open-swe/agent/tools/search_repo_code.py

85 lines
3.2 KiB
Python
Raw Normal View History

feat: chat with your PR on the review page (#1534) * feat: chat with your PR on the review page Add a sandbox-less `chat` graph that answers questions about a single PR from its diff, the published review findings, and read-only GitHub access. - agent/chat.py: deepagents graph, no sandbox (default StateBackend, file mutation + execute tools excluded). PR context is seeded as virtual files under /pr/; a repo-scoped App token is resolved in-graph. - tools: read_repo_file, search_repo_code, list_review_findings. - dashboard/review_chat_api.py + routes: per-user chat thread, LangGraph stream/commands/state/history proxy pinned to the chat assistant, seeds diff/findings/overview on first run. Gated by repo access. - UI: Chat tab wired to a chat-scoped StreamProvider (replaces Coming Soon). * feat: admin setting for review-chat default model Add a 'Open SWE Review Chat' default to team settings (default_chat_model / default_chat_reasoning_effort). get_team_default_model("chat") inherits the Agent default when unset; the chat graph resolves through it. Admin RolePicker gains an 'Agent default' inherit option that clears the override. * feat: multi-conversation review chat (tabs, new chat, history) Replace the single per-PR chat thread with multiple per-user conversations: - threads minted client-side; first message persists with a title derived from the prompt. - list + delete endpoints; chat panel gets a tab strip (history), new-chat (+), close (x), refresh, an intro greeting, and suggested prompts. - get_review_chat now returns availability only (ids are client-minted). * ui fixes * ui: review-chat history dropdown, full-width AI replies, resizable side panel * fix(review-chat): enforce per-user thread ownership on proxy endpoints; reseed PR context on head change --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-15 17:17:30 -07:00
"""Tool: ``search_repo_code``. Search the PR's repository via the GitHub code-search API."""
from __future__ import annotations
from typing import Any
refactor: durable interrupt dispatch + completion webhook (#1621) * wip(rebuild): core reliability spine - remove PR-babysitting (ci_autofix + ci_monitor graph + webhook wiring) - dispatch core: agent/dispatch.py with multitask_strategy=interrupt + durability=sync + completion webhook; reroute all webhook + plan triggers; drop the racy in-process lock + is_thread_active busy-check - completion webhook: agent/completion.py + /webhooks/run-complete loopback route for failure/timeout replies (idempotent) Co-authored-by: open-swe[bot] * feat(rebuild): async tools, reconcile, shared http timeouts, assembly tuning Parallel batch on top of the reliability spine: - async-ify all 24 tools (drop asyncio.run; requests->httpx); re-implement the http_request/fetch_url SSRF + DNS-rebinding defense httpx-natively and harden the IP check to 'not is_global' (+ IPv4-mapped unwrap) - reconcile.py: stale pending-run sweep (threads.search -> per-thread runs.list -> cancel_many), wired into the scheduler graph via task='reconcile' - shared DEFAULT_HTTP_TIMEOUT (agent/utils/http.py) on every bare httpx.AsyncClient() across utils/dashboard/webapp/middleware - run budget: MODEL_CALL_RECURSION_LIMIT 5000->250 - fix stale OpenAI->Anthropic fallback id (claude-opus-4-5 -> 4-8) - drop redundant custom repair middleware (deepagents auto-adds PatchToolCalls) - confirm tool-result eviction + summarization auto-wired via backend - slim system prompt ~8% (full harness-profile rewrite deferred) Co-authored-by: open-swe[bot] * feat(rebuild): harness-profile prompt + split webhooks out of webapp - prompt.py: own the system prompt via a registered harness profile (OPEN_SWE_SHARED_BASE, kept neutral so the read-only reviewer/analyzer that share it stay safe), registered across all 4 providers; per-thread values stay in construct_system_prompt. Assembled main-agent prompt ~6.8k -> ~3.1k tokens (~55% smaller); de-duped PR/commit/suite/force-push guidance; dropped ALL-CAPS markers. - webapp.py 3325 -> 1890 LOC: moved 14 per-source handlers into agent/webhooks/{linear,slack,github}.py; webapp re-exports them for the routes + tests; moved handlers reach shared helpers via the webapp namespace to preserve the test suite's monkeypatch targets. Full suite: 1168 passing, lint clean. Co-authored-by: open-swe[bot] * Restore MODEL_CALL_RECURSION_LIMIT to 5000 for long-running tasks Reverts the 250 cap from the run-budget change — long-running tasks legitimately need many model calls. The notify_step_limit_reached safety net still fires if a run does hit the cap, so runs end with a signal either way. Co-authored-by: open-swe[bot] * fix: address PR review (auth, SSRF, interrupted status, redirect headers) - completion.py: drop `interrupted` from