kevchess15/deepseek-harness
1
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
deepseek-harness/packages/compaction/compaction-basic/package.json

67 lines
2.2 KiB
JSON
Raw Normal View History

feat(compact-basic): baseline compaction backend (squashed from compact-basic) Collapses the per-round review churn of the prior compact-basic branch into a single clean baseline on top of compact-interface, so the upcoming retention refactor lands as fresh, well-scoped commits rather than stacking on a history of fixes that are being superseded.
2026-06-25 17:30:42 +08:00
{
refactor: apply repository naming contract Apply the accepted pre-release package, service, type, directory, and role renames as one repository-wide change.
2026-08-13 00:36:22 +08:00
"name": "@deepseek-ai/dsh-compaction-basic",
feat(llm): add replay token metering (PR2 round 1)
2026-07-15 14:47:29 +08:00
"description": "Token-meter-driven compaction policy and LLM summarization backend for the DeepSeek Harness",
release(dsh): 0.1.2-alpha.5
2026-09-02 15:48:33 +08:00
"version": "0.1.2-alpha.5",
build(release): make the release set publishable under the private scope Every package under packages/, apps/, and vendor/ drops "private": true and declares publishConfig.access "restricted": the repository now states which packages it publishes instead of deciding it at publish time. Each one also declares its repository and directory, which is how a consumer of a private package reaches its source. The Landlock packages move to restricted with them. They have never been published, so nothing anonymous depends on them today, and the whole @deepseek-ai scope stays private. The workspace constraint that required every package to be private now applies to non-members only, and asserts the publishable trio on each release member.
2026-08-11 00:02:53 +08:00
"publishConfig": {
build(release): publish the dsh family publicly Every release member now declares publishConfig.access: public, so the scope no longer mixes levels: the 221 packages/*/* and apps/* manifests join the vendored framework and the native packages. check-workspace-constraints drops the per-sequence expectation and holds every release member to public, which is what stops a member from drifting back. Access is a property of the package, not of a version: the dsh packages already published as restricted become world-readable at their next publication.
2026-08-13 18:05:10 +08:00
"access": "public"
build(release): make the release set publishable under the private scope Every package under packages/, apps/, and vendor/ drops "private": true and declares publishConfig.access "restricted": the repository now states which packages it publishes instead of deciding it at publish time. Each one also declares its repository and directory, which is how a consumer of a private package reaches its source. The Landlock packages move to restricted with them. They have never been published, so nothing anonymous depends on them today, and the whole @deepseek-ai scope stays private. The workspace constraint that required every package to be private now applies to non-members only, and asserts the publishable trio on each release member.
2026-08-11 00:02:53 +08:00
},
"repository": {
"type": "git",
"url": "git+https://github.com/deepseek-ai/deepseek-harness.git",
refactor: apply repository naming contract Apply the accepted pre-release package, service, type, directory, and role renames as one repository-wide change.
2026-08-13 00:36:22 +08:00
"directory": "packages/compaction/compaction-basic"
build(release): make the release set publishable under the private scope Every package under packages/, apps/, and vendor/ drops "private": true and declares publishConfig.access "restricted": the repository now states which packages it publishes instead of deciding it at publish time. Each one also declares its repository and directory, which is how a consumer of a private package reaches its source. The Landlock packages move to restricted with them. They have never been published, so nothing anonymous depends on them today, and the whole @deepseek-ai scope stays private. The workspace constraint that required every package to be private now applies to non-members only, and asserts the publishable trio on each release member.
2026-08-11 00:02:53 +08:00
},
feat(compact-basic): baseline compaction backend (squashed from compact-basic) Collapses the per-round review churn of the prior compact-basic branch into a single clean baseline on top of compact-interface, so the upcoming retention refactor lands as fresh, well-scoped commits rather than stacking on a history of fixes that are being superseded.
