The batteries-included agent harness.
This report summarizes scanner evidence for langchain-ai/deepagents, a Python project with 30,108 GitHub stars. SynthScan examined 702,544 lines of code across 1625 source files, recording 17035 pattern matches distributed across 24 syntactic categories. The legacy adjusted pattern signal is 26.0 (Elevated pattern signal); it is not an authorship estimate.
Use the findings to ask whether maintainers can explain intent, verify dependencies, simplify unnecessary scaffolding, and focus review effort. Risk Payload v1 adds ownership, supply-chain, over-engineering, and review-effort vectors when available. These are prompts for human verification, not probabilities, security findings, or measured maintenance costs.
Use each vector to guide manual verification of the underlying findings.
Can maintainers explain intent, assumptions, and trade-offs? 14065 finding(s).
Are imports declared and package/API names verified? 1289 finding(s).
Are wrappers, guards, and repeated structures necessary? 14612 finding(s).
Which changes need focused human review? 17035 finding(s).
This chart tracks the legacy adjusted pattern score across scan runs. Changes can reflect source changes, scan coverage, or detector/scoring versions; they do not measure AI adoption or prove that a team refactored code. Compare runs only when their scoring versions are compatible. The dashed line tracks the raw pattern-hit count.
Groups findings by configured severity weight. Severity is not a confidence estimate, security rating, or proof that a package is missing. Verify imports against the project's manifests and inspect each finding in its local design context.
This horizontal bar chart shows where configured pattern scores accumulate across directories. Treat the bars as locations to inspect, not as evidence of authorship or code quality. Use the file-level findings to decide whether a directory needs a focused ownership, dependency, complexity, or review check.
The scanner identified 17035 distinct pattern matches across 24 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.
Reading the findings table: The Severity column indicates the configured finding weight (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — legacy comment-context matches receive a ×1.5 score weight. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier under the legacy scoring model.
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | libs/talon/deepagents_talon/interfaces.py | 259 | def top_level_conversation_id(self, conversation_id: str) -> str: | CODE |
| LOW | libs/talon/deepagents_talon/media.py | 189 | def resolve_bounded_media_path( | CODE |
| LOW | libs/talon/deepagents_talon/archive_saver.py | 138 | async def aget_delta_channel_history( | CODE |
| LOW | libs/talon/deepagents_talon/config.py | 219 | def history_embedding_profile(self) -> EmbeddingProfile: | CODE |
| LOW⚡ | libs/talon/deepagents_talon/host.py | 801 | async def _reload_mcp_configuration( | CODE |
| LOW⚡ | libs/talon/deepagents_talon/host.py | 892 | async def _process_background_results(self) -> None: | CODE |
| LOW⚡ | libs/talon/deepagents_talon/host.py | 900 | async def _dispatch_background_results(self) -> None: | CODE |
| LOW⚡ | libs/talon/deepagents_talon/host.py | 2390 | def _parse_tool_approval_reaction(emoji: str) -> ToolApprovalDecision | None: | CODE |
| LOW⚡ | libs/talon/deepagents_talon/host.py | 2399 | def _normalize_reaction_emoji(emoji: str) -> str: | CODE |
| LOW⚡ | libs/talon/deepagents_talon/host.py | 2407 | def _reaction_mismatch_resolution( | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 353 | def _forget_idle_conversation(self, conversation_id: str) -> None: | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 551 | async def _handle_conversation_command( | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 1141 | def _requeue_background_results(self, result: AgentResult) -> None: | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 1368 | def _roll_back_conversation_resets(self, previous: dict[str, int]) -> None: | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 1431 | async def _cancel_conversation_tasks(self, conversation_id: str) -> _CancelOutcome: | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 1484 | def _mark_cancellation_timeout( | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 1556 | async def _handle_authorization_event( # noqa: PLR0913 # binds all channel identities. | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 1678 | async def _await_authorization_callback( | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 1701 | async def _intercept_authorization_message( | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 1763 | async def _remind_device_authorization( | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 1786 | def _register_authorization_flow( | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 1808 | def _finish_authorization_flow( | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 1855 | async def _send_tool_approval_prompt( | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 1870 | async def _handle_tool_approval_reply( | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 1893 | def _handle_tool_approval_reaction( | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 1982 | def _complete_conversation_task( | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 2130 | def _outbound_media_from_refs( | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 2177 | def _with_failed_attachment_text(text: str, failed: list[str]) -> str: | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 2210 | def _media_with_fallback_caption( | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 2263 | def _format_tool_approval_prompt(approval: ToolApprovalRequest) -> str: | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 2290 | def _load_conversation_resets(path: Path) -> dict[str, int]: | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 2310 | def _load_smart_model_override(path: Path) -> dict[str, str | None] | None: | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 2353 | def _save_conversation_resets(path: Path, resets: Mapping[str, int]) -> None: | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 2375 | def _parse_tool_approval_reply(text: str, *, batch: bool = False) -> ToolApprovalDecision | None: | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 2432 | def _log_tool_approval_reaction( | CODE |
| LOW | libs/talon/deepagents_talon/mcp_auth.py | 88 | def _no_authorization_channel_error(server_name: str) -> MCPAuthorizationError: | CODE |
| LOW | libs/talon/deepagents_talon/mcp_auth.py | 243 | async def set_tokens_and_client_info( | CODE |
| LOW | libs/talon/deepagents_talon/mcp_auth.py | 335 | def _with_stored_refresh_token( | CODE |
| LOW | libs/talon/deepagents_talon/mcp_auth.py | 349 | def _mark_authorization_complete() -> None: | CODE |
| LOW | libs/talon/deepagents_talon/mcp_auth.py | 368 | async def _authorize_discovered_device( | CODE |
| LOW | libs/talon/deepagents_talon/mcp_auth.py | 398 | async def _discover_device_metadata( | CODE |
| LOW | libs/talon/deepagents_talon/mcp_auth.py | 905 | async def _discover_refresh_metadata(self) -> None: | CODE |
| LOW | libs/talon/deepagents_talon/mcp_auth.py | 922 | async def _discover_refresh_resource(self) -> None: | CODE |
| LOW | libs/talon/deepagents_talon/mcp_auth.py | 1099 | def extract_oauth_callback_url(text: str, *, redirect_uri: str | None = None) -> str | None: | CODE |
| LOW | libs/talon/deepagents_talon/mcp_auth.py | 1120 | def extract_loopback_oauth_callback_url(text: str) -> str | None: | CODE |
| LOW | libs/talon/deepagents_talon/mcp_auth.py | 1172 | async def _preseed_slack_client_info(storage: FileTokenStorage) -> None: | CODE |
| LOW | libs/talon/deepagents_talon/observability.py | 232 | def agent_activity_logging_enabled(env: Mapping[str, str]) -> bool: | CODE |
| LOW | libs/talon/deepagents_talon/observability.py | 345 | def langsmith_tracing_enabled(env: Mapping[str, str]) -> bool: | CODE |
| LOW | libs/talon/deepagents_talon/observability.py | 483 | def _redact_equals_assignment(match: re.Match[str]) -> str: | CODE |
| LOW | libs/talon/deepagents_talon/runtime.py | 805 | async def reload_subagent_configuration(self) -> None: | CODE |
| LOW | libs/talon/deepagents_talon/runtime.py | 851 | async def reload_subagent_configuration() -> dict[str, str]: | CODE |
| LOW | libs/talon/deepagents_talon/runtime.py | 1021 | async def _invoke_payload_with_retries( | CODE |
| LOW | libs/talon/deepagents_talon/runtime.py | 1267 | def _action_requests_from_interrupt(interrupt: object) -> tuple[Mapping[str, object], ...]: | CODE |
| LOW | libs/talon/deepagents_talon/runtime.py | 1372 | def _approval_handler_from_request(request: AgentRequest) -> ToolApprovalHandler | None: | CODE |
| LOW | libs/talon/deepagents_talon/runtime.py | 1424 | def _is_allowed_backend_env_key(key: str) -> bool: | CODE |
| LOW | libs/talon/deepagents_talon/runtime.py | 1428 | def _is_scrubbed_backend_env_key(key: str) -> bool: | CODE |
| LOW | libs/talon/deepagents_talon/runtime.py | 1473 | def _recursion_limit_from_env(env: Mapping[str, str], fallback: int) -> int: | CODE |
| LOW | libs/talon/deepagents_talon/runtime.py | 1517 | def _has_summarization_tool_middleware( | CODE |
| LOW | libs/talon/deepagents_talon/runtime.py | 1549 | def _cron_origin_from_request(request: AgentRequest) -> CronOrigin: | CODE |
| LOW | libs/talon/deepagents_talon/runtime.py | 1653 | def _subagent_from_frontmatter( | CODE |
| 12832 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | libs/evals/tests/evals/external_benchmarks.py | 191 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/external_benchmarks.py | 193 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_followup_quality.py | 27 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_followup_quality.py | 30 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_tool_usage_relational.py | 33 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_tool_usage_relational.py | 35 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_tool_usage_relational.py | 206 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_tool_usage_relational.py | 208 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_tool_usage_relational.py | 249 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_tool_usage_relational.py | 251 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_tool_usage_relational.py | 406 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_tool_usage_relational.py | 408 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_tool_usage_relational.py | 432 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_tool_usage_relational.py | 434 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_memory_multiturn.py | 44 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_memory_multiturn.py | 47 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_memory_multiturn.py | 100 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_memory_multiturn.py | 102 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_memory_multiturn.py | 148 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_memory_multiturn.py | 150 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | libs/evals/tests/evals/test_memory_multiturn.py | 194 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | libs/evals/tests/evals/test_memory_multiturn.py | 196 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_external_benchmarks.py | 29 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_external_benchmarks.py | 31 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_external_benchmarks.py | 59 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_external_benchmarks.py | 61 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_tool_selection.py | 35 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_tool_selection.py | 37 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | libs/evals/tests/evals/test_tool_selection.py | 110 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | libs/evals/tests/evals/test_tool_selection.py | 112 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | libs/evals/tests/evals/test_tool_selection.py | 193 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | libs/evals/tests/evals/test_tool_selection.py | 195 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | libs/evals/tests/evals/test_tool_selection.py | 277 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | libs/evals/tests/evals/test_tool_selection.py | 279 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | libs/evals/tests/evals/utils.py | 22 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | libs/evals/tests/evals/utils.py | 24 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | libs/evals/tests/evals/utils.py | 557 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | libs/evals/tests/evals/utils.py | 559 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/utils.py | 74 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/utils.py | 76 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/utils.py | 144 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/utils.py | 146 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/utils.py | 214 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/utils.py | 216 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/utils.py | 787 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/utils.py | 789 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/utils.py | 957 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/utils.py | 959 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/utils.py | 1192 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/utils.py | 1194 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/utils.py | 1256 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/utils.py | 1258 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/utils.py | 1407 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/utils.py | 1409 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | libs/evals/tests/evals/llm_judge.py | 121 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | libs/evals/tests/evals/llm_judge.py | 123 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM⚡ | libs/evals/tests/evals/llm_judge.py | 227 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | libs/evals/tests/evals/llm_judge.py | 229 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | libs/evals/tests/evals/test_memory.py | 355 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | libs/evals/tests/evals/test_memory.py | 357 | # --------------------------------------------------------------------------- | COMMENT |
| 483 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | libs/DEVELOPMENT.md | 108 | Send an email to a recipient with specified priority. Any additional context about the function can go here. A | STRING |
| HIGH | libs/talon/deepagents_talon/media.py | 162 | Build an outbound channel media payload for a markdown media ref. Args: ref: Markdown media reference. | STRING |
| HIGH | libs/talon/deepagents_talon/media.py | 195 | Resolve a local media path and enforce containment under a trusted root. Args: path: Candidate media path. | STRING |
| HIGH | libs/talon/deepagents_talon/archive_saver.py | 261 | Delete selected past sessions owned by this chat. Failures may leave a partially deleted batch; retry the same | STRING |
| HIGH | libs/talon/deepagents_talon/subagents.py | 252 | Resolve exact attachments, compiling fresh roles without inherited middleware. Frontmatter tool names are resolved | STRING |
| HIGH | libs/talon/deepagents_talon/config.py | 64 | Build runtime configuration from environment variables. Args: env: Environment mapping to read. Def | STRING |
| HIGH | libs/talon/deepagents_talon/host.py | 1157 | Invoke the agent for one scheduled job. Args: job: Claimed cron job to run. Returns: | STRING |
| HIGH | libs/talon/deepagents_talon/mcp_auth.py | 705 | Validate and resolve `url` off the event loop, under its own bound. `asyncio.to_thread` keeps a blocking `getaddrin | STRING |
| HIGH | libs/talon/deepagents_talon/clock.py | 23 | Describe the current instant in a timezone. Args: timezone: IANA timezone name. Defaults to the host's loca | STRING |
| HIGH | libs/talon/deepagents_talon/model_selection.py | 212 | Return the chat model for `spec`, building it on first use. Blocking: discovery reads provider profile data and | STRING |
| HIGH | libs/talon/deepagents_talon/runtime.py | 530 | Report estimated context costs without running the agent. Args: conversation_id: Host-resolved agen | STRING |
| HIGH | libs/talon/deepagents_talon/runtime.py | 658 | Invoke the Deep Agents graph for one Talon request. Args: request: Agent request supplied by the Ta | STRING |
| HIGH | libs/talon/deepagents_talon/sandbox.py | 67 | Start the configured sandbox for the host lifetime. Yields `None` when `DEEPAGENTS_TALON_SANDBOX` is unset. An owne | STRING |
| HIGH | libs/talon/deepagents_talon/mcp_config.py | 271 | Hold an exclusive lock for `path` while the block runs. The lock is a sidecar `.lock` file beside `path`, so reader | STRING |
| HIGH | libs/talon/deepagents_talon/async_subagents.py | 20 | Load async subagent definitions from `config.toml`. Reads the `[async_subagents]` section where each sub-table defi | STRING |
| HIGH | libs/talon/deepagents_talon/pairing.py | 625 | Build a channel's pairing policy from env, or `None` when disabled. Args: env: Environment variable mapping | STRING |
| HIGH | libs/talon/deepagents_talon/timezones.py | 33 | Look up an IANA timezone by name. Legacy POSIX aliases such as `EST5EDT` and bare UTC offsets are rejected: the | STRING |
| HIGH | libs/talon/deepagents_talon/fleet_import.py | 53 | Materialize a Fleet zip export into a Talon local agent directory. Args: zip_path: Fleet export zip file to | STRING |
| HIGH | libs/talon/deepagents_talon/cron/jobs.py | 240 | Deserialize a cron origin from disk. Args: data: JSON origin dictionary. Returns: | STRING |
| HIGH | libs/talon/deepagents_talon/cron/jobs.py | 374 | Parse a supported schedule string. Recognized forms are `in 30m`, `every 15m`, `at YYYY-MM-DD HH:MM <tz | STRING |
| HIGH | libs/talon/deepagents_talon/cron/jobs.py | 561 | Deserialize a cron schedule from disk. Every field is type-checked before use: the file is a trust boundary, | STRING |
| HIGH | libs/talon/deepagents_talon/cron/jobs.py | 634 | Deserialize repeat state from disk. Args: data: JSON repeat dictionary. Returns: | STRING |
| HIGH | libs/talon/deepagents_talon/cron/jobs.py | 778 | Deserialize a cron job from disk. Args: data: JSON job dictionary. Returns: Pa | STRING |
| HIGH | libs/talon/deepagents_talon/cron/jobs.py | 867 | Create and persist a cron job. Args: prompt: Prompt passed to the agent when the job fires. | STRING |
| HIGH | libs/talon/deepagents_talon/cron/jobs.py | 976 | Edit a job within the current conversation scope. Args: job_id: Job identifier. origin: | STRING |
| HIGH | libs/talon/deepagents_talon/cron/jobs.py | 1042 | Remove a job within the current conversation scope. Args: job_id: Job identifier. origi | STRING |
| HIGH | libs/talon/deepagents_talon/cron/jobs.py | 1188 | Delete completed jobs older than the retention window. Args: retain_for: Duration to keep disabled | STRING |
| HIGH | libs/talon/deepagents_talon/cron/jobs.py | 1374 | Parse an `until` bound written as `YYYY-MM-DD HH:MM <IANA tz>`. Uses the same local-time rules as the `at` schedule | STRING |
| HIGH | libs/talon/deepagents_talon/cron/jobs.py | 1403 | Resolve a schedule's first run, rejecting a one-shot that already passed. Args: schedule: Schedule being in | STRING |
| HIGH | libs/talon/deepagents_talon/cron/jobs.py | 1427 | Look up an IANA timezone, reporting failures as a cron job error. Cached because every schedule validates its zone | STRING |
| HIGH | libs/talon/deepagents_talon/cron/jobs.py | 1468 | Attach `zone` to a naive local wall-clock time. A time skipped by a spring-forward transition is snapped forward to | STRING |
| HIGH | libs/talon/deepagents_talon/cron/jobs.py | 1495 | Return the next local `hour:minute` in `zone` strictly after `now`. Each candidate is rebuilt from a local date rat | STRING |
| HIGH | libs/talon/deepagents_talon/cron/jobs.py | 1524 | Return the first instant strictly after `now` that `expression` matches in `zone`. Candidates are local wall-clock | STRING |
| HIGH | libs/talon/deepagents_talon/cron/jobs.py | 1553 | Parse a 24-hour local `HH:MM` time. Args: value: Time text. Returns: Hour and minute. Rai | STRING |
| HIGH | libs/talon/deepagents_talon/cron/jobs.py | 1580 | Parse a local `YYYY-MM-DD` date. Args: value: Date text. Returns: Parsed date. Raises: | STRING |
| HIGH | libs/talon/deepagents_talon/cron/jobs.py | 1741 | Confirm a decoded JSON value is an object before reading fields from it. Called once per record rather than once pe | STRING |
| HIGH | libs/talon/deepagents_talon/cron/jobs.py | 1834 | Rebuild a local date from its integer components. Args: record: Schedule dictionary. Returns: | STRING |
| HIGH | libs/talon/deepagents_talon/cron/expression.py | 130 | Parse a five-field cron expression or an `@` macro. Args: text: Expression such as `*/15 9-17 * * mon-fri` | STRING |
| HIGH | libs/talon/deepagents_talon/cron/expression.py | 200 | Expand one `*`, `N`, `A-B`, or stepped term into its values. A step on a single value, `A/S`, runs from `A` to the | STRING |
| HIGH | libs/talon/deepagents_talon/channels/whatsapp.py | 131 | Build WhatsApp channel configuration from Talon environment values. Args: config: Talon process con | STRING |
| HIGH | libs/talon/deepagents_talon/channels/telegram.py | 135 | Build Telegram channel configuration from Talon environment values. Args: config: Talon process con | STRING |
| HIGH | libs/talon/deepagents_talon/channels/telegram.py | 227 | Call a Bot API method and return the decoded response. Args: method: Bot API method name (e.g. `get | STRING |
| HIGH | libs/talon/deepagents_talon/channels/telegram.py | 258 | Call a Bot API method with one local file as multipart form data. Args: method: Bot API method name | STRING |
| HIGH | libs/talon/deepagents_talon/channels/telegram.py | 459 | Send validated image, video, or document media to a Telegram chat. Args: conversation_id: Telegram | STRING |
| HIGH | libs/talon/deepagents_talon/channels/telegram.py | 999 | Validate a Bot API response envelope and return the raw ``result`` value. Args: payload: Full Bot API respo | STRING |
| HIGH | libs/talon/deepagents_talon/channels/telegram.py | 1024 | Extract a dict result from a validated Bot API response. Args: result: Validated ``result`` field from a Bo | STRING |
| HIGH | libs/talon/deepagents_talon/channels/telegram.py | 1051 | Extract the list of updates from a getUpdates response result. Args: result: Validated ``result`` field fro | STRING |
| HIGH | libs/talon/deepagents_talon/channels/discord.py | 116 | Build Discord channel configuration from Talon environment values. Args: config: Talon process conf | STRING |
| HIGH | libs/talon/deepagents_talon/channels/discord.py | 1186 | Parse a boolean environment value. Args: value: Raw environment value, or `None` when unset. defaul | STRING |
| HIGH | libs/talon/deepagents_talon/channels/discord.py | 1210 | Parse an optional Discord guild id. Args: value: Raw environment value, or `None` when unset. Returns: | STRING |
| HIGH | libs/talon/deepagents_talon/channels/base.py | 149 | Split outbound text into channel-sized chunks. Args: text: Text to split. limit: Maximum characters | STRING |
| HIGH | libs/talon/deepagents_talon/channels/base.py | 181 | Build shared channel exposure policy from provider-specific env prefix. Args: env: Environment variable map | STRING |
| HIGH | libs/talon/deepagents_talon/channels/base.py | 243 | Validate outbound media path, type, and size. Args: media: Media payload to validate. root: Optiona | STRING |
| HIGH | libs/talon/deepagents_talon/channels/base.py | 393 | Return the configured global media cap. Args: env: Environment variable mapping. Returns: Maxi | STRING |
| HIGH | libs/talon/deepagents_talon/channels/base.py | 418 | Parse an optional float value with a default. Args: value: Raw environment value. default: Value re | STRING |
| HIGH | libs/talon/deepagents_talon/channels/base.py | 434 | Parse an optional integer value with a default. Args: value: Raw environment value. default: Value | STRING |
| HIGH | libs/talon/deepagents_talon/channels/slack.py | 160 | Build Slack channel configuration from Talon environment values. Args: config: Talon process config | STRING |
| HIGH | libs/talon/deepagents_talon/channels/slack.py | 1276 | Split a Talon conversation id into a Slack channel and thread. Args: conversation_id: DM channel id, or `ch | STRING |
| HIGH | libs/evals/harbor_adapters/contextbench/adapter.py | 32 | Parse a `cb-<suite>-<i>` task id. Args: task_id: Identifier of the form `cb-<suite>-<i>`, where `<i>` is th | STRING |
| HIGH | libs/evals/harbor_adapters/contextbench/adapter.py | 52 | Look up the Context-Bench record identified by a `cb-<suite>-<i>` task id. Args: task_id: Identifier of the | STRING |
| 272 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | libs/talon/deepagents_talon/interfaces.py | 6 | CODE | |
| LOW | libs/talon/deepagents_talon/media.py | 6 | CODE | |
| LOW | libs/talon/deepagents_talon/archive_saver.py | 7 | CODE | |
| LOW | libs/talon/deepagents_talon/archive_saver.py | 22 | CODE | |
| LOW | libs/talon/deepagents_talon/subagents.py | 3 | CODE | |
| LOW | libs/talon/deepagents_talon/history_profiles.py | 3 | CODE | |
| LOW | libs/talon/deepagents_talon/config.py | 6 | CODE | |
| LOW | libs/talon/deepagents_talon/history_adapters.py | 3 | CODE | |
| LOW | libs/talon/deepagents_talon/history_adapters.py | 13 | CODE | |
| LOW | libs/talon/deepagents_talon/history_vector_backends.py | 3 | CODE | |
| LOW | libs/talon/deepagents_talon/history_vector_backends.py | 21 | CODE | |
| LOW | libs/talon/deepagents_talon/history_vector_backends.py | 22 | CODE | |
| LOW | libs/talon/deepagents_talon/history_backends.py | 3 | CODE | |
| LOW | libs/talon/deepagents_talon/mcp_oauth.py | 3 | CODE | |
| LOW | libs/talon/deepagents_talon/host.py | 6 | CODE | |
| LOW | libs/talon/deepagents_talon/mcp_middleware.py | 3 | CODE | |
| LOW | libs/talon/deepagents_talon/history_vectors.py | 3 | CODE | |
| LOW | libs/talon/deepagents_talon/history_vectors.py | 16 | CODE | |
| LOW | libs/talon/deepagents_talon/checkpoint_backends.py | 3 | CODE | |
| LOW | libs/talon/deepagents_talon/mcp_auth.py | 3 | CODE | |
| LOW | libs/talon/deepagents_talon/clock.py | 6 | CODE | |
| LOW | libs/talon/deepagents_talon/store_records.py | 3 | CODE | |
| LOW | libs/talon/deepagents_talon/history_embeddings.py | 3 | CODE | |
| LOW | libs/talon/deepagents_talon/model_selection.py | 23 | CODE | |
| LOW | libs/talon/deepagents_talon/background.py | 3 | CODE | |
| LOW | libs/talon/deepagents_talon/background.py | 25 | CODE | |
| LOW | libs/talon/deepagents_talon/background.py | 32 | CODE | |
