Changelog

What’s new in Tempr

Every release of every Tempr product, newest first. Everything here is live: the extensions update through their marketplaces, and the Gateway and the Portal update for everyone on the date shown.

75releases
337changes
Sep 22last update

Subscribe via RSS Read the docs

Latest release of each product

GatewayUpdated VS Code1.1.6 JetBrains1.1.6 Visual Studio2.2.30 CLI0.9.1 PortalUpdated

75 releases, 337 changes since Jul 31, 2026

September 2026

Gateway

Update

Latest

Added

  • Other labs' reasoning on /v1/messages — when a Messages API request runs on a model that reasons outside Claude, such as DeepSeek, Z.AI, Moonshot or Xiaomi MiMo, its reasoning now comes back as a thinking block ahead of the text and tool calls, with thinking_delta events when streaming. Those blocks carry the signature tempr:reasoning. Send them back unchanged, as Claude Code does, and models that need their earlier reasoning across tool calls get it back as reasoning_content. When a later turn goes to Claude, Tempr leaves these blocks out, because Claude would reject their signature. See the Messages API section.

Changed

  • Perplexity now runs on Perplexity's Agent API, which replaces the Sonar chat completions it retires on 2026-09-27. Perplexity already refuses Sonar requests from newer API keys. The models are now its presets: perplexity/fast, low, medium, high and xhigh. The Sonar ids keep working, including in virtual-key allowlists, and run as the matching preset: sonar as fast, sonar-pro as low, sonar-reasoning-pro as medium, sonar-deep-research as high. Answers still return citations and search_results as Sonar did. Usage is billed at the cost Perplexity reports, which includes its web-search fees, and is returned as usage.cost. Presets set their own reasoning, so these models don't offer a reasoning level. See Perplexity.

Fixed

  • Claude's thinking blocks on /v1/messages now keep Claude's own signature when Tempr translates the request: Claude on AWS Bedrock, OpenRouter's anthropic/… models, and Anthropic models with response caching. Claude 4.7 and later, whose thinking text is empty, now return their block instead of none, and redacted thinking comes back as a redacted_thinking block. Blocks you send back reach Claude on the next turn, so its reasoning carries through a tool call.
  • When Claude on AWS Bedrock or OpenRouter rejects a thinking block's signature sent back in a later turn, Tempr now retries once without that thinking instead of returning the 400, as it already did for Anthropic.
  • A response-cache hit for a request that was first answered as a stream now replays the model's reasoning along with the answer.
JetBrains

1.1.6

Latest

Added

  • Cloud sync switch — Tempr Settings now has a Cloud sync switch in the Account card. Turn it off and Tempr stops storing your chats, custom agents and tool preferences on your Tempr account; your chats stay on this machine. The switch belongs to your account, so it covers every machine and every Tempr extension signed in to it, and you can also change it in the Tempr Portal. Turning it off offers to delete what's already stored, and Delete synced data does that at any time. Sync stays on unless you turn it off.
Visual Studio

2.2.30

Latest

Added

  • Cloud sync switch — Tools > Options > Tempr > General has a new setting, Sync chats and settings to your Tempr account. Turn it off and Tempr stops storing your chats, tool preferences, custom agents and code search index on your Tempr account. Your chats stay on this machine. The setting belongs to your account, so it covers every machine and every Tempr extension signed in to it, and it takes effect as soon as you change it. When you turn it off, Tempr asks whether to also delete what's already stored. Delete synced data... does that at any time and ends any share links. Sync stays on unless you turn it off.

Fixed

  • Your solution's code search index never reached your Tempr account: every upload failed without a message. Uploads now work, and each solution's existing local index is uploaded once. Until the synced index has caught up, search keeps ranking with the index on your machine, so results never get worse while it fills.
CLI

0.9.1

Latest

Changed

  • An unknown flag is an error — a mistyped option such as --aproval-mode bypass now stops with "Unknown option" and exit code 2. Before, the CLI dropped it silently and ran anyway, in this case in the default approval mode. To send a prompt that starts with a dash, put -- before it.

Fixed

  • A command line that doesn't parse, such as an extra word after the prompt, now exits 2 as documented. It exited 255 (127 from Git Bash).
  • A run whose saved session can't be used, because it has no token or expired and couldn't be refreshed, now exits 3 (not signed in) instead of 1.
  • When tempr doctor can't reach the server, it now names the variable that sets it, TEMPRAPP_SERVER_URL (or serverUrl in config.json). It named TEMPR_SERVER_URL, which the CLI doesn't read.
Gateway

Update

Added

  • POST /v1/embeddings — OpenAI's embeddings API on your own provider keys: OpenAI, Azure OpenAI, Azure AI Foundry, Google, Mistral, Cohere, AWS Bedrock (Titan Text and Cohere Embed), DeepInfra, Together AI, Fireworks AI, Nscale, OpenRouter and custom models. encoding_format: "base64" works on every provider, and input_type passes the document or query hint to Cohere and Gemini. The same keys, allowlists, limits, budgets, fallback chains and request logs apply as for chat, and cost is input tokens only. See Embeddings.
  • OpenAI's pro and codex models — OpenAI serves models such as gpt-5-pro, o3-pro and gpt-5.3-codex only on its Responses API, so they used to fail on /v1/chat/completions and /v1/messages. Tempr now bridges those calls to the Responses API and back, streaming included.
  • Xiaomi MiMo v2.6 — MiMo v2.6 models are listed and priced.

Changed

  • /v1/models lists chat models only by default — tools that fill a chat model picker from it no longer get embedding models. Add ?type=embedding for the embedding models, or ?type=all for both. Each model now has a type of language or embedding.
  • Reasoning effort max on newer OpenAI models — gpt-5.6, its luna, sol and terra variants, and gpt-6-astra take max only on OpenAI's Responses API. A request at max now goes there, and gets the deepest reasoning, instead of quietly running at the model's default.
  • Function tools on those models — a request with function tools and reasoning on now goes straight to the Responses API. The same model's other requests stay on chat completions, where parameters like stop and seed still apply.
  • When a provider rejects the reasoning level you asked for, Tempr now retries at the nearest level the provider lists instead of dropping reasoning altogether. x-tempr-reasoning-effort reports what the retry sent.
  • OpenAI models past their shutdown date, and OpenAI's completions-only models, are no longer listed.
  • Xiaomi's speech and transcription models are no longer listed, since they don't chat.

Deprecated

  • Xiaomi MiMo v2.5 — mimo-v2.5 and mimo-v2.5-pro stop working at Xiaomi on 2026-10-21 at 02:00 UTC and leave the model list then. Move to MiMo v2.6.

