WeKnora/internal/agent
lyingbug c40b33ecc3
fix(agent): admit catalog operations only from knowledge API areas (#4317)
The operation catalog refused routes under a list of forbidden prefixes,
matched as "<prefix>" or "<prefix>/". Areas whose names only extend a
listed one passed: /sandbox-configs, /storage-backends,
/web-search-providers and /im-channels. Areas nobody listed passed too,
including /agent/tool-approvals and /agent/prompts, where an annotated
operation would let the assistant answer its own approval prompts.
Nothing reachable is annotated today, so this closes the gap before an
annotation can open it.

The check is now an allow-list of first path segments (knowledge bases,
knowledge, Wiki, chunks, FAQ). Anything else, including APIs added
later, is refused until listed on purpose. Inside those areas, "shares"
is refused: who can reach a knowledge base is the user's decision.
2026-10-15 14:20:27 +08:00
..
approval feat(agent): add the built-in WeKnora assistant with an operation catalog (#4302) 2026-10-15 12:18:30 +08:00
compaction fix(agent): 将空闲超时覆盖到模型流建立阶段 2026-10-10 20:40:58 +08:00
hitl feat(agent): persist human-in-the-loop prompts with a shared broker (#4250) 2026-10-14 20:37:28 +08:00
operations fix(agent): admit catalog operations only from knowledge API areas (#4317) 2026-10-15 14:20:27 +08:00
skills feat(lite): install and run skills on the host (#3661) 2026-09-24 21:30:34 +08:00
token refactor(models): rebuild vendor integration on protocol + catalog + vendor layers (#3470) 2026-09-20 21:28:23 +08:00
tools feat(agent): let the WeKnora assistant read the bundled documentation (#4303) 2026-10-15 13:06:58 +08:00
act.go feat(agent): persist human-in-the-loop prompts with a shared broker (#4250) 2026-10-14 20:37:28 +08:00
act_order_test.go fix(agent): recover tool panics instead of crashing the server 2026-09-25 18:22:14 +08:00
attachment_timeout_test.go feat(agent): read chat attachments on demand (#4203) 2026-10-13 14:37:17 +08:00
calibration.go feat(agent): size agent history by the window and calibrate token estimates (#3413) 2026-09-18 22:51:31 +08:00
calibration_test.go feat(agent): size agent history by the window and calibrate token estimates (#3413) 2026-09-18 22:51:31 +08:00
checkpoint.go feat(agent): size agent history by the window and calibrate token estimates (#3413) 2026-09-18 22:51:31 +08:00
complete_event_model_test.go feat(agent): name the turn's chat model on the completion event (#4252) 2026-10-13 23:07:32 +08:00
const.go fix(models): keep Retry-After on HTTPError and honour it in agent LLM retries 2026-09-29 01:22:15 +08:00
const_test.go fix(browser): support human handoffs and resume interrupted tasks 2026-09-11 23:56:13 +08:00
context_debug.go refactor(models): rebuild vendor integration on protocol + catalog + vendor layers (#3470) 2026-09-20 21:28:23 +08:00
engine.go feat(agent): add the built-in WeKnora assistant with an operation catalog (#4302) 2026-10-15 12:18:30 +08:00
engine_image_test.go feat(agent): read chat attachments on demand (#4203) 2026-10-13 14:37:17 +08:00
engine_memory_test.go feat(memory): add cross-session long-term memory 2026-08-13 18:00:02 +08:00
engine_test.go fix(llm): treat cut-off streams as broken and tighten LLM retries 2026-09-25 18:22:14 +08:00
finalize.go feat(agent): persist human-in-the-loop prompts with a shared broker (#4250) 2026-10-14 20:37:28 +08:00
grounding_prompt.go fix(agent): search bound knowledge bases before answering, and pass suggested-question origins (#3400) 2026-09-18 17:00:47 +08:00
