adam/open-swe
1
0
Fork 0
mirror of https://github.com/Sea-Haven-Industries/open-swe.git synced 2026-09-30 17:23:15 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
open-swe/agent/middleware/__init__.py

22 lines
843 B
Python
Raw Normal View History

refactor: extract shared utils from server.py into agent/utils/ package
2026-02-10 11:22:52 -08:00
from .check_message_queue import check_message_queue_before_model
fix: Middleware to ensure no empty msg (#1010)
2026-03-04 17:59:52 -08:00
from .ensure_no_empty_msg import ensure_no_empty_msg
feat: add reviewer graph + eval target wiring (#1241) * feat: add reviewer graph + eval target wiring - New `reviewer` graph (`agent/reviewer.py`) registered in langgraph.json alongside the main `agent` graph. Reuses the same sandbox lifecycle, GH proxy auth, and middleware primitives from `agent.server`, but with a narrower tool set, a reviewer-specific system prompt, no commit/push, and the `task` (subagent) tool stripped via `_ToolExclusionMiddleware` so review stays in one context. - New `github_comment` tool: agents call it once per issue with `(file, line, body, severity)` and the eval scores those calls against golden comments. - `ensure_no_empty_msg` middleware (the no_op nudge) is intentionally *not* on the reviewer's stack — that middleware exists to enforce the main agent's "always finalize via Slack/Linear/PR" contract, which the reviewer doesn't have. The main agent's behavior is unchanged. - `evals/reviewer/target.py`: send PR info as a user message, extract every `github_comment` tool call (multiple expected per review) into the run output. - `evals/reviewer/judge.py`: per-example evaluator now returns a list of metrics under `{"results": [...]}` so LangSmith averages each numeric key (f1/precision/recall/tp/fp/fn) across the experiment in the UI. Dropped the broken `aggregate_pr` summary evaluator that reached for an attribute that doesn't exist on `RunTree`. - `evals/reviewer/run_eval.py`: `--limit` now slices the dataset via `client.list_examples(limit=N)` since `aevaluate` doesn't accept `max_examples`. - Makefile: `dev` and `run` targets now use `uv run` so they work without an activated venv. * resolve comments --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-05-06 10:15:58 -07:00
from .exclude_tools import ExcludeToolsMiddleware
feat: cross-provider model fallback on transient errors (#1281) When the primary model raises a transient provider error (5xx, 429, connection/timeout) the request is retried once against a fallback model from the other provider. Anthropic primaries fall back to OpenAI and vice versa. Also bumps the SDK max_retries from the default 2 to 6 so quick blips stay on the primary and keep prompt caching warm. Triggered by 529 OverloadedError traces that ended runs silently with no Slack/Linear/PR reply.
2026-05-08 15:35:13 -07:00
from .model_fallback import ModelFallbackMiddleware
fix: notify users via Slack when agent hits model call step limit (#1204) * fix: notify users via Slack when agent hits model call step limit - Root cause: GraphRecursionError at 1000 steps bypassed all @after_agent middleware including open_pr_if_needed, leaving users with no notification - Change: Added ModelCallLimitMiddleware(run_limit=60) to intercept gracefully before the hard recursion limit, and added notify_step_limit_reached @after_agent middleware to post a Slack thread reply when the limit fires - Verified: 107 existing tests pass, no regressions * fix: harden step-limit Slack notification Ensure the step-limit notification runs after the PR safety net and cover the new middleware behavior with focused unit tests. --------- Co-authored-by: LangSmith Forge <forge-agent@langsmith.ai> Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
2026-05-01 14:24:25 -07:00
from .notify_step_limit import notify_step_limit_reached
feat: add optional Slack Assistants API typing status indicator (#1269) * feat: add optional Slack Assistants API typing status indicator Mirrors OpenClaw's pragmatic approach: instead of rebuilding around assistant_thread_started events, just opt into assistants.threads.setStatus to show 'is thinking…' while the agent is working, and clear it when post_slack_thread_reply lands. Gated behind SLACK_ASSISTANTS_API_ENABLED so it can be toggled without touching code. * fix(slack): drop redundant clear, add status heartbeat across model calls - Slack auto-clears the typing indicator on bot post; remove the explicit assistants.threads.setStatus("") call from post_slack_thread_reply. - The indicator expires after ~2 minutes; add a before_model middleware that refreshes it on every model tick so it stays visible across long agent runs. Reuses the existing slack_thread.{channel_id,thread_ts} configurable already plumbed for notify_step_limit. - chat:write is sufficient on the bot token (assistant:write is on the way out per Slack docs); no scope or app-config change required. * feat(slack): contextual status text + rotating loading_messages - set_slack_assistant_status now accepts an optional loading_messages list (capped at 10 per Slack's API), surfaced via the assistants.threads.setStatus payload so Slack rotates through them client-side. - The heartbeat middleware derives a contextual status from the last assistant message's tool calls (e.g. "searching the codebase…" after grep, "running commands…" after execute), falling back to the default "is thinking…" when no tool calls or unknown tool name. - Adds a curated DEFAULT_LOADING_MESSAGES list passed alongside the contextual status on each refresh. * fix slack assistant status lifecycle --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
2026-05-08 10:21:55 -07:00
from .refresh_slack_status import SlackAssistantStatusMiddleware
fix: recover from mid-run sandbox death (#1274) * fix: recover from mid-run sandbox death Recreate dead sandboxes during tool execution and stop repeated unrecoverable timeout loops with a user-facing notification. * fix: count repeated sandbox recreations Treat consecutive sandbox recreations as an unrecovered failure streak so outages cannot loop until the model-call limit.