Fixed

  • Tool calls from Google's Gemini and Gemma models came back with finish_reason: "stop" (end_turn on /v1/messages), so agent loops ended the turn instead of running the tool. They now return tool_calls (tool_use).
  • Turning reasoning off for Gemma 4 on the Gemini API failed with a 400, and turning it on had no effect. Both now work.
  • A connection to a provider that dropped before it answered ended in a 500. Tempr now retries it like a provider 5xx, and then answers 502 upstream_unreachable, so fallback chains and backup keys take over.
  • Usage on Xiaomi MiMo models was recorded at $0. It's now priced.
  • /v1/messages requests to gpt-6 models failed on max_tokens. GPT-6 models now get max_completion_tokens and no temperature, as GPT-5 models do.
VS Code

1.1.6

Latest

Added

  • Cloud sync switch — Tempr: Open Settings now has a Cloud sync switch in the Account card. Turn it off and Tempr stops storing your chats, custom agents and tool preferences on your Tempr account; your chats stay on this machine. The switch belongs to your account, so it covers every machine and every Tempr extension signed in to it, and you can also change it in the Tempr Portal. Turning it off offers to delete what's already stored, and Delete synced data does that at any time. Sync stays on unless you turn it off.
JetBrains

1.1.5

Fixed

  • If your IDE can't run its built-in browser (JCEF), for example because it was started on a Java runtime without it, Tempr no longer raises an IDE error every time a project opens. The Tempr panel instead explains why the chat can't start, with a link to Choose Boot Java Runtime for the IDE so you can switch to a runtime that includes JCEF.
Visual Studio

2.2.29

Security

  • Automatic error reports no longer include your license key. A report is now linked to your account by your signed-in session. It carries only that session's activation ID, the error message and the stack trace.
Portal

Update

Latest

Added

  • Cloud sync switch — the Profile page has a Cloud sync card. Turn it off and the Visual Studio, VS Code and JetBrains extensions stop storing your chats, tool preferences, custom agents and code search index on Tempr's servers. It's one setting for your whole account, so it covers every machine and every extension signed in to it. Sync stays on unless you turn it off, and Delete synced data removes what's already stored at any time.
  • Team request logs — organization owners and admins can now read the requests made with the organization's keys, under Organization > Team request logs. The list shows metadata only; opening a request that holds captured content is recorded in the organization's audit log.

Changed

  • Closing your account takes effect straight away — Close account has moved to the Profile page, where every user can reach it. It now deletes your account and everything tied to it at once: license keys, synced chats and settings, provider keys, Gateway keys and logs, MCP credentials, prompt templates, sign-in history and usage history. Your subscriptions are cancelled, and any unbilled Gateway overage is charged first. If you own an organization, it closes too and its members are emailed; their own accounts stay. To use the rest of a paid period, cancel from the Plan page first and close your account later. See the privacy policy.
  • Sign-in locations on the Security page are now worked out on Tempr's own servers, so your sign-in IP addresses are no longer sent to an outside lookup service. The page also loads faster.
  • Very small Gateway costs now read "<$0.0001" instead of "$0.0000".

Fixed

  • Saving a custom model endpoint that answers slowly now shows a spinner while it's checked, ignores a second click, and ends with a clear timeout message naming the step that ran out of time. An endpoint that's out of credit says so.
  • The Playground's model list no longer repeats the provider name in model ids (such as openai/openai/gpt-5), which made those requests fail.
  • Azure OpenAI deployments that only work through OpenAI's Responses API can now be saved.
  • The org-wide Sessions and End users pages no longer link to a detail page that couldn't open.

Security

  • Captured Gateway request content is now redacted in every case where redaction applies.
  • When a Team subscription ends, or an owner removes a member, that member's Team access and signed-in devices end straight away.
  • Organization invitations can only grant the Member or Admin role.
Gateway

Update

Added

  • Nscale — Nscale's hosted open-weight models are available with your Nscale key as nscale/…, and usage is priced from Nscale's catalog.
  • Reasoning control on inference hosts — the reasoning object and reasoning_effort now work on DeepInfra, AWS Bedrock, Together AI and Fireworks AI, each in the host's own format. On Bedrock, Claude gets thinking and effort, and Amazon Nova 2 gets its reasoning config. A few models report no levels because their host can't steer them reliably, such as GLM on Together AI. Hugging Face reports none because it routes each model to a host it picks. GET /v1/models shows each model's reasoning_options. See Reasoning.

Fixed

  • Claude on AWS Bedrock now returns its reasoning as reasoning and reasoning_details, and reasoning you send back reaches the model, which a thinking Claude needs across a tool call.
JetBrains

1.1.4

Changed

  • Google's Gemini models are now listed as google/… instead of gemini/…, the same name OpenRouter, Vercel's AI Gateway and models.dev give them, so a model id copied from any of those works in Tempr as it is. Nothing you have set needs changing: your chat model, inline-completion model, per-agent models and reasoning levels follow the new name by themselves, and the old gemini/… name keeps working everywhere.
Visual Studio

2.2.28

Changed

  • Google's Gemini models are now listed as google/… instead of gemini/…. That's the name OpenRouter, Vercel's AI Gateway and models.dev give them, so a model ID copied from any of those works in Tempr as it is. You don't need to change anything: your chat model, inline-completion model, per-persona models and reasoning levels move to the new name on their own, and the old gemini/… name still works everywhere.
CLI

0.9.0

Added

  • First public release — Tempr's bring-your-own-key coding agent in the terminal, on the same license, provider keys and models as the IDE extensions. Sign in with tempr auth, pick a default model with tempr config set-model <id>, and tempr doctor checks that everything is set up. The quickstart walks through it, and the command reference lists every command and flag.
  • Install in one line — curl -fsSL https://temprhq.io/cli/install.sh | sh on macOS and Linux, or irm https://temprhq.io/cli/install.ps1 | iex on Windows. The builds are self-contained, so nothing needs installing first. Direct downloads for Windows, macOS and Linux on x64 and Arm64 are on the CLI page, each with a .sha256 beside it, and tempr update tells you when a newer release is out and how to install it.
  • Three ways to run — tempr "<prompt>" runs one agent turn and exits, tempr on its own opens an interactive session with persistent history, line editing and Tab completion, and <something> | tempr reads its prompt from piped input for scripts. tempr --ask "<prompt>" is plain chat with no tools.
  • A real agent loop — the agent reads, writes and edits files, runs commands, searches your code by meaning and by symbol, reads build diagnostics, and discovers and runs tests, all against the current directory. Every file path is checked against the workspace, including through symbolic links and Windows junctions.
  • Approval modes — file edits, commands and MCP calls ask first by default (interactive). autopilot runs edits and allow-listed commands unattended and still asks before anything that deletes, force-pushes, resets or reboots; bypass runs edits and asks for every command. Set the default with tempr config set-approval-mode, or use --approval-mode or -y for one run. Add allow-listed commands with tempr config allow-command, or per repository in an .agentcommands.json file.
  • Personas and your own agents — tempr "@debugger why does this fail" runs a specialist persona, and /persona switches for the rest of a session. Your own slash commands and agents are Markdown files in .tempr/commands/ and .tempr/agents/, in a project or in your home folder.
  • Context in a message — @path/to/file attaches a file (images go in as images), @workspace adds an overview of the workspace, and @problems adds your current build errors. Every agent turn also carries AGENTS.md and .github/copilot-instructions.md from the current directory, plus a global ~/.tempr/AGENTS.md. tempr init drafts an AGENTS.md from a scan of the workspace.
  • Sessions you can pick up again — every session is saved and encrypted at rest. tempr -c resumes this folder's most recent one, /resume picks from a list, --id resumes a specific one, and tempr history lists, shows, renames, forks and deletes them. /diff shows what the last turn changed on disk and /undo puts it back, skipping any file that has changed since.
  • Models and reasoning — tempr models lists the models your license can use, with prices and context sizes, and /model opens a picker over them. -m overrides the model for one run. /reasoning sets how much the model reasons, saved per model, and --reasoning overrides it for one run.
  • MCP servers — tempr mcp add connects your own Model Context Protocol servers, tempr mcp browse installs one from Tempr's curated catalog, and list, remove, enable and disable manage them.
  • Scripting and CI — --json writes one event per line and then a final result object, and the exit code says how the run ended (finished, failed, a usage error, not signed in, step limit reached, a tool call refused, or interrupted). --max-turns, --allowed-tools, --disallowed-tools and --prompt-file shape an unattended run, and TEMPR_LICENSE_KEY signs in without putting the key on a command line. With no terminal to ask on, a tool call that would have asked is refused instead of waiting. See Scripts, pipes & CI.
  • Usage and cost — --verbose prints token usage and cost after each turn, and tempr usage shows what this machine's turns have cost, by model.
  • Shell completion — tempr completion bash|zsh|fish|powershell prints a completion script.
  • Crash reports are opt-in — the first interactive session asks once, and tempr config set-crash-reports on|off changes it. Nothing is sent without a terminal to ask on, or when CI, DO_NOT_TRACK or TEMPR_NO_CRASH_REPORTS is set. There's no other telemetry.
Portal

Update

Added

  • Nscale — Nscale is now available as a provider key for Chat, the Gateway and organization keys.
  • Reasoning in the Playground — a Reasoning dropdown in the Gateway Playground sets how much the model thinks before it answers, from Off to Max, or the model's own default. Each reply shows the level that was actually applied, since a level the model lacks is sent as the nearest one it has.

