Files
OmniRoute/src/lib/db/compression.ts
Diego Rodrigues de Sa e Souza fa367dd99e Release v3.8.27 (#3968)
* chore(release): open v3.8.27 development cycle

* fix(security): polynomial ReDoS in comboAgentMiddleware regex (#3982)

* fix(security): eliminate polynomial ReDoS in comboAgentMiddleware <omniModel> regex (CodeQL js/polynomial-redos)

CACHE_TAG_PATTERN wrapped the tag in an unbounded `(?:\\n|\n|\r)*` prefix/suffix.
On an unanchored `.test()`/`.exec()` that is O(n²) on inputs with many newlines
(CodeQL js/polynomial-redos, alerts #612/#613). The surrounding runs are irrelevant
to detecting/capturing the tag, so the detection pattern now matches only the core
`<omniModel>([^<]+)</omniModel>`; the global strip pattern still consumes the
wrapping newlines (combo.ts streaming, #531) but BOUNDED ({0,16}) so it stays linear.

Behavior preserved: detection, model extraction, multi-tag stripping (#454) and
blank-line cleanup all unchanged (107 related tests green). Adds ReDoS-safety
regression tests (50k-newline inputs complete in <1ms).

* docs(changelog): add #3982 ReDoS fix to [3.8.27]

* ci(security): harden workflows — artipacked persist-credentials + cache-poisoning + SC2086 (#3965)

* Refine provider quota card display (#3969)

Integrated into release/v3.8.27

* feat: add sidebar group separator toggles (#3971)

Integrated into release/v3.8.27

* Gate control-plane proxy direct fallback (#3963)

Integrated into release/v3.8.27

* Capture actual upstream provider requests (#3941)

Integrated into release/v3.8.27

* ci(quality): flip require-tighten + osv + Trivy to blocking (v3.8.27 cycle-end) (#3984)

* fix(resilience): respect connection cooldown stored as numeric epoch (#3954) (#3995)

rate_limited_until is a TEXT column, but setConnectionRateLimitUntil (Antigravity full-quota path) persists a raw epoch number that SQLite coerces to a numeric string ("1781696905131.0"). The selection predicate isAccountUnavailable then did new Date("1781696905131.0") -> NaN, so the cooling connection was never skipped and the router kept dispatching to rate-limited accounts. Normalize numeric-epoch strings (and number/Date/ISO) via a shared cooldownUntilMs() helper in isAccountUnavailable / getEarliestRateLimitedUntil / filterAvailableAccounts / parseFutureDateMs. ISO behavior preserved.

* fix(providers): fetch live /models for LLM7 and BytePlus (#3976) (#3996)

llm7 and byteplus carry a real modelsUrl but were not classified by any live-fetch branch of the model-import route, so their hardcoded 4-entry registry catalog was served (source local_catalog) instead of the upstream catalog. Add both to NAMED_OPENAI_STYLE_PROVIDERS so the route probes <baseUrl>/models and serves the live list, falling back to the local catalog only on fetch failure.

* fix(dashboard): logs auto-refresh reads live visibility, not a stale mount ref (#3972) (#3997)

The auto-refresh interval gated each tick on visibleRef, seeded once at mount and updated only by a visibilitychange event. A tab mounted while document.visibilityState is 'hidden' (background load, bfcache, embedded/proxied webviews) with no later visibilitychange left the ref false forever, so the interval ticked but never fetched — only the manual button worked. Read the live document.visibilityState in the tick instead.

* feat(compression): add Indonesian caveman rules and language pack (#3975)

Integrated into release/v3.8.27

(cherry picked from commit c9b5b1a892)

* fix(combo): shuffle strict-random fallback remainder to spread load (#3959) (#3998)

strict-random shuffled only the deck-selected slot 0 and left the fallback remainder in fixed priority order, so after a failing deck pick the chain always fell through to the same top-priority model — a persistently-failing model was retried on essentially every request and fallback load never spread across peers. Shuffle the remainder too (like the random strategy).

* Add provider auth visibility controls (#3953)

Integrated into release/v3.8.27

* fix(claude): forward client tool-search-tool anthropic-beta on the Claude OAuth path (#3974) (#3999)

The client-negotiated anthropic-beta: tool-search-tool-2025-10-19 was dropped on both Claude code paths (default executor rebuilt from static ANTHROPIC_BETA_CLAUDE_OAUTH; selectBetaFlags only read the client beta to gate thinking/effort), so claude.ai rejected deferred-tool requests with 400 'Tool reference not found'. Add an allowlist-merge (mergeClientAnthropicBeta) that unions the client's allowlisted betas into the outbound set on both paths, preserving #3415 (no forced thinking/effort).

* feat(providers): add model search filter to provider dashboard (#3950)

Integrated into release/v3.8.27

* fix(vision-bridge): force bridge for tokenrouter deepseek models (#3946)

Integrated into release/v3.8.27

* fix(executor): strip stream_options on non-streaming requests (#3884) (#4000)

Clients that send stream_options:{include_usage:true} regardless of stream (e.g. the OpenAI Python SDK) had it passed through on non-streaming calls; NVIDIA NIM rejected it with 400 'Stream options can only be defined when stream=True'. DefaultExecutor.transformRequest only injected/cleared stream_options on the streaming branch and never stripped a client-sent value when stream=false. Add a !stream strip branch; the streaming injection path is unchanged. Global to openai-compat providers.

