Skip to content

refactor(provider-core): add ProviderHost as the server port for providers - #17287

Closed
juliusmarminge wants to merge 1 commit into
t3/provider-kitfrom
t3/provider-host
Closed

juliusmarminge wants to merge 1 commit into
t3/provider-kitfrom
t3/provider-host

Conversation

@juliusmarminge

@juliusmarminge juliusmarminge commented Oct 8, 2026 •

Copy link
Copy Markdown
Member

Drivers reached into the server for its config, settings service, background policy, and attachment store, so no provider could live outside apps/server.

This adds ProviderHost to provider-core, the one service a provider uses to reach the server: paths (cwd, home, state, probe cache), settings reads and change streams, the background-work gate, and attachment path resolution. The server implements it once (ProviderHostLive). The managed status provider and every driver now take ProviderHost instead of BackgroundPolicy. Pi's adapter and driver use it for their cwd, probe cache, and attachments. @t3tools/provider-testing gains a scoped test host.

No behavior change.


Part of the provider-packages stack: #17282 → #17283 → #17284 → #17285 → #17286 → #17287 → #17288.

Done by Claude Opus 5.5 in Claude Code.

🤖 Generated with Claude Code

…iders

Drivers and adapters reached into the server for its config, settings
service, background policy, and attachment store, so no provider could
live outside apps/server. Add a ProviderHost service to provider-core
with the paths, settings reads, background-work gate, and attachment
resolution a provider needs, implemented once in the server.

The managed status provider and every driver now take ProviderHost
instead of BackgroundPolicy. Pi's adapter and driver use it for their
cwd, probe cache, and attachments, which leaves Pi with no direct server
imports beyond the code that will move with it. provider-testing gains a
scoped test host for driver and adapter tests.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
@github-actions

github-actions Bot commented Oct 8, 2026

Copy link
Copy Markdown
Contributor

Thread transfer impact

✅ Thread transfer remains within every enforced ceiling.

ℹ️ No successful main baseline artifact is available yet. This run establishes the initial measurement.

Provider Metric Main baseline This PR Impact PR ceiling
Codex Total thread wire — 5.0 KiB — 6.8 KiB ✅
Codex Thread snapshot wire — 3.8 KiB — 4.9 KiB ✅
Codex Live turn WebSocket wire — 1.2 KiB — 2.0 KiB ✅
Codex Live turn WebSocket decoded — 20.9 KiB — 29.3 KiB ✅
Codex Live turn messages — 2 — 8 ✅
Claude Total thread wire — 5.0 KiB — 6.8 KiB ✅
Claude Thread snapshot wire — 3.8 KiB — 4.9 KiB ✅
Claude Live turn WebSocket wire — 1.2 KiB — 2.0 KiB ✅
Claude Live turn WebSocket decoded — 21.2 KiB — 29.3 KiB ✅
Claude Live turn messages — 2 — 8 ✅

Baseline: unavailable · PR result: ce31ac6 · Source CI: failure

Scenario and decoded snapshot size

10 historical turns, 5 command tools per turn, 878.9 KiB retained MCP result per historical turn, and a 1.05 MiB retained result in the measured turn.

  • Codex decoded thread snapshot: 108.5 KiB
  • Claude decoded thread snapshot: 108.8 KiB

Updated in place by a trusted workflow. PR artifacts are strictly validated and never executed.

@juliusmarminge

Copy link
Copy Markdown
Member Author

Superseded by the squashed 3-PR stack #17299 → #17300 → #17302 (same changes, regrouped; Effect service modules renamed to PascalCase).

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

macroscope-review Opt PRs made by unvouched contributors in for Macroscope review. Vouched contributors auto-reviews size:L 100-499 changed lines (additions + deletions). vouch:trusted PR author is trusted by repo permissions or the VOUCHED list.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant