The mount-local baseline guard was seeded from "a baseline already exists in
the log", which a resumed session and a hot plugin remount both satisfy. That
made a resume skip its baseline, so offline AGENTS.md edits or removals never
reached the first resumed request — violating the documented resume contract.
Distinguish the two by agent/session-start: a startup or resume emits it before
the first step, while a remount attaches to an already-live session and never
witnesses it. Only a remount (no witnessed start, baseline already logged)
keeps the single logged baseline and skips; a resume falls through and
re-composes from current files. Adds a regression that resumes a session with
an offline baseline edit and asserts the fresh baseline reflects it.
goal-session rides retry turns and survives admission failures. A
recovery policy closes a goal round's failed turn and reopens its
history under a retry trigger; the attempt now adopts that turn and
drops the failed turn's provisional reason, so the round settles from
the retry's own outcome instead of blocking an armed goal with
turn-error after a successful response. A downstream admission hook
that throws (rather than blocks) used to strand the queued reservation
forever; the listener now clears a still-turnless matching attempt on
the rejection path and reschedules the round.
agent-loop contains a persistently rejecting step close in the catch
path the same way the finally contains the turn close, so the
post-finally tail always publishes the terminal status — previously a
double veto escaped run(), leaving status at running while whenIdle()
resolved. The whenIdle catch arm is annotated as the backstop it now
is: every driver rejection path is contained today.
workspace-context folds an already-appended baseline from the session
log when the plugin is hot-remounted over a live session, instead of
injecting a duplicate from its fresh mount-local guard.
The TUI's reference-admission discard listener installs before
followup(): admission runs synchronously inside it on the common path,
so a listener installed afterwards missed its own cleanup and leaked
one callback per referenced prompt.
Downstream packages lost the tests that exercised their agent-loop-facing
edges when the loop was rewritten. Restore 100% per-file coverage with
behavior tests through public seams: llm-retry config validation and
cancellation races, goal replay drift/staleness/teardown edges, plan-mode
disposed-flush, workspace-context empty-change commits, api-proxy
synchronous send failures, acp-snapshot spill-path extraction and refresh
write-back, ACP injection-triggered turns, cli-demo and tui inbox
lifecycle edges, and agent-loop retry/settlement/lifecycle branches.
The only source changes are narrowly-justified v8 ignore annotations on
invariant guards and one redundant-guard removal (workspace-context).
Address the review bot's five genuinely-new findings on the current code:
- disposal now discards any still-pending inbox items before the loop
exits, so every enqueued id gets a terminal lifecycle event.
- injection (next-step/no-wakeup) validates its payload up front, before
opening the idle one-shot turn, honoring 'invalid input throws before
any append'; and rejects attached contexts (which belong only to inbox
messages) rather than silently dropping them.
- agentMessage() freezes the agent/inbox/* payload so a listener cannot
mutate the shared correlation object mid-dispatch.
- refresh the package READMEs (compact, goal, guard, hook-protocol,
plan-mode, time-context, workspace-context) that still referenced the
removed context/message event, with the source-based user/message
distinction.
The up-front injection validation makes two finally branches unreachable
(v8-ignored as the turn-enclosure backstop). Adds regression tests for
disposal discard, context rejection, up-front validation, and the frozen
payload; per-file coverage stays 100%.
Add a branded AgentMessageId assigned to each accepted send message and
returned from send/followup/steer/inject (was void). Rename the inbox
event payload InboxItemInfo to AgentMessage, carrying that id so a caller
can correlate a queued item with its enqueue/dequeue/discard events.
Replace send/steer/inject with one Agent.send primitive over the
(target × wakeup) matrix; followup/steer/inject become fixed-preset
alias methods on the now-abstract Agent class. Coalesce context/message
into user/message (injected context is a non-user source). Replace
agent/queued with agent/inbox/enqueue/dequeue/discard, add cancel
keepInbox, and add a FIFO-conservation invariant.
- workspace-context: a transiently unavailable but still-effective candidate
keeps its cached trimmed digest in the directory's dedup slot, so an
identical later sibling is not emitted as a duplicate set until the next
successful reconciliation
- app-boot: --resume rejects a following token that is itself resume syntax
instead of accepting it as a session id
- tui: the queued-steering badge tracks per-entry sources and a drain removes
one matching entry, so loop-authored steering (no agent/queued) cannot
consume a pending user message's slot
Path expectations derive from join() per the cross-platform fixtures
convention; the fake fs resolves against the host root so drive-letter
targets match seeded keys; the unreadable-candidate cases use the provider
throwOnRead fixture (host chmod 0 is a no-op for the owner on Windows),
keeping the read-failure branch covered there, with a narrow win32 skip only
for the host-chmod discovery case.