* fix(qwen-web): cookie validation false-positive - check response body for user object (#3958)

Integrated into release/v3.8.27

* fix(db): persist backup retention days (#3970)

Integrated into release/v3.8.27

* 大量UI显示和i18n优化 (#3973)

Integrated into release/v3.8.27

* deps: bump the npm_and_yarn group across 1 directory with 2 updates (#3943)

Integrated into release/v3.8.27

* deps: bump form-data from 4.0.5 to 4.0.6 (#3944)

Integrated into release/v3.8.27

* deps: bump vite from 8.0.5 to 8.0.16 (#3942)

Integrated into release/v3.8.27

* chore(quality): re-baseline validation.ts 4407->4428 (#3958 qwen body-check)

The qwen-web validation body-check merged in #3958 pushed validation.ts past its
frozen size on the integrated release tip. Bump the baseline with justification;
no logic is separately extractable from the existing qwen-web validation branch.

* deps: bump the production group with 13 updates (#3915)

Integrated into release/v3.8.27 — low-risk group (playwright 1.60→1.61 minor + transitive patches; fumadocs-core 16.9→16.10 minor).

* chore(deps): ignore jscpd major bumps (v5 Rust rewrite breaks the duplication gate)

Our duplication ratchet (scripts/check/check-duplication.mjs) is pinned to jscpd@4
and parses jscpd-report.json against a frozen baseline. jscpd v5 is a native Rust
binary with no Node.js API and a different report/bin, so a major bump would break
the gate. Migrate deliberately, not via dependabot. Closes the noise from #3916.

* fix(perplexity-web): parse schematized diff_block stream so answers aren't empty (#4001)

Integrated into release/v3.8.27 — schematized diff_block parsing follow-up to #3938.

* refactor: modularize providerRegistry.ts into 159 individual provider plugins (#3993)

Modularize provider registry (#3594). Integrated into release/v3.8.27 after rebase + behavior-preservation verification (provider-consistency gate 159/232/0, typecheck, registry tests, build 556/556).

Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>

* fix(registry): restore byteplus + mimocode dropped by #3993 modularization

The provider-registry modularization (#3993) was cut from a base predating the
byteplus (#3877) and mimocode (#3837) registry entries, so merging it silently
dropped both providers (getRegistryEntry returned undefined → validation reported
'not supported'). Re-add them as registry modules in the new structure; registered
count 159→161, provider-consistency 161/232/0.

Also align the pre-existing qwen-web validator test to #3958: since the validator
now requires a real `user` object in the 200 body, the mock must carry one.

* refactor: modularize schemas (non-stacked) (#3988)

Modularize validation schemas (#3594). Integrated into release/v3.8.27 after rebase (reconciled the merged hiddenSidebarGroupLabels #3971 + intelligenceSyncRequestSchema into the new modules) + behavior verification (typecheck, 195 schema/settings/validation tests, build 556/556).

Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>

* fix(default-executor): honor custom providerSpecificData.baseUrl for OpenAI-format providers (#4002)

Integrated into release/v3.8.27 — honor custom providerSpecificData.baseUrl in DefaultExecutor (openai-format), tested.

* feat(openai): honor custom base URL in model discovery + complete openai/codex pricing (#4005)

Integrated into release/v3.8.27 — openai model-discovery honors custom base URL (SSRF-guarded) + pricing rows for new openai/codex models. Tested + baselines bumped.

* fix(live-ws): bridge sidecar events to dashboard (#4004)

Integrated into release/v3.8.27 — repair LiveWS sidecar (startup, same-origin /live-ws, main→sidecar compression.completed bridge, early-msg queue). Fixed the cookie-parse regex (\s) + added a focused unit test; baseline bumped for the non-blocking chatCore bridge.

* docs(troubleshooting): note MITM proxy cannot intercept Windows-host apps under WSL (#4003)

Integrated into release/v3.8.27 — MITM/WSL troubleshooting note.

* fix(repo): untrack accidentally-committed root node_modules symlink + gitignore it

A worktree node_modules symlink (-> the main checkout's node_modules) was staged by a
`git add -A` during the #3988 merge and committed into 05213ac6a. The symlink points
at the repo's own node_modules path, so checking it out turns the main checkout's
node_modules into a self-referential symlink (breaking tsx/all node ops). Untrack it and
add a root-anchored /node_modules ignore so the symlink form can't be re-committed (the
existing 'node_modules/' only matches directories).

* fix(quality): allowlist socks dep (declared by #4004, never allowlisted)

socks@^2.8.7 was added to package.json in #4004 (LiveWS sidecar, 02302131f)
as a phantom-dep cleanup but never added to dependency-allowlist.json, so
check:deps has been red on the release tip ever since. socks is the standard
SOCKS proxy client (dep of fetch-socks), legitimate and years old.

* feat(sse): real LLMLingua-2 ONNX compression engine (stable) (#4014)

Integrated into release/v3.8.27.

Adjustments before merge:
- Synced with the current release tip (was 11 commits behind).
- Added the 3 LLMLingua-2 ONNX optional-runtime deps to dependency-allowlist.json
  (@atjsh/llmlingua-2, @tensorflow/tfjs, js-tiktoken) — the only gate that was red.
- socks was allowlisted directly on release (separate fix d7db5c73d; it was declared
  by #4004 but never allowlisted, leaving check:deps red release-wide).