| LOW | libs/talon/deepagents_talon/history_drivers.py | 3 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 8 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 9 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 10 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 10 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 10 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 10 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 10 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 10 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 10 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 19 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 20 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 20 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 20 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 20 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 20 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 20 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 20 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 20 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 20 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 20 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 20 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 20 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 20 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 20 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 20 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 37 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 37 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 37 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 37 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 45 | CODE | |
| LOW | libs/talon/deepagents_talon/__init__.py | 45 | CODE | |
| LOW | libs/talon/deepagents_talon/observability.py | 6 | CODE | |
| 1104 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | libs/talon/tests/unit_tests/test_tool_approvals.py | 29 | b'{"tool": null}', | CODE |
| HIGH⚡ | libs/talon/tests/channels/test_slack.py | 888 | ("a < b && c > d", "a < b && c > d"), | CODE |
| HIGH | libs/evals/harbor_adapters/drbench/adapter.py | 1198 | # password null) keep each app's built-in login. | COMMENT |
| HIGH | libs/evals/tests/evals/test_auto_mode_authorization.py | 257 | arguments={"command": "source .env && python -m project.cli diagnose"}, | CODE |
| HIGH | libs/code/tests/unit_tests/test_server_manager.py | 69 | '["ls", null]', # list with a null element | CODE |
| HIGH | libs/code/tests/unit_tests/test_uninstall_command.py | 683 | `dcode uninstall openai && echo removed` printing "removed" would tell a | STRING |
| HIGH | libs/code/tests/unit_tests/test_install_script.py | 3180 | f"rc=0\nwget_download - {url!r} '' true || rc=$?\n" | CODE |
| HIGH | libs/code/tests/unit_tests/test_auto_mode.py | 4031 | ("Run git status", "git status && git push origin feature"), | CODE |
| HIGH | libs/code/tests/unit_tests/test_extras_info.py | 485 | '{"dir_info": null}', # valid JSON, dir_info not an object | CODE |
| HIGH⚡ | libs/code/tests/unit_tests/test_shell_allow_list.py | 159 | ("ls && cat file", True), | CODE |
| HIGH⚡ | libs/code/tests/unit_tests/test_shell_allow_list.py | 160 | ("ls && rm file", False), | CODE |
| HIGH⚡ | libs/code/tests/unit_tests/test_shell_allow_list.py | 161 | ("ls -la && grep pattern file && cat output.txt", True), | CODE |
| HIGH⚡ | libs/code/tests/unit_tests/test_shell_allow_list.py | 162 | ("ls && cat file && grep test", True), | CODE |
| HIGH⚡ | libs/code/tests/unit_tests/test_shell_allow_list.py | 163 | ("cat a.txt && cat b.txt && cat c.txt", True), | CODE |
| HIGH⚡ | libs/code/tests/unit_tests/test_shell_allow_list.py | 164 | ("ls && rm -rf /", False), | CODE |
| HIGH⚡ | libs/code/tests/unit_tests/test_shell_allow_list.py | 177 | ("ls || cat file", True), | CODE |
| HIGH⚡ | libs/code/tests/unit_tests/test_shell_allow_list.py | 178 | ("ls || rm file", False), | CODE |
| HIGH⚡ | libs/code/tests/unit_tests/test_shell_allow_list.py | 549 | ("ls && cat file", True), | CODE |
| HIGH⚡ | libs/code/tests/unit_tests/test_shell_allow_list.py | 550 | ("ls && grep test file", True), | CODE |
| HIGH⚡ | libs/code/tests/unit_tests/test_shell_allow_list.py | 639 | assert not contains_dangerous_patterns("ls && cat file") | CODE |
| HIGH⚡ | libs/code/tests/unit_tests/test_shell_allow_list.py | 170 | """Test commands with && operator (commonly used by Claude for chaining).""" | STRING |
| HIGH⚡ | libs/code/tests/unit_tests/test_shell_allow_list.py | 184 | """Test commands with || operator.""" | STRING |
| HIGH⚡ | libs/code/tests/unit_tests/test_shell_allow_list.py | 638 | """Double && should not be flagged as dangerous (it's a safe operator).""" | STRING |
| HIGH | libs/code/tests/unit_tests/test_update_check.py | 1251 | == f"export PATH={quoted_bin_dir}:$PATH\nhash -r 2>/dev/null || true" | CODE |
| HIGH | …ode/tests/integration_tests/test_sandbox_operations.py | 41 | "rm -rf /tmp/test_sandbox_ops && mkdir -p /tmp/test_sandbox_ops" | CODE |
| HIGH | libs/code/deepagents_code/update_check.py | 1992 | return f"export PATH={quoted}:$PATH\nhash -r 2>/dev/null || true" | CODE |
| HIGH⚡ | libs/code/deepagents_code/local_context.py | 413 | BRANCH="$(git rev-parse --abbrev-ref HEAD 2>/dev/null)" | CODE |
| HIGH⚡ | libs/code/deepagents_code/local_context.py | 415 | COMMIT="$(git rev-parse --short HEAD 2>/dev/null)" | CODE |
| HIGH⚡ | libs/code/deepagents_code/local_context.py | 423 | refs/heads/main refs/heads/master 2>/dev/null); do | CODE |
| HIGH | libs/code/deepagents_code/local_context.py | 283 | GIT_INFO="$(git rev-parse --is-inside-work-tree --show-toplevel 2>/dev/null)" | CODE |
| HIGH | libs/code/deepagents_code/local_context.py | 326 | $MONOREPO && echo "- Monorepo: yes" | CODE |
| HIGH | libs/code/deepagents_code/local_context.py | 344 | if grep -q '\[tool\.uv\]' pyproject.toml 2>/dev/null; then PKG="Python: uv" | CODE |
| HIGH | libs/code/deepagents_code/local_context.py | 345 | elif grep -q '\[tool\.poetry\]' pyproject.toml 2>/dev/null; then PKG="Python: poetry" | CODE |
| HIGH | libs/code/deepagents_code/local_context.py | 400 | $_RT_CLEANUP && rm -rf "$_RT_TMP" | CODE |
| HIGH | libs/code/deepagents_code/local_context.py | 485 | $_GH_CLEANUP && rm -rf "$_GH_TMP" | CODE |
| HIGH | libs/code/deepagents_code/local_context.py | 510 | _STACK_GIT_DIR="$(git rev-parse --git-dir 2>/dev/null)" | CODE |
| HIGH | libs/code/deepagents_code/local_context.py | 529 | if [ -f Makefile ] && grep -qE '^tests?:' Makefile 2>/dev/null; then TC="make test" | CODE |
| HIGH | libs/code/deepagents_code/local_context.py | 536 | && grep -q '"test"' package.json 2>/dev/null; then | CODE |
| HIGH | libs/code/deepagents_code/local_context.py | 551 | { ls -1 2>/dev/null; [ -e .deepagents ] && echo .deepagents; } | | CODE |
| HIGH | libs/code/deepagents_code/local_context.py | 616 | $TREE_TRUNCATED && echo "... (more lines truncated)" | CODE |
| HIGH | libs/code/deepagents_code/offload_api.py | 610 | msg = f"context.{key} must be a string or null, got {type(value).__name__}." | CODE |
| HIGH | libs/code/deepagents_code/offload_api.py | 622 | "context.model_context_limit must be an integer or null, " | CODE |
| HIGH | libs/code/deepagents_code/offload_api.py | 629 | f"context.auto_approve must be a boolean or null, " | CODE |
| HIGH | libs/partners/quickjs/tests/unit_tests/test_ptc.py | 394 | undefined = await repl.eval_async("await tools.myTool({ name: undefined })") | CODE |
| HIGH | …tners/quickjs/tests/unit_tests/test_repl_middleware.py | 1302 | "mustThrow('assign', () => { globalThis.task = null; });" | CODE |
| HIGH | …tners/quickjs/tests/unit_tests/test_repl_middleware.py | 1305 | "if (!Object.isFrozen(task) || task.extra !== undefined) {" | CODE |
| HIGH | …tners/quickjs/tests/unit_tests/test_repl_middleware.py | 1557 | " calls.push(task({" | CODE |
| HIGH⚡ | …s/partners/quickjs/tests/unit_tests/test_end_to_end.py | 302 | code = "const r = await tools.getUserEmailOrNone({user_id: -1});\n`${r === null}`;" | CODE |
| HIGH | libs/partners/quickjs/tests/benchmarks/_common.py | 26 | " values.push(await tools.echoPayload({value: `value-${i}`}));" | CODE |
| HIGH | libs/partners/quickjs/tests/benchmarks/_common.py | 35 | " values.push(value);" | CODE |
| HIGH | libs/partners/quickjs/langchain_quickjs/_prompt.py | 115 | reviewed.push(...(await Promise.all(batch.map(async (file) => { | CODE |
| HIGH⚡ | libs/deepagents/tests/unit_tests/test_version.py | 250 | pytest.param('{"dir_info": null}', id="null-dir-info"), | CODE |
| HIGH | …ents/tests/unit_tests/test_local_sandbox_operations.py | 267 | sandbox.execute("rm -rf /tmp/test_sandbox_ops && mkdir -p /tmp/test_sandbox_ops") | CODE |
| HIGH | …ents/tests/unit_tests/test_local_sandbox_operations.py | 1653 | sandbox.execute("rm -rf /tmp/test_sandbox_ops && mkdir -p /tmp/test_sandbox_ops") | CODE |
| HIGH | …ents/tests/unit_tests/test_local_sandbox_operations.py | 1924 | assert sandbox.execute(f"test -e {off_path} && echo Y || echo N").output.strip() == "N" | CODE |
| HIGH | …ents/tests/unit_tests/test_local_sandbox_operations.py | 1941 | self.sandbox.execute("rm -rf /tmp/test_sandbox_ops && mkdir -p /tmp/test_sandbox_ops") | CODE |
| HIGH | libs/deepagents/deepagents/backends/sandbox.py | 1358 | { ( eval "$__da_cmd" ); echo "$?" > "$__da_ecf"; } 2>&1 | { head -c __MAXBYTES__ > "$__da_f"; cat > /dev/null; } | CODE |
| HIGH | libs/deepagents/deepagents/backends/sandbox.py | 1359 | __da_ec=$(cat "$__da_ecf" 2>/dev/null) | CODE |
| HIGH | libs/deepagents/deepagents/backends/sandbox.py | 1963 | Runs `test -e || test -L` first: a path that does not exist (and is not | STRING |
| HIGH⚡ | libs/acp/tests/test_dangerous_patterns.py | 65 | assert not contains_dangerous_patterns("cd dir && ls") | CODE |
| 48 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | libs/talon/deepagents_talon/history_adapters.py | 55 | except Exception: # noqa: BLE001 # Provider validation can include API keys. | CODE |
| LOW | libs/talon/deepagents_talon/history_vector_backends.py | 185 | except Exception: # noqa: BLE001 # Plugin errors may contain URI credentials. | CODE |
| LOW | libs/talon/deepagents_talon/history_backends.py | 66 | except Exception: # noqa: BLE001 # Metadata errors may include URI credentials. | CODE |
| LOW | libs/talon/deepagents_talon/history_backends.py | 88 | except Exception: # noqa: BLE001 # Driver errors may contain credentials. | CODE |
| LOW | libs/talon/deepagents_talon/history_backends.py | 114 | except Exception: # noqa: BLE001 # Plugin errors may contain URI credentials. | CODE |
| LOW | libs/talon/deepagents_talon/history_backends.py | 145 | except Exception: # noqa: BLE001 # SQLite errors may contain sensitive connection details. | CODE |
| LOW | libs/talon/deepagents_talon/history_backends.py | 175 | except Exception: # noqa: BLE001 # Driver startup errors may contain URI credentials. | CODE |
| LOW | libs/talon/deepagents_talon/history_backends.py | 240 | except Exception: # noqa: BLE001 # Driver startup errors may contain URI credentials. | CODE |
| LOW⚡ | libs/talon/deepagents_talon/host.py | 781 | except Exception: # noqa: BLE001 | CODE |
| LOW⚡ | libs/talon/deepagents_talon/host.py | 791 | except Exception: # noqa: BLE001 | CODE |
| LOW⚡ | libs/talon/deepagents_talon/host.py | 811 | except Exception: # noqa: BLE001 # Do not disclose config or transport errors. | CODE |
| LOW⚡ | libs/talon/deepagents_talon/host.py | 897 | except Exception: | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 397 | except Exception: # noqa: BLE001 | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 477 | except Exception: | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 699 | except Exception: # noqa: BLE001 # Diagnostics must not disclose runtime errors. | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 712 | except Exception: # noqa: BLE001 # Do not disclose provider discovery errors. | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 729 | except Exception: # noqa: BLE001 # Do not disclose provider or credential errors. | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 1057 | except Exception: # noqa: BLE001 # _invoke_agent logged the traceback for operators | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 1268 | except Exception: | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 1310 | except Exception: | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 1357 | except Exception: # noqa: BLE001 # Report failure without disclosing stored history. | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 1382 | except Exception: | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 1471 | except Exception: | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 2224 | except Exception: # noqa: BLE001 # typing indicators are best-effort adapter calls. | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 2254 | except Exception: # noqa: BLE001 | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 2367 | except Exception: | CODE |
| LOW | libs/talon/deepagents_talon/history_vectors.py | 241 | except Exception as error: # noqa: BLE001 # Optional indexing must not stop conversation writes. | CODE |
| LOW | libs/talon/deepagents_talon/history_vectors.py | 371 | except Exception: # noqa: BLE001 # Search remains usable without the optional backend. | CODE |
| LOW | libs/talon/deepagents_talon/checkpoint_backends.py | 39 | except Exception: # noqa: BLE001 # Driver errors can contain URI credentials. | CODE |
