feat: use neutral current input filenames

[Activer007]

Summary

• apply current_input_file.filename_policy to generated context/tool upload names
• default-capable neutral_random names use conversation-notes-xxxxxx.txt and tool-reference-xxxxxx.txt
• keep tool reference cache keyed by logical file type and content hash, not randomized upload names

Tests

• go test ./internal/httpapi/openai/history ./internal/completionruntime ./internal/httpapi/openai/... ./internal/httpapi/claude/... ./internal/httpapi/gemini/...

Phase 2 PR2, stacked on #36.

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: cc27e36eff

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".

[chatgpt-codex-connector]

Include filename policy in tools cache key

uploadCachedToolsFile now accepts a generated filename, but the cache lookup key still hard-codes currentToolsFilename. If current_input_file.filename_policy is changed at runtime (for example from legacy to neutral_random), requests within the 5-minute cache TTL can reuse a previously uploaded file_id whose visible filename does not match the new policy, so the policy change does not take effect immediately and can still expose DS2API_* names. The cache key should include a stable policy dimension (or non-randomized filename class) so cache hits respect the active filename policy.

Useful? React with 👍 / 👎.