Verified locally: check:deps OK, file-size OK, public-creds OK, provider-consistency
161/232/0, typecheck:core clean, 24/24 LLMLingua tests pass. The only remaining Fast-QG
red is the pre-existing #3972 orphan test (request-logger-autorefresh-visibility-3972.test.tsx),
which is release-wide and unrelated to this PR.

* test(dashboard): rehome #3972 logs auto-refresh test so a runner collects it

tests/unit/request-logger-autorefresh-visibility-3972.test.tsx (added by #3972
via #3997) sat at the top level of tests/unit/ as a .tsx vitest test, which NO
runner collects: the node runner only globs *.test.ts, and test:vitest:ui only
runs tests/unit/ui. So the #3972 regression guard never executed in CI and
check:test-discovery was red release-wide. Move it under tests/unit/ui/ (the
collected vitest:ui path) and fix the relative import depth. Verified: the test
now runs and passes (2/2), and check:test-discovery is green.

* feat(compression): capture per-engine analytics (#3960) + Lite schema fix (#3952) (#4018)

Captures the net-new value from #3960 (per-engine breakdown analytics) and #3952 (Lite engine schema fix) onto release/v3.8.27. Fast QG green; 622/622 compression+analytics tests pass.

* fix(sse): guard model-less registry entries in getUnsupportedParams (mimocode) (#4015)

Real bugfix: guard model-less registry entries (mimocode) in getUnsupportedParams so handleChatCore no longer throws 'entry.models is not iterable' / reports 'All models failed' for unrelated requests. Includes a regression test. Fast QG green.

* feat(ci): Quality Gate v2 — Onda 0 + Onda 1 (gate flips, TIA, SAST, DAST-smoke, mutation infra) (#4016)

* docs(ops): add quality-gate assessment + replication playbook (Fase 9 foundation)

* feat(ci): flip oasdiff breaking-change gate to blocking (ratchet)

* docs(ops): deliver main branch-protection ruleset for owner to apply

* fix(ci): run typecheck:core in PR->release fast-gates (close fast-gates hole, part 1)

* perf(mutation): enable Stryker incremental mode + cache (scales the 60/80 rollout)

* feat(ci): commit CodeQL advanced config (security-extended), replacing default-setup

* feat(ci): version semgrep SAST workflow (owasp/secrets), advisory

* feat(quality): TIA test-impact map builder (import-graph; map built at runtime, gitignored)

* feat(quality): TIA impacted-test selector with run-all fail-safe

* fix(ci): run TIA-impacted unit tests in PR->release fast-gates (build map at runtime, fail-safe full)

* feat(ci): DAST-smoke per-PR (schemathesis subset + promptfoo injection-guard, blocking)

* fix(ci): unbreak Fase 9 PR CI (MDX frontmatter, CodeQL conflict, dast-smoke advisory)

- Add MDX frontmatter to docs/ops/{BRANCH_PROTECTION_MAIN,QUALITY_GATE_PLAYBOOK}.md.
  fumadocs rejects frontmatter-less docs -> 'npm run build' failed -> broke dast-smoke's
  build step (the release fast-gates never runs build, so this only surfaced on the PR).
- codeql.yml: workflow_dispatch-only until the owner switches repo CodeQL Default->Advanced
  (advanced configs cannot be processed while default setup is enabled; documented inline).
- dast-smoke.yml: job-level continue-on-error (advisory) so this brand-new gate matures
  before it blocks (repo convention: advisory -> blocking).

* ci(quality): make TIA unit-test step advisory until release test-debt is cleared

release/v3.8.27 carries ~17 pre-existing failing unit tests (budget #3537, apiKey
#3552, several Zod schemas, Puter/Qwen executors, mimocode entry, etc.) unrelated to
this PR — the new 'run tests on PR->release' gate surfaced them. Per the repo's
advisory->blocking convention, this step enters advisory (it still runs + reports)
so pre-existing debt doesn't block the gate program. typecheck:core stays blocking.
Flip to blocking (remove continue-on-error) once the release suite is green.

* fix(sse): preserve Kiro streaming finish_reason tool_calls (#3980) (#4025)

* fix(guardrails): preserve original image when vision-bridge describe fails (#4012) (#4026)

* feat(api): advertise combo capabilities on import surfaces (#3979) (#4027)

* feat(sse): delegated Anthropic Context Editing for Claude (clear_tool_uses) (#4021)

Opt-in Claude-only delegated compression: injects context_management.clear_tool_uses_20250919 at the Claude pre-serialization chokepoint (composes with clear_thinking, thinking first), threaded via ExecuteInput from handleChatCore. Pure edit-builder + 11 tests (7 unit + 4 e2e fetch-capture). Beta context-management-2025-06-27 already advertised; allowlist done. Telemetry/400-fallback/claude-web coverage deferred.

* fix(opencode): map x-session-affinity to x-opencode-session for custom providers (#4022) (#4028)

* fix(dashboard): Playground Compare tab loading + HTTP method guard (#4024)

randomUUID non-HTTPS fallback + static CompareTab import; raw HTTP TRACE->405 method guard wired into dev + standalone servers. Integrated into release/v3.8.27.

