Merge pull request #31 from huggingface/agent-improvements

Fix premature agent loop exit in long-running autonomous tasks

Use Haiku 4.5 for research sub-agent

Use Haiku for research sub-agent when main model is Anthropic

Research stats tick every second via background timer

Live research stats: tool count, tokens, elapsed time in header

Revert "Sub-agent log: tool_name → output_preview on one line"

Sub-agent log: tool_name → output_preview on one line

Log 20-char output preview for sub-agent tool calls

feat: add headless CLI mode with local filesystem tools and rich terminal rendering

Deduplicate file re-reads via content hashing for local and sandbox tools

fix: move import/signature validation to sandbox, keep host-side lightweight

feat: emit tool_log events from research sub-agent for UI liveness

feat: add research sub-agent tool, slim down main agent system prompt

Improve tool output quality: ANSI stripping, tail-biased truncation, noise suppression

feat: cancel sandbox creation on user interrupt

feat: kill sandbox processes and cancel HF jobs on user interrupt

fix: retry sandbox API calls on transient failures

chore: double sandbox command timeouts

chore: increase sandbox sleep_time to 45 min

Revert "feat: stream sandbox bash output to frontend in real-time"

feat: stream sandbox bash output to frontend in real-time

feat: upgrade CLI with local tools, slash commands, and interrupt support

stream sandbox creation logs to tool output, fix hf_jobs final status race

fix: only set sleep_time for non-CPU-basic sandboxes

fix: increase sandbox sleep_time to 1500s

fix: buffer websocket events during disconnects and replay on reconnect

feat: resolve sandbox file paths for hf_jobs script display

fix: use user OAuth token for job creation (has job.write on org)

fix: route all HF token usage through session.hf_token from OAuth

fix: use correct HF API filter param and improve integration tests

feat: add hf_papers tool for paper discovery and reading

fix: remove TRANSFORMERS_VERBOSITY from sandbox env

feat: inject OAuth token as HF_TOKEN secret into sandbox Space

feat: require sandbox_create approval before sandbox operations

fix: use OAuth token for sandbox creation instead of env HF_TOKEN

feat: use hf_agent tool descriptions, hardware flavors, and default env

feat: restore sandbox tools and proactive compaction

feat: merge HF Space improvements

rewording

v3 prompt and tool desc rework

enabled passing sandbox scripts to hf jobs

sandbox working and agent can use it

add create sandbox tool

sandbox start

frontend update

Merge branch 'main' into feature/web-frontend

plan tool bottom right

log streaming

hf jobs desc update