Anandan d1c5af7392 Polish model status and reasoning streams (#190) ...

* Polish model status and reasoning streams

* Polish custom provider setup flow

* Clean up pending composer hints

* Address custom provider setup review

* Polish composer overflow handling

* Fix composer paste and wheel edge cases

* Use line counts for paste previews

* Revert "Use line counts for paste previews"

This reverts commit 4feb814d09.

* Fix composer paste preview deletion

* Disable textinput ctrl-v paste binding

* Preserve paste previews through file suggestions

* Clarify composer paste preview behavior

* Keep OpenAI reasoning out of answer text

2026-06-13 22:40:32 +05:30

..

ask_user_test.go

Agent runtime: ask_user interception, context compaction, guardrails (#125)

2026-06-07 22:34:40 +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

Add session context compaction flow (#166)

2026-06-11 20:16:22 +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

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

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

confirmation_policy.md

Agent runtime: ask_user interception, context compaction, guardrails (#125)

2026-06-07 22:34:40 +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

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

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

deferred_loop_test.go

Deferred (lazy) tool loading: tool_search + auto threshold for large MCP tool sets (#148)

2026-06-09 12:20:22 +05:30

denial_test.go

Tool quality: per-tool denial categorization + secret scanning (#137)

2026-06-08 09:08:51 +05:30

escalate_loop_test.go

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

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

guardrails_test.go

TUI scrollback re-architecture, Lime chat surface, and deep-audit fixes (#158)

2026-06-10 17:18:30 +05:30

guardrails.go

TUI scrollback re-architecture, Lime chat surface, and deep-audit fixes (#158)

2026-06-10 17:18:30 +05:30

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

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

Polish model status and reasoning streams (#190)

2026-06-13 22:40:32 +05:30

loop.go

Polish model status and reasoning streams (#190)

2026-06-13 22:40:32 +05:30

permission_scope_test.go

permissions: scope-enforced grants (permission-UX Phase 0 + 1) (#170)

2026-06-11 20:33:52 +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

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

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

system_prompt_models_test.go

Expose active provider model to agent

2026-06-11 00:54:49 +05:30

system_prompt_models.go

Model harness: per-model system prompts + summarizer fallback (#135)

2026-06-08 09:08:28 +05:30

system_prompt_preview.go

Add context budget report (#139)

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

system_prompt_test.go

Expand agent quality eval module (#178)

2026-06-13 11:30:20 +05:30

system_prompt.go

Expand agent quality eval module (#178)

2026-06-13 11:30:20 +05:30

system_prompt.md

Add agent quality eval foundation (#177)

2026-06-12 13:31:57 +05:30

types.go

Polish model status and reasoning streams (#190)

2026-06-13 22:40:32 +05:30