Commit Graph
41 Commits
Author SHA1 Message Date
Turtle 32905d5ab5 Revert "feat: reconcile timed questions with legacy default" 2026-09-24 20:06:09 +08:00
Magolorandimccyu bb19061473 feat(user-questions): support timed waits and late replies
Co-authored-by: imccyu <[email protected]>
2026-09-24 19:43:16 +08:00
Chinesezjc 7a362b263b Merge pull request #4335 from deepseek-harness/feat/schedule-storage-phase1
feat(schedule): persist tasks and resume due sessions
2026-09-23 23:33:33 +08:00
Turtle e7def469e1 feat(i18n): key translation pairing records by heading section (#5036)
* 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 Migrate all active records, archive the superseded Agent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.
2026-09-23 22:32:06 +08:00
Dudu-0223 a978ad1994 fix(subagent): version unknown catalog payloads locally 2026-09-20 15:09:37 +08:00
Dudu-0223 f984683956 fix(subagent): store unknown mode in the existing catalog event 2026-09-20 14:46:54 +08:00
Dudu-0223 17a52a8fe3 fix(subagent): retain unreadable children in migrated catalogs 2026-09-20 14:30:02 +08:00
Tianyi Cui b28fca7e87 docs(session): correct incomplete child evidence migration policy
The V4 acknowledgement still said missing child descriptors reject migration. The converter already skips backfill when a child has no single supported own descriptor, while explicit identity, timestamp, and mode conflicts still reject publication. Align both language versions with that behavior so release reviewers and corpus testers do not expect an obsolete refusal. Preserve every machine acknowledgement and schema fingerprint.
2026-09-19 18:51:32 +08:00
Tianyi Cui 0112eaf3a8 feat(session): finalize the accepted V4 compatibility baseline
The integrated V3-to-V4 records contain the header increase that authorizes
their breaking changes. Leaving those terminal records editable would let a
later change reuse that already accepted 3-to-4 increase, so version 4 would
not establish a stable compatibility baseline for persisted user data.

Capture the accepted root classifications and semantic record digests in a
separate finalization checkpoint. Validate that checkpoint before rendering
or writing acknowledgement artifacts, and preserve its accepted records even
after the current writer advances. Keep publication evidence independent:
the verified released version remains 3 until a release establishes otherwise.

Compare future writer-4 schemas with the accepted baseline using the existing
compatibility classifier. Compatible additions remain permitted through new
same-version acknowledgement records. Breaking changes require a higher
writer and their own header transition; comments, aliases and source-location
changes do not alter the accepted semantics. Later unaccepted compatible
records retain the existing update workflow.

Document the distinction between finalization, publication and compatible
evolution, with regression coverage for locked records, incomplete or
inconsistent checkpoints, additive changes and future-version transitions.
2026-09-18 23:40:56 +08:00
Yixiang TuandTianyi Cui e0bd7e1960 feat(session): add developer changes using historical tool schemas
Session V4 reserves developer-role messages for incremental model-visible
session changes. The role, tool addition/removal blocks, and deferred-loading
marker need a durable representation before independent provider and UI
integrations can emit or consume them. Known developer events must match an
open turn and step; unsupported providers and UI consumers fail explicitly.

Request headers already capture full tool definitions. Persisting another
ToolSchema in each addition would duplicate Session information and create
two definitions that could drift. Additions therefore store toolName, and
the containing developer event uses headerSeq to select one earlier known
request/header for all its additions. A same-name replacement keeps its
historical definition identity through restart, fork and surface changes.
Removals require no definition copy, and ordinary developer messages omit
headerSeq. Generic sourceEventSeqs remains independent derivation metadata.

The rejected inline tool field is optional never with @persistenceReserved.
The schema extractor retains that uninhabited slot, so permitting a future
value requires a format bump instead of being mistaken for compatible
optional metadata. Unrelated optional fields remain additive and readable.

