anandh8x a3b09218aa Add deterministic completion policy ...

Extract completion decisions from the agent loop into a feature-gated typed policy with complete, incomplete, and uncertain outcomes. Preserve bounded plan-stall nudges and allow at most one semantic acceptance check for self-correcting runs.

Tested: make build

Tested: make test

Tested: go fmt ./...

Tested: go vet ./...

Tested: make lint

Tested: govulncheck ./...

Note: repository-wide pinned golangci-lint reports 36 pre-existing unrelated findings; internal/agent/... reports 0 issues.

2026-07-18 00:21:22 +05:30

..

acceptance_gate_test.go

fix(exec): stop false INCOMPLETE downgrades on conversational final messages (#608)

2026-07-10 08:59:33 +08:00

additional_permissions_validation_test.go

fix(agent): reject a malformed additional_permissions payload before prompting (#453)

2026-07-04 08:51:14 +08:00

ask_user_test.go

perf(output): add token-aware semantic output budgeting (PR11) (#717)

2026-07-18 00:02:43 +05:30

async_diagnostics_test.go

perf: universal tool-output ceiling with spill + async post-edit diagnostics (#518)

2026-07-05 23:50:31 +08:00

async_diagnostics.go

perf: universal tool-output ceiling with spill + async post-edit diagnostics (#518)

2026-07-05 23:50:31 +08:00

command_prefix_test.go

fix(tools): Block MSYS coreutils under Windows sandbox (#476)

2026-07-06 08:03:32 +08:00

command_prefix.go

chore: fix golangci-lint findings (dead code, ineffassign, staticcheck) (#527)

2026-07-06 08:09:32 +08:00

compaction_calibrate_test.go

polish v2: smoothness & delight (#484)

2026-07-05 13:15:14 +05:30

compaction_metadata_test.go

Add session context compaction flow (#166)

2026-06-11 20:16:22 +05:30

compaction_preserve_test.go

Add session context compaction flow (#166)

2026-06-11 20:16:22 +05:30

compaction_preserve.go

polish v2: smoothness & delight (#484)

2026-07-05 13:15:14 +05:30

compaction_recent_edits_test.go

polish v2: smoothness & delight (#484)

2026-07-05 13:15:14 +05:30

compaction_summarizer_test.go

Deep-audit remediation + sandbox hardening (batches 1–35) (#189)

2026-06-13 21:32:48 +05:30

compaction_test.go

Deep-audit remediation + sandbox hardening (batches 1–35) (#189)

2026-06-13 21:32:48 +05:30

compaction.go

Add per-turn tracing and a turn-benchmark harness (Phase 0 baseline) (#700)

2026-07-16 21:58:20 +08:00

completion_gate_test.go

fix(agent): gate headless run completion on honesty (no false-success on no-tool-call / self-reported-incomplete turns) (#325)

2026-06-27 12:31:41 +05:30

completion_policy_test.go

Add deterministic completion policy

2026-07-18 00:21:22 +05:30

completion_policy.go

Add deterministic completion policy

2026-07-18 00:21:22 +05:30

confirmation_policy.md

Improve sandbox permission handling (#323)

2026-06-26 16:21:06 +05:30

context_measurement_test.go

Agent: per-category context token budget (system / tools / messages) (#133)

2026-06-08 08:14:49 +05:30

context_measurement.go

perf(tools): lower default deferThreshold to stop eager MCP-schema token waste (#241)

2026-06-18 19:41:36 +05:30

decode_args_test.go

fix: agent runtime resilience — stream stalls, weak-model tool args, and sub-agent reliability (#349)

2026-07-01 09:15:08 +05:30

defer_savings_test.go

perf(tools): lower default deferThreshold to stop eager MCP-schema token waste (#241)

2026-06-18 19:41:36 +05:30

deferred_loop_test.go

Move deferred tool discovery into tool search (#324)

2026-06-27 13:02:09 +05:30

denial_test.go

Align sandbox permission blocks and backend states (#253)

2026-06-19 19:50:12 +05:30

effective_permission_test.go

feat(subagent): proactive specialist delegation + swarm execution fixes (#243)

2026-06-18 20:00:12 +05:30

escalate_loop_test.go

Mid-run model escalation: escalate_model tool + --allow-escalation (#146)

2026-06-08 20:50:32 +05:30

file_diagnostics_test.go

feat: agent quality, caching, retry, and tooling upgrades (#506)

2026-07-05 17:25:26 +08:00

file_diagnostics.go

feat: agent quality, caching, retry, and tooling upgrades (#506)

2026-07-05 17:25:26 +08:00

guardrails_test.go

fix(openai): handle Ollama reasoning stream deltas (#486)

2026-07-05 17:05:54 +08:00

guardrails.go

fix(exec): stop false INCOMPLETE downgrades on conversational final messages (#608)

2026-07-10 08:59:33 +08:00

hook_wiring_test.go

Edit safety: file read/write tracking, external-modification detection, post-apply hooks (#172)