Changed

  • Google's Gemini API key is now listed as Google Gemini, and Gateway usage, logs and analytics show Gemini models under google/. Keys, allowlists and fallback chains you saved under the old name keep working.
Gateway

Update

Added

  • Reasoning control — set how much a model thinks with OpenRouter's reasoning object or OpenAI's reasoning_effort on /v1/chat/completions, thinking and output_config.effort on /v1/messages, or reasoning.effort on /v1/responses. Tempr sends it in each lab's own format. A level the model lacks becomes the nearest one it has, and the x-tempr-reasoning-effort response header says what was applied. A malformed value returns 400 invalid_reasoning. See Reasoning.
  • Claude's reasoning on chat completions — Claude's thinking now comes back as reasoning and reasoning_details, streamed and not. Send the assistant message back with reasoning_details unchanged and Claude gets its thinking blocks, which a tool-calling turn needs.
  • Refusals you can see — a model that declines now finishes with content_filter, as in OpenAI's API, with Claude's explanation in the refusal field (delta.refusal when streaming). Before, Claude's refusals read as an empty, normal stop. Gemini's safety, recitation and blocked-prompt stops are content_filter too. /v1/messages reports a refusal with stop_details, and /v1/responses as a refusal content part. Refusals are never cached.

Changed

  • Google's Gemini models are now google/… instead of gemini/…, the same prefix OpenRouter, Vercel's AI Gateway and models.dev use. gemini/… keeps working permanently, and your keys' allowlists and fallback chains were updated to match.

Fixed

  • Requests to openrouter/… models were rejected by OpenRouter with a 400, and an OpenRouter stream could be cut off right after [DONE].
  • Gemini's thinking tokens are now counted in usage.
  • A model id using a provider's older name, such as azure_openai/…, could reach the provider with that prefix still on it and fail. Old names now resolve fully.
VS Code

1.1.4

Changed

  • Google's Gemini models are now listed as google/… instead of gemini/…, the same name OpenRouter, Vercel's AI Gateway and models.dev give them, so a model id copied from any of those works in Tempr as it is. Nothing you have set needs changing: your chat model, inline-completion model, per-agent models and reasoning levels follow the new name by themselves, and the old gemini/… name keeps working everywhere.
VS Code

1.1.3

Added

  • Reasoning level — a Reasoning dropdown beside the model dropdown sets how much the model thinks before it answers: Default (the model's own setting), Off, or the levels that model offers, from Minimal to Max. Tempr remembers your pick for each model, and it applies when you use a Tempr model from Copilot Chat too. The dropdown only appears for models that have reasoning control, and a level a model lacks is sent as the nearest one it has.

Fixed

  • After you first signed in, the model dropdown could stay empty for up to five minutes. It now fills in right away.
JetBrains

1.1.3

Added

  • Reasoning level — a Reasoning dropdown beside the model dropdown sets how much the model thinks before it answers: Default (the model's own setting), Off, or the levels that model offers, from Minimal to Max. Tempr remembers your pick for each model. The dropdown only appears for models that have reasoning control, and a level a model lacks is sent as the nearest one it has.

Fixed

  • The Tempr tool window's sidebar icon was drawn at the full size of the logo. It's now the same size as the other tool window icons, in both the classic and the new UI.
Visual Studio

2.2.27

Added

  • Reasoning level — a new Reasoning dropdown beside the model dropdown sets how much the model thinks before it answers. The choices are Default (the model's own setting), Off, and whichever levels that model offers, from Minimal to Max. Tempr remembers your choice for each model. The dropdown only appears for models that support reasoning control, and a level a model doesn't have is sent as the nearest one it does.
VS Code

1.1.2

Added

  • Settings follow you with Settings Sync — with VS Code Settings Sync turned on, your Tempr settings reach your other machines: the chat model, approval mode, inline completions, agent limits, chat font size and the rest. MCP servers and auto-approved commands stay on each machine, and custom agents keep syncing through your Tempr account.

Security

  • A repository's .vscode/settings.json can no longer point Tempr at a different server. The development override moved from the tempr.serverUrl setting to the TEMPRAPP_SERVER_URL environment variable, the same one Visual Studio reads.
  • A repository's .vscode/settings.json can no longer change Tempr's settings, such as switching approval mode to Autopilot, pre-approving commands, or adding MCP servers or custom agents. Tempr now reads tempr.* values only from your user settings.
  • A symbolic link or Windows junction inside your workspace can no longer lead Tempr's file tools outside it. Reading, writing, patching and searching files now follow a link to where it really goes, and refuse it when that's outside the workspace.
  • Every spelling of a delete command is now treated as destructive, so it asks for approval every time, in every approval mode, and can't be trusted for the session. Before, rm -fr and Remove-Item -Force -Recurse weren't recognized, so approving rm -fr build once trusted rm -fr on any path for the rest of the session. Tempr now goes by the command itself (rm, rmdir, rd, del, erase, Remove-Item, ri, unlink), whatever its flags or a sudo in front.
JetBrains

1.1.2

Security

  • A symbolic link or Windows junction inside your project can no longer lead Tempr's file tools outside it. Reading, writing, patching, listing and searching files now follow a link to where it really goes, and refuse it when that's outside the project.
  • Every spelling of a delete command is now treated as destructive, so it asks for approval every time, in every approval mode, and can't be trusted for the session. Before, rm -fr and Remove-Item -Force -Recurse weren't recognized, so approving rm -fr build once trusted rm -fr on any path for the rest of the session. Tempr now goes by the command itself (rm, rmdir, rd, del, erase, Remove-Item, ri, unlink), whatever its flags or a sudo in front.
Visual Studio

2.2.26

Security

  • A symbolic link or Windows junction inside your solution can no longer lead Tempr's file tools outside it. Reading, writing, patching, listing and searching files now follow a link to where it really goes, and refuse it if that's outside the solution. A link that points back at one of its own parent folders no longer sends a search into a loop.
  • Every spelling of a delete command now counts as destructive, so it asks for approval every time, in every approval mode, and can't be trusted for the session. Before, rm -fr and Remove-Item -Force -Recurse weren't recognized, so approving rm -fr build once trusted rm -fr on any path for the rest of the session. Tempr now goes by the command itself (rm, rmdir, rd, del, erase, Remove-Item, ri, unlink), whatever its flags and even with sudo in front.
Gateway

Update

Added

  • Custom models — call models on your own OpenAI-compatible server (vLLM, SGLang, LiteLLM and others) as custom/<alias>, on every Gateway plan. Add the endpoint and its models in the Portal; Tempr checks each with a test call before saving, and you can give each model its own prices. See Custom models.

Fixed

  • An error from a custom endpoint now names the endpoint, for example "The custom endpoint 'Prod vLLM' rejected its key (401)".
  • A provider error whose error field is a plain string, such as {"error": "Model is loading"}, came back as a 500 from Tempr. It now comes back as the provider's error.