2026-05-08 12:55:36 -07:00
from .sandbox_circuit_breaker import SandboxCircuitBreakerMiddleware
fix: coerce malformed integer strings in read_file offset/limit params (#1216) - Root cause: LLM occasionally generates strings like '1, 80' or '170, "limit": 60' for integer fields, causing a Pydantic ValidationError and wasting an LLM turn - Change: add SanitizeToolInputsMiddleware in agent/middleware/sanitize_tool_inputs.py that extracts the leading integer from any string value in offset/limit before the call reaches Pydantic validation; registered before ToolErrorMiddleware in server.py - Verified: 14 unit tests covering all three production trace patterns pass Co-authored-by: LangSmith Forge <forge-agent@langsmith.ai> Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
2026-05-01 14:29:48 -07:00
from .sanitize_tool_inputs import SanitizeToolInputsMiddleware
Refactor middleware into package and update repo config
2026-02-09 12:53:34 -08:00
from .tool_error_handler import ToolErrorMiddleware
refactor: extract inline middleware from server.py into separate files
2026-02-09 15:34:18 -08:00
__all__ = [
feat: add reviewer graph + eval target wiring (#1241) * feat: add reviewer graph + eval target wiring - New `reviewer` graph (`agent/reviewer.py`) registered in langgraph.json alongside the main `agent` graph. Reuses the same sandbox lifecycle, GH proxy auth, and middleware primitives from `agent.server`, but with a narrower tool set, a reviewer-specific system prompt, no commit/push, and the `task` (subagent) tool stripped via `_ToolExclusionMiddleware` so review stays in one context. - New `github_comment` tool: agents call it once per issue with `(file, line, body, severity)` and the eval scores those calls against golden comments. - `ensure_no_empty_msg` middleware (the no_op nudge) is intentionally *not* on the reviewer's stack — that middleware exists to enforce the main agent's "always finalize via Slack/Linear/PR" contract, which the reviewer doesn't have. The main agent's behavior is unchanged. - `evals/reviewer/target.py`: send PR info as a user message, extract every `github_comment` tool call (multiple expected per review) into the run output. - `evals/reviewer/judge.py`: per-example evaluator now returns a list of metrics under `{"results": [...]}` so LangSmith averages each numeric key (f1/precision/recall/tp/fp/fn) across the experiment in the UI. Dropped the broken `aggregate_pr` summary evaluator that reached for an attribute that doesn't exist on `RunTree`. - `evals/reviewer/run_eval.py`: `--limit` now slices the dataset via `client.list_examples(limit=N)` since `aevaluate` doesn't accept `max_examples`. - Makefile: `dev` and `run` targets now use `uv run` so they work without an activated venv. * resolve comments --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-05-06 10:15:58 -07:00
"ExcludeToolsMiddleware",
feat: cross-provider model fallback on transient errors (#1281) When the primary model raises a transient provider error (5xx, 429, connection/timeout) the request is retried once against a fallback model from the other provider. Anthropic primaries fall back to OpenAI and vice versa. Also bumps the SDK max_retries from the default 2 to 6 so quick blips stay on the primary and keep prompt caching warm. Triggered by 529 OverloadedError traces that ended runs silently with no Slack/Linear/PR reply.
