Anandan 1fde941803 perf: reduce startup and turn overhead (#932) ...

* perf(tui): disable duplicate composer cursor blink

* perf(tui): stop composer wakeups after idle

* refactor(tools): publish immutable registry snapshots

* perf(startup): defer optional tool discovery

* perf(provider): reuse compatible response sessions

* feat(provider): add native patch tool input

* fix(provider): recognize saved chat sessions

* perf(tui): render only on screen changes

* fix(runtime): address performance review findings

* fix(usage): expose cache efficiency details

* perf(agent): reduce redundant bounded-task turns

* fix: harden runtime review edge cases

* fix: address runtime review findings

* build: restore official Bubble Tea dependency

* fix(cli): redact MCP registration errors

* fix: harden turn session regressions

* fix: keep run tools and patch roots consistent

* fix: bind freeform patch writes to scoped roots

* test: keep patch fixtures out of worktree

* fix(tools): reject mixed-root freeform patches

2026-08-26 13:22:05 +08:00

..

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): end the additional_permissions retry loop (#864)

2026-08-06 21:34:54 +05:30

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(sandbox): normalize launcher names before the command-prefix denylist (#934)

2026-08-21 12:50:11 +08:00

command_prefix.go

chore: remove code unreachable on every supported platform (#706)

2026-07-24 09:04:41 +08:00

compaction_calibrate_test.go

polish v2: smoothness & delight (#484)

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

compaction_cheap_test.go

perf(agent): cheap compaction — dedicated summarizer model, input cap… (#532)

2026-08-25 21:18:04 +08:00

compaction_metadata_test.go

Reduce compaction context while preserving task state (#873)

2026-08-08 11:26:27 +05:30

compaction_preserve_test.go

Reduce compaction context while preserving task state (#873)

2026-08-08 11:26:27 +05:30

compaction_preserve.go

Reduce compaction context while preserving task state (#873)

2026-08-08 11:26:27 +05:30

compaction_projection_test.go

perf: reduce startup and turn overhead (#932)

2026-08-26 13:22:05 +08:00

compaction_projection.go

perf: reduce startup and turn overhead (#932)

2026-08-26 13:22:05 +08:00

compaction_recent_edits_test.go

Reduce compaction context while preserving task state (#873)

2026-08-08 11:26:27 +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

perf: reduce startup and turn overhead (#932)

2026-08-26 13:22:05 +08:00

compaction.go

perf: reduce startup and turn overhead (#932)

2026-08-26 13:22:05 +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 transcript-grounded structured task state (#761)

2026-07-19 21:38:58 +05:30

completion_policy.go

Add transcript-grounded structured task state (#761)

2026-07-19 21:38:58 +05:30

confirmation_policy.md

Improve sandbox permission handling (#323)

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

context_measurement_test.go

Centralize agent context planning (#879)

2026-08-08 16:40:17 +05:30

context_measurement.go

Centralize agent context planning (#879)

2026-08-08 16:40:17 +05:30

context_planner_test.go

perf: reduce startup and turn overhead (#932)

2026-08-26 13:22:05 +08:00

context_planner.go

perf: reduce startup and turn overhead (#932)

2026-08-26 13:22:05 +08:00

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

feat(agent): add PermissionModePlan for interactive read-only planning (#853)

2026-08-10 10:15:29 +08:00

denial_test.go

chore: remove code unreachable on every supported platform (#706)

2026-07-24 09:04:41 +08:00

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

fix(providers): discover ChatGPT capabilities (#890)

2026-08-12 22:41:05 +05:30

export_test.go

chore: remove code unreachable on every supported platform (#706)

2026-07-24 09:04:41 +08:00

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

freeform_tool_test.go

perf: reduce startup and turn overhead (#932)

2026-08-26 13:22:05 +08:00

guardrails_test.go

perf: reduce startup and turn overhead (#932)

2026-08-26 13:22:05 +08:00

guardrails.go

perf: reduce startup and turn overhead (#932)

2026-08-26 13:22:05 +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

perf: reduce startup and turn overhead (#932)

2026-08-26 13:22:05 +08:00

loop.go

perf: reduce startup and turn overhead (#932)

2026-08-26 13:22:05 +08:00

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: improve harness context efficiency (#838)

2026-07-31 23:30:03 +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: remove code unreachable on every supported platform (#706)

2026-07-24 09:04:41 +08:00

partition_cache_test.go

perf: reduce startup and turn overhead (#932)

2026-08-26 13:22:05 +08:00

permission_additional_perms_test.go

feat(sandbox): unify command execution and enforcement (#781)

2026-07-21 18:55:13 +05:30

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

prefix_escalation_disclosure_test.go

fix(agent): tell the user a prefix approval leaves the sandbox (#885)

2026-08-10 10:56:49 +08:00

profile_controller_test.go

perf(agent): execution profiles with one-shot posture escalation (PR10b+PR10c) (#740)

2026-07-19 00:53:17 +05:30

profile_controller.go

fix(lint): resolve static analysis baseline (#769)

2026-07-27 09:59:33 +08:00

prompt_budget_test.go

fix(tools): make apply_patch tolerant and re-expose edit_file (#956)

2026-08-25 20:23:48 +08:00

prompt_fingerprint_test.go

perf: reduce startup and turn overhead (#932)

2026-08-26 13:22:05 +08:00

prompt_fingerprint.go

perf: reduce startup and turn overhead (#932)

2026-08-26 13:22:05 +08:00

prune_test.go

perf: improve harness context efficiency (#838)

2026-07-31 23:30:03 +05:30

prune.go

perf: improve harness context efficiency (#838)

2026-07-31 23:30:03 +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

chore: remove code unreachable on every supported platform (#706)

2026-07-24 09:04:41 +08:00

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

perf: improve harness context efficiency (#838)

2026-07-31 23:30:03 +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

perf: reduce startup and turn overhead (#932)

2026-08-26 13:22:05 +08:00

system_prompt_models.go

perf: reduce startup and turn overhead (#932)

2026-08-26 13:22:05 +08:00

system_prompt_preview.go

Add context budget report (#139)

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

system_prompt_test.go

perf: reduce startup and turn overhead (#932)

2026-08-26 13:22:05 +08:00

system_prompt.go

feat(agent): add PermissionModePlan for interactive read-only planning (#853)

2026-08-10 10:15:29 +08:00

system_prompt.md

perf: reduce startup and turn overhead (#932)

2026-08-26 13:22:05 +08:00

task_state_test.go

Reduce compaction context while preserving task state (#873)

2026-08-08 11:26:27 +05:30

task_state.go

Reduce compaction context while preserving task state (#873)

2026-08-08 11:26:27 +05:30

tokens_test.go

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

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

tool_result_images_test.go

feat(tools): give tool results an image channel and add view_image (#843)

2026-08-06 21:35:41 +05:30

turn_session_test.go

perf(providers): provider capabilities and default turn-session adapter (PR7) (#720)

2026-07-18 09:33:07 +05:30

turn_session.go

perf(providers): provider capabilities and default turn-session adapter (PR7) (#720)

2026-07-18 09:33:07 +05:30

types.go

perf(agent): cheap compaction — dedicated summarizer model, input cap… (#532)

2026-08-25 21:18:04 +08:00