Yufeng He a4f6665ef4

fix(security): sanitize MCP-sourced tool results through the same trust boundary (#4839) ...

* fix(security): sanitize MCP-sourced tool results through the same trust boundary

Signed-off-by: Yufeng He <40085740+he-yufeng@users.noreply.github.com>

* fix(security): sync the trust-boundary docs with tag coverage and pin the untagged branch

Signed-off-by: Yufeng He <40085740+he-yufeng@users.noreply.github.com>

---------

Signed-off-by: Yufeng He <40085740+he-yufeng@users.noreply.github.com>

2026-09-01 09:49:32 +08:00

..

agents

fix(security): sanitize MCP-sourced tool results through the same trust boundary (#4839)

2026-09-01 09:49:32 +08:00

authz

fix(authz): recheck policy before sandbox reuse (#5006)

2026-08-30 15:29:51 +08:00

community

fix: enforce custom agent skill allowlists in sandboxes (#5077)

2026-08-31 14:35:08 +08:00

config

fix: enforce custom agent skill allowlists in sandboxes (#5077)

2026-08-31 14:35:08 +08:00

extensions

feat(harness): deterministic tool receipts with model-visible ledger (RFC #4651, layer 1) (#4659)

2026-08-23 15:43:37 +08:00

guardrails

feat(extensions): let an out-of-tree extension observe what the agent did (#4863)

2026-08-23 09:57:12 +08:00

integrations

fix(lark): keep CLI lock directory writable in sandboxes (#4701)

2026-08-10 11:01:14 +08:00

mcp

fix(mcp): reject credentials that cannot travel as HTTP header values (#5066)

2026-08-31 15:07:30 +08:00

models

docs: govern agent guidance size (#4799)

2026-08-13 21:49:04 +08:00

persistence

feat(auth): add personal access tokens for programmatic API access (#5041)

2026-08-29 23:50:45 +08:00

reflection

docs: govern agent guidance size (#4799)

2026-08-13 21:49:04 +08:00

runtime

feat(streaming): make heartbeat interval configurable (#5017)

2026-08-30 10:46:01 +08:00

sandbox

fix: enforce custom agent skill allowlists in sandboxes (#5077)

2026-08-31 14:35:08 +08:00

scheduler

fix(scheduler): normalize once-schedule next_run_at to UTC (#4607)

2026-07-31 17:27:51 +08:00

skills

fix: enforce custom agent skill allowlists in sandboxes (#5077)

2026-08-31 14:35:08 +08:00

subagents

fix(subagents): clean up background task entry on unexpected poller exit (#5069)

2026-08-31 23:38:12 +08:00

tools

fix(subagents): clean up background task entry on unexpected poller exit (#5069)

2026-08-31 23:38:12 +08:00

tracing

docs: govern agent guidance size (#4799)

2026-08-13 21:49:04 +08:00

tui

fix(tui): preserve transcript scroll position (#4975)

2026-08-25 20:15:08 +08:00

uploads

fix(uploads): keep deduplicated filenames within the 255-byte limit (#5059)

2026-08-28 09:16:51 +08:00

utils

fix(gateway):unify thread id validation (#4589)

2026-08-01 19:42:44 +08:00

workspace_changes

fix(mcp): exclude internal temp files from workspace changes (#4898)

2026-08-20 08:57:10 +08:00

__init__.py

refactor: split backend into harness (deerflow.*) and app (app.*) (#1131)

2026-03-14 22:55:52 +08:00

AGENTS.md

fix: enforce custom agent skill allowlists in sandboxes (#5077)

2026-08-31 14:35:08 +08:00

checkpoint_patches.py

fix(checkpoint): unwrap Overwrite first writes into empty channels (#4383)

2026-07-26 10:44:50 +08:00

client.py

feat(subagents): add unified capacity and durable batch execution (#4998)

2026-08-25 07:49:38 +08:00

constants.py

fix(mcp): exclude internal temp files from workspace changes (#4898)

2026-08-20 08:57:10 +08:00

logging_config.py

feat(observability): add trace-id correlation and enhanced logging (#3902)

2026-07-03 08:01:46 +08:00

trace_context.py

fix(gateway): prefer X-Trace-Id over metadata.deerflow_trace_id when header is set (#4283)

2026-07-19 09:13:51 +08:00