wowdespacito/anthropics_skills
1
0
Fork 0
mirror of https://github.com/anthropics/skills.git synced 2026-08-02 13:05:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add Opus 4.8 migration guide and model updates to claude-api skill (#1216)

Browse Source 
* Add Managed Agents self-hosted sandboxes + mid-session agent updates + MCP tool-output offload to claude-api skill

Self-hosted sandboxes: new shared/managed-agents-self-hosted-sandboxes.md for config:{type:"self_hosted"} — agent loop on Anthropic's orchestration, tool execution on customer infra via outbound-polling worker. Covers EnvironmentWorker.run()/.run_one() (Py/TS), ant beta:worker poll/run, mid-level work.poller()/WorkPoller (Py/TS/Go only; Go has no auto_stop opt-out), AgentToolContext/beta_agent_toolset/tool_runner(), monitoring (environments.work.stats/stop — x-api-key, call from outside worker host), runtime deps, cloud-vs-self_hosted delta table, credentials, security ownership split. Cross-refs in environments.md, overview.md (Reading Guide + rewrote cloud-only pitfall), api-reference.md (SDK row + naming-quirks + schema + work REST rows), tools.md (Who-runs-it carve-out), onboarding.md, live-sources.md.

Mid-session agent updates: sessions.update(session_id, agent={tools, mcp_servers}, vault_ids=[...]) — session-local override (doesn't bump agent version), full-replacement semantics, session must be idle. New core.md section + pointers in tools.md, api-reference.md (UpdateSession row), overview.md.

Large MCP tool outputs → files: >100K tokens → automatic offload to sandbox file; agent gets truncated preview + path. Plus: invalid vault credentials don't block sessions.create() — session.error event fires, auth retries on next idle→running. Both in tools.md.

* Point ant CLI install ref to live-sources.md (OSS has no anthropic-cli.md)

* Add Opus 4.8 model migration guide to claude-api skill

* Add prescriptive tool-description guidance for Opus 4.8 to claude-api skill
This commit is contained in:
Lance Martin
2026-05-28 19:02:26 -07:00
committed by GitHub
parent 690f15cac7
commit da20c92503
34 changed files with 296 additions and 192 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skills/claude-api/shared/prompt-caching.md
+2 -2
View File
@@ -111,11 +111,11 @@ Fix by moving the dynamic piece after the last breakpoint, making it determinist
| Model | Minimum |
|---|---:|
| Opus 4.7, Opus 4.6, Opus 4.5, Haiku 4.5 | 4096 tokens |
| Opus 4.8, Opus 4.7, Opus 4.6, Opus 4.5, Haiku 4.5 | 4096 tokens |
| Sonnet 4.6, Haiku 3.5, Haiku 3 | 2048 tokens |
| Sonnet 4.5, Sonnet 4.1, Sonnet 4, Sonnet 3.7 | 1024 tokens |
A 3K-token prompt caches on Sonnet 4.5 but silently won't on Opus 4.7.
A 3K-token prompt caches on Sonnet 4.5 but silently won't on Opus 4.8.
**Economics:** Cache reads cost ~0.1× base input price. Cache writes cost **1.25× for 5-minute TTL, 2× for 1-hour TTL**. Break-even depends on TTL: with 5-minute TTL, two requests break even (1.25× + 0.1× = 1.35× vs 2× uncached); with 1-hour TTL, you need at least three requests (2× + 0.2× = 2.2× vs 3× uncached). The 1-hour TTL keeps entries alive across gaps in bursty traffic, but the doubled write cost means it needs more reads to pay off.