failure statuses — with multitask_strategy=interrupt a follow-up ends the prior run as interrupted, which is healthy, not a failure to report. [open-swe] - /webhooks/run-complete: shared-secret auth — dispatch appends ?token= when RUN_COMPLETE_WEBHOOK_SECRET is set; route verifies via hmac.compare_digest. [corridor-security] - SSRF: extract the URL validator to agent/utils/url_safety.py and apply it before server-side image fetches in multimodal.fetch_image_block. [corridor-security] - http_request: preserve caller headers/extensions across redirect hops instead of dropping them on the first hop. [open-swe] Co-authored-by: open-swe[bot] * chore: remove REBUILD_PLAN.md (planning doc, not needed in the repo) Co-authored-by: open-swe[bot] * fix: fail closed on run-complete webhook auth when secret unset Corridor follow-up: verify_run_complete_token returns False (not True) when RUN_COMPLETE_WEBHOOK_SECRET is unset, so the public route is never unauthenticated. Logs a startup warning when the secret is absent, and dispatch skips registering the webhook when there's no secret (no rejected callbacks). Co-authored-by: open-swe[bot] --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-26 13:48:38 -07:00
import httpx
feat: chat with your PR on the review page (#1534) * feat: chat with your PR on the review page Add a sandbox-less `chat` graph that answers questions about a single PR from its diff, the published review findings, and read-only GitHub access. - agent/chat.py: deepagents graph, no sandbox (default StateBackend, file mutation + execute tools excluded). PR context is seeded as virtual files under /pr/; a repo-scoped App token is resolved in-graph. - tools: read_repo_file, search_repo_code, list_review_findings. - dashboard/review_chat_api.py + routes: per-user chat thread, LangGraph stream/commands/state/history proxy pinned to the chat assistant, seeds diff/findings/overview on first run. Gated by repo access. - UI: Chat tab wired to a chat-scoped StreamProvider (replaces Coming Soon). * feat: admin setting for review-chat default model Add a 'Open SWE Review Chat' default to team settings (default_chat_model / default_chat_reasoning_effort). get_team_default_model("chat") inherits the Agent default when unset; the chat graph resolves through it. Admin RolePicker gains an 'Agent default' inherit option that clears the override. * feat: multi-conversation review chat (tabs, new chat, history) Replace the single per-PR chat thread with multiple per-user conversations: - threads minted client-side; first message persists with a title derived from the prompt. - list + delete endpoints; chat panel gets a tab strip (history), new-chat (+), close (x), refresh, an intro greeting, and suggested prompts. - get_review_chat now returns availability only (ids are client-minted). * ui fixes * ui: review-chat history dropdown, full-width AI replies, resizable side panel * fix(review-chat): enforce per-user thread ownership on proxy endpoints; reseed PR context on head change --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-15 17:17:30 -07:00
from langgraph.config import get_config
from ..utils.github_checks import github_headers
_GITHUB_API = "https://api.github.com"
def _chat_repo_context() -> tuple[str, str, str | None]:
config = get_config()
configurable = config.get("configurable", {}) if isinstance(config, dict) else {}
if not isinstance(configurable, dict):
configurable = {}
owner = configurable.get("chat_repo_owner")
repo = configurable.get("chat_repo_name")
token = configurable.get("chat_github_token")
return (
owner if isinstance(owner, str) else "",
repo if isinstance(repo, str) else "",
token if isinstance(token, str) and token else None,
)
refactor: durable interrupt dispatch + completion webhook (#1621) * wip(rebuild): core reliability spine - remove PR-babysitting (ci_autofix + ci_monitor graph + webhook wiring) - dispatch core: agent/dispatch.py with multitask_strategy=interrupt + durability=sync + completion webhook; reroute all webhook + plan triggers; drop the racy in-process lock + is_thread_active busy-check - completion webhook: agent/completion.py + /webhooks/run-complete loopback route for failure/timeout replies (idempotent) Co-authored-by: open-swe[bot] * feat(rebuild): async tools, reconcile, shared http timeouts, assembly tuning Parallel batch on top of the reliability spine: - async-ify all 24 tools (drop asyncio.run; requests->httpx); re-implement the http_request/fetch_url SSRF + DNS-rebinding defense httpx-natively and harden the IP check to 'not is_global' (+ IPv4-mapped unwrap) - reconcile.py: stale pending-run sweep (threads.search -> per-thread runs.list -> cancel_many), wired into the scheduler graph via task='reconcile' - shared DEFAULT_HTTP_TIMEOUT (agent/utils/http.py) on every bare httpx.AsyncClient() across