# Claude subscription
Use an installed Claude Code CLI for claude.ai access while magi-code manages tools, approvals, history, and compaction.
Setup: [Provider authentication](provider-authentication.md#claude-subscription).
## Runtime ownership
| Owner | Responsibility |
| --- | --- |
| Installed Claude CLI | Subscription login, refresh, model access and authenticated Messages requests |
| Rust provider | Projection, native process, deadlines, cancellation, ordered events and tool validation |
| One-admission relay | Forward one generation to Anthropic, replace placeholder with ordered host history, validate response |
| Host agent runner | Durable history, approvals, tools, continuation and compaction |
Each request launches installed `claude -p` with one ordinary placeholder prompt. The relay replaces its messages with the complete host conversation. There is no SDK dependency, manual assistant-input protocol, mirrored Claude session, or second credential-refresh owner. Temporary system prompt, settings and inert tool inventory live in an owner-private directory. Native session persistence is disabled.
Built-in CLI tools and skills are disabled. User/project/local settings are disabled; managed policy still applies. Strict MCP configuration exposes only the inert host inventory. Magi-code replaces the system prompt and disables native compaction. The CLI and inert MCP server share a process group, terminated on completion, failure or cancellation.
The [subscription guidance](https://support.claude.com/en/articles/15036540-use-the-claude-agent-sdk-with-your-claude-plan) permits CLI, SDK and third-party usage against subscription limits. It does not specifically certify this history-rewriting relay. API-key and alternate-backend environment overrides are removed from children, but existing subscription usage credits may still be charged. Magi-code never enables credits or changes billing settings.
## Execution and failure policy
`CLAUDE_CODE_MAX_RETRIES=0` and `CLAUDE_CODE_DISABLE_NONSTREAMING_FALLBACK=1` constrain native retries. They are not enforcement: the relay refuses every Messages request after the first admission. Unexpected history replacement fails before upstream I/O. Both native and restored requests are capped at 8 MiB; captured response at 16 MiB.
The CLI is launched with `--thinking-display summarized` to request provider-generated thinking summaries. They use the same live reasoning display and saved-history path as other providers. Signed thinking blocks remain intact for replay; signatures and redacted thinking payloads are never displayed. Empty or provider-hidden thinking produces no reasoning card.
Text, reasoning and usage may stream before completion. Tools and the remaining ordered suffix require:
- Valid upstream stop and usage records.
- Native assistant, result and `message_stop` records.
- Successful native exit.
- A tool name in the request's host inventory.
A completed tool-use response may end the one-turn CLI with `error_max_turns` and exit 1. Only that exact subtype with a validated upstream tool call permits exit 1. Other errors, missing terminal records and incomplete streams fail without releasing tools. Accepted partial text remains durable. A later host continuation is a new request, not a retry within the same admission.
An upstream `refusal` fails the turn without releasing tools. The error identifies Anthropic as the source, includes its refusal category and explanation when supplied, and takes precedence over the CLI's subsequent retry errors. Missing explanations are reported explicitly. Category and explanation are redacted, stripped of terminal controls, normalized to one line, and capped at 128 and 1,024 characters respectively. Magi-code does not retry refusals or change models automatically; the relay still blocks every additional request.
Native lines are capped at 1 MiB and cross a bounded 16-message channel. Startup allows five minutes; configured semantic inactivity applies after progress. Upstream completion starts one fixed finalization grace interval. Each generation has a 30-minute overall limit. Diagnostics exclude raw prompts, authorization headers and native stderr.
## Context capacity
| Explicit model selection | Input ceiling |
| --- | ---: |
| Opus 4.6 and newer with `[1m]`, including `claude-opus-5-5[1m]` | 1,000,000 |
| Fable 5 and newer with `[1m]`, including `claude-fable-5[1m]` and `claude-fable-5-1[1m]` | 1,000,000 |
| All other selections, including aliases | 202,000 |
Compaction uses the same settings, context reserve, model inheritance and prompt-border display as every other provider. Defaults are an 80% automatic trigger and four compactions per run; no separate Claude controls or required alternative model. Catalog windows and native `modelUsage` cannot raise transport limits. Refresh the catalog to show extended-context variants of eligible listed models, or select one explicitly. No suffix is added automatically.
The explicit suffix matters when `ANTHROPIC_BASE_URL` points at a relay: native gateway defaults can differ from direct subscription defaults. See [Claude model configuration](https://code.claude.com/docs/en/model-config). Account entitlements still decide acceptance. Estimates are not provider token counts; token-dense input can exceed them substantially. Keep headroom. Oversize rejection uses host compaction, not a hidden model or billing fallback.
## Verification limits
The input ceilings above are enforced limits, not promises that every CLI version, account, or model accepts a full window. Native observations include successful large-history replay, tool calls, cancellation, and recovery, alongside rate-limit and retry failures.
See the [archived observations](../archive/claude-subscription-observations.md) for versions, measured token counts, failures, and the direct-CLI/SDK comparison. Those observations do not establish current billing or model access.