8000 Releases · dominicrico/jev-router · GitHub
[go: up one dir, main page]
Skip to content

    • Releases

    v0.5.0

    v0.5.0 Latest
    Latest

    Choose a tag to compare

    View all tags
    @dominicrico dominicrico released this 23 Oct 12:37
    v0.5.0
    57cde57
    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    GPG key ID: B5690EEEBB952194
    Verified
    Learn about vigilant mode.

    Added

    • router option: jev (TypeSafe, default), laya or kev (self-hosted), each with its own default endpoint, model id and key variable (TYPESAFE_API_KEY, LAYA_API_KEY, KEV_API_KEY). routerModel and routerUrl override them. /jev status shows the active router.
    • Configurable routerModel and routerUrl options, to route with a pinned Jev version or a hosted Laya or Kev.

    Fixed

    • An invalid effortCap or ceiling value now falls back to the lean values (medium, sonnet). Before, it fell back to high and no ceiling, so a typo quietly raised cost.
    • The router timeout timer is cancelled as soon as the router answers, so no stray timer is left behind each step.
    • /jev lists every command in its unknown-option reply (preset, ceiling, floor, stats clear were missing).
    • The effortCap setting help text no longer repeats itself.

    Security

    • A TypeSafe key from /jev key or TYPESAFE_API_KEY is only sent to api.typesafe.ai, never to a custom routerUrl.
    Assets 2
    Loading

    v0.4.2

    v0.4.2

    Choose a tag to compare

    View all tags
    @dominicrico dominicrico released this 12 Oct 07:41
    v0.4.2
    39712e3
    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    GPG key ID: B5690EEEBB952194
    Verified
    Learn about vigilant mode.

    [0.4.2] - 2026-10-12

    Fixed

    • An explicit model on a subagent's Agent call is now kept for its whole life. Before, the subagent's first step asked Jev and replaced it. Every spawn outcome (explicit model, routed pick, failed pick) is now recorded, so a subagent never asks Jev again behind a decision made at spawn.
    • The band no longer drops what other plugins draw above the prompt: it composes with them (theirs above, the band last, right above the input), also when routing is off.
    Loading

    v0.4.1

    v0.4.1

    Choose a tag to compare

    View all tags
    @dominicrico dominicrico released this 10 Oct 20:35
    v0.4.1
    8434b75
    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    GPG key ID: B5690EEEBB952194
    Verified
    Learn about vigilant mode.

    [0.4.1] - 2026-10-10

    Fixed (documentation, corrected measurements)

    • Re-measured the long-session benchmark with 5 sessions per strategy and the new lean default. The guard still cuts model switches (6 to 7 down to 1) and halves cache re-writes, but it does not lower cost: guard on and off both cost +42% against Opus. The earlier "+24% vs +38%" (3 sessions) was noise and is retracted. lean averaged the same cost as Opus in long warm sessions (range $0.26 to $0.63 per session); plain Sonnet was 43% cheaper. README, benchmarks, site and charts updated.
    Loading

    v0.4.0

    v0.4.0

    Choose a tag to compare

    View all tags
    @dominicrico dominicrico released this 10 Oct 07:46
    v0.4.0
    19cd162
    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    GPG key ID: B5690EEEBB952194
    Verified
    Learn about vigilant mode.

    [0.4.0] - 2026-10-10

    Changed (behaviour change)

    • The default is now the lean preset: a Sonnet ceiling and effort capped at medium. Chosen by a pre-registered rule on 100 more graded runs: 39/40 hard tasks done against 38/40 for always-Opus and always-Sonnet, at $0.064 per run against $0.163 (Opus) and $0.062 (Sonnet); 18/18 on the multi-step set at $0.061 per run. Opus is still used when Jev is at least 90% sure (ceilingBreak). To keep the old behaviour set preset: balanced (or /jev preset balanced).

    Added

    • /jev preset lean|balanced|max and a preset option; /jev status shows the active preset.
    • Benchmark harness: > strategy filter, a lean strategy, and an opt-in Wilson interval for pass rates (CI=1). CI checks that the shipped defaults match the lean preset.
    Loading

    v0.3.0

    v0.3.0

    Choose a tag to compare

    View all tags
    @dominicrico dominicrico released this 09 Oct 14:57
    v0.3.0
    a38d8bf
    This commit was created on GitHub.com and signed with GitHub’s verified signature.
    GPG key ID: B5690EEEBB952194
    Verified
    Learn about vigilant mode.

