
next_action=_redact(fields.get("next action")),
)
CommentSource = Callable[[str, int], list[dict[str, Any]]]
def build_comment_source(host: str, org: str, repo: str) -> CommentSource | None:
"""Build an authenticated ``(kind, number) -> comments`` fetcher, or None.
Returns None when the console is running in offline test mode or when no
credential is available for *host*, so the caller reports the handoff source
as unavailable instead of as an empty thread.
"""
if _offline_test_mode() or not (host and org and repo):
return None
auth = get_auth_header(host)
if not auth:
return None
def _fetch(kind: str, number: int) -> list[dict[str, Any]]:
segment = "pulls" if kind == "pr" else "issues"
url = f"{repo_api_url(host, org, repo)}/{segment}/{int(number)}/comments"
comments: list[dict[str, Any]] = []
page = 1
while page <= 20:
raw, meta = api_fetch_page(url, auth, page=page, limit=50)
comments.extend(raw)
if bool(meta["is_final_page"]):
break
page += 1
return comments
return _fetch
# --- Snapshot ----------------------------------------------------------------
@dataclass(frozen=True)
class LinkageNode:
"""One issue or PR row with its resolved links and display metadata."""
kind: str
number: int
title: str
state: str
labels: tuple[str, ...] = ()
links: tuple[IssueLink, ...] = ()
linked_prs: tuple[int, ...] = ()
ambiguous: bool = False
contested: bool = False
deep_link: str | None = None
handoff: HandoffSummary | None = None
handoff_status: HandoffStatus = HandoffStatus(HANDOFF_NOT_LOADED)
links_authoritative: bool = True
def to_dict(self) -> dict[str, Any]:
return {
"kind": self.kind,
"number": self.number,
"title": self.title,
"state": self.state,
"labels": list(self.labels),
"links": [link.to_dict() for link in self.links],
"linked_prs": list(self.linked_prs),
"ambiguous": self.ambiguous,
"contested": self.contested,
"deep_link": self.deep_link,
"links_authoritative": self.links_authoritative,
"handoff": self.handoff.to_dict() if self.handoff else None,
"handoff_status": self.handoff_status.to_dict(),
}
@dataclass(frozen=True)
class LinkageSnapshot:
"""One answered linkage query over a scoped window of a Gitea repo."""
ok: bool
project_id: str
repo_label: str
host: str
state_scope: str
issues: tuple[LinkageNode, ...] = ()
prs: tuple[LinkageNode, ...] = ()
contested_issues: tuple[int, ...] = ()
focus: tuple[str, int] | None = None
inventory_complete: bool = False
deep_links_enabled: bool = False
handoff_status: HandoffStatus = HandoffStatus(HANDOFF_NOT_LOADED)
fetch_error: str | None = None
@property
def orphan_prs(self) -> tuple[LinkageNode, ...]:
"""PRs in the loaded window that point at no issue at all."""
return tuple(node for node in self.prs if not node.links)
def to_dict(self) -> dict[str, Any]:
return {
"ok": self.ok,
"schema_version": LINKAGE_SCHEMA_VERSION,
"project_id": self.project_id,
"repo": self.repo_label,
"state_scope": self.state_scope,
"inventory_complete": self.inventory_complete,
"deep_links_enabled": self.deep_links_enabled,
"focus": (
None
if self.focus is None
else {"kind": self.focus[0], "number": self.focus[1]}
),
"handoff_source": self.handoff_status.to_dict(),
"fetch_error": self.fetch_error,
"contested_issues": list(self.contested_issues),
"issues": [node.to_dict() for node in self.issues],
"prs": [node.to_dict() for node in self.prs],
"evidence_kinds": [
{"name": name, "description": EVIDENCE_DESCRIPTIONS[name]}
for name in EVIDENCE_ORDER
],
}
def snapshot_to_dict(snapshot: LinkageSnapshot) -> dict[str, Any]:
"""JSON-serializable export for ``/api/v1/gitea/linkage``."""