Native and Session admission reject missing, forward, non-header, unknown,
ambiguous and incomplete referenced definitions, and reject the retired
inline tool field. Validate complete schema fields only for referenced
definitions, preserving unrelated header behavior and extra JSON metadata.
Unknown ignorable records remain opaque. Empty developer nodes retain their
surface position without producing a message or shadowing the system head.
No automatic emitter, provider activation, UI implementation, or speculative
public resolver is added.

Keep the core-owned developer source binding beside the introduced role,
including the request-only type rejection and attribution round trips. Update
consumer guards, SDK/snapshot handling, bilingual owner documentation, and
the same unreleased V4 acknowledgement. Keep earlier tool/source migration
work and its documentation in the parent. Preserve the existing recorded
Cordis inspection generation from the original developer change.

Integration keeps the final source layer as the sole parent and preserves
master's Messages input filtering, empty-user omission, empty tool results,
and system-update placement. Developer/deferred guards still run before
conversion. Native V4 admission, header references, reservation declarations,
and generic tooling match the validated marker candidate. Parent-owned
fixture and generator fixes remain in the parent.

Earlier feature validation passed full build, full lint, 41 doc-sync gates,
and 16 hygiene gates. The unchanged native implementation retains that evidence.
The focused Session/V4/request-input run passes 884 tests across 38 files with
100% statement, branch, function and line coverage for the V3-to-V4 package
and Session surface. Consumer tests pass 482 with one existing skip; tool,
message and optional-field tests pass 146. Cordis inspection and compaction
replays pass in both source and built modes (two cases per mode). Ten invalid
referenced-definition/unknown-header controls failed before their scoped
guards and pass after them.

Reservation validation: the actual generated developer root records tool as
optional primitive never. Widening it requires a bump, while traceId remains
additive and preserved; all 85 focused reader/classifier tests pass.

Final-parent validation: 205 tests across eight provider, type, catalog,
Session and native-format files pass. The preserved parent fixture verifies
Messages input-history replay; runtime/declaration and parent-owned-file
comparisons show no loss during the final rebase.

Co-authored-by: Tianyi Cui <[email protected]>
2026-09-18 19:08:11 +08:00
Tianyi Cui b88afa8a72 fix(ptc): name persisted producer attribution ptc-mode
The producer-source refactor introduced the unreleased V4 discriminator
code-mode even though this source identifies images deferred from successful
PTC subcalls. Name it ptc-mode before V4 ships so persisted attribution
matches the producer and does not freeze obsolete terminology into new logs.

Keep the live writer, V3-to-V4 migration output, collision guard, and reserved
producer policy aligned. Both released tools-code-mode and tools-ptc plugin
lookup keys map to ptc-mode. Preserve those historical keys, opaque message
text and IDs, all frozen V0-to-V3 generations, and recorded Session inputs.

Update the owning tests, producer documentation, current catalog, and V4
acknowledgement. The canonical schema audit identifies exactly three changed
roots; reversing only the source literal restores each prior digest. The
large generated JSON diff comes from graph ordering, with 61 roots and 572
types retained.

Validation: the seven-file focused run passed 298 tests and exposed four
stale current-output expectations in two migration files. After correcting
those expectations, both files passed all 23 tests. All 41 documentation
gates and full lint passed; frozen generations and recorded inputs are
unchanged.
2026-09-18 19:07:12 +08:00
_KermanandTianyi Cui fb79a944f5 refactor(llm): separate durable producer sources from request inputs
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]>
2026-09-18 19:07:12 +08:00
Tianyi Cui 29f7e7bdf5 fix(session): reserve retired system text in request-header schemas
Native V4 admission and Session adoption reject every request/header.header.system field because system prompts belong to system/message events. EpochHeader omitted that key, so the generated schema classified adding optional system text as a same-version optional-property addition even though released readers would reject it.

Declare system?: never with the shared persistenceReserved marker so the schema records the existing prohibition. Widening the field to string now changes a forbidden value set and requires a version bump. Keep both runtime guards and all unknown-metadata handling unchanged, and document the reservation alongside the current header type and V4 acknowledgement.

