weichen 6841e7f45e Apply evidence normalization before checkpoint commits ...

Why: Valid but underdetermined model claims must become pending without losing the batch or leaking unsupported status text.

Evidence: Mixed-batch, source-input binding, approval-status, tool-receipt and prompt regressions failed before changes; go test ./... -count=1 and selected live-tag fake-provider tests passed.

Impact: Validate all task-bound sources, normalize once, return a safe receipt, and version material processing as v9; no extra provider call.

Refs: Dev task feature/fast-slow-u2-u3-plan; r0.3 evidence implementation plan Task 3

2026-10-13 16:27:33 +00:00

..

testdata

Check final replies before the direct run stops

2026-10-01 13:54:15 +00:00

checkpoint_plugin_test.go

Preserve source authority and task identity through delivery and recovery

2026-10-13 03:55:04 +00:00

compose_test.go

Keep artifact ids and byte counts out of the final reply

2026-10-02 14:02:19 +00:00

compose.go

Repair the quality-gate failure chain observed on real runs

2026-10-09 12:34:21 +00:00

context_window_test.go

Keep original materials and cleared results reachable across turns

2026-10-09 14:28:39 +00:00

deliverable_latest_test.go

Keep tool-result dumps out of the deliverable gate and cards

2026-10-09 14:56:34 +00:00

dual_speed_nudge_test.go

Strip inline think blocks from subagent summaries and card bodies

2026-10-10 10:01:15 +00:00

e4_escalation_test.go

Switch the R4 failure trigger to a sliding window

2026-10-10 18:43:03 +00:00

factcheck_test.go

Add R4 escalation reminders and the structured source-id evidence ledger (E4)

2026-10-10 17:41:38 +00:00

factcheck.go

Log R4 reminder injection for observable evidence

2026-10-11 01:22:49 +00:00

final_reply_test.go

Keep the final reply clean when checks continue or the verifier is skipped

2026-10-10 07:48:03 +00:00

hostbridge.go

Route conversations through a squad entry when selected

2026-10-01 09:34:53 +00:00

llm_direct_e1_test.go

Enable parallel tool execution, fix delegate truncation, sandbox deps layer

2026-10-10 09:02:10 +00:00

llm_direct_n3_test.go

Make the kernel transcript the authoritative cross-turn context

2026-10-09 15:38:33 +00:00

llm_direct.go

Bind evaluation budgets to actual run IDs

2026-10-13 14:44:53 +00:00

llm_test.go

Bind evaluation budgets to actual run IDs

2026-10-13 14:44:53 +00:00

llm_think_test.go

Return deliverable generation to the agent and fix the artifact-card root cause

2026-10-01 03:32:30 +00:00

llm_verify_test.go

Keep the final reply clean when checks continue or the verifier is skipped

2026-10-10 07:48:03 +00:00

llm.go

Add deliverable-choice chain: confirm_choice tool, notice contract, backstops

2026-10-11 16:53:53 +00:00

material_final_reserve_test.go

Reserve material subagent budget for final answers

2026-10-13 10:13:48 +00:00

material_final_reserve.go

Reserve material subagent budget for final answers

2026-10-13 10:13:48 +00:00

material_flow_test.go

Add deliverable-choice chain: confirm_choice tool, notice contract, backstops

2026-10-11 16:53:53 +00:00

mock.go

Make background subagents observable as the slow lane of dual-speed tasks

2026-10-10 06:40:00 +00:00

model_test.go

Rewind tracked files and fall back before the first token

2026-10-03 17:31:56 +00:00

model.go

Store secrets apart from settings and assemble context at the end

2026-10-04 18:20:10 +00:00

permission_ask_test.go

Validate plugin agent declarations and wire the squad ask port

2026-10-07 05:14:06 +00:00

planless_nudge_test.go

Add the working-method base prompt and demote the compose rewrite

2026-10-09 23:12:53 +00:00

provider_run_identity.go

Bind evaluation budgets to actual run IDs

2026-10-13 14:44:53 +00:00

review_test.go

Let subagents run in the background and be reviewed

2026-10-01 15:29:01 +00:00

review.go

Let subagents run in the background and be reviewed

2026-10-01 15:29:01 +00:00

run_budget_stream_test.go

Publish validated material findings during background work

2026-10-13 02:29:23 +00:00

run_budget_stream.go

Publish validated material findings during background work

2026-10-13 02:29:23 +00:00

runner.go

Add the generative-ui plugin, capability gating, and surface projection

2026-10-11 10:38:15 +00:00

squad_runner_test.go

Add the generative-ui plugin, capability gating, and surface projection

2026-10-11 10:38:15 +00:00

squad_runner.go

Enable parallel tool execution, fix delegate truncation, sandbox deps layer

2026-10-10 09:02:10 +00:00

sub_loop_test.go

Stream tool progress and drop hard agent limits

2026-10-02 02:17:02 +00:00

sub_loop.go

Bind evaluation budgets to actual run IDs

2026-10-13 14:44:53 +00:00

toolselect_test.go

Cap tool results by character and gate stale file writes

2026-10-03 16:21:02 +00:00

transcript_compact.go

Make the kernel transcript the authoritative cross-turn context

2026-10-09 15:38:33 +00:00

transcript_seed_test.go

Make the kernel transcript the authoritative cross-turn context

2026-10-09 15:38:33 +00:00

transcript_seed.go

Make the kernel transcript the authoritative cross-turn context

2026-10-09 15:38:33 +00:00

usage_n3_test.go

Bind evaluation budgets to actual run IDs

2026-10-13 14:44:53 +00:00

verify.go

Add deliverable-choice chain: confirm_choice tool, notice contract, backstops

2026-10-11 16:53:53 +00:00

work_checkpoint_test.go

Apply evidence normalization before checkpoint commits

2026-10-13 16:27:33 +00:00

work_checkpoint.go

Apply evidence normalization before checkpoint commits

2026-10-13 16:27:33 +00:00

workflow_compiled_test.go

Add the generative-ui plugin, capability gating, and surface projection

2026-10-11 10:38:15 +00:00

workflow_compiled.go

Enable parallel tool execution, fix delegate truncation, sandbox deps layer

2026-10-10 09:02:10 +00:00

workspace_tools_test.go

Open the kernel workspace tools and the markdown-source build pipeline

2026-10-09 18:01:06 +00:00

wp5_ab_test.go

Keep the final reply clean when checks continue or the verifier is skipped

2026-10-10 07:48:03 +00:00