utils/dashboard/webapp/middleware - run budget: MODEL_CALL_RECURSION_LIMIT 5000->250 - fix stale OpenAI->Anthropic fallback id (claude-opus-4-5 -> 4-8) - drop redundant custom repair middleware (deepagents auto-adds PatchToolCalls) - confirm tool-result eviction + summarization auto-wired via backend - slim system prompt ~8% (full harness-profile rewrite deferred) Co-authored-by: open-swe[bot] * feat(rebuild): harness-profile prompt + split webhooks out of webapp - prompt.py: own the system prompt via a registered harness profile (OPEN_SWE_SHARED_BASE, kept neutral so the read-only reviewer/analyzer that share it stay safe), registered across all 4 providers; per-thread values stay in construct_system_prompt. Assembled main-agent prompt ~6.8k -> ~3.1k tokens (~55% smaller); de-duped PR/commit/suite/force-push guidance; dropped ALL-CAPS markers. - webapp.py 3325 -> 1890 LOC: moved 14 per-source handlers into agent/webhooks/{linear,slack,github}.py; webapp re-exports them for the routes + tests; moved handlers reach shared helpers via the webapp namespace to preserve the test suite's monkeypatch targets. Full suite: 1168 passing, lint clean. Co-authored-by: open-swe[bot] * Restore MODEL_CALL_RECURSION_LIMIT to 5000 for long-running tasks Reverts the 250 cap from the run-budget change — long-running tasks legitimately need many model calls. The notify_step_limit_reached safety net still fires if a run does hit the cap, so runs end with a signal either way. Co-authored-by: open-swe[bot] * fix: address PR review (auth, SSRF, interrupted status, redirect headers) - completion.py: drop `interrupted` from failure statuses — with multitask_strategy=interrupt a follow-up ends the prior run as interrupted, which is healthy, not a failure to report. [open-swe] - /webhooks/run-complete: shared-secret auth — dispatch appends ?token= when RUN_COMPLETE_WEBHOOK_SECRET is set; route verifies via hmac.compare_digest. [corridor-security] - SSRF: extract the URL validator to agent/utils/url_safety.py and apply it before server-side image fetches in multimodal.fetch_image_block. [corridor-security] - http_request: preserve caller headers/extensions across redirect hops instead of dropping them on the first hop. [open-swe] Co-authored-by: open-swe[bot] * chore: remove REBUILD_PLAN.md (planning doc, not needed in the repo) Co-authored-by: open-swe[bot] * fix: fail closed on run-complete webhook auth when secret unset Corridor follow-up: verify_run_complete_token returns False (not True) when RUN_COMPLETE_WEBHOOK_SECRET is unset, so the public route is never unauthenticated. Logs a startup warning when the secret is absent, and dispatch skips registering the webhook when there's no secret (no rejected callbacks). Co-authored-by: open-swe[bot] --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-26 13:48:38 -07:00
async def search_repo_code(query: str, max_results: int = 20) -> dict[str, Any]:
feat: chat with your PR on the review page (#1534) * feat: chat with your PR on the review page Add a sandbox-less `chat` graph that answers questions about a single PR from its diff, the published review findings, and read-only GitHub access. - agent/chat.py: deepagents graph, no sandbox (default StateBackend, file mutation + execute tools excluded). PR context is seeded as virtual files under /pr/; a repo-scoped App token is resolved in-graph. - tools: read_repo_file, search_repo_code, list_review_findings. - dashboard/review_chat_api.py + routes: per-user chat thread, LangGraph stream/commands/state/history proxy pinned to the chat assistant, seeds diff/findings/overview on first run. Gated by repo access. - UI: Chat tab wired to a chat-scoped StreamProvider (replaces Coming Soon). * feat: admin setting for review-chat default model Add a 'Open SWE Review Chat' default to team settings (default_chat_model / default_chat_reasoning_effort). get_team_default_model("chat") inherits the Agent default when unset; the chat graph resolves through it. Admin RolePicker gains an 'Agent default' inherit option that clears the override. * feat: multi-conversation review chat (tabs, new chat, history) Replace the single per-PR chat thread with multiple per-user conversations: - threads minted client-side; first message persists with a title derived from the prompt. - list + delete endpoints; chat panel gets a tab strip (history), new-chat (+), close (x), refresh, an intro greeting, and suggested prompts. - get_review_chat now returns availability only (ids are client-minted). * ui fixes * ui: review-chat history dropdown, full-width AI replies, resizable side panel * fix(review-chat): enforce per-user thread ownership on proxy endpoints; reseed PR context on head change --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-15 17:17:30 -07:00
"""Search code in the PR's repository for a keyword, symbol, or phrase.