2026-06-25 17:30:42 +08:00
"type": "module",
"main": "lib/index.js",
"types": "lib/types/index.d.ts",
"exports": {
".": {
"types": "./lib/types/index.d.ts",
"default": "./lib/index.js"
},
"./src/*": "./src/*",
"./package.json": "./package.json"
},
"files": [
"lib/index.js",
fix(packages): omit source publication payloads
2026-08-04 22:06:32 +08:00
"lib/types/**/*.d.ts"
feat(compact-basic): baseline compaction backend (squashed from compact-basic) Collapses the per-round review churn of the prior compact-basic branch into a single clean baseline on top of compact-interface, so the upcoming retention refactor lands as fresh, well-scoped commits rather than stacking on a history of fixes that are being superseded.
2026-06-25 17:30:42 +08:00
],
Adopt MIT for DSH packages
2026-08-13 01:46:57 +08:00
"license": "MIT",
feat(compact-basic): baseline compaction backend (squashed from compact-basic) Collapses the per-round review churn of the prior compact-basic branch into a single clean baseline on top of compact-interface, so the upcoming retention refactor lands as fresh, well-scoped commits rather than stacking on a history of fixes that are being superseded.
2026-06-25 17:30:42 +08:00
"peerDependencies": {
chore(deps): refresh package manifests
2026-08-30 02:29:53 +08:00
"@deepseek-ai/cordis": "workspace:^",
build(release): reference workspace members through the workspace protocol 1504 hand-written ranges pointing at workspace members become workspace:^, so pnpm pack substitutes each member's real version at publication: sibling peerDependencies follow the family version instead of being pinned at ^0.0.1, and a reference to a vendored package follows that package's own line. Without this, publishing 0.0.2 ships peer ranges naming a version that does not exist, and 0.0.1-rc.1 does not satisfy ^0.0.1 either. It also retires ranges that had gone stale against the workspace: ^4.0.0-rc.6 for a 4.0.0-rc.7 checkout, ^3.17.0 for schemastery 3.18.0. workspace:* stays where an exact published version is the point, which is how the Landlock entry pins its platform packages. A workspace constraint now requires the protocol, so a new package cannot reintroduce a hand-written range. The same constraint caught packages/boot/cmdline arriving on master without the publishable trio, which this change completes.
2026-08-11 00:16:45 +08:00
"@deepseek-ai/dsh-agent": "workspace:^",
"@deepseek-ai/dsh-commands": "workspace:^",
chore(deps): refresh package manifests
2026-08-30 02:29:53 +08:00
"@deepseek-ai/dsh-compaction": "workspace:^",
"@deepseek-ai/dsh-compaction-tool-result-pruner": "workspace:^",
build(release): reference workspace members through the workspace protocol 1504 hand-written ranges pointing at workspace members become workspace:^, so pnpm pack substitutes each member's real version at publication: sibling peerDependencies follow the family version instead of being pinned at ^0.0.1, and a reference to a vendored package follows that package's own line. Without this, publishing 0.0.2 ships peer ranges naming a version that does not exist, and 0.0.1-rc.1 does not satisfy ^0.0.1 either. It also retires ranges that had gone stale against the workspace: ^4.0.0-rc.6 for a 4.0.0-rc.7 checkout, ^3.17.0 for schemastery 3.18.0. workspace:* stays where an exact published version is the point, which is how the Landlock entry pins its platform packages. A workspace constraint now requires the protocol, so a new package cannot reintroduce a hand-written range. The same constraint caught packages/boot/cmdline arriving on master without the publishable trio, which this change completes.
2026-08-11 00:16:45 +08:00
"@deepseek-ai/dsh-llm": "workspace:^",
"@deepseek-ai/dsh-session": "workspace:^",
chore(deps): refresh package manifests
2026-08-30 02:29:53 +08:00
"@deepseek-ai/dsh-token-meter": "workspace:^"
feat(compact-basic): baseline compaction backend (squashed from compact-basic) Collapses the per-round review churn of the prior compact-basic branch into a single clean baseline on top of compact-interface, so the upcoming retention refactor lands as fresh, well-scoped commits rather than stacking on a history of fixes that are being superseded.
2026-06-25 17:30:42 +08:00
},
feat(compact): prune tool results before summarization (round 1)
2026-07-16 18:02:15 +08:00
"peerDependenciesMeta": {
refactor: apply repository naming contract Apply the accepted pre-release package, service, type, directory, and role renames as one repository-wide change.