The regression extracts the actual event:request/header schema, checks the optional-never field, widens only that property, and verifies the version-bump diagnostic and native refusal. It fails without marker extraction and passes with the shared tooling support. The focused reservation, retired-syntax, and Session surface suites pass 65 tests; all 436 type-equiv blocks match their source. Generic marker extraction belongs to the foundational tooling change.
2026-09-18 19:05:33 +08:00
_KermanandTianyi Cui f4a32dbd0a refactor(llm): flatten tool results and validate native V4 sessions
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]>
2026-09-18 19:05:32 +08:00
Tianyi Cui c6e62ff971 fix(persistence): retain explicitly forbidden JSON fields
A reader can reject a property name while its type declares that property
as optional never. Dropping it from the extracted schema makes a future
optional JSON value look additive, although the existing reader refuses it.
The type history must retain that explicit prohibition.

Support the argument-free @persistenceReserved marker only on optional
properties whose values are never or undefined. Keep those properties as
optional primitive-never nodes, so later JSON values change an existing
field and require a version bump. Reject invalid placement, arguments,
repeated tags, required or JSON-valued declarations, and mapped uses that
violate the reservation. Keep every unmarked omission rule unchanged.

The classification regression failed before this change with an additive
optional-property result and now requires a type-change bump. All fifteen
focused reservation cases and all 210 tooling tests pass, including inherited
fields, misuse, and unmarked preservation. Host typecheck, scoped lint, and
pairing pass. Regeneration leaves the unannotated baseline catalog and
inventory byte-identical; all 61 roots still match their existing history.
No runtime property is activated in this tooling commit.
2026-09-18 19:05:32 +08:00
Tianyi Cui a6981c56f6 feat(persistence): add stable catalogs and policy-aware schema review
Traversal ordinals and first-owner paths gave shared persistence types
unstable display names. Keep authored names and source locations as metadata,
use structural digests for identity, and render complete kind/form groups
with bounded array labels. Preserve historical rendering and stored graphs.

Record supported source compatibility promises with their property binding,
policy version, discriminator, preservation rule, and qualified kind set.
The extractor and classifier require explicit opt-ins in both compared
schemas; ordinary or unsupported changes retain strict classification.
Policy-bearing graphs use the format-2 fingerprint domain while unannotated
graphs keep their format-1 fingerprints. Runtime owners activate bindings
only with the corresponding reader behavior; this tooling layer activates
none and changes no package source or Session generation.

Provide a read-only before/after review command that groups shared structural
evidence without replacing authoritative compatibility diagnostics. Match
changed alternatives only through unique literal discriminators and retain
ambiguous additions and removals as independent facts.

