Sessions resume across runs (ADR-0017). Without auto-compact the SDK jsonl
grows unboundedly — a 7-day / 26-run session hit 31 MB / 1995 lines, making
every API call resend the full history and inflating a trivial "change a
title" task to 22 minutes. Enable autoCompactEnabled in the SDK settings so
the SDK compacts automatically when the context window fills.
If StreamingAgentCard.finish cannot patch the live card, plain-text fallback
can still succeed with partial answer text. Interrupt is terminal — always
emit the explicit 已中断 notice when the card path failed so teachers see the
abort. Harden the integration assertion with waitFor.
Explorer POST /projects was dropping projectId/folderId/workspaceDir after a
narrowed response shape, breaking admin-explorer. Make seedTestOrganization
idempotent under shared-DB isolation, force single-worker vitest, and align the
OAuth no-membership redirect expectation with authRoutes.
Fail fast if TRUNCATE left Organization rows, drop the extra deleteMany
before seed create, and force vitest maxWorkers=1 so forks cannot race
the shared Postgres.
seedTestOrganization now wipes+creates instead of fragile upsert.
hub-check drops pull_request triggers so push/PR pairs no longer double
migrate against the runner; branch push status remains the gate.
deleteMany could not reliably clear nested agent-config folders and left
ghost Organization rows that broke the next upsert. Truncate every public
table except _prisma_migrations before seeding the default org.
Admin routes always construct OrganizationAgentConfiguration via
readSkillStoreRoot(); CI and local runs without HUB_SKILL_STORE_ROOT
failed open. Seed a tmp root when unset. Also make preflight CLI tests
honor DATABASE_URL and set the skill-store env in hub-check.
CI hub-check reaches Postgres as the service hostname `postgres`, but
helpers hard-coded 127.0.0.1:5432, so migrate ran against the service
while vitest connected to the wrong place. Prefer env when set.
Claude SDK may report an extra host/doctor skill id even with
disableBundledSkills. Keep the ADR-0018 guarantee: managed outline
loads and workspace-local untrusted skills do not.
Rebased feat/agent-config-folder-tree onto current main, keeping cursor
invalidation (not session archive) and requireFolder helpers. Regenerated
package-lock so npm ci finds @emnapi/*; tighten session-cursor test assert
for missing claudeSessionId key.
Add a shared transparent OrganizationAgentConfigFolder tree for grouping
agent roles and skills in the admin UI without affecting identity, bindings,
run loading, or slash commands.
Agent tool downloads and trigger attachment staging both used the SDK
messageResource path, which fails closed for multi-MB teacher files and
did not share the bot-identity transport contract. Route every download
through Hub-owned createFeishuBotCli (secret via stdin, disposable HOME,
HUB_FEISHU_CLI_BIN), keep workspace containment on write, and inject the
adapter in trigger tests.
SubmitDocParserJobAdvance uploads PDFs to Aliyun OSS via tea/httpx, which
defaults readTimeout to 3000ms when RuntimeOptions is empty. Multi-MB
teacher PDFs on para silo failed with ReadTimeout(3000) before the job
could start. Set connectTimeout=15s and readTimeout=5m.
createReadStream emits async ENOENT without a listener, which became an
unhandled 'error' event and exited the silo process. Teachers then saw the
startup "process restart" notice. Wait for stream open and convert missing
files into DocmindClientError instead.
The claude_code preset exposed Agent/SendMessage/Task. Background agents
abort with reason "background", which the SDK maps to Bash
toolDenialKind "cancelled" ("user doesn't want this action") and freezes
command execution mid-run.
Headless Claud agents expose TaskCreate/TaskUpdate rather than TodoWrite.
Fold those tool events into the live card checklist, pass real tool names
and inputs through tool-result, and hide Task* noise once the panel is up.
Native Claude TodoWrite is not registered in headless agent mode even with
--tools default. Add mcp__cph_hub__todo_write (always enabled), mirror the
TodoWrite schema, instruct multi-step runs to use it, and keep the Feishu
progress panel parsing both native and hub tool names.
Unrestricted roles were still passed an explicit --tools name list. The
native Claude binary only reliably registers bundled tools like TodoWrite
on --tools default. Treat role tools JSON null as unrestricted, use the
claude_code preset (→ default) in that case, and keep TodoWrite on allowedTools.
Always expose Claude Agent SDK TodoWrite (todoFeatureEnabled) so multi-step
runs can plan in the open. Parse TodoWrite payloads into a progress panel on
the streaming Feishu card (completed/in_progress/pending) and filter raw
TodoWrite noise out of the tool-use list.
pbank materialize previously shelled out to `unzip` and soft-failed when
the binary was missing, so agents only saw titles. Read zip entries with
Node zlib (store/deflate) and write under workspace .pbank-sources.
Register pbank as an ADR-0027 external capability with org-scoped
username/password envelopes, readiness via /login, and in-process
cph_hub MCP tools (search/get/get_many) that materialize sources under
the run workspace. Extend the capability secret payload for docmind vs
pbank kinds, admin capabilities UI, role tool umbrella `pbank`, and the
pbank-problem-report skill. Credentials never reach the Agent process.
After removing the Typing reaction, add CheckMark on success or CrossMark
on failure so teachers can see completion on the source message without
opening the card.
Teachers convert many PDFs in one tool call with bounded Docmind concurrency.
Each item keeps its own output_dir/document.md and UsageFact; failures are
per-file. Mirror role skills to .cph/runtime-skills and CPH_RUNTIME_SKILLS_DIR
so agents can Read SKILL.md instead of dead .claude/sandbox stubs.
Host egress requires the local forward proxy; sandbox env previously
omitted PROXY vars so Bash/curl timed out on public image URLs. Pass
HTTP(S)/ALL/NO_PROXY (+ lowercase) and NODE_USE_ENV_PROXY from the
trusted service environment into the agent subprocess.
Defaults and silo env go to 150 turns / 1800s wall clock. Run completion
appends a clear Feishu notice for max-turns, timeout, and other failures
(partial answer kept). Startup process-restart kills notify the bound chat.
Release v0.0.38.
Feishu interactive markdown rejects  without image_key
(error 230099 empty/missing imagekey). Always mask residual image md in
card builders; skip img tags with empty keys; skip inline-code examples;
fetch remote images with a browser UA and without env HTTP_PROXY.
Steer the agent: use  for 图文, send_file only for
downloadable attachments.
Release v0.0.37.
Alpha silo bootstrap created the root Inbox without kind=SYSTEM_INBOX, so
Feishu card project creation tried to insert a second Inbox and hit the
sibling-name unique index. Tag the bootstrap folder correctly and promote
any legacy root Inbox on ensure.
白
hongjr03
ChickenPige0n