Add @deepseek-ai/dsh-agent-model. It provides ctx.agentModel
(resolveForNextStep, select, applyConfiguredRoute) and owns the
modelSelection projection, which the Agent registry no longer registers.
dsh-agent-loop now injects agentModel; the base and SDK-minimal bundles
and the Python SDK runtime include it.
The provider keeps the projection registered until consumers that are
still unloading finish their cleanup. The model-switch notice becomes an
opt-in per-Agent plugin at @deepseek-ai/dsh-agent-model/notice, and
agent/request now also rejects reasoning-effort changes after step
preparation.
Mount the provider in every composition that loads dsh-agent-loop, and
update consumers, the switch-notice snapshot driver, docs, and the
upgrade guide.
Delete @deepseek-ai/dsh-invariants, every package's ./invariant companion
and its tests, the invariant gates and Vitest setup, the scoped-event
resolver generator, and the INVARIANT-coded listener rethrow paths.
Update docs, READMEs, Agent Notes, and add an upgrade guide.
Log tool changes as developer messages independently of model capability,
fold committed headers and updates into Session.toolHistory(), and let the
LLM runtime construct deferred and retained declarations for routes that
declare a toolUpdate mode. DeepSeek serializes updates as system-role
tool_addition/tool_removal blocks with defer_loading and the tool-changes
beta header. An unchanged restored tool continues the series and is
re-offered through its recorded blocks instead of rewriting declarations.
Replace the obsolete rejection tests with wire assertions and add coverage
for the session fold, loop emission, route projection, config validation,
and the beta header. Chat and Trajectory changes land separately.
* feat(i18n): key translation pairing records by heading section
Replace the whole-file blob hashes in *.i18n.yaml with one entry per
heading section that still holds language-specific content, keyed by the
English heading-slug path. Blocks identical across the pair (generated
table rows, code blocks, shared regions) stay out of the hash, so edits to
different sections and identical regenerations merge with Git's default
text merge, including on GitHub.
Remove the dsh-translation-pairing merge driver, its resolver command and
installer wiring; gen-translation-brief recovers last-confirmed text from
commit history. Migrate all active records, archive the superseded Agent
Note, and record the replayed conflict reduction in the new one.
* test(i18n): refresh translation prompt snapshot for the terminology note
* feat(i18n): exclude only code blocks and generated regions from pairing records
Replace byte-equality masking with an explicit rule: a record hash skips
fenced code blocks and BEGIN/END GENERATED regions, the two kinds of
content the pairing gate already requires to be identical on both sides.
Move generated data into regions written into both pages:
gen-config-catalog renders both languages and the record with per-package
regions labelled by code identifiers; gen-module-graph keeps its table in a
region; gen-doc-graphs splices the event matrix regions into the Chinese
page. Add a generic region splice beside the region grammar.
Review follow-up: nothing consumed the field. The reserve stays an input to
`resolveCompactSpec`, whose returned budgets already express its effect, so
`ResolvedCompactSpec` keeps its exported shape.
Note the name collision a consumer would have hit: `ResolvedTargetPolicy.maxTokens`
is the compaction *summarization* output cap (default 8192), not the routed
request's cap reserved from the same window.
Proactive pressure scaled `thresholdRatio` by the routed model's entire
context window, but a request also reserves output tokens the provider
charges to that same window — the LLM service deliberately never clamps
them (`packages/llm/llm/src/index.ts`).
With a 1,000,000-token window and the default 256,000-token request cap the
gate therefore sat at 800,000 while the provider refused any prompt above
792,576. Observed in a real session: three requests died at 792,850 /
797,639 / 793,352 message tokens ("maximum context length is 1048576 ...
you requested 1048850 tokens"), no pressure compaction ever fired, and the
overflow recovery that did run could not condense an ~800k-token history
into the 8192-token summary cap.
