Move the IMAGE_OFFLOAD_REQUIRED recovery out of llm-retry into the new
@deepseek-ai/dsh-compaction-image-offload package, a sibling of the
tool-result pruner: image offload is compaction in another capacity
dimension. Each replaced node is priced through the seam's compaction/prune
shadow-price protocol before its marked copy lands. llm-retry returns to
master; the base bundle mounts the executor.
Remove the llm-image-offload package and every registration it needed. The
recovery branch lives in dsh-llm-retry, which already sits on the
agent/request-error waterfall: an IMAGE_OFFLOAD_REQUIRED failure advances the
image/offload watermark by the count the adapter names and retries the step
outside the provider retry budget. Drop pre-dispatch planning with it: routes
no longer declare a request-image budget on their model info, and the byte
checks that stay in the DeepSeek and pi-ai adapters are provisional until the
provider reports uncacheable images itself.
Keep the agent loop unchanged: the new @deepseek-ai/dsh-llm-image-offload
plugin plans the image/offload watermark on agent/pre-step from the routed
model's budget and advances it on agent/request-error when an adapter fails
with IMAGE_OFFLOAD_REQUIRED, returning the retry action the loop already
honours. Drop PreparedLlmCall.imageRequest and its validation, the planner
wrapper, the replay adapter's imageRequestMaxBytes option, and the duplicate
ACP snapshot scenario; share the exact-byte overflow count between the
DeepSeek and pi-ai adapters through requiredImageOffload(). The SDK image
snapshot replays an authored IMAGE_OFFLOAD_REQUIRED attempt instead of a
replay-only budget.
Record sdk-minimal as the narrow repository-owned exception to base-first profile composition: callers still launch only dsh and cannot provide an arbitrary Cordis tree, while the shipped bundle may own a complete explicit roster. Cross-link the launcher, profile-bundle, Python-runtime, minimal-agent, snapshot, and telemetry decisions; the supersession audit keeps each older note active because its remaining rationale is independent.
Update the CLI, architecture, Python tutorial/reference, example, runtime-wheel reference, and bundle documentation. The docs distinguish the full sdk profile from sdk-minimal, explain explicit-home/plugin/patch customization, state the minimal permission and persistence choices, and retain the separately packaged web profile and frontend assets for direct dsh use.
Correct dsh-base descriptions to cover base-backed profiles, make SDK startup configuration visible in the generated config catalog, add sdk-minimal to the module graph, and regenerate the base-composition graph. English and Chinese pairs are re-recorded at the exact reviewed contents.
Move the shared module-reload policy into dsh-base by inserting its HMR row disabled, then remove the redundant disabled overrides from Web, headless, SDK, and ACP. No shipped profile enables server module reload; live profile patch watching continues through the launcher-owned config-only fallback, and browser client HMR remains a separate mechanism.
A later profile layer can opt into source-module reload explicitly with disabled: false while retaining the base root configuration. Composition tests cover every shipped mode and the explicit enable path, and the bundle references plus launcher Agent Notes document the resulting ownership and safety rationale.
The storage hub, json backend, and domain form are general infrastructure,
and the projection cache is a session-layer service that depends on them —
both belong in the shared base, not in the web overlay. Base now provides
storage / storage-json / storage-domain / session-projection-cache; the
web-app overlay keeps its surface consumers (workspace, message-feedback),
which inherit storageDomain from base (a child layer sees parent services).
This reverts the storage stack's historical web-app-only placement and the
file-root design's base mount of the cache.
The cache now opens its domain through ctx.storageDomain, which the
web-app overlay provides (storage-json + storage-domain, backend json).
A parent layer cannot see a child layer's services, so the base-layer
mount from the file-root design is reverted: the cache mount moves back
to web-app next to its storage dependencies, and Config.root is gone.
The cache now owns its storage root (dshHomePath('projections')), so the
mount moves from the web-app overlay to base with that root declared, next
to the other base session layers. web-app inherits it; its overlay mount is
removed.
The Codex and Claude Code subagent providers were production dependencies of
@deepseek-ai/dsh-base and mounted by its Cordis composition, so every install of
the base bundle carried two providers that only some products want.
Drop both from the base bundle's dependencies and composition. The examples keep
them as explicit dependencies, base's tests lock their absence, and the product
preset e2e mounts the providers it needs explicitly.
Cherry-picked from #2387 (two commits squashed into one).
The shipped bundles keep ctx.sessionQuery mounted but set the new
session-query-sqlite `openAt: never` phase: searchSessions/searchEvents
fail with the typed SESSION_QUERY_SEARCH_DISABLED code before any request
normalization, node:sqlite is never imported or opened, and no source
observation or reconciliation runs. Every inherited exact read, filter,
and trace — session export descendants, subagent-fork Workspace
inheritance, title reads — keeps working, and the Web sidebar search
degrades to its designed local title/workspace matching. Enabling content
search is a one-line openAt override in a later patch layer; the web e2e
scaffold keeps it enabled as the assembled opt-in coverage.
Resolve three conflicts:
- packages/bundle/base/tests/base.spec.ts: keep both assertion sets — this
branch's telemetry-otel mode expression and master's subagent rows plus
manifest dependencies.
- packages/session/session-telemetry-otel/tests/otel.spec.ts: keep master's
per-mode sharing disclosure test, but select FULL explicitly instead of
relying on an omitted mode, because the default is now DISABLED; the
default-construction test keeps asserting disabled delivery and gains a
case pinning that an omitted mode reports 'disabled' sharing.
- scripts/snapshots/translation-prompt-v4/request-response.expected.json:
re-recorded from the merged READMEs rather than hand-merging the embedded
document text.
Tianyi Cui