return snapshot.to_dict()
def _offline_test_mode() -> bool:
return (os.environ.get("WEBUI_TEST_OFFLINE") or "").strip().lower() in {
"1",
"true",
"yes",
}
def _labels_of(item: dict[str, Any]) -> tuple[str, ...]:
return tuple(
str(_redact(label.get("name")))
for label in (item.get("labels") or [])
if label.get("name")
)
def _failed_snapshot(
*,
project_id: str,
repo_label: str,
host: str,
state_scope: str,
reason: str,
) -> LinkageSnapshot:
"""A read that could not be answered. Never an empty-and-healthy snapshot."""
return LinkageSnapshot(
ok=False,
project_id=project_id,
repo_label=repo_label,
host=host,
state_scope=state_scope,
inventory_complete=False,
deep_links_enabled=deep_links_enabled(),
handoff_status=HandoffStatus(
HANDOFF_UNAVAILABLE, reason="linkage inventory could not be loaded"
),
fetch_error=str(_redact(reason)),
)
def _resolve_project(project_id: str | None) -> ProjectRecord | None:
registry = load_registry()
if project_id:
for entry in registry.projects:
if entry.id == project_id:
return entry
return None
return registry.projects[0] if registry.projects else None
def _normalize_state(state: str | None) -> str:
text = (state or STATE_OPEN).strip().lower()
return text if text in _SUPPORTED_STATES else STATE_OPEN
def load_linkage_snapshot(
project_id: str | None = None,
*,
state: str | None = None,
issue: int | None = None,
pr: int | None = None,
fetch_prs: Callable[..., tuple[list[dict], PaginationMeta]] | None = None,
fetch_issues: Callable[..., tuple[list[dict], PaginationMeta]] | None = None,
comment_source: CommentSource | None = None,
) -> LinkageSnapshot:
"""Load issue↔PR linkage for a registry project.
``issue``/``pr`` focus one thread: the focused row is the only one whose
Canonical Thread Handoff comments are fetched, because handoff comments are
thread-scoped and loading them for a whole queue would be one request per
row. Every unfocused row reports its handoff as ``not_loaded``.
"""
state_scope = _normalize_state(state)
try:
project = _resolve_project(project_id)
except Exception as exc: # registry invalid — fail closed with the reason
return _failed_snapshot(
project_id=project_id or "",
repo_label="",
host="",
state_scope=state_scope,
reason=f"project registry unavailable: {exc}",
)
if project is None:
return _failed_snapshot(
project_id=project_id or "",
repo_label="",
host="",
state_scope=state_scope,
reason=(
f"project {project_id!r} not found in registry"
if project_id
else "no projects registered"
),
)
host = _host_from_url(project.remote_host)
repo_label = f"{project.gitea_owner}/{project.repo_name}"
offline_test = _offline_test_mode()
def _empty_fetch(*_args, **_kwargs):