Scale both ratios by the message budget left after the reserve, sourced from
the effective request envelope's `maxTokens` and falling back to the
adapter's per-request output default. A reserve that leaves no message
budget reports a target-specific pressure configuration error, matching the
existing per-route warning policy rather than silently disabling proactive
compaction. The headless compaction e2e advertises a coherent capacity/cap
pair so its 8000-token message budget and 4000-token threshold are unchanged.
Related #1841
Give durable user context its producer-owned source kind instead of a generic plugin wrapper. The V3-to-V4 conversion preserves the frozen rename and collision rules, all own JSON metadata, event coordinates, and historical request-only kinds. Native catalog and JSONL admission retain source validation so unknown attribution can survive without its producer while malformed owned sources are refused.
Use an explicit user-only RequestUserInput for auxiliary LLM prompts that do not own durable message identity. Auto Review and compaction remove their request-only source registrations while retaining prompt content and freezing; provider serializers and projections keep the same wire data, assistant replay isolation, image ordering, and tool correlation. Session writes, Agent delivery, and recorded title requests continue to require identified durable messages.
Bind the saved compatibility policy only to user sources and qualify tmux location attribution without weakening fixed system, model, or tool semantics. Rebuild the current inventory and unpublished V4 acknowledgement on the actual tool-role parent, preserving its rationale and all accepted historical records. The catalog format version records tooling metadata; Session remains V4. Developer-role policy and activation belong to their own feature.
The latest-master Messages adapter, serialization, request-input typing, EpochHeader reservation, and attribution checks pass 103 tests across five files. The retained V3 Messages input-history snapshot passes through the source profile; Host/Client typechecks and all 41 documentation gates pass. The generated comparison records four changed roots and 447 unchanged type fingerprints. Latest-master ARIA changes are retained, with producer source labels applied independently; new Messages fixtures retain their producer names as declared source kinds and use the fixed system-message helper; recorded Session generations are unchanged by this regrouping.
Co-authored-by: Tianyi Cui <[email protected]>
Represent tool results as tool-role messages and migrate released wrappers
without losing outer own JSON fields, call identity, error state, or writer
field order. Refuse nested or wrapper-only information that has no lossless
current representation before successor publication.
Validate current event relationships directly instead of projecting V4 data
back into V3. Keep lifecycle, PTC, title/command, compaction, system-field and
retired-syntax checks on catalog restoration and ordinary JSONL opens. The
Worker JSON equality helper must inspect own keys so it cannot admit PTC
arguments that Node rejects.
Keep the source role change, required native admission and consumer fixture
updates in one complete review layer. Explain shared-type changes in the
persistence record and the native reader rationale in its existing note.
Use checked branded fixture identities and discriminant narrowing instead
of unknown double casts; fixture values and assertions remain intact.
This recomposes the original tool-role work by _Kerman with the independently
validated migration and admission repairs by Tianyi Cui. Frozen generations
and snapshot input version selection are retained.
Co-authored-by: Tianyi Cui <[email protected]>
Merge master 62b700bba7bb71e66d2d5a3b850ba8f4dd0fd6b4 into release/session-log-v4 at 4825bc01a999f564e79172a6af28e34fc757c540. Preserve this pinned integration checkpoint before any later upstream movement so the dependent session-format repairs have an immutable rebase base.
Keep release projection-backed child catalogs, independent Session references, exact fork behavior, V4 writer, and existing migration data. Adapt the incoming subagent sidebar chat to refreshProjections rather than the removed dedicated catalog API, preserve title projections in complete projection fixtures, and retain both sidebar actions and release lineage/status behavior. Remove the duplicate SessionProjectionMap import introduced by automatic merging.
Preserve both disjoint archive seals without changing any existing hash. Regenerate current Cordis and documentation catalogs from the combined source, retaining release session methods plus master slot factories. The frozen V0-V3 runtime paths are unchanged. Initial validation passed the full build, 93 focused Client tests, and all 1905 archived artifact seals; remaining integration and snapshot checks follow on this checkpoint.
imccyu