can1357 b6559861d0 feat(cli): standardized throughput calculation to total duration ...

- Removed the `computeTokensPerSecond` helper function in favor of a direct calculation.
- Standardized throughput to use total request duration instead of post-TTFT decode time.
- Updated UI usage display to calculate tokens per second against total duration.
- Prevented over-inflation of throughput metrics caused by hidden reasoning tokens.

2026-07-12 01:06:24 +02:00

..

advisor

fix(advisor): kept defaults for invalid tools

2026-07-11 06:14:11 +00:00

async

feat(coding-agent): enabled asynchronous background task execution

2026-07-11 16:17:03 +02:00

auto-thinking

feat(coding-agent): centralized preprocessing and guidance for small models

2026-07-11 12:28:18 +02:00

autolearn

fix(agent): kept autolearn memory prompts cache-stable

2026-06-28 18:10:57 +00:00

autoresearch

fix(autoresearch): guarded before_agent_start against undefined event.systemPrompt

2026-06-27 15:51:31 +00:00

capability

…

cli

feat(cli): standardized throughput calculation to total duration

2026-07-12 01:06:24 +02:00

collab

fix collab reconnect backpressure drain

2026-07-05 13:25:26 +02:00

commands

feat(ai): added cache invalidation command for usage reports

2026-07-11 20:55:19 +02:00

commit

feat(coding-agent-task): implemented agent-centric flat task structure

2026-07-11 13:44:04 +02:00

config

feat(coding-agent): implemented interactive fallback chain configuration

2026-07-11 22:03:35 +02:00

dap

fix(debug): stopped native fallback for missing delve

2026-07-10 14:06:57 +02:00

debug

fix(debug): guarded v8.setFlagsFromString call so CPU profiler works on Bun

2026-06-30 12:47:07 +00:00

discovery

feat(coding-agent): updated thinking-level configuration and precedence

2026-07-11 13:35:05 +02:00

edit

fix(coding-agent): decoupled lsp diagnostics from tool execution

2026-07-11 07:33:19 +02:00

eval

fix(coding-agent): hardened same-realm runtime guards from PR review

2026-07-10 12:33:53 +02:00

exa

…

exec

Merge remote-tracking branch 'origin/farm/872f49e0/fix-commit-false-success'

2026-07-11 07:41:28 +02:00

export

perf(export): skip TTSR delta buffering when no rule matches text/thinking

2026-07-02 17:29:50 +09:00

extensibility

fix(plugins): skipped invalid custom tool entries

2026-07-11 14:31:07 +00:00

goals

refactor(coding-agent): streamlined codebase by deduplicating helper logic and shims

2026-07-02 02:40:08 +02:00

hindsight

fix(mnemopi): stripped retention markers from embeddings

2026-07-03 04:59:02 +00:00

internal-urls

fix: handle stale tests

2026-07-11 07:54:19 +02:00

irc

feat(coding-agent): implemented resumable subagent yielding for tasks

2026-07-11 17:27:35 +02:00

jsonrpc

refactor(coding-agent): consolidated message framing logic

2026-06-22 05:29:00 +02:00

lib

…

lsp

fix(coding-agent): decoupled lsp diagnostics from tool execution

2026-07-11 07:33:19 +02:00

markit

fix(coding-agent): handled inline image pdf delimiters

2026-07-04 12:18:06 +00:00

mcp

Merge remote-tracking branch 'origin/farm/903c642e/fix-stdio-tcc-spawn'

2026-07-11 07:38:17 +02:00

memories

feat(coding-agent): removed canonical model variant selection and tracking

2026-07-01 05:22:42 +02:00

memory-backend

fix(agent): kept autolearn memory prompts cache-stable

2026-06-28 18:10:57 +00:00

mnemopi

fix(mnemopi): made recall fact ids resolvable via memory reads

2026-07-09 18:27:23 +02:00

modes

feat(cli): standardized throughput calculation to total duration

2026-07-12 01:06:24 +02:00

plan-mode

fix(coding-agent): prevented asynchronous write races in plan reviews

2026-07-02 02:19:26 +02:00

prompts

feat(coding-agent): implemented resumable subagent yielding for tasks

2026-07-11 17:27:35 +02:00

registry

feat(coding-agent): supported advisor transcript persistence

2026-06-19 03:50:00 +02:00

secrets

fix(coding-agent): hid secrets from advisor prompts

2026-06-22 07:05:23 +00:00

session

feat(storage): implemented persistent model performance tracking and migration

2026-07-12 01:06:19 +02:00

slash-commands

feat(coding-agent): introduced sequential message queueing and commands

2026-07-11 22:07:51 +02:00

ssh

Merge remote-tracking branch 'origin/farm/16f7ef23/ssh-helper-timeouts'

2026-07-02 23:43:11 +02:00

stt

style: bun run fix

2026-07-01 00:07:30 +00:00

subprocess

fix(tiny): repaired cuda sidecars for auto gpu requests

2026-07-03 18:34:56 +00:00

task

feat(coding-agent): implemented resumable subagent yielding for tasks

2026-07-11 17:27:35 +02:00

tiny

fix(coding-agent): preserved chat envelope in title preprocessing

2026-07-11 12:47:02 +02:00

tool-discovery

refactor(coding-agent): migrated tool schema helpers to toolWireSchema

2026-06-18 01:57:23 +02:00

tools

feat: removed redundant pre-execution bash command fixup logic

2026-07-11 18:28:32 +02:00

tts

feat(coding-agent): supported streaming TTS for long text inputs

2026-07-06 04:12:39 +02:00

tui

feat(coding-agent): refactored eval tool to single-step execution

2026-06-23 00:59:58 +02:00

utils

feat(coding-agent): centralized preprocessing and guidance for small models

2026-07-11 12:28:18 +02:00

vibe

feat(coding-agent): enabled asynchronous background task execution

2026-07-11 16:17:03 +02:00

web

fix(coding-agent): guarded browser header generation

2026-07-11 11:41:45 +00:00

cli-commands.ts

feat: add manual coding-agent gc command

2026-06-26 08:39:50 +01:00

cli.ts

fix(coding-agent): dispatched CLI entry in Bun.build-compiled windows binaries

2026-07-11 11:08:55 +02:00

config.ts

…

cursor.ts

feat(coding-agent/tools)!: replaced paths arrays with path strings

2026-07-02 08:30:33 +02:00

index.ts

refactor(coding-agent): integrated zod validation and upgraded typebox shim

2026-06-18 01:57:23 +02:00

main.ts

fix(coding-agent): bound startup changelog rendering

2026-07-11 02:28:27 +00:00

priority.json

config(coding-agent): extended model priority lists

2026-06-27 04:34:39 +02:00

sdk.ts

feat(coding-agent): improved vibe mode tool lifecycle management

2026-07-11 07:33:20 +02:00

startup-splash.ts

fix(coding-agent): tighten startup splash review coverage

2026-06-17 10:53:08 -04:00

system-prompt.test.ts

feat: introduced max reasoning effort tier across model and rpc systems

2026-07-10 13:39:42 +02:00

system-prompt.ts

feat(coding-agent): centralized task orchestration and prompt policy logic

2026-07-11 00:03:53 +02:00

telemetry-export.ts

…

thinking.ts

feat: introduced max reasoning effort tier across model and rpc systems

2026-07-10 13:39:42 +02:00

workspace-tree.ts

feat: standardized elision markers and improve transcript viewer robustness

2026-06-19 04:35:18 +02:00