| LOW | libs/talon/deepagents_talon/clock.py | 83 | except Exception as exc: # noqa: BLE001 # tool errors are returned to the agent | CODE |
| LOW | libs/talon/deepagents_talon/background.py | 279 | except Exception: | CODE |
| LOW | libs/talon/deepagents_talon/background.py | 326 | except Exception: | CODE |
| MEDIUM | libs/talon/deepagents_talon/runtime.py | 851 | def reload_subagent_configuration() -> dict[str, str]: | CODE |
| LOW | libs/talon/deepagents_talon/runtime.py | 594 | except Exception: # noqa: BLE001 # a stale selection must not fail the turn | CODE |
| LOW | libs/talon/deepagents_talon/runtime.py | 779 | except Exception: # noqa: BLE001 # keep the previous graph usable after an invalid edit | CODE |
| LOW | libs/talon/deepagents_talon/runtime.py | 791 | except Exception: | CODE |
| LOW | libs/talon/deepagents_talon/runtime.py | 827 | except Exception: # noqa: BLE001 # never return configuration contents | CODE |
| LOW | libs/talon/deepagents_talon/runtime.py | 854 | except Exception: # noqa: BLE001 # report reload failure without leaking config values | CODE |
| LOW | libs/talon/deepagents_talon/runtime.py | 895 | except Exception: | CODE |
| LOW | libs/talon/deepagents_talon/runtime.py | 1045 | except Exception as exc: | CODE |
| LOW | libs/talon/deepagents_talon/sandbox.py | 173 | except Exception as exc: | CODE |
| LOW | libs/talon/deepagents_talon/mcp.py | 374 | except Exception: | CODE |
| LOW | libs/talon/deepagents_talon/mcp.py | 628 | except Exception as exc: | CODE |
| LOW | libs/talon/deepagents_talon/mcp.py | 661 | except Exception: # noqa: BLE001 # status delivery cannot expose or undo OAuth state. | CODE |
| LOW | libs/talon/deepagents_talon/speech.py | 176 | except Exception: | CODE |
| LOW | libs/talon/deepagents_talon/pairing.py | 688 | except Exception: # noqa: BLE001 # A failed courtesy reply must not break inbound handling. | CODE |
| LOW | libs/talon/deepagents_talon/messaging.py | 69 | except Exception: # noqa: BLE001 # Keep transport failures out of model context. | CODE |
| LOW | libs/talon/deepagents_talon/cron/tools.py | 248 | except Exception as exc: # noqa: BLE001 | CODE |
| LOW | libs/talon/deepagents_talon/cron/tools.py | 260 | except Exception as exc: # noqa: BLE001 | CODE |
| LOW | libs/talon/deepagents_talon/cron/tools.py | 286 | except Exception as exc: # noqa: BLE001 | CODE |
| LOW | libs/talon/deepagents_talon/cron/tools.py | 301 | except Exception as exc: # noqa: BLE001 | CODE |
| LOW | libs/talon/deepagents_talon/cron/scheduler.py | 107 | except Exception as exc: | CODE |
| LOW | libs/talon/deepagents_talon/cron/scheduler.py | 148 | except Exception as exc: | CODE |
| LOW | libs/talon/deepagents_talon/cron/scheduler.py | 185 | except Exception as exc: | CODE |
| LOW | libs/talon/deepagents_talon/channels/whatsapp.py | 346 | except Exception: | CODE |
| LOW | libs/talon/deepagents_talon/channels/discord.py | 461 | except Exception: # noqa: BLE001 # A failed registration must not stop the channel. | CODE |
| LOW | libs/talon/deepagents_talon/channels/discord.py | 541 | except Exception as error: | CODE |
| LOW | libs/talon/deepagents_talon/channels/discord.py | 762 | except Exception as error: # noqa: BLE001 # transport errors must not crash the host loop | CODE |
| LOW | libs/talon/deepagents_talon/channels/discord.py | 861 | except Exception: # noqa: BLE001 # Report the failure through the interaction. | CODE |
| LOW | libs/talon/deepagents_talon/channels/base.py | 641 | except Exception as exc: # noqa: BLE001 # transport errors must not crash the host loop | CODE |
| 519 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | libs/talon/deepagents_talon/interfaces.py | 0 | register the host callback for inbound messages. args: handler: coroutine callback invoked for each inbound channel mess | STRING |
| HIGH | libs/talon/deepagents_talon/channels/discord.py | 0 | register the host callback for inbound messages. args: handler: coroutine callback invoked for each inbound channel mess | STRING |
| HIGH | libs/talon/deepagents_talon/channels/slack.py | 0 | register the host callback for inbound messages. args: handler: coroutine callback invoked for each inbound channel mess | STRING |
| HIGH | libs/talon/deepagents_talon/interfaces.py | 0 | register the host callback for inbound reactions. args: handler: coroutine callback invoked for each inbound channel rea | STRING |
| HIGH | libs/talon/deepagents_talon/channels/discord.py | 0 | register the host callback for inbound reactions. args: handler: coroutine callback invoked for each inbound channel rea | STRING |
| HIGH | libs/talon/deepagents_talon/channels/slack.py | 0 | register the host callback for inbound reactions. args: handler: coroutine callback invoked for each inbound channel rea | STRING |
| HIGH | libs/evals/tests/evals/test_followup_quality.py | 0 | apply summarization category to all tests in this module. tier is set per-test. | STRING |
| HIGH | …bs/evals/tests/evals/tau2_airline/test_tau2_airline.py | 0 | apply summarization category to all tests in this module. tier is set per-test. | STRING |
| HIGH | libs/evals/tests/evals/test_tool_usage_relational.py | 0 | apply summarization category to all tests in this module. tier is set per-test. | STRING |
| HIGH | libs/evals/tests/evals/test_tool_selection.py | 0 | apply summarization category to all tests in this module. tier is set per-test. | STRING |
| HIGH | libs/evals/tests/evals/test_todos.py | 0 | apply summarization category to all tests in this module. tier is set per-test. | STRING |
| HIGH | libs/evals/tests/evals/test_summarization.py | 0 | apply summarization category to all tests in this module. tier is set per-test. | STRING |
| HIGH | libs/evals/tests/evals/test_memory_multiturn.py | 0 | apply memory category and baseline tier to all tests in this module. | STRING |
| HIGH | libs/evals/tests/evals/test_memory.py | 0 | apply memory category and baseline tier to all tests in this module. | STRING |
| HIGH | …ts/evals/memory_agent_bench/test_memory_agent_bench.py | 0 | apply memory category and baseline tier to all tests in this module. | STRING |
| HIGH | libs/evals/tests/evals/test_system_prompt.py | 0 | apply unit_test category and baseline tier to all tests in this module. | STRING |
| HIGH | libs/evals/tests/evals/test_subagents.py | 0 | apply unit_test category and baseline tier to all tests in this module. | STRING |
| HIGH | libs/evals/tests/evals/test_skills.py | 0 | apply unit_test category and baseline tier to all tests in this module. | STRING |
| HIGH | libs/code/tests/unit_tests/test_configuration.py | 0 | resolve `option` through production code as `(value, source)`. thin alias for the shared `resolve_option_for_test`; see | STRING |
| HIGH | …code/tests/unit_tests/test_configuration_resolution.py | 0 | resolve `option` through production code as `(value, source)`. thin alias for the shared `resolve_option_for_test`; see | STRING |
| HIGH | libs/code/tests/unit_tests/test_config_manifest.py | 0 | resolve `option` through production code as `(value, source)`. thin alias for the shared `resolve_option_for_test`; see | STRING |
| HIGH | libs/code/tests/unit_tests/test_config.py | 0 | redirect the credential store into a temp directory. | STRING |
| HIGH | libs/code/tests/unit_tests/test_model_config.py | 0 | redirect the credential store into a temp directory. | STRING |
| HIGH | …code/tests/unit_tests/tui/widgets/test_auth_widgets.py | 0 | redirect the credential store into a temp directory. | STRING |
| HIGH | …e/tests/unit_tests/tui/widgets/test_thread_selector.py | 0 | pressing esc should dismiss the modal with none result. | STRING |
| HIGH | …de/tests/unit_tests/tui/widgets/test_model_selector.py | 0 | pressing esc should dismiss the modal with none result. | STRING |
| HIGH | …de/tests/unit_tests/tui/widgets/test_agent_selector.py | 0 | pressing esc should dismiss the modal with none result. | STRING |
| HIGH | …s/code/tests/integration_tests/test_sandbox_factory.py | 0 | test async upload followed by download for data integrity. | STRING |
| HIGH | …s/tests/unit_tests/backends/test_filesystem_backend.py | 0 | test async upload followed by download for data integrity. | STRING |
| HIGH | …s/unit_tests/backends/test_filesystem_backend_async.py | 0 | test async upload followed by download for data integrity. | STRING |
| HIGH | libs/code/deepagents_code/goal_rubric.py | 0 | omit hook inputs from traces by default; set a `tracepolicy` to override. | STRING |
| HIGH | libs/code/deepagents_code/_glm_5p2_profile.py | 0 | omit hook inputs from traces by default; set a `tracepolicy` to override. | STRING |
| HIGH | libs/code/deepagents_code/resume_state.py | 0 | omit hook inputs from traces by default; set a `tracepolicy` to override. | STRING |
| HIGH | libs/code/deepagents_code/configurable_model.py | 0 | omit hook inputs from traces by default; set a `tracepolicy` to override. | STRING |
| HIGH | libs/code/deepagents_code/cost_tracking.py | 0 | omit hook inputs from traces by default; set a `tracepolicy` to override. | STRING |
| HIGH | libs/code/deepagents_code/ask_user.py | 0 | omit hook inputs from traces by default; set a `tracepolicy` to override. | STRING |
| HIGH | libs/code/deepagents_code/auto_mode.py | 0 | omit hook inputs from traces by default; set a `tracepolicy` to override. | STRING |
| HIGH | libs/code/deepagents_code/goal_tools.py | 0 | omit hook inputs from traces by default; set a `tracepolicy` to override. | STRING |
| HIGH | libs/code/deepagents_code/agent.py | 0 | omit hook inputs from traces by default; set a `tracepolicy` to override. | STRING |
| HIGH | libs/code/deepagents_code/local_context.py | 0 | omit hook inputs from traces by default; set a `tracepolicy` to override. | STRING |
| HIGH | libs/code/deepagents_code/memory_guard.py | 0 | omit hook inputs from traces by default; set a `tracepolicy` to override. | STRING |
| HIGH | libs/code/deepagents_code/hooks/server_middleware.py | 0 | omit hook inputs from traces by default; set a `tracepolicy` to override. | STRING |
| HIGH | libs/deepagents/deepagents/middleware/rubric.py | 0 | omit hook inputs from traces by default; set a `tracepolicy` to override. | STRING |
| HIGH | libs/deepagents/deepagents/middleware/subagents.py | 0 | omit hook inputs from traces by default; set a `tracepolicy` to override. | STRING |
| HIGH | libs/deepagents/deepagents/middleware/skills.py | 0 | omit hook inputs from traces by default; set a `tracepolicy` to override. | STRING |
| HIGH | libs/deepagents/deepagents/middleware/memory.py | 0 | omit hook inputs from traces by default; set a `tracepolicy` to override. | STRING |
| HIGH | libs/deepagents/deepagents/middleware/filesystem.py | 0 | omit hook inputs from traces by default; set a `tracepolicy` to override. | STRING |
| HIGH | …s/deepagents/deepagents/middleware/patch_tool_calls.py | 0 | omit hook inputs from traces by default; set a `tracepolicy` to override. | STRING |
| HIGH | libs/deepagents/deepagents/middleware/summarization.py | 0 | omit hook inputs from traces by default; set a `tracepolicy` to override. | STRING |
| HIGH | …bs/deepagents/deepagents/middleware/async_subagents.py | 0 | omit hook inputs from traces by default; set a `tracepolicy` to override. | STRING |
| HIGH | …eepagents/deepagents/middleware/unsupported_content.py | 0 | omit hook inputs from traces by default; set a `tracepolicy` to override. | STRING |
| HIGH | libs/code/deepagents_code/subagents.py | 0 | what this subagent does. the main agent uses this to decide when to delegate. | STRING |
| HIGH | libs/deepagents/deepagents/middleware/subagents.py | 0 | what this subagent does. the main agent uses this to decide when to delegate. | STRING |
| HIGH | …bs/deepagents/deepagents/middleware/async_subagents.py | 0 | what this subagent does. the main agent uses this to decide when to delegate. | STRING |
| HIGH | libs/code/deepagents_code/tui/modals/model_switch.py | 0 | focus the modal so its bindings receive keyboard input. | STRING |
| HIGH | libs/code/deepagents_code/tui/modals/resume_compact.py | 0 | focus the modal so its bindings receive keyboard input. | STRING |
| HIGH | …ode/deepagents_code/tui/widgets/thread_agent_switch.py | 0 | focus the modal so its bindings receive keyboard input. | STRING |
| HIGH | libs/code/deepagents_code/tui/widgets/cwd_switch.py | 0 | focus the modal so its bindings receive keyboard input. | STRING |
| HIGH | libs/code/deepagents_code/tui/modals/cold_cache.py | 0 | toggle selection styling. args: selected: whether this row is currently under the cursor. | STRING |
| HIGH | …ode/deepagents_code/tui/widgets/notification_center.py | 0 | toggle selection styling. args: selected: whether this row is currently under the cursor. | STRING |
| 41 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | libs/talon/deepagents_talon/interfaces.py | 203 | def set_message_handler(self, handler: MessageHandler) -> None: | CODE |
| LOW | libs/talon/deepagents_talon/interfaces.py | 275 | def set_reaction_handler(self, handler: ReactionHandler) -> None: | CODE |
| LOW | libs/talon/deepagents_talon/history_adapters.py | 40 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/history_vector_backends.py | 30 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/host.py | 99 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/mcp_middleware.py | 54 | __all__ = ["MCP_TOOL_METADATA_KEY", "talon_mcp_middleware"] | CODE |
| LOW | libs/talon/deepagents_talon/history_vectors.py | 35 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/mcp_auth.py | 228 | async def set_tokens(self, tokens: OAuthToken) -> None: | CODE |