Security

  • Tempr doesn't follow redirects from a custom endpoint. A redirect is answered with a 502 that says so.
Portal

Update

Added

  • Authenticator app sign-in — on the Profile page you can set up an authenticator app (such as Google Authenticator, Microsoft Authenticator or 1Password) and get ten single-use recovery codes. Sign-in then asks for a code from the app. Unlike an emailed code, it still protects your account if someone gets into your email, so emailed codes stop working once an app is set up. Signing in with a recovery code emails you with how many are left.
  • Require two-factor for owners and admins — an organization owner can require an authenticator app for the organization's owners and admins. Anyone it covers is asked to set one up before using the rest of the Portal. Members who sign in with single sign-on are exempt, since your identity provider handles that.
  • Dark mode — choose System, Light or Dark from the theme menu in the sidebar or the Appearance card on the Profile page. System follows your device.
  • Custom models — connect your own OpenAI-compatible endpoint (vLLM, a hosted inference service and so on) and add its models under your own names. Tempr tests the endpoint before saving it and can list the models it serves. It's on the Gateway's Provider keys page, on Org keys for teams, and on Chat's Provider keys page for Pro licenses. Custom models have no price, so budget pages show their token use separately. See custom models.
  • The Security page's sign-in history now shows how each sign-in was made.
  • Chat's Provider keys page now reminds accounts that also have the Gateway that Gateway provider keys are set up separately.

Changed

  • Text and form field borders now meet WCAG contrast guidelines in both light and dark themes.
Gateway

Update

Changed

  • Quotas follow your billing period — the monthly allotment, overage cap and overage metering now count from the day your paid plan started, not the calendar month, and x-tempr-quota-resets reports that date. Free plans keep the calendar month. Quota alerts now fire again each period; before, an account alerted once was never alerted again.
  • Changing paid plans — moving between Gateway Pro and Scale, or between team plans, now updates your subscription in place and takes effect right away, prorated, instead of starting a second subscription.

Fixed

  • Cancelling and resubscribing, or changing plan, within a month could bill that month's overage twice.
  • Overage used in the last hour of a billing period, or before a cancellation, is now billed on that period's invoice.
JetBrains

1.1.1

Fixed

  • Agent turns no longer lose their connection when the chat goes quiet for more than ten seconds, such as while a model thinks or a tool waits for your confirmation. Before, a long enough quiet stretch could end the turn with "Lost connection to the agent run".
Portal

Update

Added

  • Gateway billing — personal and team Gateway plans now have a Manage billing button, and Billing history lists Gateway invoices, labelled by plan.
  • Manage Team seats — owners and admins see their Team plan and seats in use on the Plan page, with a Manage seats & billing button to add or release seats.
  • Allowed MCP servers per key — Gateway keys and org keys can be limited to a list of MCP servers.
  • Gateway-only accounts get a Try Tempr Chat link in the sidebar.

Changed

  • A new look — every Portal page has been redesigned with the same type and colours as temprhq.io, a lighter sidebar with your account at its foot, and a slide-out menu on small screens. Some pages have clearer names: BYOK is now Provider keys, Org config is Personas & commands, SSO is Single sign-on, Compliance is Audit log, and Gateway home is Overview.
  • Switching between Gateway Pro and Scale, for yourself or your team, now changes your current plan straight away with a prorated charge, instead of starting a new checkout.
  • Gateway quotas and overage now count from the start of your billing period instead of the calendar month, so resubscribing starts you with a fresh allowance. Quota alert emails now arrive again each period.
  • The Org keys page now explains that Team chat, like the Gateway, moves on to your organization's backup keys when a key is rejected or rate-limited.
  • Error text in agent traces is now always redacted.

Fixed

  • Turning on emailed two-factor codes from the Profile page didn't take effect.
  • Cancelling and resubscribing to a Gateway plan in the same month could bill that month's overage twice.
  • Budget charts could break when you went back to the Budget page from the sidebar.
  • Messages shown after a redirect, such as being sent to Provider keys from the Playground, were sometimes lost.
Gateway

Update

Removed

  • /v1/chat/stream and /v1/chat/tools — these older organization-key chat routes now answer 410 endpoint_retired. Use /v1/chat/completions, which takes the same keys and enforces the same limits.

Security

  • Tightened checks on webhook and remote MCP server addresses each time Tempr connects to them. Tempr no longer follows redirects from either; a remote MCP server that answers with a redirect returns 502.

Fixed

  • Usage from many simultaneous requests on one account could go partly unrecorded, under-counting spend in budgets and analytics.
VS Code

1.1.0

Added

  • Explain, Fix, and Write Tests from the editor — right-click in a file and choose Tempr to send the selection (or the whole file, with nothing selected) to the chat as /explain, /fix, or /tests. They're in the Command Palette too, as Tempr: Explain, Tempr: Fix, and Tempr: Write Tests.
  • Generate Commit Message — a sparkle button in a Git repository's Source Control title bar writes a message for the staged changes (or the unstaged ones, when nothing is staged) into the commit box, following the style of the repository's recent commits. It asks before replacing a message you've already typed.
  • Open Chat shortcut — Ctrl+Shift+Alt+T (Ctrl+Cmd+T on macOS).
  • Get Started with Tempr — a walkthrough on VS Code's Welcome page: sign in, open the chat, the editor menu, and settings.
  • Accessibility — screen readers now hear when a reply finishes, when a reply fails, and when a tool call is waiting for confirmation. Chat tabs, the mode, approval mode, and model dropdowns, the attach menu, and chat history all work from the keyboard. The history, license, and tools panels and the settings dialogs behave as dialogs (focus moves in, stays in, and returns when they close), and keyboard focus is always visible.

Changed

  • The Tempr Settings screen uses Tempr's own theme colors, matching the chat panel beside it, instead of the current VS Code theme's.
  • Editing a message you've already sent is hidden for now: saving an edit never worked in VS Code, and it comes back once it does.
  • If the Tempr server speaks a newer agent-run protocol than this version understands, the extension says so once per session, instead of failing in unclear ways.
  • When an agent turn can't start on the server and falls back to running in the extension, that is now counted in the anonymous error diagnostics (still controlled by the diagnostics setting in Tempr Settings).

Fixed

  • A tool call Tempr ran in VS Code could have its result overwritten by the server's summary — for example "Read 12 lines." becoming "Done", or a rejected call turning into an error.
  • In @tempr chat, a tool call the server rejected as unknown could show a stray "Error" progress line.
  • The chevron on the pending changes panel did nothing when clicked.
JetBrains

1.1.0

Added

  • Accessibility — screen readers now hear when a reply finishes, when it fails, and when a tool call is waiting for confirmation. Chat tabs, the mode, approval mode, and model dropdowns, the attach menu, and chat history all work from the keyboard. The history, license, and tools panels and the settings dialogs behave as dialogs, and keyboard focus is always visible.
  • Vault MCP servers in settings — MCP servers assigned to your account in Tempr's vault now appear in the Tempr Settings MCP list, as read-only cards.
  • Sub-agent cards — when the agent delegates work to a sub-agent on the server, the delegation now shows as a tool card in the chat, with the sub-agent's messages under it.

Changed

  • If the Tempr server speaks a newer agent-run protocol than this version understands, the plugin says so once per session instead of failing in unclear ways.
  • Editing a message you've already sent is hidden for now: saving an edit never worked in JetBrains IDEs, and it comes back once it does.
Visual Studio

2.2.25

Changed

  • If the Tempr server uses a newer agent protocol than your version of the extension understands, Tempr tells you so instead of failing in unclear ways.
  • The extension's Marketplace description no longer mentions inline chat, which is turned off for now.