2026-08-13 00:36:22 +08:00
"@deepseek-ai/dsh-compaction-tool-result-pruner": {
feat(compact): prune tool results before summarization (round 1)
2026-07-16 18:02:15 +08:00
"optional": true
}
},
feat(llm): add replay token metering (PR2 round 1)
2026-07-15 14:47:29 +08:00
"dependencies": {
chore(deps): refresh package manifests
2026-08-30 02:29:53 +08:00
"@deepseek-ai/dsh-util-values": "workspace:^",
build(release): reference workspace members through the workspace protocol 1504 hand-written ranges pointing at workspace members become workspace:^, so pnpm pack substitutes each member's real version at publication: sibling peerDependencies follow the family version instead of being pinned at ^0.0.1, and a reference to a vendored package follows that package's own line. Without this, publishing 0.0.2 ships peer ranges naming a version that does not exist, and 0.0.1-rc.1 does not satisfy ^0.0.1 either. It also retires ranges that had gone stale against the workspace: ^4.0.0-rc.6 for a 4.0.0-rc.7 checkout, ^3.17.0 for schemastery 3.18.0. workspace:* stays where an exact published version is the point, which is how the Landlock entry pins its platform packages. A workspace constraint now requires the protocol, so a new package cannot reintroduce a hand-written range. The same constraint caught packages/boot/cmdline arriving on master without the publishable trio, which this change completes.
2026-08-11 00:16:45 +08:00
"@deepseek-ai/schemastery": "workspace:^"
feat(llm): add replay token metering (PR2 round 1)
2026-07-15 14:47:29 +08:00
},
feat(compact-basic): baseline compaction backend (squashed from compact-basic) Collapses the per-round review churn of the prior compact-basic branch into a single clean baseline on top of compact-interface, so the upcoming retention refactor lands as fresh, well-scoped commits rather than stacking on a history of fixes that are being superseded.
2026-06-25 17:30:42 +08:00
"devDependencies": {
chore(deps): refresh package manifests
2026-08-30 02:29:53 +08:00
"@deepseek-ai/cordis": "workspace:^",
build(vendor): rescope the vendored Cordis packages into @deepseek-ai Machine-produced by `pnpm run rescope-vendor --apply` plus the regeneration it prints: `pnpm install` for the lockfile, `pnpm run gen-third-party-notices`, `verify-translation-pairing --write` for the touched bilingual pairs, `gen-doc-graphs`, and one typert snapshot whose ids embed character offsets. `pnpm run rescope-vendor --check` verifies the result. Renames nine vendored packages (cordis, cosmokit, schemastery and the six @cordisjs plugins) and every reference that resolves them: manifest names and dependency keys, module specifiers including declare-module merges, cordis.yml plugin names, tsconfig paths, every Markdown fence, and `docs/` prose. Directory names, upstream versions, and dependency ranges are unchanged, so vendor/README.md still reads as an upstream snapshot; its manifest table gains an upstream-name column so THIRD_PARTY_NOTICES keeps MIT attribution pointed at each fork's origin. The tutorial tier follows the rename end to end: its yaml fences named plugins the Loader can no longer resolve, its `ts ignore-check` fences disagreed with the compiled fences beside them, and its prose quoted both. The contracts that told readers to keep upstream names — the root convention and the vendoring cookbook's tree comment and manifest invariant — now say to rescope instead. Two rules read `@deepseek-ai/` as "another workspace plugin": the client bundle purity gate now names the vendored libraries a browser bundle inlines, and the files where a bare `cordis` is an agent-preset id keep that product data.
2026-08-10 22:04:06 +08:00
"@deepseek-ai/cordis-plugin-include": "workspace:^",
"@deepseek-ai/cordis-plugin-loader": "workspace:^",
feat(compact-basic): baseline compaction backend (squashed from compact-basic) Collapses the per-round review churn of the prior compact-basic branch into a single clean baseline on top of compact-interface, so the upcoming retention refactor lands as fresh, well-scoped commits rather than stacking on a history of fixes that are being superseded.