Backed by GitHub code search, which indexes the repository's default branch
(not arbitrary refs). Use it to locate where a symbol is defined or used,
then ``read_repo_file`` for the surrounding context. For matches within the
changed lines, search the virtual file ``/pr/diff.patch`` instead.
Args:
query: Search terms. Repo scoping is added automatically.
max_results: Max matches to return (capped at 50).
Returns:
``{success, total_count, results}`` where each result is
``{path, fragments}``; ``{success: False, error}`` on failure.
"""
owner, repo, token = _chat_repo_context()
if not owner or not repo:
return {"success": False, "error": "repository context unavailable"}
capped = max(1, min(max_results, 50))
headers = github_headers(token or "")
headers["Accept"] = "application/vnd.github.text-match+json"
params = {"q": f"{query} repo:{owner}/{repo}", "per_page": capped}
try:
refactor: durable interrupt dispatch + completion webhook (#1621) * wip(rebuild): core reliability spine - remove PR-babysitting (ci_autofix + ci_monitor graph + webhook wiring) - dispatch core: agent/dispatch.py with multitask_strategy=interrupt + durability=sync + completion webhook; reroute all webhook + plan triggers; drop the racy in-process lock + is_thread_active busy-check - completion webhook: agent/completion.py + /webhooks/run-complete loopback route for failure/timeout replies (idempotent) Co-authored-by: open-swe[bot] * feat(rebuild): async tools, reconcile, shared http timeouts, assembly tuning Parallel batch on top of the reliability spine: - async-ify all 24 tools (drop asyncio.run; requests->httpx); re-implement the http_request/fetch_url SSRF + DNS-rebinding defense httpx-natively and harden the IP check to 'not is_global' (+ IPv4-mapped unwrap) - reconcile.py: stale pending-run sweep (threads.search -> per-thread runs.list -> cancel_many), wired into the scheduler graph via task='reconcile' - shared DEFAULT_HTTP_TIMEOUT (agent/utils/http.py) on every bare httpx.AsyncClient() across utils/dashboard/webapp/middleware - run budget: MODEL_CALL_RECURSION_LIMIT 5000->250 - fix stale OpenAI->Anthropic fallback id (claude-opus-4-5 -> 4-8) - drop redundant custom repair middleware (deepagents auto-adds PatchToolCalls) - confirm tool-result eviction + summarization auto-wired via backend - slim system prompt ~8% (full harness-profile rewrite deferred) Co-authored-by: open-swe[bot] * feat(rebuild): harness-profile prompt + split webhooks out of webapp - prompt.py: own the system prompt via a registered harness profile (OPEN_SWE_SHARED_BASE, kept neutral so the read-only reviewer/analyzer that share it stay safe), registered across all 4 providers; per-thread values stay in construct_system_prompt. Assembled main-agent prompt ~6.8k -> ~3.1k tokens (~55% smaller); de-duped PR/commit/suite/force-push guidance; dropped ALL-CAPS markers. - webapp.py 3325 -> 1890 LOC: moved 14 per-source handlers into agent/webhooks/{linear,slack,github}.py; webapp re-exports them for the routes + tests; moved handlers reach shared helpers via the webapp namespace to preserve the test suite's monkeypatch targets. Full suite: 1168 passing, lint clean. Co-authored-by: open-swe[bot] * Restore MODEL_CALL_RECURSION_LIMIT to 5000 for long-running tasks Reverts the 250 cap from the run-budget change — long-running tasks legitimately need many model calls. The notify_step_limit_reached safety net still fires if a run does hit the cap, so runs end with a signal either way. Co-authored-by: open-swe[bot] * fix: address PR review (auth, SSRF, interrupted status, redirect headers) - completion.py: drop `interrupted` from failure statuses — with multitask_strategy=interrupt a follow-up ends the prior run as interrupted, which is healthy, not a failure to report. [open-swe] - /webhooks/run-complete: shared-secret auth — dispatch appends ?token= when RUN_COMPLETE_WEBHOOK_SECRET is set; route