Fixed

  • When the agent ran on the Tempr server, a tool you approved and Visual Studio ran could have its result replaced by the server's generic summary. For example, "Read 12 lines." became "Done", or a rejected call showed as an error. Results now keep their real summaries.
Portal

Update

Added

  • Prompt caching settings — turn on automatic prompt caching for Anthropic models across your Gateway account or team, choose a 5-minute or 1-hour cache, and override it per key. Request logs and Analytics show cache reads, writes and savings.
  • DeepInfra — DeepInfra is now available as a provider key for Chat, the Gateway and organization keys, with usage priced at DeepInfra's own rates.
  • Backup keys for teams — Org keys can hold more than one key per provider, used in turn and skipped while a key is rate-limited or failing. Analytics and Provider keys show when a key or model is cooling down, and until when.
  • Content capture per key — each Gateway key can now turn request and response capture on or off, or follow the account setting, so a development key can keep full logs while a production key keeps metadata only. Redaction of captured content is on by default for new Gateway accounts.

Changed

  • Webhook and remote MCP server URLs must now point to public internet addresses.

Fixed

  • Errors and missing pages now show a proper error page instead of a blank one.

Security

  • The Portal now sends standard browser security headers and enforces HTTPS on every page.
Gateway

Update

Added

  • POST /v1/responses — OpenAI's Responses API, the format Codex CLI speaks. OpenAI models and Azure OpenAI deployments pass straight through, so reasoning items, hosted tools and previous_response_id work as they do directly. Every other model is translated: hosted tools are dropped and named in the x-tempr-unsupported-tools header. See the Codex CLI guide.
  • Native Anthropic on /v1/messages — anthropic/… models now pass straight through to Anthropic, so extended thinking, server tools, anthropic-beta features and cache breakpoints work as they do against Anthropic directly.
  • Fallback chains and backup keys on every endpoint — /v1/messages and /v1/responses now try the next model in a chain, and the next key for a provider, just as chat completions does.
  • DeepInfra — DeepInfra's models are available with your DeepInfra key as deepinfra/…, priced from DeepInfra's catalog, cached input included.
  • Content capture per key — each virtual key can now inherit the account's content capture setting or turn it on or off, so a development key can keep full request logs while a production key logs metadata only. Redaction of captured content is now on by default for new accounts.

Changed

  • Rate limits — a 429 now sits out only the model it was for, not the provider's other models, and a wait the provider asks for is honored from the first failure. When that wait is longer than ten seconds, the 429 or 503 comes back at once with Retry-After instead of Tempr waiting it out. See retries and fallback.

Fixed

  • OpenAI's o-series and GPT-5 models were rejected when a request set max_tokens or temperature. They now get max_completion_tokens and no temperature.
  • OpenAI's dated model snapshots, Claude's dashed model ids, Azure deployments, and Amazon and Anthropic models on Bedrock could be recorded at $0. They're now priced.
Gateway

Update

Added

  • Prompt caching — turn it on for the account (5-minute or 1-hour cache), per key, or per request with x-tempr-prompt-cache, and Tempr places Anthropic's cache breakpoints for you, sorts tools into a stable order, and keeps requests that share a prompt on the same provider key. Cache reads and writes are billed at their own prices, and request logs show cached tokens and estimated savings. See prompt caching.

Changed

  • /v1/messages keeps the cache breakpoints a client sets itself, like Claude Code's, and returns Anthropic's split of input, cache-read and cache-write tokens in usage.

Fixed

  • A streamed /v1/messages response on a translated model reported 0 output tokens.
Portal

Update

Added

  • Gateway sign-up and paid plans — you can now create a free Gateway account from the Portal's sign-up page, no card or Chat license needed, and upgrade to Pro or Scale from the Gateway Plan page. Choosing a paid plan on temprhq.io takes you straight to checkout once you've verified your email, even if you open the email on another device.

Changed

  • The Gateway Plan page is now for managing your plan; compare plans on the pricing page.

Fixed

  • Azure OpenAI, Azure AI Foundry and AWS Bedrock keys can now be fully set up on the Gateway's Provider keys page, with the endpoint, deployment, region and model fields and the live check Chat already had. Before, the key saved but couldn't be used.
VS Code

1.0.8

Fixed

  • MCP tool calls to Anthropic models could fail outright — qualified MCP tool names ({server}.{tool}) contained a ., which Anthropic's API rejects in a tool name. Qualified names now use {server}__{tool} instead, matching the Tempr CLI and the Visual Studio and JetBrains extensions.
JetBrains

1.0.2

Fixed

  • MCP tool calls to Anthropic models could fail outright: qualified MCP tool names ({server}.{tool}) contained a ., which Anthropic's API rejects in a tool name. Qualified names now use {server}__{tool} instead, the same as Tempr's other extensions and the CLI.
  • An agent turn no longer fails when the connection drops or stalls partway through. Tempr reconnects and picks the turn up where it left off, without repeating anything you've already seen, and only gives up after several attempts.
Visual Studio

2.2.24

Fixed

  • MCP tool calls to Anthropic models could fail outright. MCP tool names were shown to the model as {server}.{tool}, and Anthropic's API doesn't allow a . in a tool name. They are now {server}__{tool}, the same as in Tempr's other extensions.
Portal

Update

Added

  • Prompt templates — keep a system prompt in the Portal and update it without releasing new code. Every change is kept as a version, and you choose which one is live.
  • Sessions and End users — two new Gateway pages group your requests by the session id or end-user id your application sends, with a timeline for each. Organization owners and admins get the same views for their team.
  • Request cost — Gateway requests now record their cost. Sessions and End users show what each one cost, and Analytics breaks cost down by prompt template.
  • LLM guardrail — a Gateway account or key can have each request screened for prompt-injection and jailbreak attempts before it is sent. It uses one extra call to your own provider, at that provider's normal rate.
  • Guardrail activity — Gateway Analytics shows how many requests the guardrails blocked or flagged, and for what.
  • Model list in the Playground — the Playground now offers the models your provider keys can reach, instead of only a text box.
  • Product switcher — accounts with both Chat and the Gateway switch between them at the top of the sidebar.
  • Organization owners and admins now have an Organization section in the sidebar.

Fixed

  • The Gateway page's Resend verification button didn't work.

Security

  • A closed or deactivated account's Portal sessions now stop working right away.
  • Opening a sign-in, password reset or license key link now always starts from a signed-out page.
Gateway

Update

Added

  • Prompt templates — keep a system prompt in the Portal, with versions, and name it on a request with the x-tempr-prompt header. Its {{variables}} are filled from the header, and it goes in front of the request as the first system message.
  • Prompt-injection check — an optional guardrail, per account or per key, that asks the request's model whether the prompt is an injection or jailbreak attempt before sending it on. In Block mode a match returns 400 guardrail_blocked.
  • Sessions and end users — send x-tempr-session-id to group a conversation's or agent run's requests into one session in the Portal, and the request's own end-user field (safety_identifier or user, or metadata.user_id on /v1/messages) to see usage per customer. Each request log now records its cost.
Gateway

Update

Fixed

  • Requests that used a fallback chain, or rotated between several keys for a provider, could fail with a spurious 503.
Portal

Update

Fixed

  • With emailed two-factor codes turned on, entering the code sent you back to the sign-in page instead of signing you in.
  • After regenerating a license key, the new key wasn't shown on the page.
  • If starting a checkout or opening billing fails, you now get a message and can try again instead of an error page.

August 2026

Gateway

Update

Added

  • Several keys per provider — add more than one key for a provider and Tempr spreads requests across them, skips a key that's cooling down, and moves to the next key when one fails. 502 all_keys_failed means every key was tried.
  • Sensitive-content guardrail — scan requests for emails, card numbers, JWTs, bearer tokens, AWS keys and other secrets before they reach a provider. Flag mode records what matched on the request log; Block mode returns 400 guardrail_blocked.
  • Redacted request logs — optionally mask the same kinds of sensitive content in captured request and response bodies before they're stored.
  • Cost anomaly alerts — a webhook fires when the last hour's spend is several times the account's usual hourly spend.
VS Code

1.0.7

Added

  • Vault MCP servers — MCP servers assigned to your account in Tempr's server-side vault now show up in the extension automatically, merged in with your local tempr.mcpServers entries (a vault entry wins on a name collision, and vault servers appear as read-only cards in the Tempr Settings MCP list).
  • Remote MCP servers — vault-assigned remote servers connect over MCP's Streamable HTTP transport through Tempr's own proxy relay instead of to the remote server directly, so the real remote URL and its credentials never leave the Tempr server.

