# Copy to .env and fill in. .env is git-ignored.

# Your GLM (Zhipu / Z.ai) API key. Used as a Bearer token.
GLM_API_KEY=your-zai-key-here

# Anthropic-compatible endpoint for the GLM coding plan.
GLM_BASE_URL=https://api.z.ai/api/anthropic

# --- optional tuning (sensible defaults baked in) ---
# GLM_USE_HAIKU=off           # off (DEFAULT) = skip the Haiku `glm` subagent and call GLM directly
#                             # (mcp__glm__glm_agent) so ALL tokens stay on GLM. Set to `on` to allow
#                             # the Haiku-orchestrated subagent (it spends some Claude tokens).
# GLM_DELEGATE=off            # off (DEFAULT) = hide the text-only glm_delegate tool so orchestrators
#                             # always use glm_agent (which handles text-only tasks too). Set on to expose it.
# GLM_COST_BIAS=7             # how hard to favor GLM. Default 7 => GLM handles ~98-100% of tasks
#                             # (Opus only for vision/parallel/huge-context/sensitive/heavy tool-loops).
#                             # Lower (e.g. 1.5) to route more hard tasks to Opus; 0 = capability only.
# GLM_MAX_CONCURRENT=1        # GLM caps in-flight requests ~1; keep at 1 unless your tier allows more
# --- output token cap (OFF by default = generous) ---
# The glm_agent/glm_delegate max_tokens param defaults to "auto" (uncapped/generous -- the
# orchestrating agent decides; it may pass a specific number to cap a given call).
# By default the cap is OFF: every call may use up to GLM_MAX_TOKENS_CEILING (131072).
# max_tokens is a ceiling, not a target -- you pay for ACTUAL output, so leaving it off
# just prevents truncation. Turn the cap ON to control spend.
# GLM_CAP=off                      # off (default) | on  -- enforce GLM_MAX_TOKENS when on
# GLM_MAX_TOKENS=32768             # the hard per-call limit applied WHEN GLM_CAP=on
# GLM_MAX_TOKENS_CEILING=131072    # the generous default used when the cap is OFF
# GLM_MAX_RETRIES=4
# GLM_STALL_TIMEOUT_MS=120000 # abort a turn only after this long with NO stream bytes (idle/stall
#                             # timeout). Streaming keeps resetting it, so a long-but-active turn is
#                             # never cut off. Falls back to GLM_TIMEOUT_MS, then 120000.
# GLM_TIMEOUT_MS=300000
# GLM_AGENT_MAX_ITERS=30           # max tool-loop turns for glm_agent before it stops
# GLM_AGENT_BASH_TIMEOUT_MS=120000 # per-command timeout for glm_agent's run_bash
# GLM_OFFPEAK_MODEL=glm-5.2   # model(s) for "auto" off-peak. Can be a COMMA LIST, e.g.
#                             # "glm-5.2,glm-5-turbo" -> the router auto-picks (most capable for
#                             # hard tasks, cheapest for easy ones).
# GLM_PEAK_MODEL=glm-5.2      # model(s) for "auto" during peak. glm-5.x carries the ~3x surcharge,
#                             # so when "auto" lands on a glm-5.x model the router routes LESS to GLM
#                             # at peak. Include a no-surcharge model (e.g. "glm-5.2,glm-4.7") and
#                             # the router will prefer it at peak -> GLM stays fine to use.
# GLM_CHEAP_MODEL=glm-4.5-air
# GLM_PEAK_START_CN=14        # peak window start, China hour (UTC+8)
# GLM_PEAK_END_CN=18          # peak window end (exclusive)