    [0.3.0] - 2026-10-09

    Added

    • The band shows the model that really ran the last step. A mismatch reads sonnet (picked opus); after a Jev failure it shows the session model instead of "waiting for the first task"; it flips from warm to cold on its own.
    • Model ceiling and floor (ceiling, floor, ceilingBreak, /jev ceiling, /jev floor), applied before the cache guard. Off by default. A sonnet ceiling finished 20/20 hard tasks at half the cost of opus.
    • A real long-session benchmark (benchmarks/session.mts, one process per session via stream-json) and a debug line with the cache state per Jev call.

    Changed

    • README and charts now use the measured long-session numbers. The earlier simulation's "3x more" is replaced by +38% (guard off) and +24% (guard on) against opus, and the README says plainly that in a long warm session routing cost more than staying on opus.
    Loading

    v0.2.0

    v0.2.0

    Choose a tag to compare

    View all tags
    @dominicrico dominicrico released this 09 Oct 13:20
    v0.2.0
    87a0f4b

    [0.2.0] - 2026-10-09

    Added

    • Per-step routing: Jev is asked again before every step of a task, not only at the prompt (routeSteps).
    • Per-subagent routing: each subagent is routed at spawn from its full task prompt, sets the subagent's model and tags its description in the subagent list (routeSubagents). Verified live.
    • Effort cap, high by default, so the xhigh/max that Jev suggests on hard tasks no longer drives cost above always-opus. Lift it for one prompt with a !full prefix or /jev full; change it with /jev cap <effort|none> or the effortCap option. The band shows the cap (⤓xhigh) and the unlock (🔓).
    • Circuit breaker: three failed Jev calls in a row pause routing, then it recovers; strict stickiness with a warm cache makes no step calls.
    • Per-prompt markers: !opus, !sonnet, !haiku, !fable pin a model and skip Jev; !cheap, !efficient set the mode; they combine with !full.
    • Escalation: after escalateAfter failed tool calls in a row the rest of the task moves up one model (verified live).
    • Estimated savings tally in /jev status against baselineModel, kept across sessions; /jev stats clear resets it.
    • Privacy: redact (on by default), sendHistory, maxTaskChars, and an opt-in local fallback: heuristic when Jev is down.
    • A debug log line per Jev call (jev prompt|step N|agent), used to verify the above live.
    • CI workflow, band render test and an animated band GIF.
    • Benchmark on harder tasks graded by hidden tests (100 real runs). On those tasks plain sonnet did as well as opus and cost 61% less; jev-router sits between them.
    • Benchmarks for the effort cap and for multi-step and subagent routing on tasks with tools, with updated README images.

    Changed

    • Ponytail cleanup pass over the hook module: one subagent router, one usage tally (steps per model, in /jev status), shared benchmark helpers, and the band GIF now renders the real segments() so it cannot drift.

    Fixed

    • Secret redaction now catches lowercase names (password=, client_secret:, api_key=), JSON keys ("apiKey": "...") and user:password@ in URLs, and no longer mangles type words like token: string.
    • A pinned model (!opus) now works without a Jev key, and the marker no longer sticks to the next prompt. A prompt with no key no longer runs on the previous task's pick.
    • The hard-task benchmark's hidden tests and reference solutions are sealed in an archive and unpacked only into a random temp directory while grading, so an agent cannot read them from disk. (A first run was discarded because they were readable.)
    • Background-task notifications no longer trigger a Jev call or overwrite the task text.
    • Spinner leak: the band ticker now stops on turn.complete and on /jev commands, and cancels itself if a prompt never completes.
    Loading

    v0.1.0

    v0.1.0

    Choose a tag to compare

    View all tags
    @dominicrico dominicrico released this 09 Oct 12:09
    v0.1.0
    310a1a3

    First release: Jev model and effort routing per prompt, per step and per subagent, effort cap (default high) with !full unlock, cache stickiness, the band above the prompt, /jev commands and benchmarks.

    Loading
    0