Models coordinate subagents through send_message, interrupt_agent, list_agents,
and Team task owners, but every one of those addressed a member by a
36-character Session id. Each new child now has a name, unique among its
creator's children, recorded as a field of the subagent/catalog entry the
creator already appends (payload version 3).
The Session id stays the only execution identity for routing, authorization,
persistence, task ownership, and navigation. A name is a model-facing
reference: 1-32 lower-case letters, digits, or hyphens starting with a letter,
never `lead`, so a UUID never parses as one. Omission selects the first free
`agent-N`; an explicit duplicate or invalid name fails before startup. The
creator reserves the name synchronously at admission and releases it when the
catalog entry commits or startup fails, so no second write, rollback protocol,
or optional naming service exists.
The root is `lead`, and a descendant's full name is its path from the root
without a `lead/` prefix, such as `reviewer/checker`. Sibling-unique segments
make full names tree-unique without a root registry, and cold resume rebuilds
a member's path from the catalogs along its creation chain. A member below an
unnamed historical creator keeps its Session id as its name. resolveName()
reads only the catalogs along the path and grants no authority.
Tools, runtime-authored text, and the Web client consume names: delegation
takes an optional name and returns { kind, subagentId, name }; send_message and
interrupt_agent take `agent`; list_agents rows carry name, status, and
description; Team task results report the owner's name while storage keeps
ownerId; identity runtime context, message framing, and settlement notices use
full names. Recorded sessions, CLI and Web expectations, the Python runtime
snapshots, bilingual docs, an upgrade guide, and an Agent Note follow.
A new Agent Note owns the shipped defaults and the original apply_patch note
keeps its opt-in decision with a supersession link; the policy README, the
tool-catalog note, the filesystem page, and the fs group README state the
current defaults without evaluation figures. The PTC overlay sets
`applyPatch: false` so the SDK and Desktop PTC tool sets match without a
parity exception; the fixed-budget compaction scenarios pin the tool set in
their live patches too; the apply-patch composition drops its no-op override.
The upgrade guide scopes the change to base-backed profiles, the README
refusal example is one every composition can produce, the integration suite
names its deployments by guard, and the keyless SDK smoke edits a file the
model never read through the shipped profile.
Takes master's re-recorded plan-review, creation-recommendations, and
plugin-recommendations scenarios from the base and refreshes their headers
and schema sidecar for the enabled apply_patch tool.
Evaluation on the shipped compositions decided the defaults: the `dsh-base`
`tool-fs` row and the Web `standard` preset enable apply_patch, keeping the
SDK and Desktop `standard` tool sets equal (the SDK PTC overlay keeps the
base row while the Desktop PTC preset lists its own, which the parity
exceptions record); the `fs-observation-policy` row ships `disabled: true`,
so write, edit, and apply_patch mutate unconditionally in every profile, and
the package is classified as an optional product package.
The write and edit guidance stops citing the policy as the default and the
apply_patch guidance asks for enough hunk context instead of a prior read.
The two recordings that capture a policy refusal re-enable the row through a
per-scenario runtime.cordis.yml; the fixed-budget compaction scenarios pin
`applyPatch: false` so their recorded thresholds hold; every other sidecar
and recorded header follows. An upgrade guide records the default change.
This pull request lands the tool; switching the shipped defaults is a
separate pull request stacked on it. Every shipped `tool-fs` row states
`applyPatch: false`, the `fs-observation-policy` row stays mounted, the
write, edit, and apply_patch guidance names the policy, and every recorded
expectation outside the apply-patch scenarios returns to the master
baseline. The upgrade guide, the parity exception, and the optional
classification of the policy package move to the stacked change.
The SDK/Desktop parity check requires the `standard` tool sets to match, so
the base row enables apply_patch like the Web standard preset; the SDK PTC
overlay keeps that row while the Desktop PTC preset lists its own, which the
parity exceptions now record. fs-observation-policy, no longer mounted by
default, is classified as an optional product package.