The smoke's inline Python pty driver only ran on POSIX (no termios on
Windows). Rebuild every scenario — banner sweep, scripted conversation with
model switch, /skill:, Code Mode overlay, resume failure, and the dsh CLI
suite (default boot, personal overlay, invalid overlay, --resume flag,
source-path prompt) — as marker-gated action lists on pty-harness.ts, which
drives ConPTY via node-pty on Windows and the Python driver elsewhere. The
harness gains configArgs (bins with built-in default configs), prepare
(workspace seeding), and inspect (post-run log assertions); examples/
declares the session-title provider the shipped cordis.yml now mounts.
The acp escalation smoke advertises the shipped deepseek-v4-pro; the
workspace-context e2e asserts the per-candidate scope key. The PTY harness
drops COLORTERM (deterministic banner) and gains configArgs/prepare/inspect
for the dsh CLI scenarios.
workspace-context's abort-tool test uses agent.cancel({kind:'user'}) (master's
AgentCancelCause shape); tui-demo forwards no welcome when none is configured.
Load a per-directory local overlay in addition to the base instruction
file, matching the Claude Code AGENTS.local.md / CLAUDE.local.md
convention for git-ignored personal guidance.
- New config `localInstructionFileCandidates`, default
`['AGENTS.local.md', 'CLAUDE.local.md']`; empty disables the overlay.
The default lives in the plugin Config schema, so every front door
(TUI/ACP/headless) reads .local. files consistently.
- Per project directory the plugin loads the first-existing base
candidate, then additively the first-existing local candidate,
rendered after the base so it takes precedence within the byte budget.
- Base and local tiers get distinct scope keys via a NUL sentinel
(scopeKey/decodeScopeKey) so they never collide in the baseline map,
pending window, or version cache.
- The fixed user-global $DSH_HOME/AGENTS.md stays base-only.
Docs: README (config, lifecycle, Known Limitations), regenerated
config-catalog, and a new bilingual Agent Note cross-linked to the
owning workspace-context note. 100% per-file coverage retained.
Squash of the linearized fix/tui-color-scheme-v2 merge and the follow-up
catalog regeneration. Renders error cause chains at every diagnostic seam
(origin/fetch-failed-diagnostics) and adds color scheme detection with a
light-terminal palette.
Delete packages/ui/stdio and examples/repl-agent; rename stdio-demo to
@deepseek-ai/dsh-tui-demo (TUI-only, refuses pipes before Loader boot).
tui-agent owns the coding composition inline; echo-agent and the CI demo
smoke move to the one-shot cli-demo bin, which gains -p/--prompt. The
UI-independent with-key e2es move verbatim to tui-agent. SDK wizard's
'stdio' interface becomes 'tui'. PTY testing stays confined to TUI
surfaces; all other subprocess tests ride pipes.
See .agents/notes/implemented/simplification/2026-07-20-retire-readline-front-door.md
Delete @deepseek-ai/dsh-home and make dsh-paths the sole owner of the
single-root harness home ($DSH_HOME || ~/.dsh). Migrate tool-bash,
skill-local, and agent-spine-demo off dsh-home, and fold telemetry's
divergent globalConfigDir onto the shared resolver, dropping its second
XDG/APPDATA policy and the deepseek-harness namespace so the anonymous
id lives under the harness home. Add dshHomeDisplay() for symbolic
user-facing paths, replacing workspace-context's bespoke check.
The test 'labels the default DSH home as ~/.dsh when HOME points at the
configured default' mocks node:os to return a temporary home directory
and expects discoverBaselineInstructionFiles to fall back to the default
~/.dsh path. However, when DSH_HOME is externally set (e.g. in the DSH
agent environment), resolveDshHome(undefined) reads that external value
instead of falling back to defaultDshHome(), causing the test to look for
AGENTS.md in the wrong directory and return an empty result.
Stub DSH_HOME to undefined so the test controls the full resolution path.
_Kerman
Tianyi Cui
Turtle
Huanqi Cao