grounding_prompt_test.go fix(agent): search bound knowledge bases before answering, and pass suggested-question origins (#3400) 2026-09-18 17:00:47 +08:00
knowledge_base_profile_prompt_test.go feat(knowledge): derive knowledge base descriptions from document profiles (#3370) 2026-09-17 22:21:55 +08:00
langfuse_test.go refactor(agent): introduce modelcontext registry and fix handle-codec bugs 2026-07-27 11:05:43 +08:00
length_truncation_test.go fix(agent): end the turn when the completion cap truncates an answer (#3449) 2026-09-20 13:17:50 +08:00
mcp_exposure_test.go fix(mcp): normalize JSON-encoded argument envelopes 2026-09-09 16:11:52 +08:00
mcp_proxy_test.go fix(mcp): normalize JSON-encoded argument envelopes 2026-09-09 16:11:52 +08:00
observe.go feat(agent): add the built-in WeKnora assistant with an operation catalog (#4302) 2026-10-15 12:18:30 +08:00
observe_test.go feat(agent): add the built-in WeKnora assistant with an operation catalog (#4302) 2026-10-15 12:18:30 +08:00
prompt_composition_test.go feat(agent): add the built-in WeKnora assistant with an operation catalog (#4302) 2026-10-15 12:18:30 +08:00
prompts.go feat(agent): add the built-in WeKnora assistant with an operation catalog (#4302) 2026-10-15 12:18:30 +08:00
prompts_browser.go fix(browser): align BrowserSkill 0.3.0 and repair task lifecycle 2026-09-17 11:54:12 +08:00
prompts_browser_test.go feat(browser): polish connection settings, open tasks in a new window, and streamline prompts (#3193) 2026-09-11 21:28:58 +08:00
prompts_shell_test.go feat(sandbox): run unpinned Lite sessions on the host OS sandbox (#3549) 2026-09-22 19:35:03 +08:00
prompts_wiki.go fix(wiki): 整页重写被补全预算截断时续写,续写用尽则拒绝写回(长名单 146→119) (#3582) 2026-09-23 12:17:07 +08:00
prompts_wiki_test.go refactor(agent): introduce modelcontext registry and fix handle-codec bugs 2026-07-27 11:05:43 +08:00
resume.go feat(agent): persist human-in-the-loop prompts with a shared broker (#4250) 2026-10-14 20:37:28 +08:00
resume_mcp_test.go feat(agent): persist human-in-the-loop prompts with a shared broker (#4250) 2026-10-14 20:37:28 +08:00
resume_test.go feat(agent): persist human-in-the-loop prompts with a shared broker (#4250) 2026-10-14 20:37:28 +08:00
retry_delay_test.go fix(models): keep Retry-After on HTTPError and honour it in agent LLM retries 2026-09-29 01:22:15 +08:00
steer.go feat(agent): persist human-in-the-loop prompts with a shared broker (#4250) 2026-10-14 20:37:28 +08:00
steer_order_test.go fix(agent): preserve steering order across persistence failures (#4078) 2026-10-10 20:32:20 +08:00
steer_test.go fix(chat): preserve steering continuity and composer focus 2026-09-09 20:15:23 +08:00
stream_start_timeout_test.go fix(agent): 将空闲超时覆盖到模型流建立阶段 2026-10-10 20:40:58 +08:00
suspend.go feat(agent): persist human-in-the-loop prompts with a shared broker (#4250) 2026-10-14 20:37:28 +08:00
suspend_test.go feat(agent): persist human-in-the-loop prompts with a shared broker (#4250) 2026-10-14 20:37:28 +08:00
terminal_event_test.go fix(agent): stop emitting terminal answer events for retryable empty stops 2026-09-14 21:02:15 +08:00
think.go fix(agent): 将空闲超时覆盖到模型流建立阶段 2026-10-10 20:40:58 +08:00
tool_goroutine_panic_test.go fix(agent): 工具自起 goroutine 的 panic 自行兜底,MCP 预热不再带走进程 (#3846) 2026-10-08 01:24:36 +08:00
tool_images.go fix(agent): clarify attachment image paths and chart readings (#4283) 2026-10-14 14:23:28 +08:00
tool_images_test.go fix(agent): clarify attachment image paths and chart readings (#4283) 2026-10-14 14:23:28 +08:00
turn_usage_test.go feat(agent): size agent history by the window and calibrate token estimates (#3413) 2026-09-18 22:51:31 +08:00