fix(ai): retain Anthropic cache checkpoints across tool loops

[codeg-dev]

Summary

Fixes direct anthropic-messages prompt-cache replay during tool loops by retaining the prior dynamic cache checkpoint while marking the newest tool-result tail.

• preserves a rolling pair of dynamic checkpoints for direct and OAuth Messages requests
• keeps OAuth payloads within Anthropic’s four-breakpoint limit by omitting the redundant fixed Claude Code identity marker when a user system prompt is present
• adds no-network regression coverage for three tool loops, both OAuth system-prompt variants, disabled cache retention, and unpaired tool results

Evidence

• Stock RED: prior checkpoint was dropped after the next tool-result tail.
• GREEN: ./node_modules/.bin/vitest --run packages/ai/test/anthropic-cache-checkpoint-stability.test.ts packages/ai/test/warm-prompt-cache.test.ts (8 passed)
• ./node_modules/.bin/tsc --noEmit --pretty false passed.

Related: #1005 (goal-continuation cache prefix stability); this PR addresses the remaining serializer-level checkpoint movement.

---

Summary by cubic

Retains Anthropic prompt-cache checkpoints across tool loops to avoid prefix reprocessing. Previously we replaced the tail checkpoint each loop, dropping the prior boundary; now we keep the newest tool_result tail and the preceding cacheable user message while staying within Anthropic’s four-breakpoint limit.

• Maintain two rolling checkpoints for direct and OAuth anthropic-messages.
• In OAuth, omit the fixed Claude Code identity cache marker when a context system prompt exists to preserve the checkpoint budget.
• Add regression tests (packages/ai/test/anthropic-cache-checkpoint-stability.test.ts) and docs updates (packages/ai/CHANGELOG.md, packages/ai/src/changes.md).

Review notes

• Core changes in packages/ai/src/api/anthropic-messages.ts (convertMessages, buildParams) with new markUserMessageCacheCheckpoint helper.

^{Written for commit 5437b99. Summary will update on new commits.}

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 32ee10114a

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".