* refactor(dashboard): settings UI layout + API Keys naming (#4020)

Presentation/relabel refactor of the Settings dashboard (API Manager -> API Keys), card relocations, Toggle adoption, present-but-disabled engine steps. Auth-file changes are string/comment-only (no behavior change). Integrated into release/v3.8.27.

* fix: restore unit regressions dropped by lossy schema/registry modularizations (#4030)

Restores schema fields (combo reasoningTokenBuffer, budget-0 #3537, openrouter preset, proxy family #3777, resilience degradation/providerCooldown), qwen-web v2 endpoint+catalog, mimocode models key — all dropped by #3988/#3993 — and aligns 3 tests to #3941/#3993. Verified: 8 failing regression tests on release tip -> 131/131 green on this branch. Integrated into release/v3.8.27.

* fix(api): return 400 (not 500) for malformed JSON on /api/auth/login (#4031)

Wrap request.json() so a malformed/non-JSON login body returns a structured 400 instead of falling through to the 500 catch. Fixes the schemathesis high-risk-endpoint DAST finding (verified: schemathesis step now passes). +TDD test. Integrated into release/v3.8.27.

* feat(dashboard): real circuit-breaker state in the Combo Live cascade (U1b) (#4029)

Overlays real provider circuit-breaker state (GET /api/monitoring/health) onto the Combo Live cascade as a 'CB: OPEN · 41s' badge. Pure enrichRunWithBreakers + fail-soft useProviderBreakerHealth poll; graceful when health is absent. +13 tests. Integrated into release/v3.8.27.

* Fix promptfoo security assertion parsing (#4032)

* chore(deps): dependabot security bumps + drop unused gray-matter (#4036)

Integrated into release/v3.8.27 — dependabot security bumps (form-data/js-yaml/protobufjs/dompurify/hono) + drop unused gray-matter. Unblocks the npm audit:deps gate (Lint) branch-wide.

* fix(ci): scope TIA to node:test unit files only (mirror test:unit glob) (#4035)

Integrated into release/v3.8.27 — scopes the advisory TIA step to the test:unit node:test glob, fixing the 99 false failures. +4 TDD.

* Refine compression settings, storage labels, and sidebar grouping (#4033)

Integrated into release/v3.8.27 — relocate Token Saver into Compression Settings (controlled component), reorder Security/Authz tabs, storage labels + i18n relabel. Thanks @rdself!

* [codex] add per-key local usage command (#4034)

Integrated into release/v3.8.27 — per-key local @@om-usage command (cached quota, no upstream routing). Rebased onto modularized schemas/keys.ts + file-size rebaseline. Thanks @Witroch4!

* chore(release): reconcile v3.8.27 CHANGELOG + i18n mirrors

* ci(quality): unblock v3.8.27 release gates (zizmor pin + test-masking allowlist)

- zizmor ratchet (151→139, no regression): SHA-pin every action ref ADDED this
  cycle — codeql/dast-smoke/semgrep (3 new workflows) + trivy-action (docker-publish)
  + actions/cache (nightly-mutation). Pre-existing tag refs keep the repo convention.
- test-masking: add config/quality/test-masking-allowlist.json + allowlist support in
  check-test-masking.mjs (exempts ONLY the net-assert-reduction signal; tautology/skip/
  deletion still fire). Allowlists 2 verified-legitimate reductions:
  appearance-widget-settings-schema (#4033 removed showTokenSaverOnEndpoint field) and
  dashboard-shell-tabs (#3973 tabs→redirect refactor, asserts replaced). +4 gate tests.

* test(quality): reword test-masking self-test comments to avoid literal masking patterns

The added allowlist-test comments contained the literal strings 'assert.ok(true)' and
'.skip' which the masking detector's own regexes match as text — making the gate flag
its own test file (net +1 tautology/skip/extended-tautology vs main). Reworded to plain
prose ('a new tautology', 'a new skip marker'); test logic unchanged (24/24 pass).

* fix(quality): unblock v3.8.27 release — align 3 stale tests + restore modularized settings-schema parity

Release-PR full CI surfaced 3 deterministic test failures (no live product regression),
all stale vs legitimate cycle changes:

- settings-schema parity (#3988): the modularized updateSettingsSchema barrel
  (schemas/settings.ts) had diverged from the canonical settingsSchemas.ts (45 vs 85
  fields — 40 dropped + 6 extra), a lossy-modularization dead-code copy. Re-export from
  the canonical source so the barrel can never diverge again (runtime already uses
  canonical). Parity test now passes.
- api-manager permissions modal: #4034 added a 4th self-service switch (per-key usage
  allowance); a11y invariant (every switch type="button") still holds. Updated the
  static count 3 -> 4.
- pack-artifact policy: dist/http-method-guard.cjs became a required runtime path;
  added it to the test's expected missing-paths list.

Also documents the gate gap for Fase 9 (QUALITY_GATE_PLAYBOOK Parte 6): G1 run the
deterministic unit layer + test-masking on PR->release (not just PR->main), G2 a
modularization-parity gate (would have caught the #3988 drop at its PR), G3 flake
quarantine. Env flakes (LiveWS startup timeout, integration server-startup cascade)
are pre-existing/CI-env, triaged separately.

