feat(harness): add AForge parity across Python, Go, and TypeScript

[AbirAbbas]

Summary

• adds AForge provider parity to the Python, Go, and TypeScript SDKs
• makes direct aforge exec --json the default AForge adapter contract
• retains AGENTFIELD_AFORGE_COMMAND=do as an explicit routed-workflow override
• preserves stdin-only task delivery and maps both JSON envelopes into common AgentField result, usage, cost, and failure fields
• pins supplied work and plan models for exec, keeps system prompts separate, and gives the CLI a timeout landing window
• accepts usable exec budget/turn-cap landings while retaining strict do exit semantics
• keeps caller environment overrides and per-invocation schema isolation intact

Dependencies

The default exec path depends on:

• Agent-Field/aforge-v2#5 for the command contract
• Agent-Field/aforge-v2#6 for the released downstream CLI image

Consumer rollout PRs:

• feat: make AForge exec the default runtime SWE-AF#137
• feat: make AForge exec the default harness sec-af#129
• feat: make AForge exec the default harness pr-af#72
• feat: make AForge exec the default harness cloudsecurity-af#7
• feat: make AForge exec the default harness contract-af#3

Default contract

aforge exec --json -w <project-root> \
  --timeout <outer-minus-5s> --context-fill 60 --completion-reserve 65536

The task is written to stdin. A supplied system prompt is passed with --system; a supplied model is passed to both --model and --plan-model.

To use AForge routing instead:

AGENTFIELD_AFORGE_COMMAND=do

Verification

• Python AForge provider: 20 tests passed
• Go AForge provider: go test ./harness
• TypeScript AForge provider: 15 tests passed
• TypeScript: npm run lint and npm run build
• live Python, Go, and TypeScript adapter canaries against the ported AForge binary

[github-actions]

Performance

SDK	Memory	Δ	Latency	Δ	Tests	Status
Python	9.0 KB	-	0.30 µs	-14%	✓	✓
Go	226 B	-19%	0.64 µs	-36%	✓	✓
TS	497 B	+42%	1.62 µs	-19%	✓	✗

⚠ Regression detected:

• TypeScript memory: 350 B → 497 B (+42%)

[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	87.10%	87.40%	↓ -0.30 pp	🟡
sdk-go	92.70%	92.00%	↑ +0.70 pp	🟢
sdk-python	94.20%	93.73%	↑ +0.47 pp	🟢
sdk-typescript	91.26%	90.42%	↑ +0.84 pp	🟢
web-ui	84.76%	84.79%	↓ -0.03 pp	🟡
aggregate	85.62%	85.75%	↓ -0.13 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	282	90.00%	✅
sdk-python	0	—	➖ no changes
sdk-typescript	124	94.00%	✅
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.