Every headless, SDK, and ACP recording follows: sidecars and recorded headers
gain the apply_patch schema, the fixed-budget compaction scenarios pin
`applyPatch: false` so their recorded thresholds hold (model-switch-notice and
session-resume own their schema sidecars again), the parent presets that
borrow the default pin mirror the base row, and the pwsh and Python PTC pins
carry the schema and guidance.
The MCP SDK answers resources/list and resources/templates/list for a
server without the resources capability with an empty page, but first
writes a console.debug line to stdout. Under the ACP profile that line
lands in the JSON-RPC stream whenever the model lists resources of a
client-supplied, tools-only MCP server. Return the same empty pages
before calling the SDK, and cover it with a unit assertion and an ACP
stdout regression test.
Replace the literal "Approval policy: ask." runtime-context sentence
with a statement parallel to the never-policy sentence, and refresh the
current-generation fixtures that persist it.
Co-authored-by: Tianyi Cui <[email protected]>
* fix(ui): separate navigation pins from selection and show menu icons
* fix(ui): simplify More menus and fold conversation views on resize
* test(ui): fix navigation CI regressions and refresh catalogs
* refactor(ui): render sidebar panel icons directly
* fix(ui): keep Chat visible and stop persisting navigation pins
* refactor(ui): drop unreachable pin validation from in-memory stores
The DeepSeek search and Search/Fetch API providers now report readiness
from credential presence alone, on any model route: the account token
first on the deepseek-account route, then a literal apiKey or a
configured apiKeyEnv reference. A conversation on another provider's
model keeps web_search and web_fetch while a DeepSeek key is configured,
as on master, so the route refusal WEB_PROVIDER_ROUTE_DISABLED and its
upgrade guide are removed.
The pi-ai-conversation-updates and deepseek-messages-system-prompt
snapshots replay their master recordings again, the headless keyless
smoke points its search key reference at an unset variable, and the
readiness Agent Note records the rejected route and endpoint rules.
Review found two faults in the endpoint and configuration checks. The
providers took the official chat route's endpoint from the first active
dsh-llm-deepseek-api-key Loader row, so a composition that isolates several
instances answered for an unrelated one: a correct route lost search, or a
gateway's key reached DeepSeek. And a key saved on the Web search settings
page lands under the default DEEPSEEK_API_KEY reference, so the inference
that search had its own configuration never saw it.
Both DeepSeek web packages now serve only the deepseek-account and
deepseek-official routes, whatever key they are configured with, and no
longer compare the chat endpoint with their own. ready() checks the route
and then credential presence as before; the API-key resolver repeats the
route check and refuses with WEB_PROVIDER_ROUTE_DISABLED. The packages no
longer read Loader rows or depend on dsh-llm-deepseek-api-key, so the
lockfile, the module graph, and the keyless smoke expectations that the
endpoint check had changed return to master's.
An upgrade guide covers conversations on other providers' models, which
lose DeepSeek web search and, with the Search and Fetch APIs selected,
web_fetch.
* ci: run native Windows PR jobs in a separate workflow
GitHub re-runs failed jobs only after a whole run finishes, so slow Windows jobs blocked re-running failed Linux jobs. CI Windows now owns the native Windows jobs and the Windows x64 Python runtime target, with its own required 'windows checks passed' verdict.
Refs #6893
* ci: run Python PR jobs in a separate workflow
Python rarely fails while the Windows lanes run long, so the Python SDK suite and the Linux/Windows x64 runtime matrix move into CI Python. The three pull-request workflows can now be re-run without waiting for each other, and branch protection gains "python checks passed" beside the existing verdicts.
Refs #6893
* docs: record the three PR verdicts in the failover runbook
* test: pin the shared environment across the PR workflows
* test: read the python SDK lane from CI Python
* test(sdk): parse session JSONL frames in the keyless smoke
Node 24.19 returned only the first frame of a concatenated zstd log, so the single JSON.parse saw just the header; 24.22 returns every frame and the JSONL body broke the parse. Read frames explicitly and select the main session by its header so both versions agree.
Dudu-0223