feat(sdk/python): isolate OpenCode harness runs

[ddbaron]

Summary

• Configure each standalone Python OpenCode run with a generated agentfield-harness agent through OPENCODE_CONFIG_CONTENT.
• Preserve caller and ambient OpenCode configuration through a deep merge while giving the generated harness fields precedence.
• Keep credentials out of the generated configuration and preserve the task prompt as the normal positional or stdin prompt.
• Keep AgentField's max_turns runner limit separate from OpenCode's fixed steps setting.
• Add targeted recursion protection for AgentField orchestration skills while leaving unrelated skills available.
• Retain an opt-in inline system-prompt compatibility path through AGENTFIELD_OPENCODE_INLINE_SYSTEM_PROMPT=1.

The overlay also carries the resolved model and OpenCode-specific reasoning variant when available. The provider-agnostic public variant API is intentionally kept in the related follow-up rather than duplicated here.

Validation

• uv run --extra dev pytest -q tests/test_harness_provider_opencode.py tests/test_harness_agent_wiring.py tests/test_harness_runner.py tests/test_harness_types.py
• Python compilation
• git diff --check

The focused tests pass against the current main branch.

Related to the original proposal: #960

Related to the provider-agnostic follow-up: #1024

The fork preview remains available at ddbaron#3.

[santoshkumarradha]

Focused Python harness tests passed locally for me, and the config-overlay path looks sound. I also approved the fork-gated workflows so the full matrix is running now.

[github-actions]

Performance

SDK	Memory	Δ	Latency	Δ	Tests	Status
Python	9.0 KB	-	0.26 µs	-26%	✓	✓

✓ No regressions detected

[github-actions]

📊 Coverage gate

Thresholds from .coverage-gate.toml: per-surface ≥ 84%, aggregate ≥ 85%, max per-surface regression ≤ 1.0 pp, max aggregate regression ≤ 0.50 pp.

Surface	Current	Baseline	Δ
control-plane	87.70%	87.40%	↑ +0.30 pp	🟡
sdk-go	93.10%	92.00%	↑ +1.10 pp	🟢
sdk-python	94.33%	93.73%	↑ +0.60 pp	🟢
sdk-typescript	91.72%	90.42%	↑ +1.30 pp	🟢
web-ui	84.77%	84.79%	↓ -0.02 pp	🟡
aggregate	85.85%	85.75%	↑ +0.10 pp	🟡

✅ Gate passed

No surface regressed past the allowed threshold and the aggregate stayed above the floor.

[github-actions]

📐 Patch coverage gate

Threshold: 80% on lines this PR touches vs origin/main (from .coverage-gate.toml:thresholds.min_patch).

Surface	Touched lines	Patch coverage	Status
control-plane	0	—	➖ no changes
sdk-go	0	—	➖ no changes
sdk-python	0	—	➖ no changes
sdk-typescript	0	—	➖ no changes
web-ui	0	—	➖ no changes

✅ Patch gate passed

Every surface whose lines were touched by this PR has patch coverage at or above the threshold.