Fixed

  • A vault-fetch failure or a slow/hanging remote MCP connect (now capped at 5 seconds) no longer delays or blocks local MCP servers from starting.
JetBrains

1.0.1

Added

  • Vault MCP servers — MCP servers assigned to your account in Tempr's server-side vault now start alongside the ones you've configured yourself, and their tools are available to the agent. When a vault server and one of yours share a name, the vault's entry wins.
  • Remote MCP servers — vault-assigned remote servers connect over MCP's Streamable HTTP transport through Tempr's own relay instead of to the remote server directly, so the real remote URL and its credentials never leave the Tempr server.

Changed

  • The plugin is now called Tempr Chat on the JetBrains Marketplace and in the IDE's plugin list.

Fixed

  • A vault fetch that fails or hangs (now capped at five seconds) no longer delays or blocks your own MCP servers from starting.
  • Works with newer IDE versions, which deprecated or changed some of the platform APIs the plugin used, including the one that serves the chat panel into the IDE's built-in browser.
Visual Studio

2.2.22

Added

  • Vault MCP servers — MCP servers assigned to you in Tempr's server-side vault, your own or shared by your team, now show up in the extension automatically alongside the servers you set up yourself. Tools > Options > Tempr > MCP Servers lists them in a read-only Vault-managed servers table. You manage them in the Tempr Portal.
  • Remote MCP servers — remote servers from the vault connect through Tempr's own relay, not to the remote server directly, so the real remote URL and its credentials never leave the Tempr server. You need to be signed in to use them. A remote server that can't connect is skipped, and your other servers keep working.
Portal

Update

Added

  • Audit log — organization owners and admins can review who changed what in the organization, filter by action, and export it to CSV.
  • Gateway log controls — export request logs to CSV, turn on redaction of emails, tokens, API keys and card numbers in captured content, and shorten how long logs are kept.
  • Multiple keys per provider — Gateway provider keys can hold backup keys, used in turn and routed around a key that's rate-limited or revoked. Each key can be turned on or off.
  • Request guardrails — scan each Gateway request for emails, tokens, API keys and card numbers before it reaches a provider, and choose to flag or block it. Set it for the account and override it per key.
  • Cost anomaly webhook — get a webhook when Gateway spending jumps.
Gateway

Update

Added

  • POST /v1/messages — Anthropic's Messages API, so Claude Code and tools built on Anthropic's SDK can point at Tempr and run on any model you have a key for, streaming included. Send the key as a bearer token or in x-api-key; errors come back in Anthropic's format. See the Claude Code guide.
  • Remote MCP proxy — POST /mcp/proxy/{serverSlug} relays MCP requests to a remote MCP server you've added in the Portal, with the virtual key's limits, logs and an optional MCP server allowlist.
  • Gateway for teams — an organization can hold one Gateway plan whose quota its keys share, with a monthly organization budget (402 organization_budget_exceeded, with x-tempr-org-budget-limit). Alert and digest emails go to the organization's owners and admins.
Portal

Update

Added

  • Team Gateway — organizations can take a Gateway plan together: one pooled quota and one bill shared across every member's keys, with team-wide alerts and analytics.
  • Gateway alerts and webhooks — email alerts as you near your monthly quota or overage cap, a signed webhook when the error rate spikes, a daily digest email, and a Send test webhook button.
  • MCP credentials — store MCP server connection details and secrets in the Portal instead of in each machine's mcp.json, and pick servers from a catalog. Owners and admins can add team credentials shared with every member. See MCP.
  • Agent traces — a record of each finished agent run from your IDE: its steps, tool calls, tokens, cost and errors. Organization owners and admins can see their team's runs.
Gateway

Update

Added

  • Webhooks and alerts — set a webhook URL to receive quota and budget alerts, signed with HMAC-SHA256 in x-tempr-webhook-signature. Optional error-rate alerts fire when a sustained share of recent requests fails, and a daily digest email summarizes usage.

Changed

  • Provider ids use hyphens — azure_openai, aws_bedrock, azure_ai_foundry, together_ai, fireworks_ai, xiaomi_mimo, meta_llama and aleph_alpha became azure-openai, aws-bedrock and so on. The old names are still accepted.
JetBrains

1.0.0

Added

  • Initial Marketplace release: a bring-your-own-key AI coding assistant for the JetBrains IDE family, working with your own keys for 20+ model providers or a gateway like OpenRouter.
  • Agent mode — a tool-calling agent that reads and searches your project, edits files, and runs shell commands, pausing for your approval before anything that changes something (interactive, autopilot, or bypass approval modes).
  • "@" persona modes — run the conversation as a specialist persona (plan, debugger, test, profiler, modernize, security, review, docs, refactor, git), or define your own custom agents (Pro).
  • Inline completions — optional ghost-text suggestions as you type.
  • "Send to Tempr" quick-fix — send any diagnostic straight to chat with the surrounding code attached.
  • Chat history — saved locally and encrypted at rest, searchable, pinnable and renameable, with cross-machine sync.
  • Multiple chat tabs — run several conversations side by side, each with its own model, mode, and history.
  • Live usage and cost footer — token and cost totals for the active conversation, updated as you go.
  • MCP servers — browse and install from the built-in catalog, or configure your own; their tools become available to the agent alongside the built-in ones.
  • Attachments — attach the active editor document, pick or paste images, or use #file/#symbol and drag-and-drop to add specific files to a message.
  • In-chat settings for your license key, approval mode, response style, iteration limits, disabled tools, and more.
VS Code

1.0.6

Fixed

  • Chat scrollbar — the message list's scrollbar (and its clickable/hoverable area) now stops above the input bar instead of running down behind it.
  • Chat input box — after switching chat tabs, the input box's auto-resize height sometimes computed too tall while its layout was still settling; it now recalculates once the box's width has actually settled.
Gateway

Update

Added

  • Azure AI Foundry — call models deployed in your Azure AI Foundry resource as azure-ai-foundry/….
  • Hugging Face — Hugging Face's inference router is available with your Hugging Face token.
  • Microsoft Entra ID for Azure OpenAI — authenticate Azure OpenAI with a service principal instead of an API key. If Tempr can't sign in with it, the request returns 402 provider_auth_failed with a message saying what to fix.
VS Code

1.0.5

Fixed

  • The tools/skills panel's "Select all" is now a single panel-level toggle that flips to "Deselect all" once every tool is enabled, replacing two redundant "Select all" links (one panel-level, one scoped to the "Built-in" section).
  • Settings key-value editors (custom headers, environment variables, etc.) now drop a removed row from view immediately when its Remove button is clicked, instead of leaving it on screen until it lost focus.
Visual Studio

2.2.12

Changed

  • In the tools picker, the button that switches every tool on or off now says Deselect all once every tool is on. Each group's button is now called Toggle all.