---------

Co-authored-by: Randi <55005611+rdself@users.noreply.github.com>
Co-authored-by: Veier04 <118300867+Veier04@users.noreply.github.com>
Co-authored-by: Felipe Sartori <felipesartori.ti@gmail.com>
Co-authored-by: WormAlien <164898390+WormAlien@users.noreply.github.com>
Co-authored-by: thezukiru <121331256+thezukiru@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: NOXX - Commiter <artur1992123@mail.ru>
Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com>
Co-authored-by: Demiurge The Single <megamen932@gmail.com>
Co-authored-by: Witroch4 <witalo_rocha@hotmail.com>
2026-06-17 02:43:21 -03:00

561 lines
19 KiB
TypeScript

import { backupDbFile } from "./backup";
import { getDbInstance } from "./core";
import { invalidateDbCache } from "./readCache";
import {
DEFAULT_AGGRESSIVE_CONFIG,
DEFAULT_CAVEMAN_CONFIG,
DEFAULT_CAVEMAN_OUTPUT_MODE_CONFIG,
DEFAULT_COMPRESSION_LANGUAGE_CONFIG,
DEFAULT_COMPRESSION_CONFIG,
DEFAULT_CONTEXT_EDITING_CONFIG,
DEFAULT_MCP_ACCESSIBILITY_CONFIG,
DEFAULT_RTK_CONFIG,
DEFAULT_ULTRA_CONFIG,
type AggressiveConfig,
type CavemanConfig,
type CavemanOutputModeConfig,
type CompressionLanguageConfig,
type CompressionPipelineStep,
type CompressionConfig,
type CompressionMode,
type ContextEditingConfig,
type McpAccessibilityConfig,
type RtkConfig,
type UltraConfig,
} from "@omniroute/open-sse/services/compression/types.ts";
const NAMESPACE = "compression";
const COMPRESSION_MODES = new Set<CompressionMode>([
"off",
"lite",
"standard",
"aggressive",
"ultra",
"rtk",
"stacked",
]);
type JsonRecord = Record<string, unknown>;
// TTL cache for compression settings (5s)
let compressionSettingsCache: {
value: CompressionConfig;
expiresAt: number;
dbRef: WeakRef<object>;
} | null = null;
function toRecord(value: unknown): JsonRecord {
return value && typeof value === "object" ? (value as JsonRecord) : {};
}
function parseJsonSafe(raw: string | null): unknown {
if (!raw) return undefined;
try {
return JSON.parse(raw);
} catch {
return undefined;
}
}
function normalizeCavemanConfig(value: unknown): CavemanConfig {
const record = toRecord(value);
const intensity =
record.intensity === "lite" || record.intensity === "full" || record.intensity === "ultra"
? record.intensity
: DEFAULT_CAVEMAN_CONFIG.intensity;
return {
...DEFAULT_CAVEMAN_CONFIG,
...record,
compressRoles: Array.isArray(record.compressRoles)
? record.compressRoles.filter(
(role): role is "user" | "assistant" | "system" =>
role === "user" || role === "assistant" || role === "system"
)
: DEFAULT_CAVEMAN_CONFIG.compressRoles,
skipRules: Array.isArray(record.skipRules)
? record.skipRules.filter((rule): rule is string => typeof rule === "string")
: DEFAULT_CAVEMAN_CONFIG.skipRules,
minMessageLength:
typeof record.minMessageLength === "number" && Number.isFinite(record.minMessageLength)
? Math.max(0, Math.floor(record.minMessageLength))
: DEFAULT_CAVEMAN_CONFIG.minMessageLength,
preservePatterns: Array.isArray(record.preservePatterns)
? record.preservePatterns.filter((pattern): pattern is string => typeof pattern === "string")
: DEFAULT_CAVEMAN_CONFIG.preservePatterns,
intensity,
};
}
function normalizeCavemanOutputModeConfig(value: unknown): CavemanOutputModeConfig {
const record = toRecord(value);
return {
...DEFAULT_CAVEMAN_OUTPUT_MODE_CONFIG,
enabled:
typeof record.enabled === "boolean"
? record.enabled
: DEFAULT_CAVEMAN_OUTPUT_MODE_CONFIG.enabled,
intensity:
record.intensity === "lite" || record.intensity === "full" || record.intensity === "ultra"
? record.intensity
: DEFAULT_CAVEMAN_OUTPUT_MODE_CONFIG.intensity,
autoClarity:
typeof record.autoClarity === "boolean"
? record.autoClarity
: DEFAULT_CAVEMAN_OUTPUT_MODE_CONFIG.autoClarity,
};
}
function normalizeRtkConfig(value: unknown): RtkConfig {
const record = toRecord(value);
return {
...DEFAULT_RTK_CONFIG,
enabled: typeof record.enabled === "boolean" ? record.enabled : DEFAULT_RTK_CONFIG.enabled,
intensity:
record.intensity === "minimal" ||
record.intensity === "standard" ||
record.intensity === "aggressive"
? record.intensity
: DEFAULT_RTK_CONFIG.intensity,
applyToToolResults:
typeof record.applyToToolResults === "boolean"
? record.applyToToolResults
: DEFAULT_RTK_CONFIG.applyToToolResults,
applyToCodeBlocks:
typeof record.applyToCodeBlocks === "boolean"
? record.applyToCodeBlocks