| LOW | libs/talon/deepagents_talon/mcp_auth.py | 272 | async def set_client_info(self, client_info: OAuthClientInformationFull) -> None: | CODE |
| LOW | libs/talon/deepagents_talon/mcp_auth.py | 1225 | __all__ = [ | CODE |
| LOW | libs/talon/deepagents_talon/background.py | 34 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/__init__.py | 58 | __all__ = [ | CODE |
| LOW | libs/talon/deepagents_talon/runtime.py | 102 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/sandbox.py | 24 | logger = logging.getLogger(__name__) | CODE |
| LOW⚡ | libs/talon/deepagents_talon/authorization.py | 164 | __all__ = [ | CODE |
| LOW | libs/talon/deepagents_talon/mcp.py | 68 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/mcp_config.py | 28 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/async_subagents.py | 16 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/speech.py | 23 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/pairing.py | 43 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/data_lifecycle.py | 22 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/timezones.py | 23 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/__main__.py | 57 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/messaging.py | 41 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/cron/__init__.py | 21 | __all__ = [ | CODE |
| LOW | libs/talon/deepagents_talon/cron/jobs.py | 28 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/cron/scheduler.py | 17 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/channels/whatsapp.py | 59 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/channels/whatsapp.py | 300 | def set_message_handler(self, handler: MessageHandler) -> None: | CODE |
| LOW | libs/talon/deepagents_talon/channels/whatsapp.py | 308 | def set_reaction_handler(self, handler: ReactionHandler) -> None: | CODE |
| LOW | libs/talon/deepagents_talon/channels/telegram.py | 56 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/channels/telegram.py | 373 | def set_message_handler(self, handler: MessageHandler) -> None: | CODE |
| LOW | libs/talon/deepagents_talon/channels/telegram.py | 381 | def set_reaction_handler(self, handler: ReactionHandler) -> None: | CODE |
| LOW | libs/talon/deepagents_talon/channels/discord.py | 58 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/channels/discord.py | 633 | def set_message_handler(self, handler: MessageHandler) -> None: | CODE |
| LOW | libs/talon/deepagents_talon/channels/discord.py | 641 | def set_reaction_handler(self, handler: ReactionHandler) -> None: | CODE |
| LOW | libs/talon/deepagents_talon/channels/__init__.py | 20 | __all__ = [ | CODE |
| LOW | libs/talon/deepagents_talon/channels/base.py | 41 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/channels/slack.py | 73 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/talon/deepagents_talon/channels/slack.py | 408 | async def update_message(self, channel_id: str, ts: str, text: str) -> None: | CODE |
| LOW | libs/talon/deepagents_talon/channels/slack.py | 633 | async def update_message(self, channel_id: str, ts: str, text: str) -> None: | CODE |
| LOW | libs/talon/deepagents_talon/channels/slack.py | 674 | def set_message_handler(self, handler: MessageHandler) -> None: | CODE |
| LOW | libs/talon/deepagents_talon/channels/slack.py | 682 | def set_reaction_handler(self, handler: ReactionHandler) -> None: | CODE |
| LOW | libs/talon/tests/conftest.py | 51 | def set_message_handler(self, handler: Callable[[ChannelMessage], Awaitable[None]]) -> None: | CODE |
| LOW | libs/talon/tests/test_observability.py | 51 | def set_message_handler(self, handler: Callable[[ChannelMessage], Awaitable[None]]) -> None: | CODE |
| LOW | libs/talon/tests/integration_tests/test_core_flows.py | 34 | def set_message_handler(self, handler: Callable[[ChannelMessage], Awaitable[None]]) -> None: | CODE |
| LOW | libs/evals/deepagents_clbench/system/__init__.py | 5 | __all__ = ["DeepAgentsSystem"] | CODE |
| LOW | libs/evals/tests/evals/pytest_reporter.py | 20 | logger = logging.getLogger(__name__) | CODE |
| LOW⚡ | libs/evals/tests/evals/utils.py | 19 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/evals/tests/evals/tau2_airline/runner.py | 29 | logger = logging.getLogger(__name__) | CODE |
| LOW⚡ | libs/evals/tests/evals/tau2_airline/evaluation.py | 36 | logger = logging.getLogger(__name__) | CODE |
| LOW | …bs/evals/tests/evals/tau2_airline/test_tau2_airline.py | 45 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/evals/tests/evals/memory_agent_bench/data_utils.py | 14 | logger = logging.getLogger(__name__) | CODE |
| LOW | …ts/evals/memory_agent_bench/test_memory_agent_bench.py | 49 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/evals/tests/evals/data/bfcl_apis/travel_booking.py | 221 | def _set_card_balance(self, card_id: str, balance: float) -> None: | CODE |
| LOW | libs/evals/deepagents_harbor/__init__.py | 12 | __all__ = [ | CODE |
| LOW | libs/evals/deepagents_harbor/failure.py | 15 | logger = logging.getLogger(__name__) | CODE |
| LOW | …deepagents_harbor/langgraph_project/langgraph_agent.py | 30 | logger = logging.getLogger(__name__) | CODE |
| LOW | libs/code/tests/unit_tests/test_text_encoding.py | 18 | def _set_text_encoding(monkeypatch: pytest.MonkeyPatch, code_page: str) -> None: | CODE |
| LOW | libs/code/tests/unit_tests/test_mcp_auth.py | 931 | async def set_tokens(self, tokens: OAuthToken) -> None: | CODE |
| 358 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | libs/evals/tests/evals/data/bfcl_apis/trading_bot.py | 200 | # Define the start and end dates for the range | COMMENT |
| MEDIUM | libs/evals/scripts/analyze.py | 632 | # Create the deep agent for trajectory analysis | STRING |
| MEDIUM | libs/evals/scripts/analyze.py | 658 | # Create the user message with the trajectory and explicit status | STRING |
| MEDIUM⚡ | libs/code/tests/unit_tests/test_agent.py | 1875 | # Create the default agent directory with AGENTS.md | COMMENT |
| MEDIUM⚡ | libs/code/tests/unit_tests/test_agent.py | 1880 | # Create a non-default agent | COMMENT |
| MEDIUM | libs/code/tests/unit_tests/test_end_to_end.py | 146 | # Create a fake model that returns predefined messages | COMMENT |
| MEDIUM | libs/code/tests/unit_tests/test_end_to_end.py | 168 | # Create a CLI agent with the fake model | COMMENT |
| MEDIUM | libs/code/tests/unit_tests/test_end_to_end.py | 207 | # Create a CLI agent with the fake model | COMMENT |
| MEDIUM | libs/code/tests/unit_tests/test_end_to_end.py | 274 | # Create a fake model that calls sample_tool | COMMENT |
| MEDIUM | libs/code/tests/unit_tests/test_end_to_end.py | 296 | # Create a CLI agent with the fake model and sample_tool | COMMENT |
| MEDIUM⚡ | libs/code/tests/unit_tests/test_end_to_end.py | 329 | # Create a test file to list | COMMENT |
| MEDIUM⚡ | libs/code/tests/unit_tests/test_end_to_end.py | 333 | # Create a fake model that uses filesystem tools | COMMENT |
| MEDIUM | libs/code/tests/unit_tests/test_end_to_end.py | 355 | # Create a CLI agent with the fake model | COMMENT |
| MEDIUM⚡ | libs/code/tests/unit_tests/test_end_to_end.py | 383 | # Create a simple fake model | COMMENT |
| MEDIUM⚡ | libs/code/tests/unit_tests/test_end_to_end.py | 392 | # Create a CLI agent | COMMENT |
| MEDIUM | libs/code/tests/unit_tests/skills/test_load.py | 83 | # Create a healthy user skills directory | COMMENT |
| MEDIUM | …ode/tests/integration_tests/test_sandbox_operations.py | 285 | # Create a line with 3000 characters | COMMENT |
| MEDIUM | …s/code/tests/integration_tests/test_sandbox_factory.py | 214 | # Create a directory | COMMENT |
| MEDIUM | …s/code/tests/integration_tests/test_sandbox_factory.py | 284 | # Create a directory | COMMENT |
| MEDIUM | libs/code/deepagents_code/media_utils.py | 482 | # Create a temp file for the image | COMMENT |
| MEDIUM | libs/code/deepagents_code/agent.py | 3589 | # Create the agent | COMMENT |
| MEDIUM | libs/code/deepagents_code/plugins/adapters/mcp.py | 238 | # Create the writable data dir when MCP configs need it. Discovery itself | COMMENT |
| MEDIUM | libs/code/scripts/install.sh | 3327 | # Create the file (and parents) if missing. Keep the real error text — | COMMENT |
| MEDIUM⚡ | libs/deepagents/tests/unit_tests/test_middleware.py | 3813 | # Create a list that exceeds the token limit (20000 tokens * 4 chars = 80000 chars) | COMMENT |
| MEDIUM⚡ | libs/deepagents/tests/unit_tests/test_middleware.py | 3863 | # Create a large tool result | COMMENT |
| MEDIUM⚡ | libs/deepagents/tests/unit_tests/test_middleware.py | 3871 | # Create a request for a tool in TOOLS_EXCLUDED_FROM_EVICTION | COMMENT |
| MEDIUM⚡ | libs/deepagents/tests/unit_tests/test_middleware.py | 3893 | # Create a large tool result | COMMENT |
| MEDIUM⚡ | libs/deepagents/tests/unit_tests/test_middleware.py | 3901 | # Create a request for a tool NOT in TOOLS_EXCLUDED_FROM_EVICTION | COMMENT |
| MEDIUM⚡ | libs/deepagents/tests/unit_tests/test_middleware.py | 3927 | # Create a ToolMessage with the large execute output | COMMENT |
| MEDIUM⚡ | libs/deepagents/tests/unit_tests/test_middleware.py | 3934 | # Create a request for the execute tool | COMMENT |
| MEDIUM | libs/deepagents/tests/unit_tests/test_middleware.py | 558 | # Create a large number of files that will exceed TOOL_RESULT_TOKEN_LIMIT | COMMENT |
| MEDIUM | …/deepagents/tests/unit_tests/test_file_system_tools.py | 51 | # Create a deep agent with the fake model and a memory saver | COMMENT |
| MEDIUM⚡ | libs/deepagents/tests/unit_tests/test_end_to_end.py | 981 | # Create a file with content that exceeds the truncation threshold | COMMENT |
| MEDIUM⚡ | libs/deepagents/tests/unit_tests/test_end_to_end.py | 990 | # Create a fake model that calls read_file | COMMENT |
| MEDIUM⚡ | libs/deepagents/tests/unit_tests/test_end_to_end.py | 1039 | # Create a small file that doesn't exceed the truncation threshold | COMMENT |
| MEDIUM⚡ | libs/deepagents/tests/unit_tests/test_end_to_end.py | 1047 | # Create a fake model that calls read_file | COMMENT |
| MEDIUM⚡ | libs/deepagents/tests/unit_tests/test_end_to_end.py | 1093 | # Create a large file with many lines (each line is 500 chars + newline) | COMMENT |
| MEDIUM⚡ | libs/deepagents/tests/unit_tests/test_end_to_end.py | 1103 | # Create a fake model that calls read_file with a non-zero offset | COMMENT |
| MEDIUM⚡ | libs/deepagents/tests/unit_tests/test_end_to_end.py | 1149 | # Create a large file | COMMENT |
| MEDIUM⚡ | libs/deepagents/tests/unit_tests/test_end_to_end.py | 1157 | # Create a fake model that calls read_file | COMMENT |
| MEDIUM | libs/deepagents/tests/unit_tests/test_end_to_end.py | 231 | # Create a fake model that returns predefined messages | COMMENT |
| MEDIUM | libs/deepagents/tests/unit_tests/test_end_to_end.py | 253 | # Create a deep agent with the fake model | COMMENT |
| MEDIUM | libs/deepagents/tests/unit_tests/test_end_to_end.py | 363 | # Create a fake model that calls sample_tool | COMMENT |
| MEDIUM | libs/deepagents/tests/unit_tests/test_end_to_end.py | 385 | # Create a deep agent with the fake model and sample_tool | COMMENT |
| MEDIUM | libs/deepagents/tests/unit_tests/test_end_to_end.py | 407 | # Create a fake model that uses filesystem tools | COMMENT |
| MEDIUM | libs/deepagents/tests/unit_tests/test_end_to_end.py | 429 | # Create a deep agent with the fake model | COMMENT |
| MEDIUM | libs/deepagents/tests/unit_tests/test_end_to_end.py | 448 | # Create a fake model that makes multiple tool calls | COMMENT |
| MEDIUM | libs/deepagents/tests/unit_tests/test_end_to_end.py | 481 | # Create a deep agent with the fake model and sample_tool | COMMENT |
| MEDIUM | libs/deepagents/tests/unit_tests/test_end_to_end.py | 595 | # Create a fake model that calls read_file | COMMENT |
| MEDIUM | libs/deepagents/tests/unit_tests/test_end_to_end.py | 690 | # Create a model that handles both turns | COMMENT |
| MEDIUM | libs/deepagents/tests/unit_tests/test_end_to_end.py | 769 | # Create a model that writes then globs | COMMENT |
| MEDIUM | libs/deepagents/tests/unit_tests/test_end_to_end.py | 838 | # Create a model that handles both turns | COMMENT |
| MEDIUM | libs/deepagents/tests/unit_tests/test_end_to_end.py | 916 | # Create a model that writes then globs | COMMENT |
| MEDIUM⚡ | libs/deepagents/tests/unit_tests/test_subagents.py | 170 | # Create the subagent's chat model that will handle the calculation | COMMENT |
| MEDIUM⚡ | libs/deepagents/tests/unit_tests/test_subagents.py | 179 | # Create the compiled subagent | COMMENT |
| MEDIUM⚡ | libs/deepagents/tests/unit_tests/test_subagents.py | 182 | # Create the parent agent with subagent support | COMMENT |
| MEDIUM | libs/deepagents/tests/unit_tests/test_subagents.py | 145 | # Create the parent agent's chat model that will call the subagent | COMMENT |
| MEDIUM | libs/deepagents/tests/unit_tests/test_subagents.py | 228 | # Create the parent agent's chat model that will call both subagents in parallel | COMMENT |
| MEDIUM | libs/deepagents/tests/unit_tests/test_subagents.py | 283 | # Create the parent agent with BOTH specialized subagents | COMMENT |
| MEDIUM | libs/deepagents/tests/unit_tests/test_subagents.py | 314 | # Create a lookup map from tool_call_id to ToolMessage for precise verification | COMMENT |
| 48 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | action.yml | 481 | set +e | COMMENT |
| LOW | libs/evals/pyproject.toml | 121 | "python-multipart>=0.0.32", | COMMENT |
| LOW | libs/evals/harbor_adapters/drbench/adapter.py | 1201 | external_insight_count = {external} | COMMENT |