Fixed

  • On plans that include delegation to sub-agents, every Agent-mode and persona turn could fail with a "Tool names must be unique" error from the model provider. Those turns work again.
Portal

Update

Added

  • Gateway Playground — send a test message through your own Gateway setup to check that a provider key works.
  • Fallback chains — give a Gateway key named aliases that try a list of models in order, skipping providers that are rate-limited or not set up. Key settings can now be edited after the key is created.
  • Provider health — Gateway Analytics shows each provider's error rate and latency over the last 30 days.
  • AWS Bedrock — add an Amazon Bedrock API key and region; your available models are found automatically.
  • Azure AI Foundry and Hugging Face provider keys.
  • Entra ID for Azure — Azure OpenAI and Azure AI Foundry keys can use an Entra ID service principal instead of an API key.
  • The sign-up page now asks whether you're here for Tempr Chat or the Tempr Gateway.

Changed

  • The sidebar shows the Chat and Gateway sections only for the products you have.
  • Provider keys are sorted by provider name.

Fixed

  • Remember me on the sign-in page didn't keep you signed in.
Visual Studio

2.2.10

Changed

  • Tiered delegation concurrency — how many delegated sub-agents can run at the same time now depends on your plan: 2 on Standard and 8 on Pro. Before, every plan could run 8. When the agent asks for more at once, the extra sub-agents wait their turn.
Gateway

Update

Added

  • AWS Bedrock — call Bedrock models with your Bedrock API key, including models served through Bedrock's Converse API. Your Bedrock and Azure OpenAI models now appear in GET /v1/models, and a Bedrock error comes back with Bedrock's own message instead of a generic one.
  • Fallback chains — give a key an alias with an ordered list of models; when one fails with repeated 429s or 5xx errors, Tempr moves to the next, before any bytes reach your client, streams included. A model that keeps failing sits out for a while. See fallback chains.
  • Response caching — add x-tempr-cache-ttl: <seconds> to serve an identical request from cache without calling the provider. x-tempr-cache says HIT or MISS.
VS Code

1.0.4

Changed

  • Tiered delegation concurrency — the cap on concurrently-running delegated sub-agents ("delegate_to_agent") is now tier-based (Standard: 2, Pro/Team: 8) instead of a flat 8, matching the JetBrains/Visual Studio entitlement limits. The cap is re-applied on every delegation, so a sign-in, sign-out, or plan upgrade mid-session takes effect immediately.
VS Code

1.0.3

Added

  • Server-side agent loop — agent tool-calling turns can now be driven by the Tempr server, with MCP tool catalogs resolved server-side. Tool results are delivered with automatic retries, so a transient network hiccup no longer leaves a chat frozen mid-turn.
  • Session-scoped tool trust — confirmation cards for shell commands offer "Trust <prefix> for this session" (e.g. npm run), and PowerShell script approvals can be remembered per tool. Session prefixes match on exact command tokens, so trusting npm run never accidentally trusts npm runbook.
  • The responding indicator now stays pinned under the streaming reply with a live elapsed-time and token-estimate ticker, instead of disappearing at the first token.

Fixed

  • Assorted chat-window rendering issues and markdown formatting fixes.
Visual Studio

2.2.8

Added

  • Server-side agent loop — agent turns can now run on the Tempr server, and from 2.2.10 so can Ask-mode turns. Tools still run in Visual Studio, with your approval where it's needed. Tool results are sent with automatic retries, so a brief network problem no longer leaves a chat stuck partway through a turn.
  • Browse MCP Servers — a new plug button in the chat toolbar opens a catalog of MCP servers you can install in one click. If a server needs environment variables, such as an API key, Tempr asks for them. A newly installed server starts on your next agent turn, with no restart needed. Before, a server you added didn't start until Visual Studio restarted.

Changed

  • Between a tool call and the model's next reply, the status line under the transcript now says "Working…" instead of disappearing, so a long turn no longer looks frozen.

Fixed

  • A scrollbar no longer flashes in and out each time you send a message.
Gateway

Update

Added

  • Tempr Gateway — one OpenAI-compatible API at api.temprhq.io in front of your own provider keys: OpenAI, Anthropic, Google Gemini, Mistral, xAI, DeepSeek, OpenRouter, Together AI, Fireworks AI and more. POST /v1/chat/completions takes OpenAI's request shape for every model, and Anthropic, Gemini and Cohere are translated to it and back, streaming included. GET /v1/models lists the models your keys can reach. See the Gateway quickstart.
  • Virtual keys — tvk_ keys you create in the Portal, each with its own model allowlist, spend budget, and requests-per-minute and tokens-per-minute limits, so your provider keys never leave Tempr. See Authentication & virtual keys.
  • Plans and limits — Free, Pro and Scale plans with a monthly request allotment, a plan-level rate limit, and metered overage on Pro and Scale up to a cap you set. Limit errors carry headers saying where you stand, and alert emails go out as you approach the allotment. See pricing.
  • Request logs — every request is logged with its key, model, status, latency, tokens and cost, and x-tempr-metadata attaches your own fields to filter by. Each response carries x-tempr-request-id to match it to its log. Errors use OpenAI's error format; see the error reference.
Visual Studio

2.2.2

Added

  • Session tool trust — confirmation cards for commands now offer "Trust <prefix> for this session" (for example npm run), and PowerShell script approvals can be trusted for the whole session. Prefixes match whole words, so trusting npm run never trusts npm runbook. Destructive commands can never be trusted this way, and neither can anything in Bypass mode.
  • Confirmation cards for commands and PowerShell scripts now show the complete command or script, not just a one-line summary, and it stays visible after you decide.
  • While a reply streams, the status line stays below it with an elapsed-time counter and a running token estimate, instead of disappearing at the first word.

Changed

  • The toolbar's usage line no longer shows a lifetime token and cost total, and the Reset lifetime usage button is gone. Your lifetime usage is in the Tempr Portal. The monthly budget now counts the current calendar month and resets itself when the month changes.

Security

  • PowerShell commands that download and run code, or that send data out, now always ask for approval, in every approval mode and even when PowerShell scripts are trusted for the session.

Fixed

  • A command or script that started a background process could freeze the whole chat after it timed out. Timeouts now stop the command and everything it started, and the chat moves on.
  • The chat now scrolls along with a streaming reply. Before, it never did.
Portal

Update

Added

  • Tempr Gateway (preview) — a Gateway section for the invite-only preview: an overview with your monthly quota and optional metered overage with a cap, Gateway keys with allowed models, monthly spend and rate limits, Gateway provider keys checked live when saved, usage by key and model, searchable request logs, and analytics. You can choose whether request and response content is stored with your logs.
  • Create an account without a license — sign up with an email and password, confirmed by a verification email.
VS Code

1.0.1

Added

  • Tempr Settings — a dedicated settings page inside the Tempr chat view (gear icon in the chat toolbar, or Tempr: Open Settings from the Command Palette). Every Tempr setting now lives here instead of VS Code's native Settings UI: approval mode, response style, models and sampling, budgets, agent limits, disabled tools, per-persona model overrides, custom agents, and MCP servers.
  • Built-in editors for structured settings: validated add/edit dialogs for custom agents (with preset icon colors and an allowed-tools checklist) and MCP servers (single command-line field with live preview, masked environment variables), plus chip editors for auto-approved command prefixes and per-persona model rows.
  • Settings are searchable, grouped into collapsible sections, and show at a glance which values differ from their defaults.
  • Entitlements in the UI: custom agents show a Pro upgrade path on Standard licenses, and agent-loop iteration limits are clearly capped to your license tier.
  • Editing MCP servers now applies without reloading the window — running servers restart on the next chat turn.

Changed

  • Settings are stored in Tempr's own extension storage instead of settings.json. Existing tempr.* values in settings.json keep applying automatically — nothing to migrate by hand, and any value you change on the settings page takes over from then on.