verifies via hmac.compare_digest. [corridor-security] - SSRF: extract the URL validator to agent/utils/url_safety.py and apply it before server-side image fetches in multimodal.fetch_image_block. [corridor-security] - http_request: preserve caller headers/extensions across redirect hops instead of dropping them on the first hop. [open-swe] Co-authored-by: open-swe[bot] * chore: remove REBUILD_PLAN.md (planning doc, not needed in the repo) Co-authored-by: open-swe[bot] * fix: fail closed on run-complete webhook auth when secret unset Corridor follow-up: verify_run_complete_token returns False (not True) when RUN_COMPLETE_WEBHOOK_SECRET is unset, so the public route is never unauthenticated. Logs a startup warning when the secret is absent, and dispatch skips registering the webhook when there's no secret (no rejected callbacks). Co-authored-by: open-swe[bot] --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-26 13:48:38 -07:00
async with httpx.AsyncClient(timeout=30) as client:
response = await client.get(
f"{_GITHUB_API}/search/code", headers=headers, params=params
)
except httpx.HTTPError as exc:
feat: chat with your PR on the review page (#1534) * feat: chat with your PR on the review page Add a sandbox-less `chat` graph that answers questions about a single PR from its diff, the published review findings, and read-only GitHub access. - agent/chat.py: deepagents graph, no sandbox (default StateBackend, file mutation + execute tools excluded). PR context is seeded as virtual files under /pr/; a repo-scoped App token is resolved in-graph. - tools: read_repo_file, search_repo_code, list_review_findings. - dashboard/review_chat_api.py + routes: per-user chat thread, LangGraph stream/commands/state/history proxy pinned to the chat assistant, seeds diff/findings/overview on first run. Gated by repo access. - UI: Chat tab wired to a chat-scoped StreamProvider (replaces Coming Soon). * feat: admin setting for review-chat default model Add a 'Open SWE Review Chat' default to team settings (default_chat_model / default_chat_reasoning_effort). get_team_default_model("chat") inherits the Agent default when unset; the chat graph resolves through it. Admin RolePicker gains an 'Agent default' inherit option that clears the override. * feat: multi-conversation review chat (tabs, new chat, history) Replace the single per-PR chat thread with multiple per-user conversations: - threads minted client-side; first message persists with a title derived from the prompt. - list + delete endpoints; chat panel gets a tab strip (history), new-chat (+), close (x), refresh, an intro greeting, and suggested prompts. - get_review_chat now returns availability only (ids are client-minted). * ui fixes * ui: review-chat history dropdown, full-width AI replies, resizable side panel * fix(review-chat): enforce per-user thread ownership on proxy endpoints; reseed PR context on head change --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-15 17:17:30 -07:00
return {"success": False, "error": f"GitHub request failed: {exc!s}"}
if response.status_code == 422:
return {"success": False, "error": "query rejected by GitHub code search"}
if response.status_code >= 400:
return {"success": False, "error": f"GitHub returned {response.status_code}"}
payload = response.json()
items = payload.get("items") if isinstance(payload, dict) else None
results: list[dict[str, Any]] = []
for item in items if isinstance(items, list) else []:
if not isinstance(item, dict):
continue
fragments = [
match.get("fragment")
for match in item.get("text_matches", [])
if isinstance(match, dict) and isinstance(match.get("fragment"), str)
]
results.append({"path": item.get("path", ""), "fragments": fragments})
total = payload.get("total_count") if isinstance(payload, dict) else None
return {
"success": True,
"total_count": total if isinstance(total, int) else len(results),
"results": results,
}