2026-05-08 15:35:13 -07:00
"ModelFallbackMiddleware",
fix: coerce malformed integer strings in read_file offset/limit params (#1216) - Root cause: LLM occasionally generates strings like '1, 80' or '170, "limit": 60' for integer fields, causing a Pydantic ValidationError and wasting an LLM turn - Change: add SanitizeToolInputsMiddleware in agent/middleware/sanitize_tool_inputs.py that extracts the leading integer from any string value in offset/limit before the call reaches Pydantic validation; registered before ToolErrorMiddleware in server.py - Verified: 14 unit tests covering all three production trace patterns pass Co-authored-by: LangSmith Forge <forge-agent@langsmith.ai> Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
2026-05-01 14:29:48 -07:00
"SanitizeToolInputsMiddleware",
refactor: extract inline middleware from server.py into separate files
2026-02-09 15:34:18 -08:00
"ToolErrorMiddleware",
fix: recover from mid-run sandbox death (#1274) * fix: recover from mid-run sandbox death Recreate dead sandboxes during tool execution and stop repeated unrecoverable timeout loops with a user-facing notification. * fix: count repeated sandbox recreations Treat consecutive sandbox recreations as an unrecovered failure streak so outages cannot loop until the model-call limit.
2026-05-08 12:55:36 -07:00
"SandboxCircuitBreakerMiddleware",
feat: add optional Slack Assistants API typing status indicator (#1269) * feat: add optional Slack Assistants API typing status indicator Mirrors OpenClaw's pragmatic approach: instead of rebuilding around assistant_thread_started events, just opt into assistants.threads.setStatus to show 'is thinking…' while the agent is working, and clear it when post_slack_thread_reply lands. Gated behind SLACK_ASSISTANTS_API_ENABLED so it can be toggled without touching code. * fix(slack): drop redundant clear, add status heartbeat across model calls - Slack auto-clears the typing indicator on bot post; remove the explicit assistants.threads.setStatus("") call from post_slack_thread_reply. - The indicator expires after ~2 minutes; add a before_model middleware that refreshes it on every model tick so it stays visible across long agent runs. Reuses the existing slack_thread.{channel_id,thread_ts} configurable already plumbed for notify_step_limit. - chat:write is sufficient on the bot token (assistant:write is on the way out per Slack docs); no scope or app-config change required. * feat(slack): contextual status text + rotating loading_messages - set_slack_assistant_status now accepts an optional loading_messages list (capped at 10 per Slack's API), surfaced via the assistants.threads.setStatus payload so Slack rotates through them client-side. - The heartbeat middleware derives a contextual status from the last assistant message's tool calls (e.g. "searching the codebase…" after grep, "running commands…" after execute), falling back to the default "is thinking…" when no tool calls or unknown tool name. - Adds a curated DEFAULT_LOADING_MESSAGES list passed alongside the contextual status on each refresh. * fix slack assistant status lifecycle --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
2026-05-08 10:21:55 -07:00
"SlackAssistantStatusMiddleware",
refactor: extract inline middleware from server.py into separate files
2026-02-09 15:34:18 -08:00
"check_message_queue_before_model",
fix: Middleware to ensure no empty msg (#1010)
2026-03-04 17:59:52 -08:00
"ensure_no_empty_msg",
fix: notify users via Slack when agent hits model call step limit (#1204) * fix: notify users via Slack when agent hits model call step limit - Root cause: GraphRecursionError at 1000 steps bypassed all @after_agent middleware including open_pr_if_needed, leaving users with no notification - Change: Added ModelCallLimitMiddleware(run_limit=60) to intercept gracefully before the hard recursion limit, and added notify_step_limit_reached @after_agent middleware to post a Slack thread reply when the limit fires - Verified: 107 existing tests pass, no regressions * fix: harden step-limit Slack notification Ensure the step-limit notification runs after the PR safety net and cover the new middleware behavior with focused unit tests. --------- Co-authored-by: LangSmith Forge <forge-agent@langsmith.ai> Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
2026-05-01 14:24:25 -07:00
"notify_step_limit_reached",
refactor: extract inline middleware from server.py into separate files
2026-02-09 15:34:18 -08:00
]
Reference in a new issue Copy permalink