At the X baseline, all 61 roots and 472 schemas, digests, and source fields
are unchanged. The inventory remains format 1 and removes only 296 synthetic
names. Existing acknowledgement history still matches every root. All 195
focused tooling tests, Host build/full lint, and bilingual pairing pass.
2026-09-18 19:05:32 +08:00
Tianyi Cui 038c36b138 merge: update master integration with released fork support 2026-09-17 00:40:09 +08:00
Tianyi Cui 0a1e2691ab merge: integrate master into session-log-v4 2026-09-17 00:12:27 +08:00
Tianyi Cui 8696ec6cef feat(session): fork exact event prefixes with synthetic tail results 2026-09-17 00:00:44 +08:00
Dudu-0223 1d1ae1a5af fix(session): migrate historical subagent catalogs to V4 2026-09-16 22:00:38 +08:00
creatixchu 9a74f173d3 Merge remote-tracking branch 'origin/master' into worktree/code-diff-card 2026-09-16 16:31:23 +08:00
Tianyi Cui 669b724a78 feat(session): add the V4 integration format and retain V3 replay inputs 2026-09-16 12:50:34 +08:00
creatixchu dde4dccbd2 feat(workspace-changes): keep change summaries on the Host for the Session's lifetime
The workspace/changes event now carries only the turn number. The
recorder keeps each announced summary in memory under the event's
sequence and serves it through the new workspaceChanges service; the
Web deliverables plugin reads it once per announcement through an
authenticated summary route and renders the card only while the Host
still serves it, so a conversation reopened after a Host restart has no
card for its earlier turns. Snapshot objects move from a shared,
size-bounded store under the Harness home to a temporary directory per
Session that disposal removes, which retires the dshHome and
objectStoreMaxBytes fields. The cold-seeded fold scenario goes with the
logged file list; the client spec covers the fold and the recorded
scenario covers the served summary.
2026-09-14 18:21:12 +08:00
creatixchu f800ea46e5 refactor(deliverables): group tool-present and workspace-changes under packages/deliverables
Both Host packages hand the turn's deliverables to the user and neither
is a filesystem capability, so they leave packages/fs for a new
packages/deliverables group. The Client package stays at
packages/client/ui-deliverables. Paths in tsconfig references and
aliases, gates, generated catalogs, READMEs, and the implemented notes
follow the move; archived notes and released schema records stay as
written.
2026-09-14 13:33:54 +08:00
creatixchu 8a52d27a93 Merge remote-tracking branch 'origin/master' into worktree/code-diff-card
# Conflicts:
#	docs/persistence-changes/historical-formats/README.i18n.yaml
#	docs/persistence-changes/historical-formats/README.md
#	docs/persistence-changes/historical-formats/README.zh.md
#	docs/persistence-schema.json
2026-09-14 11:26:05 +08:00
creatixchu 0d2fcf22dc docs(persistence): refresh format facts after acknowledging the workspace/changes event 2026-09-14 11:08:18 +08:00
creatixchu a27cfb9bd3 Merge remote-tracking branch 'origin/master' into worktree/code-diff-card
# Conflicts:
#	apps/web/package.json
#	docs/event-producer-consumer.i18n.yaml
#	docs/event-producer-consumer.md
#	docs/event-producer-consumer.zh.md
#	docs/persistence-catalog.i18n.yaml
#	docs/persistence-catalog.md
#	docs/persistence-catalog.zh.md
#	pnpm-lock.yaml
2026-09-14 11:07:18 +08:00
creatixchu 2b1dabec86 Refresh merged SDK recordings and persistence documentation 2026-09-14 10:25:54 +08:00
creatixchu a7070008e7 Merge master and integrate image offload with both DeepSeek protocols 2026-09-14 10:19:11 +08:00
Tianyi Cui 38070996c1 docs(session): nest historical formats under persistence changes 2026-09-13 12:19:46 +08:00
Tianyi Cui 765c87fb87 fix(docs): address persistence format history review 2026-09-13 12:08:08 +08:00
Tianyi Cui b08f6c421b docs(session): backfill and gate persistence format references 2026-09-13 12:08:07 +08:00
Tianyi Cui 020b84c301 Merge pull request #4060 from deepseek-harness/worktree/persistence-prerelease-backfill
docs(session): backfill persistence history for all alpha and RC tags
2026-09-12 19:16:42 +08:00
Tianyi Cui 4adfe00207 fix(session): validate generated release facts 2026-09-12 18:52:17 +08:00
Tianyi Cui 2d5391eede docs(session): use tags throughout historical release records 2026-09-12 18:52:17 +08:00
Tianyi Cui aea077ac75 docs(session): backfill alpha and RC persistence history 2026-09-12 18:52:17 +08:00
Tianyi Cui ee9ae1d0e0 docs(session): acknowledge Auto review error metadata 2026-09-12 14:22:33 +08:00
Tianyi Cui 70a3be6f20 test(session): protect persistence digests from harmless reordering 2026-09-12 12:52:25 +08:00
Tianyi Cui 6e294b1c27 fix(session): infer persistence change decisions for agents 2026-09-11 23:56:06 +08:00
Tianyi Cui a0a7e2c11c fix(session): harden and automate persistence change review 2026-09-11 23:15:26 +08:00
Tianyi Cui 1e9b05d356 feat(session): verify persistence type history 2026-09-11 22:06:58 +08:00