: DEFAULT_RTK_CONFIG.applyToCodeBlocks,
applyToAssistantMessages:
typeof record.applyToAssistantMessages === "boolean"
? record.applyToAssistantMessages
: DEFAULT_RTK_CONFIG.applyToAssistantMessages,
enabledFilters: Array.isArray(record.enabledFilters)
? record.enabledFilters.filter((filter): filter is string => typeof filter === "string")
: DEFAULT_RTK_CONFIG.enabledFilters,
disabledFilters: Array.isArray(record.disabledFilters)
? record.disabledFilters.filter((filter): filter is string => typeof filter === "string")
: DEFAULT_RTK_CONFIG.disabledFilters,
maxLinesPerResult: boundedInt(
record.maxLinesPerResult,
DEFAULT_RTK_CONFIG.maxLinesPerResult,
0,
100000
),
maxCharsPerResult: boundedInt(
record.maxCharsPerResult,
DEFAULT_RTK_CONFIG.maxCharsPerResult,
0,
1000000
),
deduplicateThreshold: boundedInt(
record.deduplicateThreshold,
DEFAULT_RTK_CONFIG.deduplicateThreshold,
2,
100
),
customFiltersEnabled:
typeof record.customFiltersEnabled === "boolean"
? record.customFiltersEnabled
: DEFAULT_RTK_CONFIG.customFiltersEnabled,
trustProjectFilters:
typeof record.trustProjectFilters === "boolean"
? record.trustProjectFilters
: DEFAULT_RTK_CONFIG.trustProjectFilters,
rawOutputRetention:
record.rawOutputRetention === "never" ||
record.rawOutputRetention === "failures" ||
record.rawOutputRetention === "always"
? record.rawOutputRetention
: DEFAULT_RTK_CONFIG.rawOutputRetention,
rawOutputMaxBytes: boundedInt(
record.rawOutputMaxBytes,
DEFAULT_RTK_CONFIG.rawOutputMaxBytes,
1024,
10_000_000
),
};
}
function normalizeLanguageConfig(value: unknown): CompressionLanguageConfig {
const record = toRecord(value);
const defaultLanguage =
typeof record.defaultLanguage === "string" && record.defaultLanguage.trim()
? record.defaultLanguage.trim()
: DEFAULT_COMPRESSION_LANGUAGE_CONFIG.defaultLanguage;
const enabledPacks = Array.isArray(record.enabledPacks)
? record.enabledPacks
.filter((pack): pack is string => typeof pack === "string" && pack.trim().length > 0)
.map((pack) => pack.trim())
: DEFAULT_COMPRESSION_LANGUAGE_CONFIG.enabledPacks;
return {
...DEFAULT_COMPRESSION_LANGUAGE_CONFIG,
enabled:
typeof record.enabled === "boolean"
? record.enabled
: DEFAULT_COMPRESSION_LANGUAGE_CONFIG.enabled,
defaultLanguage,
autoDetect:
typeof record.autoDetect === "boolean"
? record.autoDetect
: DEFAULT_COMPRESSION_LANGUAGE_CONFIG.autoDetect,
enabledPacks: [...new Set(enabledPacks.length > 0 ? enabledPacks : ["en"])],
};
}
function normalizeContextEditingConfig(value: unknown): ContextEditingConfig {
const record = toRecord(value);
return {
...DEFAULT_CONTEXT_EDITING_CONFIG,
enabled:
typeof record.enabled === "boolean"
? record.enabled
: DEFAULT_CONTEXT_EDITING_CONFIG.enabled,
};
}
function normalizeStackedPipeline(value: unknown): CompressionPipelineStep[] {
const source = Array.isArray(value) ? value : (DEFAULT_COMPRESSION_CONFIG.stackedPipeline ?? []);
const pipeline: CompressionPipelineStep[] = [];
for (const entry of source) {
const record = toRecord(entry);
const engine = record.engine;
if (
engine !== "lite" &&
engine !== "caveman" &&
engine !== "aggressive" &&
engine !== "ultra" &&
engine !== "rtk"
) {
continue;
}
pipeline.push({
engine,
...(typeof record.intensity === "string"
? { intensity: record.intensity as CompressionPipelineStep["intensity"] }
: {}),
...(record.config && typeof record.config === "object"
? { config: record.config as Record<string, unknown> }
: {}),
});
}
return pipeline.length > 0 ? pipeline : (DEFAULT_COMPRESSION_CONFIG.stackedPipeline ?? []);
}
function boundedInt(value: unknown, fallback: number, min: number, max: number): number {
if (typeof value !== "number" || !Number.isFinite(value)) return fallback;
return Math.min(max, Math.max(min, Math.floor(value)));
}
function boundedNumber(value: unknown, fallback: number, min: number, max: number): number {
if (typeof value !== "number" || !Number.isFinite(value)) return fallback;
return Math.min(max, Math.max(min, value));
}
function normalizeAggressiveConfig(value: unknown): AggressiveConfig {
const record = toRecord(value);
const thresholds = toRecord(record.thresholds);
const toolStrategies = toRecord(record.toolStrategies);
return {
...DEFAULT_AGGRESSIVE_CONFIG,
thresholds: {
fullSummary: boundedInt(
thresholds.fullSummary,
DEFAULT_AGGRESSIVE_CONFIG.thresholds.fullSummary,
1,
100
),
