microsoft/amplifier-agent v0.8.0

v0.8.0

Repository: microsoft/amplifier-agent

Tag: v0.8.0

Published: 2026-06-21T19:05:50Z

Prerelease: no

Release notes:

What's new in 0.8.0

Added

• OpenAI-compatible chat-completions HTTP face (amplifier-agent serve chat-completions) — /v1/models + /v1/chat/completions over HTTP with bearer-token auth. Streams responses, multi-provider routing via served-models registry, workspace correlation through X-Client-Session-Id header. Enables direct integration with opencode via the `amplifier-app-opencode` wrapper and any OpenAI-compatible client. (#65)

• `amplifier-agent auth` subcommand — set/list/remove/status/clear actions over ~/.amplifier-agent/credentials.json (mode 0600). Resolution chain is env-first: shell env vars (ANTHROPIC_API_KEY, …) win over the file so existing shell-rc workflows are unchanged. "Set once, works everywhere" UX matching claude login / gh auth login / aws configure without the OAuth ceremony. (#65)

• Host-tool delegation — tools declared by the host (host_config.json:host_tools) are surfaced to the model with stub schemas; on invocation, server emits a signal tool_call back to the client (same chunk_id), client executes host-side, returns result for the model to continue. Lets the host own filesystem, shell, browser, or any custom tool without bundling into amplifier-agent. (#65)

• Model routing matrix integration — per-role provider/model preferences resolved per turn. (#64)

• `cost_usd` in chat-completions usage envelope — non-standard field carrying the actual dollar cost provider modules computed, accumulated across sub-turns, serialized as a string for Decimal precision. Standard OpenAI clients ignore the field; cost-aware clients render the real per-turn $$. (#68)

Changed

• Lifespan provider initialization iterates KNOWN_PROVIDERS and registers every provider whose module is installed AND whose credentials are present. Previously the chat-completions face hardcoded inject_provider("anthropic"); injection is now per-request based on the model the client picks.

• `/v1/models` response surfaces a _provider tag per model so OpenAI-compatible clients can see which provider serves each entry.

• Usage-counter telemetry in chat-completions responses correctly reflects the provider that actually served the turn.

Wire protocol

Unchanged at 0.3.0 — no wrapper bump. TypeScript wrapper stays at 0.7.0, Python wrapper stays at 0.3.0.

Migration

No breaking changes. Existing CLI (run, serve, models list) unchanged. New: amplifier-agent auth and amplifier-agent serve chat-completions subcommands.

See [CHANGELOG.md [0.8.0]](https://github.com/microsoft/amplifier-agent/blob/main/CHANGELOG.md) for full details.

What's Changed

• feat(http): opencode integration — host-tool delegation, usage fix, workspace correlation, prep refactor by @manojp99 in https://github.com/microsoft/amplifier-agent/pull/65
• chore(release): bump engine to 0.8.0 by @manojp99 in https://github.com/microsoft/amplifier-agent/pull/67
• feat(http): per-turn cost_usd in /v1/chat/completions usage by @manojp99 in https://github.com/microsoft/amplifier-agent/pull/68

Full Changelog: https://github.com/microsoft/amplifier-agent/compare/v0.7.0...v0.8.0