| LOW | libs/evals/harbor_adapters/drbench/adapter.py | 1241 | COMMENT | |
| LOW | …deepagents_harbor/langgraph_project/langgraph_agent.py | 301 | assistant_id = _harbor_assistant_id(os.environ.get("HARBOR_SESSION_ID")) | COMMENT |
| LOW | libs/code/pyproject.toml | 361 | # uses `stacklevel=2`, so it is attributed to this package, not to the | COMMENT |
| LOW | libs/code/tests/unit_tests/test_server_config.py | 21 | # ------------------------------------------------------------------ | COMMENT |
| LOW | libs/code/tests/unit_tests/test_install_script.py | 2961 | # wget implements. Answer those probes *before* any counting or output, so | COMMENT |
| LOW | libs/code/tests/unit_tests/test_config_manifest.py | 201 | COMMENT | |
| LOW | …ntegration_tests/benchmarks/test_startup_benchmarks.py | 121 | COMMENT | |
| LOW | libs/code/deepagents_code/config_manifest.py | 3281 | # signaling flags the app sets for itself rather than reading as user config. | COMMENT |
| LOW | libs/code/deepagents_code/model_retry.py | 481 | # sets `__context__` on anything raised inside an `except` block, so | COMMENT |
| LOW | libs/code/deepagents_code/config.py | 4781 | # the fail-closed boundary: if there is no upload target, there is nothing | COMMENT |
| LOW | libs/code/deepagents_code/config.py | 6901 | COMMENT | |
| LOW | libs/code/deepagents_code/theme.py | 161 | """Incognito shell accent (darkened for light bg contrast).""" | COMMENT |
| LOW | libs/code/deepagents_code/model_config.py | 1041 | exposed under `openai_codex`. The Codex backend serves a narrower lineup than | COMMENT |
| LOW | libs/code/deepagents_code/model_config.py | 1061 | # fireworks SDK reads FIREWORKS_BASE_URL. | COMMENT |
| LOW | libs/code/deepagents_code/model_config.py | 1081 | # sit on the openai SDK, whose only base-URL env var is the shared | COMMENT |
| LOW | libs/code/deepagents_code/update_check.py | 181 | showing a user the `upgrade` form would hand them a command that silently | COMMENT |
| LOW | libs/code/deepagents_code/update_check.py | 1861 | for name in ("dcode", "deepagents-code"): | COMMENT |
| LOW | libs/code/deepagents_code/_ask_user_types.py | 141 | """ | COMMENT |
| LOW | libs/code/deepagents_code/media_utils.py | 601 | images: List of ImageData objects | COMMENT |
| LOW | libs/code/deepagents_code/configurable_model.py | 801 | # the original model while `ctx.model` still names the rejected override. | COMMENT |
| LOW | libs/code/deepagents_code/mcp_auth.py | 1721 | # A peer may have rotated the token while we waited for the | COMMENT |
| LOW | libs/code/deepagents_code/mcp_auth.py | 1741 | # through to re-auth instead of replaying the refresh | COMMENT |
| LOW | libs/code/deepagents_code/cost_tracking.py | 1821 | # returns the generic slot as mutually exclusive with the TTL slots; were | COMMENT |
| LOW | libs/code/deepagents_code/file_ops.py | 621 | ) | COMMENT |
| LOW | libs/code/deepagents_code/file_ops.py | 741 | record.before_content = "" | COMMENT |
| LOW | libs/code/deepagents_code/file_ops.py | 761 | # `ValueError`) and the LangSmith backend catches only its | COMMENT |
| LOW | libs/code/deepagents_code/file_ops.py | 781 | # raised must count as a lost pre-image too, or the diff | COMMENT |
| LOW | libs/code/deepagents_code/file_ops.py | 861 | # diff the removed content against; there is nothing to read | COMMENT |
| LOW | libs/code/deepagents_code/file_ops.py | 921 | # not an invariant. | COMMENT |
| LOW | libs/code/deepagents_code/ask_user.py | 301 | # `"success"` default: | COMMENT |
| LOW | libs/code/deepagents_code/ask_user.py | 381 | COMMENT | |
| LOW | libs/code/deepagents_code/ask_user.py | 401 | # `ToolInvocationError` is built from the pre-injection | COMMENT |
| LOW | libs/code/deepagents_code/cold_cache.py | 861 | host | COMMENT |
| LOW | libs/code/deepagents_code/cold_cache.py | 1101 | case "5m": | COMMENT |
| LOW | libs/code/deepagents_code/agent.py | 3021 | # Resume state: declares private checkpoint channels used on resume. | COMMENT |
| LOW | libs/code/deepagents_code/agent.py | 3361 | composite_backend, | COMMENT |
| LOW | libs/code/deepagents_code/_session_stats.py | 1161 | if not _names_a_model(message): | COMMENT |
| LOW | libs/code/deepagents_code/offload_middleware.py | 1401 | try: | COMMENT |
| LOW | libs/code/deepagents_code/offload_middleware.py | 1481 | ) | COMMENT |
| LOW | libs/code/deepagents_code/main.py | 821 | # dir), so this same failing upgrade would otherwise be retried on | COMMENT |
| LOW | libs/code/deepagents_code/main.py | 3821 | COMMENT | |
| LOW | libs/code/deepagents_code/main.py | 5301 | KeyboardInterrupt: Re-raised out of the TUI teardown block so the | COMMENT |
| LOW | libs/code/deepagents_code/main.py | 5681 | COMMENT | |
| LOW | libs/code/deepagents_code/_tool_stream.py | 561 | # Some providers deliver the new call's name/args before its replacement | COMMENT |
| LOW | libs/code/deepagents_code/_tool_stream.py | 681 | # chunk boundary landing right after an inner `}` (e.g. | COMMENT |
| LOW | libs/code/deepagents_code/_tool_stream.py | 701 | return None | COMMENT |
| LOW | libs/code/deepagents_code/mcp_tools.py | 2081 | COMMENT | |
| LOW | libs/code/deepagents_code/mcp_tools.py | 2741 | # or the interactive approval prompt's decision). Without it, servers | COMMENT |
| LOW | libs/code/deepagents_code/_textual_patches.py | 161 | COMMENT | |
| LOW | libs/code/deepagents_code/configuration/service.py | 601 | "refresh_failure", | COMMENT |
| LOW | libs/code/deepagents_code/configuration/provider.py | 201 | parsed = parse_interpreter_tools(raw) | COMMENT |
| LOW | libs/code/deepagents_code/configuration/providers.py | 1301 | # class name -- and append the "verify that the source is | COMMENT |
| LOW | libs/code/deepagents_code/configuration/resolver.py | 1141 | # Keeping the table lets a shape collision defeat the higher value. | COMMENT |
| LOW | libs/code/deepagents_code/tui/textual_adapter.py | 1881 | thread_id = session_state.thread_id | COMMENT |
| LOW | libs/code/deepagents_code/tui/textual_adapter.py | 1961 | # streaming — log and keep going (mirrors `_on_tool_complete`). | COMMENT |
| LOW | libs/code/deepagents_code/tui/textual_adapter.py | 1981 | # the teardown sweeps close the row out, reading the outcome `defer_success` | COMMENT |
| LOW | libs/code/deepagents_code/tui/textual_adapter.py | 2621 | # tool.use to orphan if the turn | COMMENT |
| 210 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | libs/talon/deepagents_talon/media.py | 63 | CODE | |
| LOW | libs/talon/deepagents_talon/archive_saver.py | 210 | CODE | |
| LOW | libs/talon/deepagents_talon/history_vector_backends.py | 85 | CODE | |
| LOW | libs/talon/deepagents_talon/host.py | 551 | CODE | |
| LOW | libs/talon/deepagents_talon/observability.py | 269 | CODE | |
| LOW | libs/talon/deepagents_talon/runtime.py | 418 | CODE | |
| LOW | libs/talon/deepagents_talon/history_voyage.py | 35 | CODE | |
| LOW | libs/talon/deepagents_talon/mcp_config.py | 270 | CODE | |
| LOW | libs/talon/deepagents_talon/cron/jobs.py | 961 | CODE | |
| LOW | libs/talon/deepagents_talon/cron/jobs.py | 1146 | CODE | |
| LOW | libs/talon/deepagents_talon/cron/expression.py | 106 | CODE | |
| LOW | libs/talon/deepagents_talon/channels/whatsapp.py | 600 | CODE | |
| LOW | libs/talon/deepagents_talon/channels/whatsapp.py | 658 | CODE | |
| LOW | libs/talon/deepagents_talon/channels/telegram.py | 1358 | CODE | |
| LOW | libs/talon/deepagents_talon/channels/discord.py | 1260 | CODE | |
| LOW | libs/talon/deepagents_talon/channels/slack.py | 527 | CODE | |
| LOW | …talon/tests/integration_tests/test_history_postgres.py | 22 | CODE | |
| LOW | libs/talon/tests/channels/test_telegram.py | 60 | CODE | |
| LOW | libs/evals/harbor_adapters/drbench/adapter.py | 476 | CODE | |
| LOW | …vals/harbor_adapters/drbench/templates/extract_text.py | 121 | CODE | |
| LOW | libs/evals/harbor_adapters/drbench/templates/judge.py | 467 | CODE | |
| LOW | libs/evals/tests/evals/pytest_reporter.py | 120 | CODE | |
| LOW | libs/evals/tests/evals/pytest_reporter.py | 293 | CODE | |
| LOW | libs/evals/tests/evals/pytest_reporter.py | 342 | CODE | |
| LOW | libs/evals/tests/evals/utils.py | 1261 | CODE | |
| LOW | libs/evals/tests/evals/llm_judge.py | 141 | CODE | |
| LOW | …/tests/evals/test_iterative_constraint_satisfaction.py | 84 | CODE | |
| LOW | libs/evals/tests/evals/tau2_airline/domain.py | 427 | CODE | |
| LOW | libs/evals/tests/evals/tau2_airline/domain.py | 512 | CODE | |
| LOW | libs/evals/tests/evals/tau2_airline/evaluation.py | 156 | CODE | |
| LOW | libs/evals/tests/evals/tau2_airline/evaluation.py | 162 | CODE | |
| LOW | …bs/evals/tests/evals/data/bfcl_apis/vehicle_control.py | 331 | CODE | |
| LOW | …bs/evals/tests/evals/data/bfcl_apis/vehicle_control.py | 553 | CODE | |
| LOW | …bs/evals/tests/evals/data/bfcl_apis/vehicle_control.py | 618 | CODE | |
| LOW | libs/evals/tests/unit_tests/test_category_tagging.py | 92 | CODE | |
| LOW | libs/evals/deepagents_harbor/langsmith.py | 643 | CODE | |
| LOW | libs/evals/deepagents_harbor/failure.py | 95 | CODE | |
| LOW | libs/evals/scripts/generate_radar.py | 119 | CODE | |
| LOW | libs/evals/scripts/generate_eval_catalog.py | 58 | CODE | |
| LOW | libs/evals/scripts/harbor_langsmith.py | 26 | CODE | |
| LOW | libs/evals/scripts/analyze.py | 254 | CODE | |
| LOW | libs/evals/scripts/analyze.py | 779 | CODE | |
| LOW | libs/code/tests/unit_tests/test_mcp_lifecycle.py | 306 | CODE | |
| LOW | …bs/code/tests/unit_tests/test_coding_agent_metadata.py | 56 | CODE | |
| LOW | libs/code/tests/unit_tests/test_btw_api.py | 59 | CODE | |
| LOW | libs/code/tests/unit_tests/test_goal_rubric.py | 328 | CODE | |
| LOW | libs/code/tests/unit_tests/test_mcp_tools.py | 431 | CODE | |
| LOW | libs/code/tests/unit_tests/test_remote_client.py | 1770 | CODE | |
| LOW | libs/code/tests/unit_tests/test_install_script.py | 2171 | CODE | |
| LOW | libs/code/tests/unit_tests/test_auto_mode.py | 3756 | CODE | |
| LOW | libs/code/tests/unit_tests/test_model_config.py | 1924 | CODE | |
| LOW | …ode/tests/unit_tests/smoke_tests/test_system_prompt.py | 187 | CODE | |
| LOW | …s/code/tests/unit_tests/tui/widgets/test_chat_input.py | 750 | CODE | |
| LOW | libs/code/tests/unit_tests/tui/widgets/test_diff.py | 149 | CODE | |
| LOW | libs/code/deepagents_code/reasoning_effort.py | 259 | CODE | |
| LOW | libs/code/deepagents_code/reasoning_effort.py | 315 | CODE | |
| LOW | libs/code/deepagents_code/goal_rubric.py | 1142 | CODE | |
| LOW | libs/code/deepagents_code/goal_rubric.py | 1170 | CODE | |
| LOW | libs/code/deepagents_code/goal_rubric.py | 1286 | CODE | |
| LOW | libs/code/deepagents_code/config_manifest.py | 169 | CODE | |
| 202 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | libs/talon/deepagents_talon/history_profiles.py | 183 | except ValueError: | CODE |
| HIGH | libs/talon/deepagents_talon/history_profiles.py | 226 | except ValueError: | CODE |
| HIGH | libs/talon/deepagents_talon/config.py | 343 | except ValueError: | CODE |
| HIGH | libs/talon/deepagents_talon/mcp.py | 503 | except DeviceAuthorizationCompletedError: | CODE |
| HIGH | libs/talon/deepagents_talon/channels/whatsapp.py | 937 | except FileNotFoundError: | CODE |
| HIGH | libs/talon/tests/unit_tests/test_model_selection.py | 648 | except Exception: # noqa: BLE001, S110 # rejecting before the call is also correct | CODE |
| HIGH | libs/code/tests/unit_tests/test_install_script.py | 525 | except OSError: | CODE |
| HIGH | libs/code/deepagents_code/approval_mode.py | 193 | except ValueError: | CODE |
| HIGH | libs/code/deepagents_code/update_check.py | 2130 | except ProcessLookupError: | CODE |
| HIGH | libs/code/deepagents_code/auto_mode.py | 2661 | except (OSError, ValueError): | CODE |
| HIGH | libs/code/deepagents_code/event_bus.py | 325 | except (BrokenPipeError, ConnectionResetError): | CODE |
| HIGH | libs/code/deepagents_code/event_bus.py | 209 | except FileNotFoundError: | CODE |
| HIGH | libs/code/deepagents_code/iterm_cursor_guide.py | 46 | except OSError: | CODE |
| HIGH | libs/code/deepagents_code/clipboard.py | 75 | except ImportError: | CODE |
| HIGH | libs/code/deepagents_code/_git.py | 460 | except FileNotFoundError: | CODE |
| HIGH | libs/code/deepagents_code/_git.py | 533 | except FileNotFoundError: | CODE |
| HIGH | libs/code/deepagents_code/_git.py | 591 | except FileNotFoundError: | CODE |
| HIGH | libs/code/deepagents_code/_git.py | 662 | except FileNotFoundError: | CODE |
| HIGH | libs/code/deepagents_code/main.py | 3693 | except KeyboardInterrupt: | CODE |
| HIGH | libs/code/deepagents_code/tui/widgets/messages.py | 3282 | except (ValueError, SyntaxError): | CODE |
| HIGH | libs/code/deepagents_code/tui/widgets/welcome.py | 160 | except (ValueError, RuntimeError): | CODE |
| HIGH | libs/code/deepagents_code/tui/widgets/status.py | 367 | except (ValueError, RuntimeError): | CODE |
| HIGH | libs/code/deepagents_code/plugins/store.py | 524 | except OSError: | CODE |
| HIGH | …s/code/deepagents_code/integrations/sandbox_factory.py | 378 | except Exception: # noqa: S110, BLE001 # Sandbox not ready yet, continue polling | CODE |
| HIGH | libs/code/deepagents_code/hooks/runner.py | 273 | except ProcessLookupError: | CODE |
| HIGH | libs/code/deepagents_code/skills/commands.py | 626 | except Exception: # noqa: BLE001, S110 # Shadow detection is cosmetic, safe to swallow | CODE |
| HIGH | libs/code/deepagents_code/client/non_interactive.py | 359 | except ProcessLookupError: | CODE |
| HIGH | libs/code/deepagents_code/client/non_interactive.py | 351 | except ProcessLookupError: | CODE |