return [], PaginationMeta(
page=1,
per_page=50,
returned_count=0,
has_more=False,
is_final_page=True,
# An offline stub loaded nothing; claiming a complete inventory here
# would let the page assert that no issue has a linked PR.
inventory_complete=False,
pages_fetched=0,
)
pr_fetch = fetch_prs or (_empty_fetch if offline_test else _fetch_prs)
issue_fetch = fetch_issues or (_empty_fetch if offline_test else _fetch_issues)
using_live_fetch = not offline_test and (fetch_prs is None or fetch_issues is None)
auth = get_auth_header(host) if using_live_fetch else "test-auth"
if using_live_fetch and not auth:
return _failed_snapshot(
project_id=project.id,
repo_label=repo_label,
host=host,
state_scope=state_scope,
reason=(
f"Gitea credentials unavailable for {host}; linkage cannot be "
"loaded (fail closed — not rendering an empty linkage table)"
),
)
try:
raw_prs, pr_pagination = pr_fetch(
host, project.gitea_owner, project.repo_name, auth, state=state_scope
)
raw_issues, issue_pagination = issue_fetch(
host, project.gitea_owner, project.repo_name, auth, state=state_scope
)
except Exception as exc: # noqa: BLE001 — operator-visible fetch failure
return _failed_snapshot(
project_id=project.id,
repo_label=repo_label,
host=host,
state_scope=state_scope,
reason=f"Gitea fetch failed: {exc}",
)
inventory_complete = bool(
getattr(pr_pagination, "inventory_complete", False)
and getattr(issue_pagination, "inventory_complete", False)
)
index = resolve_linkage(raw_prs)
contested = index.contested_issues()
focus: tuple[str, int] | None = None
if pr is not None:
focus = ("pr", int(pr))
elif issue is not None:
focus = ("issue", int(issue))
unfocused_reason = (
"canonical handoff comments are thread-scoped; focus one issue or PR "
"to load its latest handoff"
)
handoff_status = HandoffStatus(HANDOFF_NOT_LOADED, reason=unfocused_reason)
focus_handoff: HandoffSummary | None = None
if focus is not None:
source = comment_source
if source is None and not offline_test:
source = build_comment_source(host, project.gitea_owner, project.repo_name)
target = f"{focus[0]}#{focus[1]}"
if source is None:
handoff_status = HandoffStatus(
HANDOFF_UNAVAILABLE,
reason="no authenticated comment source available for this read",
target=target,
)
else:
try:
focus_handoff = summarize_handoff(source(focus[0], focus[1]) or [])
handoff_status = HandoffStatus(HANDOFF_LOADED, target=target)
except Exception as exc: # fail soft: degrade this source only
handoff_status = HandoffStatus(
HANDOFF_UNAVAILABLE,
reason=str(_redact(f"handoff fetch failed: {exc}")),
target=target,
)
def _node_handoff(
kind: str, number: int
) -> tuple[HandoffSummary | None, HandoffStatus]:
"""Attach the handoff only to the focused row; qualify every other row."""
if focus == (kind, number):
return (focus_handoff, handoff_status)
return (
None,
HandoffStatus(
HANDOFF_NOT_LOADED,
reason=unfocused_reason if focus is None else "not the focused thread",
),
)
def _number_of(raw: dict[str, Any]) -> int | None:
try:
return int(raw["number"])
except (KeyError, TypeError, ValueError):
return None
def _sort_key(raw: dict[str, Any]) -> int:
number = _number_of(raw)
return -1 if number is None else number
issue_nodes: list[LinkageNode] = []
for raw in sorted(raw_issues or [], key=_sort_key, reverse=True):
number = _number_of(raw)
if number is None:
continue
node_handoff, node_status = _node_handoff("issue", number)
linked_prs = index.issue_prs.get(number, ())
issue_nodes.append(
LinkageNode(
kind="issue",
number=number,
title=str(_redact(raw.get("title")) or ""),
state=str(raw.get("state") or ""),
labels=_labels_of(raw),
linked_prs=linked_prs,
contested=len(linked_prs) > 1,
deep_link=_deep_link(
host, project.gitea_owner, project.repo_name, "issue", number
),
handoff=node_handoff,
handoff_status=node_status,
links_authoritative=inventory_complete,
)
)
pr_nodes: list[LinkageNode] = []
for raw in sorted(raw_prs or [], key=_sort_key, reverse=True):
number = _number_of(raw)
if number is None:
continue
node_handoff, node_status = _node_handoff("pr", number)
links = index.pr_links.get(number, ())
pr_nodes.append(
LinkageNode(
kind="pr",
number=number,
title=str(_redact(raw.get("title")) or ""),
state=str(raw.get("state") or ""),
labels=_labels_of(raw),
links=links,
ambiguous=index.ambiguous(number),
contested=any(link.issue_number in contested for link in links),
deep_link=_deep_link(
host, project.gitea_owner, project.repo_name, "pr", number
),
handoff=node_handoff,
handoff_status=node_status,
links_authoritative=inventory_complete,
)
)
return LinkageSnapshot(
ok=True,
project_id=project.id,
repo_label=repo_label,
host=host,
state_scope=state_scope,
issues=tuple(issue_nodes),
prs=tuple(pr_nodes),
contested_issues=contested,
focus=focus,
inventory_complete=inventory_complete,
deep_links_enabled=deep_links_enabled(),
handoff_status=handoff_status,
)