2026-06-11 20:34:35 +05:30

image_rejection_test.go

feat: clipboard image paste + provider 400 handler for image rejection (#268)

2026-06-20 19:40:32 +05:30

loop_images_test.go

Image (multimodal) input: exec --image, stream-json images, TUI /image across all 3 providers (#143)

2026-06-08 18:49:09 +05:30

loop_test.go

fix(hooks): run sessionEnd hooks after Esc/Ctrl+C interrupts (#606)

2026-07-17 13:03:14 +08:00

loop.go

Add deterministic completion policy

2026-07-18 00:21:22 +05:30

member_auto_test.go

feat(swarm): let swarm members build (write + sandboxed shell) (#313)

2026-06-25 11:36:40 +05:30

no_progress_stop_test.go

Improve /resume: interactive session picker + model-generated titles (#224)

2026-06-17 12:41:20 +05:30

output_budget_propagation_test.go

perf(output): add token-aware semantic output budgeting (PR11) (#717)

2026-07-18 00:02:43 +05:30

parallel_tools_test.go

perf(agent): concurrent read-only tool batches via capability gate (#715)

2026-07-17 17:52:11 +05:30

parallel_tools.go

perf(agent): concurrent read-only tool batches via capability gate (#715)

2026-07-17 17:52:11 +05:30

partition_cache_stable_test.go

chore: fix golangci-lint findings (dead code, ineffassign, staticcheck) (#527)

2026-07-06 08:09:32 +08:00

partition_cache_test.go

polish v2: smoothness & delight (#484)

2026-07-05 13:15:14 +05:30

permission_additional_perms_test.go

fix(tui): resolve every permission request so the agent can't deadlock (#397)

2026-07-03 06:02:57 +08:00

permission_scope_test.go

Align sandbox permission blocks and backend states (#253)

2026-06-19 19:50:12 +05:30

plan_staleness_test.go

polish v2: smoothness & delight (#484)

2026-07-05 13:15:14 +05:30

prompt_budget_test.go

polish: cut per-turn overhead, stabilize cache, add /new (#478)

2026-07-04 20:56:52 +08:00

prompt_fingerprint_test.go

feat(perf): emit prompt-prefix hash fingerprint per turn (#704)

2026-07-17 12:47:53 +08:00

prompt_fingerprint.go

feat(perf): emit prompt-prefix hash fingerprint per turn (#704)

2026-07-17 12:47:53 +08:00

prune_test.go

feat: five capability features from the reference-agent comparison (#276)

2026-06-20 23:12:15 +05:30

prune.go

feat: five capability features from the reference-agent comparison (#276)

2026-06-20 23:12:15 +05:30

reconnect_test.go

polish v2: smoothness & delight (#484)

2026-07-05 13:15:14 +05:30

reconnect.go

Add per-turn tracing and a turn-benchmark harness (Phase 0 baseline) (#700)

2026-07-16 21:58:20 +08:00

request_permissions_test.go

Fix shared temp roots in sandbox scope (#314)

2026-06-25 09:47:55 +05:30

response_style_test.go

audit fixes: cron lock, accounting race, O(n²) hot paths, /style wiring (#260)

2026-06-19 21:11:34 +05:30

selfcorrect_test.go

wedge build: web_search + LSP client/diagnostics (stages 01-03) (#175)

2026-06-12 15:13:05 +05:30

selfcorrect.go

Add per-turn tracing and a turn-benchmark harness (Phase 0 baseline) (#700)

2026-07-16 21:58:20 +08:00

skills_context_test.go

Skills: deterministic invocation — /<skill-name>, searchable /skills picker, discovery-budget fix (#520)

2026-07-05 21:14:53 +05:30

specialist_delegation_test.go

feat(subagent): proactive specialist delegation + swarm execution fixes (#243)

2026-06-18 20:00:12 +05:30

stall_retry_test.go

fix: cut the content-stall dead-wait and auto-retry a mid-tool-call stall (#362)

2026-07-02 00:14:51 +05:30

system_prompt_models_test.go

polish: cut per-turn overhead, stabilize cache, add /new (#478)

2026-07-04 20:56:52 +08:00

system_prompt_models.go

polish: cut per-turn overhead, stabilize cache, add /new (#478)

2026-07-04 20:56:52 +08:00

system_prompt_preview.go

Add context budget report (#139)

2026-06-08 15:37:14 +05:30

system_prompt_test.go

fix(agent,tui): resolve git branch detection when starting Zero in subdirectories (#613)

2026-07-10 10:05:36 +08:00

system_prompt.go

fix(agent,tui): resolve git branch detection when starting Zero in subdirectories (#613)

2026-07-10 10:05:36 +08:00

system_prompt.md

feat(agent): curb over-engineering the solution in the editing discipline (#517)

2026-07-05 21:38:42 +08:00

tokens_test.go

perf(tools): lower default deferThreshold to stop eager MCP-schema token waste (#241)

2026-06-18 19:41:36 +05:30

types.go

Add deterministic completion policy

2026-07-18 00:21:22 +05:30