| HIGH | libs/code/deepagents_code/client/remote_client.py | 651 | except NotFoundError: | CODE |
| HIGH | libs/code/deepagents_code/client/launch/server.py | 570 | except PermissionError: | CODE |
| HIGH | libs/acp/deepagents_acp/server.py | 667 | except json.JSONDecodeError: | CODE |
| HIGH | .github/scripts/release/check_release_deps.py | 243 | except ValueError: | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | libs/evals/pyproject.toml | 104 | # the eval harness itself has to install there. Without this, `uv sync --locked` | COMMENT |
| MEDIUM | libs/evals/pyproject.toml | 132 | # eval harness, where harbor imports filelock eagerly in a plain process with no | COMMENT |
| MEDIUM | libs/evals/harbor_adapters/contextbench/adapter.py | 298 | # from the verifier environment the harness injects (`JUDGE_MODELS`, | COMMENT |
| MEDIUM | libs/evals/harbor_adapters/drbench/templates/judge.py | 609 | # Recorded so a score is never silently attributed to the judge the harness asked for | COMMENT |
| MEDIUM⚡ | libs/evals/harbor_adapters/drbench/templates/judge.py | 746 | # broken harness, so it is scored zero like any other unearned metric. | COMMENT |
| MEDIUM⚡ | libs/evals/harbor_adapters/drbench/templates/judge.py | 755 | # the harness then counts the trial as errored rather than scored. | COMMENT |
| MEDIUM | libs/evals/tests/evals/test_auto_mode_authorization.py | 369 | # Shape violations are harness or schema-compliance failures, not policy | COMMENT |
| MEDIUM | …/evals/tests/unit_tests/test_harbor_langgraph_agent.py | 330 | # harness eval is supposed to evaluate. Passing an override would bypass it. | COMMENT |
| MEDIUM | …/evals/tests/unit_tests/test_harbor_langgraph_agent.py | 747 | # The bare path must not inject a harness system prompt, preserving the | COMMENT |
| MEDIUM | …/evals/tests/unit_tests/test_harbor_langgraph_agent.py | 796 | # a harness system prompt. | COMMENT |
| MEDIUM⚡ | libs/evals/tests/unit_tests/test_drbench_judge.py | 256 | # The harness uses this variable to publish DRBench's resolved fallback without | COMMENT |
| MEDIUM | …deepagents_harbor/langgraph_project/langgraph_agent.py | 306 | # the CLI-harness eval never exercises the dcode system prompt we ship. The | COMMENT |
| MEDIUM | libs/code/tests/unit_tests/test_goal_rubric.py | 918 | """Parsing helpers stay robust to messy nested criteria output.""" | STRING |
| MEDIUM⚡ | libs/code/tests/unit_tests/test_install_script.py | 3404 | # The harness must define every helper cleanup_on_signal calls; a missing | COMMENT |
| MEDIUM | libs/code/tests/unit_tests/test_install_script.py | 3347 | # implementations so the harness exercises shipped code without emitting | COMMENT |
| MEDIUM | libs/code/tests/unit_tests/test_install_script.py | 3363 | # so the harness exercises the real 128+signo exit path. | COMMENT |
| MEDIUM | libs/code/deepagents_code/_glm_5p2_profile.py | 301 | # Private imports: the harness registry and its lazy-load hook expose no | COMMENT |
| MEDIUM | libs/code/deepagents_code/agent.py | 3371 | # main agent. Preserve the SDK harness's model-specific tool metadata | COMMENT |
| LOW | libs/partners/quickjs/langchain_quickjs/_format.py | 210 | # stdout path -- we've already truncated the result, so we just add the marker | COMMENT |
| MEDIUM | libs/deepagents/tests/unit_tests/test_graph.py | 2115 | # A harness profile is registered under bare "openai". | COMMENT |
| MEDIUM | libs/deepagents/deepagents/graph.py | 645 | # Copy of `tools` with any harness-specific description rewrites. | STRING |
| MEDIUM | libs/deepagents/deepagents/graph.py | 817 | # Auto-add the default general-purpose subagent unless the harness profile | STRING |
| MEDIUM | libs/deepagents/deepagents/graph.py | 834 | # Add harness-profile middleware, if any | STRING |
| MEDIUM | libs/deepagents/deepagents/backends/utils.py | 405 | # (profiles/harness/_nvidia_nemotron_3_ultra.py) counts source rows to | COMMENT |
| MEDIUM | libs/deepagents/deepagents/profiles/__init__.py | 51 | # Built-in provider/harness profiles are registered lazily on first | COMMENT |
| LOW | libs/acp/deepagents_acp/utils.py | 311 | # Use specific handler if available, otherwise just use base command | COMMENT |
| LOW | libs/acp/deepagents_acp/utils.py | 316 | # Non-sensitive commands - just use the base command | COMMENT |
| MEDIUM | examples/nvidia_deep_agent/src/prompts.py | 12 | RESEARCHER_INSTRUCTIONS = """Gather and synthesize comprehensive information on the provided query, carefully addressing | STRING |
| MEDIUM | examples/better-harness/tests/__init__.py | 1 | # Tests package for better-harness. | COMMENT |
| MEDIUM | …amples/better-harness/examples/deepagents_example.toml | 1 | # Worked example for optimizing a Deep Agents-based harness. | COMMENT |
| MEDIUM | examples/better-harness/better_harness/core.py | 345 | "# better-harness report", | CODE |
| MEDIUM | .github/workflows/unified_evals.yml | 260 | # than imply a harness was used. An empty RESOLVED_CATEGORIES means | COMMENT |
| MEDIUM | .github/workflows/_harbor_run.yml | 559 | # Overlay the compared branch's agent source AFTER the harness's locked | COMMENT |
| MEDIUM | .github/workflows/_harbor_run.yml | 562 | # harness runs at the workflow ref; only the agent under test is the | COMMENT |
| MEDIUM | .github/workflows/_harbor_run.yml | 577 | # Overlay ONLY the agent-under-test libraries. The harness (harbor + | COMMENT |
| MEDIUM | .github/workflows/_harbor_run.yml | 580 | # build expects, and a compared branch's harness could diverge from them. | COMMENT |
| MEDIUM | .github/scripts/evals/unified_prep.py | 156 | # to a nonexistent harness. Validate at import; raise (not assert) so `python -O` | COMMENT |
| MEDIUM | .github/scripts/evals/unified_prep.py | 558 | # harness. Conversation is always tau3 and is never taken from this input. | COMMENT |
| MEDIUM⚡ | .github/scripts/tests/evals/test_unified_workflow.py | 689 | # Only the agent-under-test libraries are overlaid; the harness graph factory | COMMENT |
| MEDIUM | .github/scripts/tests/evals/test_unified_workflow.py | 95 | # The deep-agents harness list for autonomous/context defaults to bare. | COMMENT |
| MEDIUM⚡ | …thub/scripts/tests/release/test_build_release_notes.py | 224 | # ── Test harness ───────────────────────────────────────────────────────────── | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | libs/evals/tests/evals/test_skills.py | 54 | # Step 1: read_file to get the skill content. | COMMENT |
| LOW⚡ | libs/evals/tests/evals/test_skills.py | 55 | # Step 2: answer with the magic number. | COMMENT |
| LOW⚡ | libs/evals/tests/evals/test_skills.py | 97 | # Step 1: read_file for code-review only. | COMMENT |
| LOW⚡ | libs/evals/tests/evals/test_skills.py | 98 | # Step 2: answer with the code. | COMMENT |
| LOW⚡ | libs/evals/tests/evals/test_skills.py | 143 | # Step 1: read_file for both skills in parallel. | COMMENT |
| LOW⚡ | libs/evals/tests/evals/test_skills.py | 144 | # Step 2: answer combining both ports. | COMMENT |
| LOW⚡ | libs/evals/tests/evals/test_skills.py | 230 | # Step 1: read_file to discover the typo. | COMMENT |
| LOW⚡ | libs/evals/tests/evals/test_skills.py | 231 | # Step 2: edit_file to fix it. | COMMENT |
| LOW⚡ | libs/evals/tests/evals/test_skills.py | 232 | # Step 3: confirm. | COMMENT |
| LOW | libs/code/examples/skills/skill-creator/SKILL.md | 225 | ### Step 1: Understanding the Skill with Concrete Examples | COMMENT |
| LOW | libs/code/examples/skills/skill-creator/SKILL.md | 242 | ### Step 2: Planning the Reusable Skill Contents | COMMENT |
| LOW | libs/code/examples/skills/skill-creator/SKILL.md | 266 | ### Step 3: Initializing the Skill | COMMENT |
| LOW | libs/code/examples/skills/skill-creator/SKILL.md | 317 | ### Step 4: Edit the Skill | COMMENT |
| LOW | libs/code/examples/skills/skill-creator/SKILL.md | 358 | ### Step 5: Validate the Skill | COMMENT |
| LOW | libs/code/examples/skills/skill-creator/SKILL.md | 376 | ### Step 6: Iterate | COMMENT |
| LOW | libs/code/examples/skills/web-research/SKILL.md | 10 | ### Step 1: Create and Save Research Plan | COMMENT |
| LOW | libs/code/examples/skills/web-research/SKILL.md | 33 | ### Step 2: Delegate to Research Subagents | COMMENT |
| LOW | libs/code/examples/skills/web-research/SKILL.md | 52 | ### Step 3: Synthesize Findings | COMMENT |
| LOW | …deepagents_code/built_in_skills/skill-creator/SKILL.md | 228 | ### Step 1: Understanding the Skill with Concrete Examples | COMMENT |
| LOW | …deepagents_code/built_in_skills/skill-creator/SKILL.md | 245 | ### Step 2: Planning the Reusable Skill Contents | COMMENT |
| LOW | …deepagents_code/built_in_skills/skill-creator/SKILL.md | 269 | ### Step 3: Initializing the Skill | COMMENT |
| LOW | …deepagents_code/built_in_skills/skill-creator/SKILL.md | 320 | ### Step 4: Edit the Skill | COMMENT |
| LOW | …deepagents_code/built_in_skills/skill-creator/SKILL.md | 356 | ### Step 5: Validate the Skill | COMMENT |
| LOW | …deepagents_code/built_in_skills/skill-creator/SKILL.md | 374 | ### Step 6: Iterate | COMMENT |
| LOW | …code/deepagents_code/built_in_skills/remember/SKILL.md | 10 | ## Step 1: Identify Best Practices and Key Learnings | COMMENT |
| LOW | …code/deepagents_code/built_in_skills/remember/SKILL.md | 27 | ## Step 2: Decide Where to Store Each Learning | COMMENT |
| LOW | …code/deepagents_code/built_in_skills/remember/SKILL.md | 49 | ## Step 3: Create Skills for Significant Best Practices | COMMENT |
| LOW | …code/deepagents_code/built_in_skills/remember/SKILL.md | 102 | ## Step 4: Update Memory for Simpler Learnings | COMMENT |
| LOW | …code/deepagents_code/built_in_skills/remember/SKILL.md | 114 | ## Step 5: Summarize Changes | COMMENT |
| LOW⚡ | libs/code/scripts/install.sh | 3076 | # Step 1: try symlinking into a dir already in PATH (no profile change). | COMMENT |
| LOW⚡ | libs/code/scripts/install.sh | 3084 | # Step 2: create ~/.local/bin, symlink there, then add to shell profiles. | COMMENT |
| LOW | libs/code/scripts/install.sh | 3112 | # Step 3: detect the current shell, then write the PATH entry into every | COMMENT |
| LOW⚡ | libs/deepagents/deepagents/middleware/summarization.py | 1530 | # Step 1: Truncate args if configured | COMMENT |
| LOW⚡ | libs/deepagents/deepagents/middleware/summarization.py | 1536 | # Step 2: Check if summarization should happen | COMMENT |
| LOW⚡ | libs/deepagents/deepagents/middleware/summarization.py | 1552 | # Step 3: Perform summarization | COMMENT |
| LOW⚡ | libs/deepagents/deepagents/middleware/summarization.py | 1668 | # Step 1: Truncate args if configured | COMMENT |
| LOW⚡ | libs/deepagents/deepagents/middleware/summarization.py | 1674 | # Step 2: Check if summarization should happen | COMMENT |
| LOW⚡ | libs/deepagents/deepagents/middleware/summarization.py | 1690 | # Step 3: Perform summarization | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM⚡ | …ts/evals/memory_agent_bench/test_memory_agent_bench.py | 433 | # CI-friendly subset — file-seeded (agentic retrieval) strategy | COMMENT |
| MEDIUM | …ts/evals/memory_agent_bench/test_memory_agent_bench.py | 103 | # -- File-seeded (agentic retrieval) configuration --------------------------- | COMMENT |
| MEDIUM⚡ | libs/evals/tests/unit_tests/test_drbench_judge.py | 234 | # --- judge/embedding model selection -------------------------------------------------- | COMMENT |
| MEDIUM | …deepagents_harbor/langgraph_project/langgraph_agent.py | 237 | # Mirror create_model: pull context window + unsupported input modalities | COMMENT |
| MEDIUM | …deepagents_harbor/langgraph_project/langgraph_agent.py | 241 | # No usable profile: the identity section renders with no context window | COMMENT |
| MEDIUM | …deepagents_harbor/langgraph_project/langgraph_agent.py | 257 | # A profile that is present but lacks a usable context window is an | COMMENT |
| MEDIUM | libs/code/tests/unit_tests/test_server.py | 783 | # Config present on boot: the scaffold hook must not have fired yet. | COMMENT |
| MEDIUM | …de/tests/integration_tests/test_offload_server_side.py | 593 | # No scaffold: the workspace is fully prepared above, and a missing | STRING |
| MEDIUM | libs/code/deepagents_code/config.py | 7214 | if max_input_tokens and max_input_tokens < 8000: # noqa: PLR2004 # Model context window default | CODE |
| MEDIUM⚡ | libs/code/deepagents_code/local_context.py | 263 | # see build_detect_script() for the orchestration logic. | COMMENT |
| MEDIUM⚡ | …s/code/deepagents_code/client/launch/server_manager.py | 90 | # Workspace scaffolding | COMMENT |
| MEDIUM | libs/deepagents/tests/unit_tests/test_end_to_end.py | 4381 | # through FilesystemMiddleware so multi-agent handoffs reach the sibling node. | COMMENT |
| MEDIUM | libs/deepagents/tests/unit_tests/test_graph.py | 1654 | # and the loop variable is a specific scaffolding class — the | COMMENT |
| MEDIUM | libs/deepagents/deepagents/graph.py | 632 | # Validate profile-level invariants (required scaffolding, private names) | STRING |
| MEDIUM | libs/deepagents/deepagents/middleware/summarization.py | 603 | # Truncate when 50% of context window reached, ignoring messages in last 10% of window | STRING |
| MEDIUM | …eepagents/profiles/harness/_nvidia_nemotron_3_ultra.py | 371 | # not treat framework scaffolding as application/domain tools. | COMMENT |
| MEDIUM⚡ | libs/acp/examples/local_context.py | 60 | # see build_detect_script() for the orchestration logic. | COMMENT |
| MEDIUM | .github/RELEASING.md | 318 | ### CI guardrails around releases | COMMENT |