moderate: boundedInt(
thresholds.moderate,
DEFAULT_AGGRESSIVE_CONFIG.thresholds.moderate,
1,
100
),
light: boundedInt(thresholds.light, DEFAULT_AGGRESSIVE_CONFIG.thresholds.light, 1, 100),
verbatim: boundedInt(
thresholds.verbatim,
DEFAULT_AGGRESSIVE_CONFIG.thresholds.verbatim,
1,
100
),
},
toolStrategies: {
fileContent:
typeof toolStrategies.fileContent === "boolean"
? toolStrategies.fileContent
: DEFAULT_AGGRESSIVE_CONFIG.toolStrategies.fileContent,
grepSearch:
typeof toolStrategies.grepSearch === "boolean"
? toolStrategies.grepSearch
: DEFAULT_AGGRESSIVE_CONFIG.toolStrategies.grepSearch,
shellOutput:
typeof toolStrategies.shellOutput === "boolean"
? toolStrategies.shellOutput
: DEFAULT_AGGRESSIVE_CONFIG.toolStrategies.shellOutput,
json:
typeof toolStrategies.json === "boolean"
? toolStrategies.json
: DEFAULT_AGGRESSIVE_CONFIG.toolStrategies.json,
errorMessage:
typeof toolStrategies.errorMessage === "boolean"
? toolStrategies.errorMessage
: DEFAULT_AGGRESSIVE_CONFIG.toolStrategies.errorMessage,
},
summarizerEnabled:
typeof record.summarizerEnabled === "boolean"
? record.summarizerEnabled
: DEFAULT_AGGRESSIVE_CONFIG.summarizerEnabled,
maxTokensPerMessage: boundedInt(
record.maxTokensPerMessage,
DEFAULT_AGGRESSIVE_CONFIG.maxTokensPerMessage,
256,
32768
),
minSavingsThreshold: boundedNumber(
record.minSavingsThreshold,
DEFAULT_AGGRESSIVE_CONFIG.minSavingsThreshold,
0,
1
),
};
}
function normalizeUltraConfig(value: unknown): UltraConfig {
const record = toRecord(value);
const modelPath = typeof record.modelPath === "string" ? record.modelPath.trim() : "";
return {
...DEFAULT_ULTRA_CONFIG,
enabled: typeof record.enabled === "boolean" ? record.enabled : DEFAULT_ULTRA_CONFIG.enabled,
compressionRate: boundedNumber(
record.compressionRate,
DEFAULT_ULTRA_CONFIG.compressionRate,
0,
1
),
minScoreThreshold: boundedNumber(
record.minScoreThreshold,
DEFAULT_ULTRA_CONFIG.minScoreThreshold,
0,
1
),
slmFallbackToAggressive:
typeof record.slmFallbackToAggressive === "boolean"
? record.slmFallbackToAggressive
: DEFAULT_ULTRA_CONFIG.slmFallbackToAggressive,
...(modelPath ? { modelPath } : {}),
maxTokensPerMessage: boundedInt(
record.maxTokensPerMessage,
DEFAULT_ULTRA_CONFIG.maxTokensPerMessage,
0,
32768
),
};
}
export async function getCompressionSettings(): Promise<CompressionConfig> {
const db = getDbInstance();
if (
compressionSettingsCache &&
Date.now() < compressionSettingsCache.expiresAt &&
compressionSettingsCache.dbRef.deref() === db
) {
return compressionSettingsCache.value;
}
compressionSettingsCache = null;
const rows = db.prepare("SELECT key, value FROM key_value WHERE namespace = ?").all(NAMESPACE);
const config: CompressionConfig = {
...DEFAULT_COMPRESSION_CONFIG,
cavemanConfig: { ...DEFAULT_CAVEMAN_CONFIG },
cavemanOutputMode: { ...DEFAULT_CAVEMAN_OUTPUT_MODE_CONFIG },
rtkConfig: { ...DEFAULT_RTK_CONFIG },
languageConfig: { ...DEFAULT_COMPRESSION_LANGUAGE_CONFIG },
stackedPipeline: normalizeStackedPipeline(undefined),
aggressive: normalizeAggressiveConfig(undefined),
ultra: normalizeUltraConfig(undefined),
contextEditing: { ...DEFAULT_CONTEXT_EDITING_CONFIG },
};
for (const row of rows) {
const record = toRecord(row);
const key = typeof record.key === "string" ? record.key : null;
const rawValue = typeof record.value === "string" ? record.value : null;
if (!key || rawValue === null) continue;
const parsed = parseJsonSafe(rawValue);
if (parsed === undefined) continue;
switch (key) {
case "enabled":
config.enabled = parsed === true;
break;
case "defaultMode":
if (typeof parsed === "string" && COMPRESSION_MODES.has(parsed as CompressionMode)) {
config.defaultMode = parsed as CompressionMode;
}
break;
case "autoTriggerMode":
if (typeof parsed === "string" && COMPRESSION_MODES.has(parsed as CompressionMode)) {
config.autoTriggerMode = parsed as CompressionMode;
}
break;
case "autoTriggerTokens":
config.autoTriggerTokens =
typeof parsed === "number" && Number.isFinite(parsed)
? Math.max(0, Math.floor(parsed))
: 0;
break;
case "cacheMinutes":
config.cacheMinutes =
typeof parsed === "number" && Number.isFinite(parsed)
? Math.max(1, Math.floor(parsed))
: DEFAULT_COMPRESSION_CONFIG.cacheMinutes;
break;
case "preserveSystemPrompt":
config.preserveSystemPrompt = parsed !== false;
break;
case "mcpDescriptionCompressionEnabled":