Fixed

  • Agent-loop iteration limits are now capped to your license tier up front, instead of failing a turn mid-flight with a limit error.
  • Settings toggles now show clearly blue when enabled (previously gray in both states).
  • Unchanged settings no longer show a "modified" indicator when an empty default value is present in settings.json.
  • Custom-agent cloud sync follows server URL changes made mid-session.
VS Code

1.0.0

Added

  • Agent mode: a multi-step, tool-calling agent that reads/searches your workspace, edits files, and runs commands, pausing for your approval before anything mutating happens. Accept-all/undo controls for AI-made file edits.
  • Ask mode, plus persona-based sub-agents (plan, debugger, test, profiler, modernize, security, review, docs, refactor, git) for delegating specialized work — including custom personas you define yourself.
  • Workspace-aware semantic and symbol search, with code-intelligence-backed caller/callee lookup.
  • Inline ghost-text code completions.
  • File and image attachments, drag-and-drop, clipboard paste, and @workspace, @terminal, @problems context mentions.
  • "Send to Tempr" quick fix for sending a diagnostic straight to chat.
  • Model Context Protocol (MCP) server support for connecting custom tools.
  • Slash commands (/explain, /fix, /optimize, /refactor, /tests, /doc, /new, /clear, /help, /run).
  • Multi-tab chat history with search, pin, rename, and delete.
  • In-chat settings: license key management, approval mode, response style, model selection, font size, and a structured editor for MCP servers, custom agents, and per-persona model overrides.
  • Live token and cost usage tracking, with optional monthly budget alerts.
  • Chat sessions encrypted at rest on disk.

Fixed

  • Various startup, theming, and dropdown-loading issues from early builds.
Visual Studio

2.1.372

Changed

  • The Tools > Options > Tempr pages for allowed command prefixes, custom agents, MCP servers and per-persona models are now editable tables with Add and Remove buttons. They replace the pipe-delimited text boxes. A custom agent's system prompt opens in its own editor, and per-persona model overrides offer a dropdown of your models.
Visual Studio

2.1.366

Added

  • Chat history across machines — chats saved from another machine signed in to your license now download to this one. A fresh install starts with your history instead of an empty list.

Changed

  • Chat font size moved from the chat panel to Tools > Options > Tempr > General. It applies to open chats right away, and Ctrl+=, Ctrl+- and Ctrl+0 still adjust it in the chat window.
  • The chat toolbar's gear button now opens Tools > Options > Tempr. A new key button opens your license key and a link to manage it in the Tempr Portal.
  • The header above each chat has been removed. Its message count now appears at the start of the toolbar's usage line.

Fixed

  • Reopening a chat from history no longer leaves a large blank gap above the last message.
Portal

Update

Added

  • Team plan — an organization with shared seats. Owners and admins invite members by email as Member or Admin, change roles and remove members.
  • Org keys — shared provider keys for the whole organization, organization keys with allowed models, monthly budgets and rate limits, and per-member limits for everyday chat.
  • Org budget — a monthly organization budget as a soft email alert or a hard cap, with spend by day, by member and by model.
  • Personas & commands — publish your organization's own personas and slash commands to every member.
  • Single sign-on — members can sign in through your own identity provider, limited to your email domains, with optional automatic sign-up on first sign-in and an option to require SSO. See Teams and SSO.
Portal

Update

Added

  • Dashboard — this week's spend, requests and tokens by model, your most-used models, and notices about failed sign-ins or a reached budget.
  • Budget — month-to-date spend per license, a projection to month end, average cost per request, your top model, and a daily spend chart.
  • Billing — see your payment method, lifetime total, next invoice, and a notice with a link to fix it when a payment fails.
  • Close account — close your account from the Plan page after confirming your password.
  • Security alerts — an email when your account signs in from a new IP address and when your password changes. The Security page shows where each sign-in came from and counts failed attempts.
  • You can now set a username.
  • Usage has charts of spend, requests and tokens by model over the last 30 days.

Changed

  • Resetting your password now signs out every device using your license key, and emails you.
  • After changing your password, the Portal suggests reviewing your signed-in devices.
  • Too many failed sign-in attempts now pause sign-in for a few minutes.
Visual Studio

2.0.342

Changed

  • The Feature/Bug request button now opens the feature request page in the Tempr Portal instead of a form inside Visual Studio.

Fixed

  • The agent's run_tests tool always failed before it ran any tests. It now runs your tests and reports the results.
Visual Studio

2.0.338

Fixed

  • A chat's title now comes from the question you typed. Before, it could come from code attached to the message, such as a snippet sent with Send to Tempr.
Visual Studio

2.0.330

Initial release.

Added

  • Bring your own keys — chat with models from 20+ first-party providers, such as OpenAI, Anthropic, Google Gemini, xAI, Mistral and DeepSeek, or through OpenRouter, using your own API keys. You pick the model from a dropdown in the chat panel.
  • Agent mode — a multi-step, tool-calling agent that reads, searches and edits files in your solution and runs commands. It has three approval modes: Interactive asks before every change, Bypass applies edits for you to review afterwards, and Autopilot works hands-off. Commands are checked against an allow list you control in Tools > Options, and destructive commands always ask first.
  • Review changes — every file the agent edits shows up in a changes panel with a diff per file, plus Accept All and Undo All.
  • Debugger, test and solution awareness — the agent can read the live debugger state and evaluate expressions, run your tests with structured pass/fail results, and use compiler diagnostics, project references and callers and callees.
  • Ask mode — a plain chat that adds your active file, a solution overview and your package dependencies as context.
  • Personas and delegation — @plan, @debugger, @test, @profiler, @modernize, @security, @review, @docs, @refactor and @git switch to a specialist prompt and set of tools. The agent can also hand focused sub-tasks to these personas mid-turn. You can define your own custom agents and pick a model for each persona.
  • Semantic code search — your solution is indexed automatically for embedding-based search, so the agent finds related code even when the words don't match.
  • Precise context — #file and #symbol attach exactly the code you mean. @workspace, @terminal and @problems add a solution overview, terminal output or the Error List. You can attach or paste images too.
  • Inline completions — ghost-text suggestions as you type. Press Tab to accept.
  • Send to Tempr — the light bulb on an error or warning sends it to the chat with the surrounding code.
  • Slash commands — /explain, /fix, /tests, /doc, /refactor, /optimize, /run, /new, /clear and /help.
  • MCP servers — connect your own Model Context Protocol servers (stdio) to give the agent more tools.
  • Chat tabs and history — several chats side by side, each with its own model and mode. Your history is saved automatically and encrypted on disk, and you can search, pin, rename and delete chats.
  • Usage and budget — token and cost figures for each chat, plus an optional monthly budget alert.
  • Cloud sync — when you're signed in, your chats, settings and custom agents follow you to your other machines.
  • Open the chat from View > Tempr or with Ctrl+\\, Ctrl+O.
Portal

Update

Added

  • Subscribe from the Portal — choose Standard or Pro and check out, with a 7-day free trial. Your license key and Portal account are set up for you, and Manage subscription handles your billing afterwards.
  • Get started — a checklist that walks you through installing the extension, signing in with your license key and adding a provider key.
  • License keys — reveal a license key after confirming your password, or regenerate it, which signs out every device using the old one.
  • Budget alerts — set a monthly spend alert per license and get an email once when it's reached. It never limits your access.
  • Resend license key — lost your key? Enter your email and we'll resend every license key on the account.

Changed

  • Revealing a saved provider key now asks for your password.
  • Turning emailed two-factor codes on or off now asks for your password.
  • The Portal's address now opens the sign-in page directly.

July 2026

Portal

Update

Added

  • The Tempr Portal launches — one place to manage your Tempr account: sign in with your email and password (with optional emailed two-factor codes) and reset a forgotten password, see your licenses and signed-in devices and sign devices out, add provider keys for the models you use, compare plans, see your invoices, track lifetime usage and a daily breakdown by provider and model, review recent sign-in activity, change your password, and send feature requests.