| MEDIUM | .github/RELEASING.md | 512 | A regular release has a review point before publication: release-please generates the package changelog in a release PR, | CODE |
| MEDIUM | .github/LAYOUT.md | 43 | The two PR labelers also appear in [`RELEASING.md`](./RELEASING.md#ci-guardrails-around-releases) because the release gu | CODE |
| MEDIUM | openwiki/architecture/source-map.md | 98 | ## dcode: app orchestration versus durable local state | COMMENT |
| MEDIUM | openwiki/architecture/middleware-stack.md | 96 | ## Profile exclusions and required scaffolding | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | libs/evals/tests/evals/test_skills.py | 54 | # Step 1: read_file to get the skill content. | COMMENT |
| LOW⚡ | libs/evals/tests/evals/test_skills.py | 55 | # Step 2: answer with the magic number. | COMMENT |
| LOW⚡ | libs/evals/tests/evals/test_skills.py | 97 | # Step 1: read_file for code-review only. | COMMENT |
| LOW⚡ | libs/evals/tests/evals/test_skills.py | 98 | # Step 2: answer with the code. | COMMENT |
| LOW⚡ | libs/evals/tests/evals/test_skills.py | 143 | # Step 1: read_file for both skills in parallel. | COMMENT |
| LOW⚡ | libs/evals/tests/evals/test_skills.py | 144 | # Step 2: answer combining both ports. | COMMENT |
| LOW⚡ | libs/evals/tests/evals/test_skills.py | 230 | # Step 1: read_file to discover the typo. | COMMENT |
| LOW⚡ | libs/evals/tests/evals/test_skills.py | 231 | # Step 2: edit_file to fix it. | COMMENT |
| LOW⚡ | libs/evals/tests/evals/test_skills.py | 232 | # Step 3: confirm. | COMMENT |
| LOW⚡ | libs/code/deepagents_code/skills/commands.py | 376 | ### Step 1: [First Action] | COMMENT |
| LOW⚡ | libs/code/deepagents_code/skills/commands.py | 379 | ### Step 2: [Second Action] | COMMENT |
| LOW⚡ | libs/code/deepagents_code/skills/commands.py | 382 | ### Step 3: [Final Action] | COMMENT |
| LOW⚡ | libs/code/scripts/install.sh | 3076 | # Step 1: try symlinking into a dir already in PATH (no profile change). | COMMENT |
| LOW⚡ | libs/code/scripts/install.sh | 3084 | # Step 2: create ~/.local/bin, symlink there, then add to shell profiles. | COMMENT |
| LOW | libs/code/scripts/install.sh | 3112 | # Step 3: detect the current shell, then write the PATH entry into every | COMMENT |
| LOW⚡ | libs/deepagents/deepagents/middleware/summarization.py | 1530 | # Step 1: Truncate args if configured | COMMENT |
| LOW⚡ | libs/deepagents/deepagents/middleware/summarization.py | 1536 | # Step 2: Check if summarization should happen | COMMENT |
| LOW⚡ | libs/deepagents/deepagents/middleware/summarization.py | 1552 | # Step 3: Perform summarization | COMMENT |
| LOW⚡ | libs/deepagents/deepagents/middleware/summarization.py | 1668 | # Step 1: Truncate args if configured | COMMENT |
| LOW⚡ | libs/deepagents/deepagents/middleware/summarization.py | 1674 | # Step 2: Check if summarization should happen | COMMENT |
| LOW⚡ | libs/deepagents/deepagents/middleware/summarization.py | 1690 | # Step 3: Perform summarization | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | libs/evals/tests/evals/data/bfcl_apis/message_api.py | 181 | # Check if there is a current user logged in | COMMENT |
| LOW | libs/evals/tests/evals/data/bfcl_apis/travel_booking.py | 783 | # Check if the traveler is at least 18 years old | COMMENT |
| LOW | libs/evals/tests/evals/data/bfcl_apis/travel_booking.py | 790 | # Check if the passport number starts with 'US' (assuming this indicates a US passport) | COMMENT |
| LOW | libs/evals/scripts/analyze.py | 52 | # Check if this is a valid task directory (has solution/solve.sh) | COMMENT |
| LOW⚡ | …de/examples/skills/skill-creator/scripts/init_skill.py | 212 | # Check if directory already exists | STRING |
| LOW | libs/code/deepagents_code/config.py | 4355 | # Check if this command is in the allow set | COMMENT |
| LOW | libs/code/deepagents_code/config.py | 7028 | # Check if this provider uses a custom BaseChatModel class | COMMENT |
| LOW | libs/code/deepagents_code/media_utils.py | 535 | # Check if file was created and has content | STRING |
| LOW | libs/code/deepagents_code/tui/textual_adapter.py | 3165 | # Check if this is an AIMessageChunk with content | COMMENT |
| LOW | libs/code/deepagents_code/tui/widgets/chat_input.py | 3533 | # Check if it looked like media but failed validation | COMMENT |
| LOW | libs/code/deepagents_code/skills/commands.py | 105 | # Check if skill_dir is within base_dir | COMMENT |
| LOW | libs/code/deepagents_code/skills/commands.py | 612 | # Check if this project skill shadows a user skill with the same name. | STRING |
| LOW⚡ | …de/built_in_skills/skill-creator/scripts/init_skill.py | 256 | # Check if directory already exists | STRING |
| LOW | libs/code/scripts/install.sh | 2623 | # Check if a directory was in PATH before the installer sourced any env files. | COMMENT |
| LOW | libs/code/scripts/install.sh | 2746 | # Check if ~/.local/bin is already referenced in the shell profile's PATH | COMMENT |
| LOW | …ts/unit_tests/backends/test_composite_backend_async.py | 458 | # Write files to both backends | COMMENT |
| LOW | …ts/unit_tests/backends/test_composite_backend_async.py | 861 | # Write files to memories | COMMENT |
| LOW | …ts/unit_tests/backends/test_composite_backend_async.py | 1100 | # Write files to memories | COMMENT |
| LOW | …ts/tests/unit_tests/backends/test_composite_backend.py | 694 | # Write files to both backends | COMMENT |
| LOW | …ts/tests/unit_tests/backends/test_composite_backend.py | 1104 | # Write files to memories | COMMENT |
| LOW | …ts/tests/unit_tests/backends/test_composite_backend.py | 1285 | # Write files to memories | COMMENT |
| LOW | …/tests/unit_tests/backends/test_store_backend_async.py | 227 | # Write file with multiple occurrences | COMMENT |
| LOW | …/tests/unit_tests/backends/test_store_backend_async.py | 260 | # Write file with multiple lines | COMMENT |
| LOW | …/tests/unit_tests/backends/test_store_backend_async.py | 304 | # Write files in nested directories | COMMENT |
| LOW | …/tests/unit_tests/backends/test_local_shell_backend.py | 151 | # Read the file | COMMENT |
| LOW | libs/deepagents/deepagents/middleware/filesystem.py | 3391 | # Check if content exceeds eviction threshold | COMMENT |
| LOW | libs/deepagents/deepagents/middleware/summarization.py | 1066 | # Check if this AIMessage has tool calls we need to truncate | COMMENT |
| LOW | libs/deepagents/deepagents/backends/store.py | 331 | # Check if file is in the specified directory or a subdirectory | COMMENT |
| LOW | libs/deepagents/deepagents/backends/utils.py | 964 | # Check if path matches an exact file | STRING |
| LOW | libs/deepagents/deepagents/backends/state.py | 144 | # Check if file is in the specified directory or a subdirectory | COMMENT |
| LOW | libs/acp/deepagents_acp/server.py | 1168 | # Check if this is write_todos - auto-approve updates to existing plan | COMMENT |
| LOW | libs/acp/deepagents_acp/server.py | 1197 | # Check if ALL command types are already allowed | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| CRITICAL | libs/code/tests/unit_tests/test_remote_client.py | 599 | agent._graph.client.http.get.reset_mock() | CODE |
| CRITICAL | libs/code/tests/unit_tests/test_remote_client.py | 601 | agent._graph.client.http.get.assert_not_awaited() | CODE |
| CRITICAL | libs/code/tests/unit_tests/test_offload_api.py | 1270 | operation.execute.return_value.archive.write.assert_not_awaited() | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | libs/talon/deepagents_talon/runtime.py | 322 | CODE | |
| LOW | libs/talon/deepagents_talon/cron/jobs.py | 961 | CODE | |
| LOW | libs/talon/tests/channels/test_telegram.py | 120 | CODE | |
| LOW | libs/talon/tests/channels/test_telegram.py | 170 | CODE | |
| LOW | libs/code/tests/unit_tests/test_agent.py | 161 | CODE | |
| LOW | libs/code/tests/unit_tests/test_install_script.py | 110 | CODE | |
| LOW | libs/code/tests/unit_tests/test_install_script.py | 272 | CODE | |
| LOW | libs/code/tests/unit_tests/test_install_script.py | 307 | CODE | |
| LOW | libs/code/tests/unit_tests/test_install_script.py | 2886 | CODE | |
| LOW | libs/code/tests/unit_tests/test_main_args.py | 1102 | CODE | |
| LOW | libs/code/tests/unit_tests/test_main_args.py | 1383 | CODE | |
| LOW | libs/code/tests/unit_tests/test_auto_mode.py | 1173 | CODE | |
| LOW | libs/code/tests/unit_tests/test_main.py | 1428 | CODE | |
| LOW | libs/code/tests/unit_tests/tui/widgets/test_welcome.py | 73 | CODE | |
| LOW | libs/code/deepagents_code/reliable_rubric.py | 126 | CODE | |
| LOW | libs/code/deepagents_code/sessions.py | 2012 | CODE | |
| LOW | libs/code/deepagents_code/auto_mode.py | 2383 | CODE | |
| LOW | libs/code/deepagents_code/agent.py | 2524 | CODE | |
| LOW | libs/code/deepagents_code/_server_config.py | 937 | CODE | |
| LOW | libs/code/deepagents_code/main.py | 3127 | CODE | |
| LOW | libs/code/deepagents_code/main.py | 3474 | CODE | |
| LOW | libs/code/deepagents_code/tui/textual_adapter.py | 1753 | CODE | |
| LOW | libs/code/deepagents_code/tui/textual_adapter.py | 811 | CODE | |
| LOW | libs/code/deepagents_code/tui/widgets/messages.py | 5518 | CODE | |
| LOW | libs/code/deepagents_code/tui/widgets/welcome.py | 198 | CODE | |
| LOW | libs/code/deepagents_code/tui/widgets/model_selector.py | 525 | CODE | |
| LOW | libs/code/deepagents_code/skills/load.py | 48 | CODE | |
| LOW | libs/code/deepagents_code/client/non_interactive.py | 2068 | CODE | |
| LOW | libs/code/deepagents_code/client/non_interactive.py | 2569 | CODE | |
| LOW | …s/code/deepagents_code/client/launch/server_manager.py | 296 | CODE | |
| LOW | …s/code/deepagents_code/client/launch/server_manager.py | 497 | CODE | |
| LOW | libs/partners/quickjs/langchain_quickjs/middleware.py | 228 | CODE | |
| LOW | …bs/deepagents/tests/unit_tests/test_async_subagents.py | 44 | CODE | |
| LOW | libs/deepagents/deepagents/graph.py | 277 | CODE | |
| LOW | libs/deepagents/deepagents/middleware/rubric.py | 556 | CODE | |
| LOW | libs/deepagents/deepagents/middleware/filesystem.py | 1765 | CODE | |
| LOW | libs/deepagents/deepagents/_api/deprecation.py | 39 | CODE | |
| LOW | examples/nvidia_deep_agent/src/tools.py | 84 | CODE | |
| LOW | examples/deep_research/research_agent/tools.py | 88 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | libs/talon/tests/unit_tests/test_history_profiles.py | 55 | {"BASE_URL": "https://key:password@example.org"}, | CODE |
| LOW | …s/talon/tests/unit_tests/test_tool_approval_runtime.py | 102 | model = ToolModel(responses=[AIMessage(content="placeholder")]) | CODE |
| LOW | …s/talon/tests/unit_tests/test_tool_approval_runtime.py | 449 | model = ToolModel(responses=[AIMessage(content="placeholder")]) | CODE |
| LOW⚡ | libs/evals/tests/evals/test_tool_usage_relational.py | 598 | # 2nd step: call get_user_email(user_id=42) -> "eve@example.org". | COMMENT |
| LOW⚡ | libs/evals/tests/evals/test_tool_usage_relational.py | 603 | final_text_contains("eve@example.org"), | CODE |
| LOW | libs/evals/tests/evals/test_tool_usage_relational.py | 112 | "email": "eve@example.org", | CODE |
| LOW | libs/evals/tests/evals/test_tool_usage_relational.py | 1156 | final_text_contains("eve@example.org"), | CODE |
| LOW⚡ | libs/code/tests/unit_tests/hooks/test_execution.py | 123 | "OPENAI_API_KEY": "placeholder", | CODE |
| LOW⚡ | libs/code/tests/unit_tests/hooks/test_execution.py | 125 | "MY_TOKEN": "placeholder", | CODE |
| LOW⚡ | libs/code/tests/unit_tests/hooks/test_execution.py | 126 | "mixed_case_secret": "placeholder", | CODE |
| LOW | libs/code/tests/unit_tests/hooks/test_transcript.py | 52 | assert "placeholder" not in first["content"] | CODE |
| LOW | libs/code/tests/unit_tests/hooks/test_transcript.py | 75 | redacted = redact_transcript_value({"token": "placeholder"}) | CODE |
| LOW | libs/code/deepagents_code/tui/widgets/chat_input.py | 618 | kwargs.pop("placeholder", None) | CODE |
| LOW | …agents/tests/unit_tests/backends/test_store_backend.py | 520 | ("user@example.com",), | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | libs/talon/tests/unit_tests/test_checkpoint_backends.py | 79 | CODE | |
| MEDIUM | libs/talon/tests/unit_tests/test_sandbox.py | 190 | CODE | |
| MEDIUM | libs/code/tests/unit_tests/test_mcp_tools.py | 1550 | CODE | |
| MEDIUM | libs/code/tests/unit_tests/test_mcp_tools.py | 2376 | CODE | |
| MEDIUM | libs/code/tests/unit_tests/test_acp.py | 24 | CODE | |
| MEDIUM | libs/code/tests/unit_tests/test_extras_info.py | 538 | CODE | |
| MEDIUM | libs/code/tests/unit_tests/tui/test_textual_adapter.py | 5070 | CODE | |
| MEDIUM | libs/deepagents/tests/unit_tests/test_end_to_end.py | 5027 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | libs/code/tests/unit_tests/test_process_cwd_check.py | 46 | "from pathlib import Path as P\n\ndef handle_request():\n return P.cwd()\n", | CODE |
| LOW | libs/code/tests/unit_tests/test_process_cwd_check.py | 66 | "def handle_request(start_path=None):\n" | CODE |
| LOW | …code/tests/unit_tests/test_openai_codex_integration.py | 493 | def handle_request(self) -> None: | CODE |
| LOW | …/deepagents/tests/unit_tests/test_file_system_tools.py | 307 | "content": "def helper():\n return 42", | CODE |
| LOW⚡ | …/tests/unit_tests/middleware/test_skills_middleware.py | 833 | helper_content = "def helper(): pass" | CODE |
| LOW | …s/deepagents/tests/unit_tests/_api/test_deprecation.py | 45 | def helper() -> None: | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | .github/scripts/release/check_release_deps.py | 277 | PyPIRequestError: If PyPI cannot provide a usable response. | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | libs/code/scripts/install.sh | 4 | # Usage: | COMMENT |