2026-06-25 17:30:42 +08:00
"@deepseek-ai/dsh-agent": "workspace:^",
fix(compact): decide step-alignment from surface tool-pairing, fire compaction pre-step (CBR-001) Codex round 1 CBR-001: a head-anchored compaction checkpoint was mis-classified by the log-position step-alignment scan, so a second auto-compaction over a checkpoint-headed surface silently failed. Root cause: `isStepAlignedStart/End` scanned the LOG by seq, but a `replace` op lands a checkpoint at a high log seq whose SURFACE position is the head — its log neighbours (the open step's assistant/message) are not its surface neighbours, so the forward scan wrongly reported mid-step. Fix, per the agreed direction: - Replace the two log-position predicates with one surface-anchored helper `isToolPairingBalanced(nodes, events, beforeSeq)` in `dsh-session` (renamed step-boundary.ts → tool-pairing.ts). A cut is balanced when no unanswered tool-call precedes it on the surface; a region is collapsible iff both edges are balanced cuts. The open-tail and free-node cases fall out of the same counter. It also throws on a corrupt surface (a tool/result with no matching call). - Move compaction off the in-step seam to a new "pre-step" seam fired after turn/start and before step/start, so a compaction's log-only compact/* records and its replacement node land cleanly OUTSIDE any step (the honest structure crash-safety relies on). Renamed the event agent/pre-request → agent/pre-step and switched its dispatch from parallel → serial (listeners mutate the surface as a side effect; serial isolates them so concurrent appends can't interleave). Extended the catalog generator to accept @mode serial. Regression coverage: a real-loop test driving an auto-compaction asserts the landed checkpoint is a balanced cut on both sides; unit tests pin the checkpoint case, the mid-step injection case, multi-call steps, and the corrupt-surface guard. Proven red on the old log-position logic.
2026-06-26 13:51:01 +08:00
"@deepseek-ai/dsh-agent-loop": "workspace:^",
test(support): add shared AgentLoop testkit
2026-07-16 17:39:53 +08:00
"@deepseek-ai/dsh-agent-loop-testkit": "workspace:^",
refactor(events): add stable conversation correlation ids
2026-08-09 15:48:07 +08:00
"@deepseek-ai/dsh-commands": "workspace:^",
chore(deps): refresh package manifests
2026-08-30 02:29:53 +08:00
"@deepseek-ai/dsh-compaction": "workspace:^",
"@deepseek-ai/dsh-compaction-tool-result-pruner": "workspace:^",
fix: complete invariant omission cleanup
2026-08-31 17:10:19 +08:00
"@deepseek-ai/dsh-invariants": "workspace:^",
feat(compact-basic): baseline compaction backend (squashed from compact-basic) Collapses the per-round review churn of the prior compact-basic branch into a single clean baseline on top of compact-interface, so the upcoming retention refactor lands as fresh, well-scoped commits rather than stacking on a history of fixes that are being superseded.
2026-06-25 17:30:42 +08:00
"@deepseek-ai/dsh-llm": "workspace:^",
feat: implement bounded LLM request recovery
2026-07-20 03:34:19 +08:00
"@deepseek-ai/dsh-llm-retry": "workspace:^",
feat(compact-basic): baseline compaction backend (squashed from compact-basic) Collapses the per-round review churn of the prior compact-basic branch into a single clean baseline on top of compact-interface, so the upcoming retention refactor lands as fresh, well-scoped commits rather than stacking on a history of fixes that are being superseded.
2026-06-25 17:30:42 +08:00
"@deepseek-ai/dsh-session": "workspace:^",
chore(deps): refresh package manifests
2026-08-30 02:29:53 +08:00
"@deepseek-ai/dsh-session-projection": "workspace:^",
feat(llm): add replay token metering (PR2 round 1)
2026-07-15 14:47:29 +08:00
"@deepseek-ai/dsh-token-meter": "workspace:^",
chore(deps): refresh package manifests
2026-08-30 02:29:53 +08:00
"@deepseek-ai/dsh-tools": "workspace:^"
feat(compact-basic): baseline compaction backend (squashed from compact-basic) Collapses the per-round review churn of the prior compact-basic branch into a single clean baseline on top of compact-interface, so the upcoming retention refactor lands as fresh, well-scoped commits rather than stacking on a history of fixes that are being superseded.
2026-06-25 17:30:42 +08:00
}
}
Reference in a new issue Copy permalink