config.mcpDescriptionCompressionEnabled = parsed !== false;
break;
case "comboOverrides":
if (parsed && typeof parsed === "object") {
const overrides: Record<string, CompressionMode> = {};
for (const [comboId, mode] of Object.entries(parsed as Record<string, unknown>)) {
if (typeof mode === "string" && COMPRESSION_MODES.has(mode as CompressionMode)) {
overrides[comboId] = mode as CompressionMode;
}
}
config.comboOverrides = overrides;
}
break;
case "compressionComboId":
config.compressionComboId =
typeof parsed === "string" && parsed.trim() ? parsed.trim() : null;
break;
case "stackedPipeline":
config.stackedPipeline = normalizeStackedPipeline(parsed);
break;
case "cavemanConfig":
config.cavemanConfig = normalizeCavemanConfig(parsed);
break;
case "cavemanOutputMode":
config.cavemanOutputMode = normalizeCavemanOutputModeConfig(parsed);
break;
case "rtkConfig":
config.rtkConfig = normalizeRtkConfig(parsed);
break;
case "languageConfig":
config.languageConfig = normalizeLanguageConfig(parsed);
break;
case "aggressive":
case "aggressiveConfig":
config.aggressive = normalizeAggressiveConfig(parsed);
break;
case "ultra":
case "ultraConfig":
config.ultra = normalizeUltraConfig(parsed);
break;
case "contextEditing":
config.contextEditing = normalizeContextEditingConfig(parsed);
break;
}
}
// Store in TTL cache (5s expiry)
compressionSettingsCache = {
value: config,
expiresAt: Date.now() + 5000,
dbRef: new WeakRef(db),
};
return config;
}
export async function updateCompressionSettings(
updates: Partial<CompressionConfig>
): Promise<CompressionConfig> {
const db = getDbInstance();
const insert = db.prepare(
"INSERT OR REPLACE INTO key_value (namespace, key, value) VALUES (?, ?, ?)"
);
const tx = db.transaction(() => {
for (const [key, value] of Object.entries(updates)) {
if (value === undefined) continue;
insert.run(NAMESPACE, key, JSON.stringify(value));
}
});
tx();
backupDbFile("pre-write");
compressionSettingsCache = null;
invalidateDbCache();
return getCompressionSettings();
}
export function getDefaultAggressiveConfig(): AggressiveConfig {
return {
...DEFAULT_AGGRESSIVE_CONFIG,
thresholds: { ...DEFAULT_AGGRESSIVE_CONFIG.thresholds },
toolStrategies: { ...DEFAULT_AGGRESSIVE_CONFIG.toolStrategies },
};
}
export function getDefaultUltraConfig(): UltraConfig {
return { ...DEFAULT_ULTRA_CONFIG };
}
export function getDefaultRtkConfig(): RtkConfig {
return { ...DEFAULT_RTK_CONFIG };
}
function normalizeMcpAccessibilityConfig(value: unknown): McpAccessibilityConfig {
const record = toRecord(value);
return {
...DEFAULT_MCP_ACCESSIBILITY_CONFIG,
...record,
enabled: record.enabled !== false,
maxTextChars:
typeof record.maxTextChars === "number" && record.maxTextChars > 0
? Math.floor(record.maxTextChars)
: DEFAULT_MCP_ACCESSIBILITY_CONFIG.maxTextChars,
collapseThreshold:
typeof record.collapseThreshold === "number" && record.collapseThreshold > 0
? Math.floor(record.collapseThreshold)
: DEFAULT_MCP_ACCESSIBILITY_CONFIG.collapseThreshold,
collapseKeepHead:
typeof record.collapseKeepHead === "number" && record.collapseKeepHead >= 0
? Math.floor(record.collapseKeepHead)
: DEFAULT_MCP_ACCESSIBILITY_CONFIG.collapseKeepHead,
collapseKeepTail:
typeof record.collapseKeepTail === "number" && record.collapseKeepTail >= 0
? Math.floor(record.collapseKeepTail)
: DEFAULT_MCP_ACCESSIBILITY_CONFIG.collapseKeepTail,
minLengthToProcess:
typeof record.minLengthToProcess === "number" && record.minLengthToProcess > 0
? Math.floor(record.minLengthToProcess)
: DEFAULT_MCP_ACCESSIBILITY_CONFIG.minLengthToProcess,
};
}
export async function getMcpAccessibilityConfig(): Promise<McpAccessibilityConfig> {
const db = getDbInstance();
const row = db
.prepare("SELECT value FROM key_value WHERE namespace = ? AND key = ?")
.get(NAMESPACE, "mcpAccessibility") as { value: string } | undefined;
return normalizeMcpAccessibilityConfig(parseJsonSafe(row?.value ?? null));
}
export async function setMcpAccessibilityConfig(
value: Partial<McpAccessibilityConfig>
): Promise<void> {
const next = normalizeMcpAccessibilityConfig({ ...DEFAULT_MCP_ACCESSIBILITY_CONFIG, ...value });
const db = getDbInstance();
db.prepare("INSERT OR REPLACE INTO key_value (namespace, key, value) VALUES (?, ?, ?)").run(
NAMESPACE,
"mcpAccessibility",
JSON.stringify(next)
);
compressionSettingsCache = null;
invalidateDbCache();
}